WO2023119075A1

WO2023119075A1 - System and method for assessing the risk score of a set of users

Info

Publication number: WO2023119075A1
Application number: PCT/IB2022/062247
Authority: WO
Inventors: Juan Pablo ARANGO HERNÁNDEZ; Mateo BUSTAMANTE; Laura Catalina CANO PÉREZ; Jorge CARDOZO; Manuel DOMINGUEZ; Javier Duran; Jorge DURAN; Oscar Bernardo LONDOÑO VÉLEZ; Daniel SÁNCHEZ BARRERA; Nayith URRUCHURTU; Beatriz Elena VASQUEZ PUERTA
Original assignee: Servicios De Teleasistencia Colombia S.A.S.
Priority date: 2021-12-23
Filing date: 2022-12-14
Publication date: 2023-06-29
Also published as: CO2021017744A1

Abstract

The present invention relates to systems and methods for assessing the risk score of a set of users. The method is executed by a server or computing unit, and may include a step of accessing a database with tables related to one another by one or more fields, wherein the fields may be columns that are present in two or more tables to establish the relationship. The fields that relate the tables may include values for variables and/or data, or may include key data which relate the tables to one another. Furthermore, the method may include a step of receiving a form generation request or a process startup command from a terminal, which causes the server to access and/or load the tables, relating them with one another by means of the variables and/or data shared by said tables, or by means of the key data. The tables relate users to variables and/or data such as project names, questionnaires and/or diagnostic tools, medical history data, demographic variables, psychosocial variables, and any other variable or data that is relevant for assisting a user within the framework of a project, and defining their risk score data. The method further sends a form or questionnaire to the terminal, which includes fields to be completed that the operator fills in during the call with the user, wherein the fields are generated from the relationships between tables, considering variables such as pathology type of the patient, step in the assistance process, status of the assistance process, and any other type of variable and/or data that allows the required fields to be selected to obtain the variables and/or data that make it possible to obtain the risk score data. In the method, the server also obtains the value of the user's risk score data, following the relationships of the tables and executing one or more processes to determine said value based on rules, pre-set scales or processes for estimating risk score. Additionally, the present invention discloses embodiments of systems configured to execute any of the embodiments of the method disclosed herein, and discloses computer-readable means and computer programs, which when executed by one of the embodiments of the systems disclosed herein cause said system to execute any of the embodiments of the method disclosed herein.

Description

SYSTEM AND METHOD FOR ASSESSING THE RISK SCORE OF A GROUP OF USERS

Related technical field

The present disclosure is related to systems and methods for risk assessment of a set of users.

Description of the state of the art

Telecare methodologies assess the risk of a user with the aim of designing intervention plans that improve the living conditions of said user. This requires performing standardized tests according to the user's pathologies and estimating the risk with the results of said standardized tests. Because standardized tests depend on the pathologies associated with the user, telecare methodologies must generate questionnaires that include only the respective standardized tests to collect sufficient information to estimate the user's health risk.

In order to solve the above problem, systems and methods have been developed that facilitate user risk management by generating questions based on user information and estimating a risk score based on the answers to the questions. generated, which are disclosed in the documents US2020/143946A1, US2019/385711A1 and US2017/357771A1.

US2020/143946A1 discloses a method for increasing the performance of a case management system. The method includes receiving user data associated with a user, determining a plurality of predicted risk factors based on the user data, each of the plurality of predicted risk factors having a weighted value, and calculating a first risk score based on the user data. in the weighted values of the plurality of predicted risk factors. The method disclosed in US2020/143946A1 includes managing a query-based service that determines if the plurality of predicted risk factors includes a validated risk factor. The question-based service includes a dynamically generated questionnaire that has an initial question associated with a predicted risk factor prioritized from the plurality of predicted risk factors. In addition, said questionnaire has a plurality of subsequent questions that are each generated based on the responses received to the previous questions. The method also discloses an optimization function that minimizes a total number of questions required for the question-based service to determine if the plurality of predicted risk factors includes the validated risk factor.

Document US2020/143946A1 mentions that its method allows improving the operability of its system, for example, when determining and managing services for risk factors, reducing the number of inputs necessary to perform the operation, reducing errors when operating/interacting with the device through its optimized questionnaire. Accordingly, the document US2020/143946A1 discloses that the method allows to reduce the use of energy and memory of the system.

However, the method disclosed in US2020/143946A1 performs a question generation query for each response received and executes an optimization method that minimizes the number of questions. But the method disclosed in document US2020/143946A1 does not allow obtaining, through a single query, enough questions to obtain a user's risk score. In addition, the risk score obtained by the method disclosed in document US2020/143946A1 is a dynamic risk score, which is calculated each time a new question is filled out. This generates an increase in the consumption of computational resources since the risk score is modified in each iteration.

On the other hand, document US2019/385711A1 discloses systems and methods that can evaluate, estimate and/or monitor the mental state of human subjects. The method of described in US2019/385711A1 may use an automated module to present and/or formulate at least one query in an audio, visual and/or textual format to the subject for get at least one answer. The consulted can be based on one or more mental states to be evaluated.

Likewise, the method disclosed in the document US2019/385711A1 may comprise a step of receiving data, including at least one response from the subject in response to the at least one query, and a step of processing the data using one or more individual models. , ensembles or merged comprising a natural language processing (NLP) model, an acoustic model and/or a visual model. Likewise, document US2019/385711A1 mentions that, in the consultation, a standardized test or questionnaire can be applied, and a score related to the patient's mental health can be calculated from the consultation, which can be selected from the group that includes PHQ-9, GAD-7, HAM-D, and BDI, or other similar test or questionnaire to assess a patient's mental health status.

However, the method disclosed in document US2019/385711A1 does not allow obtaining, through a single query, enough questions to generate a diagnostic questionnaire to be completed by the user and obtain a user's risk score based on the assessment. of the responses to the diagnostic questionnaire.

For its part, document US2017/357771A1 discloses a method to facilitate the management of a patient's health, which includes a stage of receiving information from the patient and a stage of determining, based on the patient's information, a risk score. The risk score may be determined based on information other than patient information, eg, user input, referral information, follow-up information, and/or the like. In some embodiments, the method disclosed in US2017/357771A1 may have a step of determining the risk score including applying a statistical regression model to patient information.

Document US2017/357771A1 also discloses a care service related to the disclosed method, where said service may include, for example, a service of remote monitoring (for example, the patient could be monitored through remote patient monitoring), a transition of care program, post-discharge follow-up with a home visit or phone call, where such care service is intended to promote compliance or beneficial lifestyle or behavior change.

However, the method disclosed in document US2017/357771A1 does not allow the generation of a diagnostic questionnaire with questions based on the user's information and the estimation of a risk score based on the assessment of the responses to the diagnostic questionnaire.

Brief Description of Disclosure

The present disclosure is related to systems and methods for the assessment of the risk score of a set of users. The method is executed by a server or computing unit, and may include a step of accessing a database that has tables related to each other by one or more fields, where the fields may be columns present in two or more tables to establish the relationship. The fields that relate the tables can include variable values and/or data, or can include key data that allows the tables to be related to each other. In addition, the method can have a stage of receiving from a terminal, a form generation request, or a start process command, which causes the server to access and/or load the tables, relating them to each other through the variables and/ or data shared by those tables, or through the key data. The tables relate users with variables and/or data such as project names, questionnaires and/or diagnostic tools, clinical history data, demographic and psychosocial variables, and any other variables or data that are pertinent to user care within the framework. of a project, and define its risk score data. The method also sends a form or questionnaire to the terminal, which includes fillable fields that the operator fills out during the call with the user, where the fields are generated from the relationships between tables, considering variables such as the type of patient's pathology. , stage of the care process, status of the care process, and any other type of variable and/or data that allows selecting the fields required to obtain the variables and/or data that allow obtaining the risk score data. Also, in the method, the server obtains the data value of the user's risk score data, following the relationships of the tables and executing one or more processes to determine said value based on rules, predetermined scales or score estimation processes. risky.

Additionally, this disclosure describes modalities of systems configured to execute any of the modalities of the method disclosed herein, and describes computer-readable media and computer programs, which when executed by one of the modalities of the systems disclosed herein, generate that said system executes any of the modalities of the method disclosed here.

Brief description of the figures

The FIG. 1 illustrates the block diagram of a system mode and method for obtaining risk score data from a user.

The FIG. 2 illustrates the flowchart of one embodiment of the method for obtaining risk score data from a user.

The FIG. 3 illustrates the block diagram of another embodiment of the system and the method for obtaining a user's risk score data, showing a rule-based qualification process that obtains the user's risk score data. An optional step of obtaining a risk class data from the risk score data is shown in the dotted line.

The FIG. 4 illustrates a block diagram of a modality of the system and the method disclosed here, in which there is a data preprocessing method that identifies affected records of a database that is taken as input to feed a main database. The FIG. 5 illustrates a block diagram of an embodiment of the system and method disclosed herein, in which response data is obtained from a call between the user and an operator of a terminal connected to the server. The server executes stages in which it sends and receives data to and from the terminal, and stages in which it retrieves, queries, and records data through relationships between tables in the main database.

The FIG. 6 illustrates a block diagram of a modality of the system and the method disclosed herein, in which steps are executed in which the server loads and/or consults the tables of the main database to confirm the diagnosis of pathology of the user to through the comparison of the drug data value and with a pathology data.

The FIG. 7 illustrates a block diagram of a modality of the system disclosed here, which shows the server connected to a communications network that allows establishing a service-based communications protocol that interconnects the server and the terminal with a call server and an operator communications device.

The FIG. 8 illustrates a modality of the method disclosed here, in which stages are executed in which the server executes a data feeding process and validates if there are records with abnormal data in a database, and where the server enters the valid records. to the main database, assigning process data and status data values to them. Also, this figure illustrates steps in which a queue record user call process is executed, user diagnostics is validated, and an early fin detection process is executed.

The FIG. 9 illustrates a modality of the method disclosed herein, in which steps are executed in which response data is obtained from a call between the user and an operator of a terminal connected to the server. The server executes stages in which it sends and receives data to and from the terminal, and stages in which it retrieves, queries, and records data through relationships between tables in the main database. This figure shows how the server can load questionnaires and generate a generation data screen that is sent to the terminal, and shows steps in which it is validated if sufficient responses are received to change the value of the status data of the current process.

Detailed description

The present disclosure is related to systems and methods for the assessment of the risk score of a set of users. In particular, the present disclosure is related to systems and methods for obtaining risk score data (500) from a user (10) in telecare environments.

The method for obtaining risk score data (500) from a user (10) may include a step a) of accessing through a server (100) a database (200) that has a project table (210), a user table (220), a diagnostic tools table (230) and a risk estimation rules table (240).

The project table (210) contains at least one record (211) with a first field with project data (212). Said user table (220) contains at least one record (221) with a first field that includes user identification data (222), a second field that includes pathology data (223) and a third field that relates the project data (212) from the project table (210).

The diagnostic tools table (230) contains at least one record (231) with a first field with a questionnaire data (232), a second field with a question data (233), a third field with an evaluation data (234) and a fourth field that relates to the pathology data (223) of the user table (220). The risk estimation rules table (240) contains at least one record (241) with a first field with a rule data (242), a second field that relates the questionnaire data (232) from the table of risk estimation tools diagnosis (230) and a third field that relates the project data (212) from the project table (210).

The records (231) of the diagnostic tools table (230) may correspond to standardized tests which may be selected from the group comprising Test of DQL, WHOQOL Test, WHOQOL-BREF Test, Minichai Test, Morinsky Test, Hermes Test, Epworth Test and other evaluation tests of clinical, medical, psychosocial, and quality of life variables that are equivalent and what is known by a person moderately versed in the matter.

For their part, the records (241) of the estimation rules table (240) can be associated with the risk estimation requirements of each project and can be selected from the group that includes classification algorithms, mathematical operations, expert knowledge, and weighting. of data.

In addition, the method can have a step b) of receiving in the server (100) a request to generate a form (50) from a terminal (110), which includes user identification data (55), and a step c) Using the server (100) to obtain the record (221) of the user table (220) whose user identification data (222) corresponds to the user identification data (55) of the form generation request ( fifty).

For example, the request for the generation of forms (50) can be made by an operator (20) of a telecare center who communicates with the user (10) by means of a communication system (610). Similarly, the terminal (110) can connect to the server (100) directly or through a computer network (620), through which they exchange information throughout the execution of the method.

Likewise, the method can include a step d) of obtaining, through the server (100), the record (231) of the table of diagnostic tools (230) from the pathology data list (223) of the record (221). obtained in stage c), and a stage e) of obtaining a diagnostic questionnaire (300) through the server (100) from the question data (233) of the record (231) obtained in stage d). Additionally, the method may have a stage f) of transmitting the diagnostic questionnaire (300) to the terminal (110) through the server (100) for its corresponding processing.

In some modalities of the method, when it includes stages a) to f), although the method up to stage f) has not obtained a risk score data (500), the method already allows obtaining the diagnostic questionnaire (300) that It is taken as a starting point to be able to obtain the user information (10) that allows determining the value of the risk tip data (500). In particular, one of the advantages of executing the method between steps a) and f) makes it possible to obtain a diagnostic questionnaire (300) that allows an operator (20) who applies the diagnostic questionnaire (300) to a user (10) to reduce the number of queries that the terminal (110) makes to the server (100) compared to methods in which the terminal (110) sends queries frequently and periodically to determine the questions to ask the user (10). This has a positive effect in reducing the processing and memory load of the server (100), stabilizes and lightens the data traffic in the communication network (90) connecting the server (100) with the terminal (110) and it also decreases the load on the processor and memory module of the terminal (110).

Similarly, obtaining the diagnostic questionnaire (300) by executing stages a) to f) with the server (100) allows increasing the percentages of satisfactory completion of the diagnostic questionnaires (300), because by choosing the number of questions in the diagnostic questionnaire (300) based on the project data (212), pathology data (223), the user (10) receives fewer questions from the operator (20) compared to a method in which in the terminal (110) of the operator (20) a standard questionnaire is presented that would have a greater number of questions, among which there may be questions irrelevant to the user's pathology (10) or to a project with which the user is associated (10).

In accordance with the above, the user (10) receives questions with which he can understand that they are related to his pathology or project to which he belongs, and the possibility of the user (10) unilaterally ending the communication with the operator (20) decreases. ), by For example, because you consider that you are wasting time, or that you are being asked the same thing many times.

The foregoing, in addition to improving the quality of the telecare service that may be related to the execution of the method with steps a) to f), allows reducing the number of empty fields in databases in which the response data can be stored. (350) containing the user's responses (10) to the diagnostic questionnaire (300). This in turn makes it possible to considerably reduce the computational load, memory and consumption of human hours in the pre-processing of data taken as input in data analytics processes, and for example, in artificial intelligence and machine learning processes that are trained with base data arrays containing response data (350) containing the responses of a plurality of users (10) to the diagnostic questionnaire (300).

Said artificial intelligence and machine learning processes can be trained to predict or derive risk score data values (500) taking into consideration response data (350) and other variables, for example, demographic data, sociodemographic data, data pathology (223) and combinations of the above.

However, the method can in any of its modalities include a stage g) of receiving in the server (100) a response data (350) related to the question data

(233) of the diagnostic questionnaire (300) from the terminal (110), and a step h) of obtaining through the server (100) a diagnostic tool data (370) by relating the response data (350) received in step g) with the valuation data

(234) of the record (231) obtained in stage d).

Likewise, these modalities of the method can have a step i) of obtaining the risk score data (500) through the server (100) by relating the diagnostic tool data (370) with the rule data (242) of the registry. (241) related to the data from the questionnaire (232) of the record (231) obtained in stage d). In steps g) to i) the server (100) obtains the response data (350) as input data, and in these embodiments of the method, the server (100) determines the next risk score data value (500). a process based on relational type queries (eg, ORM type).

In any of the modalities of the method, said method can collect a project data set (212), obtain a diagnostic questionnaire (300) from a data set associated with a user (10), evaluate the user's responses (10) (also called response data (350)) to the diagnostic questionnaire (300) and obtain risk score data (500) from the user (10), for example, through a risk assessment process, which it takes as input data the responses of the user (10) to the diagnostic questionnaire (300).

The steps of the method can be carried out under a given project that has project data value (212), which can group the information of the method and determine the particular characteristics of the implementation of said method.

For the understanding of this disclosure, project data (212) will be understood as categorical data with a value that allows it to be identified and/or associated with at least one diagnostic tool and at least one risk estimation rule.

For the understanding of this disclosure, a user (10) will be understood as any living being that has some type of identification, for example, a type of identification with a value that can be stored in a user identification data (720) ( vg, ID number, passport, identity card, serial, demographic and sociodemographic data, and other data that allow users to be identified who are known by a person moderately versed in the matter). The user (10) can enter the information required by the system for obtaining the risk score data (500) of a user (10) directly or through an intermediary, for example, an operator who accesses a terminal (110). The collection of the project data set (212) can be performed by means of a data acquisition process, which collects the information necessary for the execution of the method. The project data set 212 may include a user data set, at least one diagnostic tool data 370, and at least one rule data 242 or risk estimation rule. The user data set may include user identification data (720) and pathology data (223) associated with a user (10). In addition, the data set associated with a user (10) can include quality of life data, clinical data, pathological data, contact data, income data, among others.

Similarly, the diagnostic tool data (370) can include one or more standardized tests for the socio-sanitary and bio-psychosocial assessment of the users, which, when the risk estimation rule contained in the rule data is applied to them, (242) allows the server (100) to obtain a risk score (500) by processing the response data values (350) contains the user's responses (10) to the questions, quizzes, or tests associated with the tool data Diagnostic Questionnaire (370) (e.g., Diagnostic Questionnaire Questions (300)).

The diagnostic questionnaire (300) can be a data set that includes at least one question data (223) generated from the data set associated with a user (10). Question data 223 may include one or more standardized tests associated with a project. The data set of the diagnostic questionnaire (300) can vary from one user (10) to another, because said data set is adapted to the particular information of a user (10), which allows the diagnostic questionnaire (300) is a dynamic questionnaire that includes questions relevant to a risk assessment process that allows determining the value of the risk score data (500).

Likewise, the diagnostic questionnaire (300) can include at least one response data (350) associated with a question, for example, a response data (350) that allows one or more possible values to be displayed (eg, multiple choice answers , binary value responses (YES/NO, False/True), values of dummy-type variables associated with categorical variables) which facilitates the completion of the questionnaire of diagnosis (300) by the user (10), and/or facilitates the application of the diagnostic questionnaire (300) by an operator who communicates with the user (10) (eg, an operator of a telecare service) .

In this disclosure, a questionnaire will be understood as a data or data structure that has fillable fields and/or records, which preferably have indices that contain information that indicates to a user (10), or an operator, what type of information must be entered. in the fields and/or fillable records. In the case of the diagnostic questionnaire (300), the indices can be categorical values, such as questions and requests, which are stored in fields and/or records that are not editable by the user (10) or the operator, but can be edited or modified by the system (particularly by the server (100)) that executes one or more steps of any of the methods disclosed herein.

In any of the modalities of the method, said method can include a risk assessment process of a user (10) configured to obtain a risk score data (500) from the values of the associated response data (350). to user responses (10) to the diagnostic questionnaire (300). To do this, the risk assessment process can score the diagnostic questionnaire (300) and determine the user's risk score value (500) (10).

For example, to score the diagnostic quiz (300), the server (100) may receive response data (350) containing the answers to the questions or tests in the diagnostic quiz (300) and assign a rating to each. one of the answers. The evaluation of a response can be defined by the standardized test to which the question belongs, and this can be qualitative or quantitative.

In addition, the risk assessment process can estimate a value of the risk score data (500) of a user (10) when processing the assessment of the diagnostic questionnaire (300) by applying to the response data (350) some rules of risk estimate that may be stored in one or more rule data (242). The risk estimation receives the evaluation of the diagnostic questionnaire, obtains the rules of estimation associated with a project related to a project data (212) from the information collected, and processes the assessment of the diagnostic questionnaire (300) with the risk estimation rules to obtain the risk score data (500) of the user (10). Risk estimation rules may include conventional calculation, averaging, weighting, and estimation steps, methods, or processes or advanced computing techniques, for example, processes related to artificial intelligence and machine learning. In addition, the risk estimation can calculate an overall risk score of a set of users from the risk score data (500) of each of the users.

In any of the modalities of the method, the risk score data (500) of a user (10) can be a quantitative measure of the risk that a user (10) faces. The risk score data (500) of a user (10) can be selected from the data group that includes a socio-health risk score data, a bio-psychosocial risk score data and equivalents known by a moderately versed person. in the matter or combination of the above. In any of the modalities of the method disclosed here, the risk score data (500) can be taken as input data for an intervention plan generation process, which obtains an intervention plan data for each user ( 10).

The intervention plan data mentioned above can be a data, file or data set that has information related to one or more instructions that must be executed by a user (10) with the main objective of reducing the risk score data (500 ) of said user (10). The instructions can be related to the well-being, physical, mental and social health of a user (10). For example, the intervention plan can be consulted directly by a user (10), or it can be communicated and/or explained to the user (10) by an operator of a telecare center.

The intervention plan data can be sent from the server (100) to the operator's terminal (110) or to a user's computing device (10) (eg, smart phones (smartphones), smart watches (smartwatch), tablets, computers , computers, and similar devices known by a person moderately versed in the matter).

Referring to FIG. 1 and FIG. 2, in step c), the server (100) can obtain the record (221) from the user table (220) whose user identification data (222) corresponds to the user identification data (55) of the request form generation (50). For this, the server (100) can consult the user identification data (55) of the form generation request (50) in the records (221) of the user table (220) and receives the record (221). retrieved by the database (200) if the user identification data (222) of the record (221) is equal to the user identification data (55) of the form generation request (50), otherwise the server ( 100) receives a null data.

In step d) of the method, the server (100) can obtain the record (231) from the diagnostic tools table (230) from the pathology data (223) relationship of the record (221) obtained in the stage c). The server (100) consults the pathology data (223) obtained in step c) in the diagnostic tools table (230) and obtains the record (231) corresponding to the standardized test that is related to the pathology data ( 223) of the record (221).

Once the record (231) of stage d) has been obtained, the server (100) proceeds to obtain, in stage e), a diagnostic questionnaire (300) from the question data (233) of the record (231). . The diagnostic questionnaire (300) is a document that can include one or more question data (233) from at least one record (231) and one response space for each question data (233). Subsequently, in stage f), the server (100) transmits the diagnostic questionnaire (300) to the terminal (110) for its corresponding completion. The diagnostic questionnaire (300) can be completed by the user (10) at the terminal (110) or by an operator (20) of a call center who communicates with the user (10) through a communication system (610). ) at the terminal (110). In addition, the server (100) receives, in step g), a response data (350) related to the question data (233) of the diagnostic questionnaire (300) from the terminal (110). For the above, the terminal (110) sends a response data (350) for each question data (233) included in the diagnostic questionnaire (300) through the computer network (620), once the diagnostic questionnaire ( 300) is completed by the user (10) or the operator (20).

Referring to FIG. 1 and FIG. 2, in step h), the server (100) can obtain diagnostic tool data (370) by relating the response data (350) received in step g) with the evaluation data (234) of the register ( 231) obtained in step d). The server (100) processes the response data (350) by the judgment data (234) to obtain a diagnostic tool data (370). The assessment data (134) corresponds to a standardized test data from the record (231) and determines the assessment of the response data (350) received in stage g), as a response to the question data (233) of the diagnostic questionnaire. (300). The diagnostic tool data (370) may include alphanumeric characters representing a qualitative or quantitative assessment of the response data (350).

Similarly, in step i), the server (100) can establish a field with a user's risk score data (500), by relating the diagnostic tool data (370) with the rule data (242). of the record (241) related to the questionnaire data (232) of the record (231) obtained in stage d).

In any of the modalities of the method, said method can include in step a) accessing a database (200) through a server (100) a substep al) accessing a database through a server (100). (200) from one or more healthcare provider institutions, medical centers, patient portals, medical record systems and healthcare professionals.

In any of the modalities of the method, said method also includes a stage I) of selecting through the server (100) at least one intervention plan stored in the database (200) based on the risk score (500) of the user. The plan of intervention includes one or more instructions to reduce the user's risk score (10).

Similarly, the method may include a step of obtaining by the server (100) a risk score of a set of users from the risk scores (500) of the records (221) of the user table (220).

In any of the modalities of the method, said method also includes a step JA) of receiving in the server (100) an alert data packet (710) from the terminal (110), and a step JB) of registering through the server (100) the early warning data (710) in the record (211) of the user table (220) whose user identification data (222) is related to the user identification data (720) of the data packet alert (710). Said data packet (710) has early warning data and user identification data (720). Also, the early warning data includes an alert type data and a priority data.

On the other hand, referring to FIG. 3, the present disclosure also describes an embodiment of the method for obtaining risk score data (500) from a user (10), executed by a server (100) comprising a step A) of receiving from a terminal (20) a process start command (800) including a process data value (801) equal to "assessment"; and a stage B) of loading a record (802) from a user-project table (803), belonging to a main database (820), where the record (802) includes a process data value (801) equal to to “assessment”.

Furthermore, this embodiment of the method has a step C) of loading a plurality of response data values (350) associated with a project to which the user (10) belongs; where the response data values (350) are obtained by relating a key data (804) of the user's (10) record (802) and to consult in a table of responses-questionnaires (805) the response data values ( 350) associated with the user (10).

Additionally, in this modality the method includes a stage D) of obtaining at least one risk score data (500) from the user (10) by executing at least one process of qualification (806) taking as input the response data (350). Preferably, the qualification process (806) is a rule-based process (807); where each rule (807) corresponds to an evaluation test that measures a psychosocial, medical, physiological, health variable of the user (10); and where each rule (807) is consulted relating the key data (804) of the registry (802) of the user (10).

This modality of the method has among its technical advantages that the data structures of the main database (820) reduce the memory consumption and computational load of the server (100) in comparison with the modalities of the method where the tables of project (210), diagnostic tools table (230) and risk estimation rules table (240) related to each other as described above.

In particular, the main database (820) can be an enhanced version of the database (200), or can be generated from said database (200). One of the improvements is that the data from the main database (820) is segmented into a plurality of tables that have key data (804) in one or more of their fields that allow the tables to be related to each other. For example, the users-projects table (803) makes it possible to group a plurality of user records (10) that can belong to different projects. Furthermore, this data structure allows a user (10) to be associated with two or more projects, without this generating errors in the server (100) when the terminal (110) sends a query request in which it is included as an identifier. of the user (10) his identification data (eg, citizenship card, DNI, driver's license). In the case where there are project tables (210), if a user (10) is registered in two projects, said user (10) appears in two project tables (210) and this could generate errors on the server (100 ), and limited the scalability of the method, for example, adding additional project tables (210) associated with other projects, health entities, among others. On the contrary, having key data (804) that relates the tables of the main database (820) allows to improve scalability since it facilitates the addition of tables, and the inclusion of new projects and health entities to which the same user is associated (10). On the other hand, in order to lighten the memory consumption and computational load of the server (100), the information registered in the project tables (210), diagnostic tools table (230) and the table of estimation rules of risk (240) can be segmented into a plurality of tables related to each other by the key data (804). For example, a user table (824) may include fields where detailed demographic, medical, contact, and type of affiliation information to health entities is stored. Now, the users-projects table (803) is a lighter table than the users table (824) because its fields mainly store the key data (804) that allow the server (100) to identify the relationships that you are taken to consult the detailed tables.

Optionally, the users-projects table (803) can include fields where variables and data required for calculating the risk score data (500) of each user (10) are stored. This has the advantage that, when the server (100) loads the users-projects table (803), it has access to the most relevant information of the users (10) for the calculation of the risk score data (500), which It allows reducing the number of queries between other tables through relationships, which, in turn, implies a reduction in computational and memory consumption of the server (100).

On the other hand, an example of a detailed table is a table of health provider entities that have fields in which variable values are stored such as: name of the health provider entities, key data (804) that relate the tables of health provider entities with other tables, date of creation, date of last update, among others. Another example of a detailed table is the table of responses-questionnaires (805), in which response data values (350) associated with user responses (10) to the forms and questions previously applied by the user (10) are stored in their fields. the operator (20).

Similarly, the main database (820) may have other detailed tables such as drug tables, diagnosis tables, medical diagnosis tables - drugs that associate medical diagnoses with drugs from the drug table, laboratory results tables, tables laboratory diagnostics, tables of user responses to questionnaires and forms applied to the user (10) by the operator (20), tables of rules for classification/qualification processes, project tables where information, variables and project data (212) of each project, user authentication data tables, and any other type of table that include key data (804) to be related to other tables, and include detail data related to users (10), their demographic, medical, psychosocial, and/or details of projects associated with the execution of the method by the server (100), which are known by a person moderately versed in the matter.

In this embodiment of the method, fields in which process data values (801) and state data (814) are stored are also included in the records of one or more tables of the main database (820). The process data (801) and status data (814) represent steps of the user service process (10) by the operator (20), which in this modality is divided into processes that in turn have one or more state. For example, the processes can be “recruitment”, “assessment”, “intervention”, “monitoring” and “evaluation/follow-up”. Similarly, the states can be “caught”, “not caught”, “call pending”, “test 1”, “test 2”, “test i”, “test n”. The process data (801) and state data (814) take categorical, or boolean values that logically determine which process and state is active. Process data (801) and status data (814) will be explained in more detail later.

However, this segmentation of the user service process (10) has the technical advantage of reducing the number of queries to the server (100) by the terminal (110), since, when the operator (20) enters the terminal (110) a command to start the process (800), the server (100) will load the tables associated with the current state of the selected process, and will avoid loading tables of other states and processes unless in the interaction of the operator (20) with the terminal (110), the server (100) determines that the stage or process has been changed, for example, when the user (10) answers all the questions programmed for the call with the operator (20) . This has a positive impact on the memory consumption and computational capacity of the server (100) and the terminal (110). In addition, when the operator (20) finishes interacting with a user (10), and prepares to attend a next user (10), preferably, the terminal (110) will automatically initiate a new call (for example, with the help of of a communications platform connected to the terminal (110) and to the server (100), where the new call will also be for a user (10) who has the same active process as the previous one.In this way, the previously loaded tables could be still loaded in a temporary memory device of the server (eg cache memory), which speeds up the computational process compared to the case in which the operator (20) selects a user (10) who changes processes and requires loading different tables.

Another advantage of segmenting the user service process (10) is that the number of unsuccessful calls is reduced, in which the user (10) suddenly cuts off communication because the number of questions that apply to them are too many, and it causes you stress, impatience, or you simply do not have enough time to answer all the questions that need to be answered in order to have the necessary data to calculate the risk score data (500). This advantage is not only of service, but also computational, since by having more successful calls, in which the response data (350) are captured gradually but constantly, the average number of queries to the server is reduced (100 ) by the terminals (110) of all the operators (20).

On the other hand, this modality of the method can include additional steps that configure other alternative modalities that share steps A) to D).

For example, referring to FIG. 3, an embodiment of the method that includes steps A) to D) may also include a step E) of assigning to the record (802) at least one risk class data (808) by means of a classification process (809) that takes as input the at least one risk score data (500). Preferably, the risk class data (808) has values associated with psychosocial, medical, physiological, or sanitary of the user (10) that are assigned based on the magnitude of the value of at least one risk data (500).

For example, the risk class data 808 may have a risk type identification data, which may have categorical or boolean values. For example, risk class data (808) may have a risk type identification data that takes values such as "psychosocial risk", "medical risk", "risk of non-adherence to treatment", "risk of development of new pathology”, “fall risk” and similar or equivalent values known by a person moderately versed in the matter that allow a user (10) to be classified within a type of risk.

Also, the risk class data 808 may store a qualitative variable configured to rank the value of the risk score data 500 on a predetermined scale. In addition, the risk class data (808) can have a risk magnitude data, which can take categorical, Boolean, or numeric values, and allows the user's risk (10) to be classified within a predetermined hierarchy.

In an example of this modality of the method, the risk magnitude data can take values such as "High risk", "medium risk", "low risk", or it can take numerical values on a scale of 1 to 5, 1 to 7, 1 to lO, or any other type of value that allows user risk levels to be defined (10).

Regarding the qualification process (806), this process takes into account rules (807) previously fed to the main database (820) or in any other database (200) to which the server (100) has access. , which are preferably stored in a rules table that has key data (804) that allows the fields and records of the rules table to be related to other tables in the main database (820).

Each rule (807) can be defined based on the expert judgment of a health professional, or can correspond to evaluation criteria of structured tests, for example, of tests such as Clinical Goals tests configured to determine the level of progress in the clinical evolution of a user, adherence to treatment test (eg, Morinsky test), quality of life test (eg, WHOQOL, WHOQOL-BREF), attendance test at medical check-ups, confirmation/verification test of diagnosis of pathology, Epworth test, MINICHAL test, Hermes test, and any other test configured to determine or quantify a variable related to the state of physical and mental health of the user (10).

In addition, the rules (807) can include decision criteria, one or more data, conditionals, weights or criteria that allow the value of the risk score data (500) to be obtained.

For example, the qualification process (806) can be a decision tree-based machine learning process, where one or more of the rules (807) are parameters, hyperparameters, or conditionals that allow defining how the ramifications of the decisions are generated. trees, for example, based on threshold values (for numeric variables), or lists of values (categorical variables) of variables extracted from the response data (350).

Examples of hyperparameters are the minimum number of children that a tree node must have in order to split down to a lower hierarchical level. These hyper parameters can be chosen by means of trial and error, for example, adjusting the values (manually or automatically) to obtain the best possible result,

Accordingly, the qualification process (806) may be a decision tree-based machine learning process selected among machine learning-based regression processes, for example, among extreme gradient-boosted tree regression processes (XGBoost Trees), Random Forest Regression (RF) regression processes, and Ordinary Least Squares (OLS) regression.

For its part, the classification process (809) can be any type of clustering process (clustering, in English), or classification configured to assign the data of risk class (808) based on the results of the risk score data (500). According to the above, the classification process (809) can be selected among support vector machines, kernel estimation, k-th neighborhood, decision trees, alternating decision trees, in English), simple decision trees, linear decision trees, deterministic decision trees, randomized decision trees, non-deterministic decision trees, quantum decision trees, pruning decision trees (Decision tree pruning), forests randomizers, neural networks (eg supervised, backpropagation, forwardpropagation), learning vector quantization, and other machine learning techniques, algorithms, or sorting, cluttering, or ordering processes known to one of ordinary skill in the art.

Alternatively, the classification process (809) can be a manually configured expert process with conditionals (e.g., “if', “while” loops, nested loops) whose compliance criteria are determined based on rules (807) generated from the experience of a health professional.

On the other hand, in any of the modalities of the method in which the server (100) accesses and/or loads tables from the main database (820), the method can include a stage AA) prior to stage A) of obtaining a main database (820) updated by means of a data feeding process (810) that takes as input a first database (200) received from a computational device (811).

The data feeding process (810) includes a sub-step AA 1) of obtaining a group of affected records (812) that includes at least one record from the first database (200) by means of a data preprocessing method (813). which takes as input the first database (200).

Referring to FIGS. 4 and FIG. 8 , the data preprocessing method (813) may include a substep AA1) of obtaining a set of affected records (812) that includes at least one record from the first database (200) by means of a data preprocessing method ( 813) that takes as input the first database (200); and a step AA2) of obtaining an alert data (831) that includes a plurality of identification data "ID" of the records of the affected group of records (812).

Also, the data preprocessing method (813) may include a substep AA3 of storing in the main database (820) the records that do not belong to the group of affected records (812); and a substep AA4) of assigning to each record added to the main database (820) a process data value (801) equal to "retrieve", and a status data value (814) equal to "call pending". . Records added to the main database (820) may be stored in at least one user table (824) having a plurality of fields storing key data (804) configured to relate the user table (824) to a plurality of tables of the main database (820).

Referring to FIG. 8, step AA) and its data preprocessing method (813) may be integrated with the "get" process. Particularly, in FIG. 8 and FIG. 4 illustrates a sequence of capture process steps that start with receiving the database (200) from the computational device (811) to start the data feed process (810). The server (100) then executes the data preprocessing method (813), which is illustrated as a conditional in FIG. 8. If so, if the data preprocessing method (813) detects affected records, then it groups them into the group of affected records (812) in step AA1), and then generates the alert data (831) in the stage AA2). Also, whether serial or parallel, the server (100) may execute step AA3) in which the unaffected records are fed to the main database (820). Furthermore, if the data feed process (810) finds no affected records, then steps AA1) and AA2) are omitted and proceed to step AA3) to feed the main database (820) with all the records. received in the database (200). In any case, whether or not affected records are detected (812), the server (100) after stage AA3) executes stage AA4), and the records fed to the main database (820) take a value of process data (801) equal to "retrieve" and status data value (814) equal to "call pending". The "pending call" value of the status data (814) of the "retrieve" process makes it possible to group the records of the main database (820) that have a call pending to be made, particularly the call in which it is contacted by the user for the first time (10) and in which explicit consent is requested to continue in the user service process (10), and/or agrees to participate in one or more projects (each identified with project data (212 )).

For example, referring to FIG. 8 after sub-step AA4) a calling process (836) can be started taking into account the queued records. The queued records are records from the main database (820) with the value "call pending" of the status data (814) and the value "capture" of the process data (801). In this call process, the server (100) receives a start process command (800) from a terminal (20), which also includes status data (814) with a value "call pending" and the data of process (801) with a value "fetch". In this way, the server (100) loads and/or accesses the call pending records that are in the capture process. Subsequently, the server (100) communicates with the terminal (110) to initiate the call.

Optionally, the server (100) and the terminal (110) are connected to a computer network (620) to establish a service-based communications protocol (835) that interconnects the server (100) with at least one call server (828). ) configured to allow communication between a first communications device (829) of the operator (20) and a second communications device (830) of the user (10); and exchange data with the server (100) related to the calls made by each operator (20). Alternatively, the terminal (110) can have a communications module configured to establish an IP voice protocol to execute the call via the Internet. Likewise, the operator (20) can have a communications device, such as a conventional telephone, smartphone, tablet or similar device that allows him to make the call, either automatically triggered by the terminal (110) or manually by dialing the user's telephone number (10). Once the operator (20) initiates the call, the server (100) and/or the terminal (110) executes a first conditional (837) where it is verified if communication with the user (10) can be established. If not, the server (100) and/or the terminal (110) execute a second conditional (838) in which it is validated if the number of contact attempts (unanswered or canceled calls) is less than a predetermined number " nor” (eg 4, 5, 6, 10, 20 calls). If so, a step of assigning a wait time before repeating the call is executed (839) and the record corresponding to this user is queued, and a call process is started (836) with the following record in line. From counting, if the number of contact attempts (unanswered or canceled calls) is greater than or equal to a predetermined number "ni", then the server (100) executes a step of storing records in a Non-Duty Users Table (840) in order to group the user records (10) to which their permanence in the project to which they are assigned must be re-evaluated.

Now, when the user (10) answers the call, the operator (20) validates whether the user (10) accepts the service. This validation is a third conditional (840) that is executed by the server (100). If the user (10) rejects the service, the operator (20) interacts with the terminal (110) to communicate to the server (100) the acceptance of the service, thereby starting a step to obtain justification data. of rejection (841) in which the server (100) sends to the terminal (110) a screen generation data that allows the terminal (110) to display a screen with fillable fields in which the operator (20) can recording comments and explanations of the user (10) for which he rejects the service, and then, the step of storing records in a Non-Service User Table (840) is executed.

On the contrary, if the user (10) accepts the service, the operator (20) interacts with the terminal (110) to communicate to the server (100) the acceptance of the service, and the server (100) executes a step of change of values (842) in which the values of the process data (801) are modified to "capture" and of the status data (814) to "captured", with which the "capture" process is finished Preferably, before changing the value of the process data (801) to "assessment", the process data (801) can take a value of "feedback" and a status data (814) "diagnosis confirmation pending". This status value of "diagnosis confirmation pending" can be present simultaneously with the value "pending call" or the value "received". In the event that the status data (814) simultaneously has the values "call pending" and "diagnosis confirmation pending", after the user (10) accepts the service, the terminal (110) sends the server ( 100 a process start command (800) that includes a process data value (801) equal to "capture" and a status data (814) equal to "diagnosis confirmation pending"; and then, the server ( 100) executes a step of EE) verifying a diagnostic data value (821) of the user (10).

Referring to FIG. 6, step EE) may include a sub-step EE1) of receiving a drug data value (822) that is supplied by a user (10) during a call with the operator of the terminal (110); and a sub-step EE2) of comparing the value of the drug data (822) with a pathology data (223) associated with the user (10), and which is included in a table of drug types (823) that belongs to the database main data (820). The drug types table (823) can be related to the user-project table (816) by means of a key data (804). Furthermore, the comparison may be made by a second comparison process (834) based on rules provided by an expert similar to the qualification process (806) based on rules (807) described above. For example, the expert can be a health professional with knowledge of what are the usual drugs for the treatment of pathologies, for which rules can be built that relate the drug data value (822) that is supplied by a user (10) during a call with the operator (20) to validate if this medication declared by the user (10) is associated with a pathology data (223) related to the project to which said user (10) is registered.

In addition, step EE) may further include a sub-step EE3) of obtaining diagnostic confirmation data (825) if the drug data value (822) matches a predetermined drug data value (825) associated with the drug data value (825). pathology (823) and end step EE), otherwise obtain diagnostic alert data (826) and continue to sub-step EE4). Sub-step EE4) is to assign a value of "healthy user" in the user record (10), if the drug data (822) has a null value, otherwise, assign a value of "pending program change" in the user record (10), if the drug data (822) is equal to a predetermined drug data value (825) associated with a pathology data (823) different from the pathology data (823) stored in the user record (10).

One of the advantages of executing the EE stage) is that it validates in advance if a user (10) associated with a project is correctly assigned, or if it is an assignment error. This makes it possible to reduce the number of queries to the server (100) by terminals (110) that, in later stages of the user service process, continue to monitor healthy users (10), or users (10) who do not have a clinical picture consistent with the care service provided. In addition, this makes it possible to correct errors in the main database (820) that would be difficult to detect with computational means, or that would require direct supervision of people who review and validate each of the records, which is technically unfeasible when the database main data (820) has records for thousands or millions of users (10).

The drug data value (822) can be categorical or alphanumeric, for example, it can be the trademark of a drug, medically generic name, active ingredient name, and can be accompanied by data such as pharmaceutical vehicle used, presentation of the medication (pills, capsules, tablets, injectables, etc.) and concentration of active component. Alternatively, the main database (820) can include a drug table where all the drugs and their associated data are listed, and that includes one or more key data (804) that allow relating said drug table with other tables. from the main database (820).

On the other hand, referring to FIG. 9, in embodiments of the method where the server (100) queries the main database (820), the server (100) can obtain the response data values (350) associated with a project to which the user belongs. (10) before stage A). For example, the method may include a step BB) of receiving from a terminal (20) a start process command (800) that includes a process data value (801) equal to "assessment"; and a step CC) of executing a user call process (815) including a sub-step CC1) of loading a user-project table record (816) belonging to the main database (820). where the loaded record is associated with a user (10) and where the loaded record includes a process data value (801) equal to "assessment".

In addition, the user call process (815) may include a sub-step CC2) of identifying a status data value (814) in the register loaded in sub-step CC1); and a substep CC3) of obtaining ID data (817) from diagnostic questionnaires (300) pending response associated with a project to which the user (10) belongs and associated with the value of the status data (814) identified in substep CC2). The ID data (817) can be obtained by relating a key data (804) of the loaded record and consulting the response-questionnaires table (805) for the response data values (350) associated with the user (10) who has “null” value.

Also, the user call process (815) can include a substep CC4) of obtaining a first screen generation data (819) that includes a form with a plurality of questions extracted from the diagnostic questionnaires (300) associated with the ID data (817); and a step CC5) of sending to the terminal (20) the first screen generation data (819) configured so that the terminal (20) displays a first screen (821) with the form.

Likewise, the user call process (815) can include a sub-step CC6) of receiving from the terminal (20) at least one response data (350) that includes the responses to the form that the operator (20) obtains when calling the user(10); and a sub-step CC7) of recording the at least one response data (350) in the response-questionnaire table (805). In addition, the user call process (815) can include a substep CC8) of modifying the value of the process data (801) or the status data (814) by means of a first comparison process (833) that validates the number of user responses (10) against a number of responses required to change the status data value (814); and a substep of CC9) repeating step CC1) loading a record from a different user (10).

In the modalities of the method in which stages BB), CC) and their sub-stages are executed, one of its technical advantages is that the "assessment" process is segmented into different states associated with the next test that must be applied to the user. For example, the status data (814) can take values such as "test 1", "test 2", "test i", "test n" when the value of the process data (801) is "assessment". According to the above, to determine the value of the risk score data (500), preferably two or more calls are made to the user (10) by the operator (20), in order to avoid incomplete calls canceled by the user. (10), or with incomplete or imprecise information provided by the user (10) due to fatigue and/or boredom.

However, if in substep CC8) it is determined that responses associated with the questionnaire related to the value of the current status data (814) are missing, then the server maintains the value of said status data (814) and the record is set. of the user in queue for a future call, preferably, assigning a predetermined wait time (e.g. one week, one month, two months, six months), or a wait time indicated by the user (10) during the call with the operator (20) (v.g. the user (10) does not have time at that moment, but in a couple of hours, or the next day, the following week).

On the contrary, if in substep CC8) it is determined that all the responses associated with the questionnaire related to the value of the current status data (814) have been answered, then the server (100) changes the value of said status data ( 814) to a hierarchically superior value (for example, it goes from “Test 1 ” to “test 2”), and if the last value of the status data (814) is reached (for example, “Test n ”, “Final Test” ), then, the server (100) changes the value of the process data (801) to "intervention

For example, when the value of the process data (801) changes to "intervention", the server (100) can execute a step I) of assigning to the user record (10) an intervention plan data by means of a classification process. (831) that takes as input the value of the risk score data (500) of the user (10), where the plan data intervention includes one or more instructions configured to reduce or contain the user's risk score (500) data value (10).

On the other hand, in any of the previously described modalities of the method, referring to FIG. 3, the method may further include an early warning detection process (843) in which the server (100) sends an early warning factor detection test to the terminal (110), which is displayed on a screen to that the operator (20) can fill it out in the event that during the conversation with the user (10) he detects a physical, psychosocial, sociodemographic risk factor, or another factor that may affect the user's physical or mental health in the short or medium term (10). Examples of risk factors may be that the user (10) reports that he does not have his medications, or does not take them on time, or that he changed or modified his medical formula without prior medical authorization. Also, other risk factors may be related to physical mobility difficulties, absence of caregivers for pathologies that require it, report of acute illnesses (e.g. Covid-19, acute respiratory infections, traumas from accidents), report of symptoms of pathologies and/or psychological or psychiatric disorders, and any other factor that is relevant and affects the physical and/or mental health of the user (10).

Referring to FIG. 3, the early warning detection process (843) may include a conditional (844) in which the server (100) validates whether the operator (20) filled in the early warning factor detection test fields during a call to a user (10), and if so, the server (100) executes a step (845) of storing user early warning factor detection tests in the main database (820) (e.g. in an alerts table warnings with at least one field where key data is stored (804) that allows the early warning table to be related to the other tables).

Subsequently, the server (100) proceeds to initiate the early warning process (846), which may include programming and/or automatic or assisted generation of reports that are periodically notified to the entity that contracts the project in which it is registered. the user (10), for example, the entity can be an EPS, IPS, state or private entity that provides health services, insurer, or any other similar or equivalent institution or entity known by a person moderately versed in the matter.

On the other hand, the present disclosure also describes modalities of a system for obtaining risk score data (500) from a user (10) that includes a server (100) configured for any of the previously described modalities of the method, and a terminal (110) that communicates via a computer network (620) with the server (100).

Referring to FIG. 1 and FIG. 3, the terminal (110) can communicate with the server (100) and they exchange information for the development of the method. The system described here is configured to execute any of the modalities of the previously described method.

The server (100) is a computational device that allows the execution of the method of the present disclosure. The server (100) may be selected from the group comprising web servers, dedicated servers, shared servers, email servers, cloud servers, database servers, FTP servers, cluster servers, file servers, and equivalents known to the public. a person moderately versed in the matter or a combination of the above.

The terminal (110) can connect with the server (100) directly or through a computer network (620), through which they exchange information in one or more stages of any of the modalities of the method.

As previously indicated, in some modalities of the method an operator (20) accesses the terminal (110), for example, from a telecare center. The operator (20) can communicate with the user (10) through a communication system (610). Accordingly, in any of the system embodiments, the system may include a communication system (610) or may be connected to a communication system (610). For the understanding of this disclosure, the communication system (610) shall be understood as instant messaging applications, voicemail, cellular telephony, fixed telephony, videoconferencing applications, text messages, social networks and equivalents known by a person. moderately versed in the subject or combination of the above.

For example, the communication system (610) may include hardware elements configured to establish communication with another device, for example, a telephone, or a computing device that is accessed by the user (10). For example, the communication system (610) may include a communications module (e.g., communication devices for VoIP, communication devices that operate in audio and/or video transmission protocols, such as GSM, GPRS, 2G, 3G, 4G, 5G) configured to send and receive audio and/or video data between the communication system (510) and the computing device (eg, telephone, smartphone, tablet, personal computer) from which the user accesses (10).

For the understanding of this disclosure, a computer network (620) will be understood as the interconnection of computer equipment that allows the exchange of information among themselves and that includes a network protocol that governs said exchange. The network protocol selects from the group comprising RS-(232), RS-485, ARP, RARP, Ethernet, Fast Ethernet, Gigabit Ethernet, Token Ring, FDDI, ATM, HDLC, CDP, IPv4, IPv6, X.25, ICMP, IGMP, NetBEUI, IPX, TCP, UDP, SPX, SNMP, SMTP, NNTP, FTP, SSH, HTTP, NFS, Telnet, IRC, POP3, IMAP, LDAP, Internet, and equivalents known to a person of ordinary skill in the art or combination of the above.

For its part, the terminal (110) can be a computer interface that allows a system operator (20) to access an application to collect the information and view the results of the analysis executed by the server (100). The terminal (110) can include a computing device that can be selected from the group that includes microcontrollers, microprocessors, DSCs (Digital Signal Controller), FPGAs (Field Programmable Gate Array), CPLDs ( Complex Programmable Logic Device), ASICs (Application Specific Integrated Circuit), SoCs (System on Chip), PSoCs (Programmable System on Chip), computers, servers, tablets, cell phones, smart phones, drives computing and equivalents known by a person moderately versed in the matter or combination of the above. In addition, the terminal (110) preferably includes a human interface device (HID) and a display device that allow the operator to enter and view commands, requests, and generally interact with the terminal (110).

During the execution of any of the modalities of the method, the server (100) can obtain a project data collection that includes a user data package, a diagnostic tools data package and an estimation rules data package. risky. The user data package and the diagnostic tools data package may be related by pathology data (223).

The user data packet may include user identification data (222) and pathology data (223) for each of the users. The user identification data (222) is configured to facilitate consultation of the data set associated with a user (10) and can include alphanumeric characters and punctuation marks. The pathology data (223) makes it possible to relate the pathologies of a user (10) with the diagnostic tools.

The diagnostic tools data package can include standardized tests for socio-sanitary and bio-psychosocial assessment with a question data (233) and an assessment data (234). Standardized tests evaluate by means of the evaluation data (234) the answer to a question defined by the question data (233). The diagnostic tools can be selected from the group that includes the DQL Test, the Minichal Test, the Morinsky Test, the Hermes Test and equivalent tests known by a person moderately versed in the matter or a combination of the above. The risk estimation rule data package includes a rule data 242, which determines the risk estimate from the information of the results of testing by the diagnostic tools. The rule data (242) can vary according to the risk estimation requirements of each project and can be selected from the group that includes classification processes, calculation processes, estimation, weighting and regression based on mathematical techniques, statistics, heuristic models and combinations. of these, and similar or equivalent processes known by a person moderately versed in the matter.

For example, classification processes can be selected from the group comprising Logistic Regression, K Near Neighbor Discriminant Analysis, Decision Trees, Support Vector Machines, Neural Networks, Bayesian Classifier, equivalent classification processes known to a person moderately versed in the field. matter and combination of the above.

On the other hand, the project data set 212 may be stored in a memory module or data storage module selected from the group including servers associated with search engines, data warehouses, databases, geographic information systems , OPC Servers, I/O Servers, Application Programming Interface (API), Enterprise Resource Planning (ERP) system, Encryption Mechanisms, Cloud Services and equivalents known to a person of ordinary skill in the art or combination of the previous ones.

In addition, the present disclosure relates to a computer-readable medium that includes instructions that, when interpreted by a computing unit or server (100) (v.g. the computing unit (100)) allows to execute any of the methods disclosed herein.

The computer-readable medium can be selected from executable files, installable files, compact discs, RAM memories (Cache, SRAM, DRAM, DDR), ROM memory (Flash, Cache, HDDs, SSD, EPROM, EEPROM, Removable ROM memories ( vg SD (miniSD, microSD, etc), MMC (MultiMedia Card), Compact Flash, SMC (Smart Media Card), SDC (Secure Digital Card), MS (Memory Stick), among others)), CD-ROM, Digital Versatile Disc (DVD) or other optical storage, cassettes magnetic, magnetic tape, storage or any other medium that can be used to store information and can be accessed by a processing unit.

The computer-readable medium can be a set of computer-readable elements into which instructions are divided or divided, which, when executed by the server (100) or by one or more servers or computing units that are part of the server (100) or that belong to a system with a service-based network architecture of which the server (100) is a part, allow the steps, stages, and sub-stages of a method to be carried out according to any of the modalities of the methods previously described in this disclosure.

Similarly, this disclosure relates to a computer program that includes instructions that, when interpreted by a computing unit or server (100), allows any of the methods disclosed here to be executed.

The computer program can be divided into two or more files, protocols, computational models, and combinations of these that are instantiable, executable, and/or installable that are configured to install and/or execute or instantiate instructions on the server (100) or on one or more servers or computing units that are part of the computing unit (100) or that belong to a service-based network architecture system of which the computing unit (100) is a part. Said installed, executed or instantiated instructions generate that the hardware elements of the system can execute the modalities of the previously described method.

Examples:

Example 1:

In a first example of the method disclosed here, the method is associated with a project for the prevention of complications generated in diabetic patients. In the first place, the data structure that this example of the method takes into consideration is explained, which is a relational database (200) that is made up of a project table (210), a user table (220), a table of diagnostic tools (230), and a table of risk estimation rules (240).

In this example, the project table (210) is a table generated in CSV format that includes a plurality of records (211) that store the project data (212), which contains the information on the project for the prevention of complications generated in patients. diabetics. In this example, the project data (212) stores information on the health service provider entity that hires or executes the project for the prevention of complications generated in diabetic patients, information related to the number of users (10) (patients) that They want to process, among other data and information relevant to the project for the prevention of complications generated in diabetic patients.

For its part, the user table (220) has a plurality of records (221), where each at least one record (221) with a first field that includes user identification data (222) that contains the identity card numbers. citizenship, ID number, or passport number of the user (10), a second field that includes a pathology data (223) that the user has or is suspected of having (10), and a third field that relates the project data (212) from the project table (210).

The user table (220) stores information on a plurality of users (10) (patients in this case) who may or may not belong to the project for the prevention of complications generated in diabetic patients. In particular, the users who do belong to the program for the prevention of complications generated in diabetic patients are those who have a pathology data value (223) true, when the pathology data (223) is a Boolean variable with a true value when the user (10) has or is suspected of having diabetes, and a false value when the user (10) does not have or is suspected of having diabetes. For its part, the diagnostic tools table (230) contains a plurality of records (231), where each record (231) has a first field with questionnaire data (232), a second field with question data ( 233), a third field with an assessment data (234) and a fourth field that relates to the pathology data (223) of the user table (220).

In the table of diagnostic tools (230) the diagnostic questionnaires (300), questions and evaluations related to the users (10) are recorded. In particular, the table of diagnostic tools (230) of the present example can include in its records (231) information from users (10) of the project for the prevention of complications generated in diabetic patients, and users of other different projects. However, the users (10) who do belong to the project for the prevention of complications generated in diabetic patients have a value in the fourth field that relates their pathology, in this case diabetes, with the user table (220) where said user (10) is registered and has a pathology data value (223) true.

The table of risk estimation rules (240) contains a plurality of records (241), where each record (241) has a first field with a rule data (242), a second field that relates the questionnaire data (232 ) from the diagnostic tools table (230) and a third field that relates the project data (212) from the project table (210). In this example, the rule data (242) and the questionnaire data (232) contain the relationships and logical rules that allow obtaining the risk score data (500) of a user (10).

Now, during the execution of this example of the method, an operator (20) accesses a terminal (110) that connects to the server (100). In the terminal (110) messages and screens are displayed that tell the operator (20) to select which project to work on, in this case, the operator (20) selects an option (eg, a button on the screen, a written command) related to with the project for the prevention of complications generated in diabetic patients. When the operator (20) selects the option, the method executes step a), whereupon the server (100) accesses the database (200) described above. At this point, the terminal (110) displays a screen in which the users (10) who should be contacted to determine if they are at risk of complications from diabetes are identified.

Then, the operator (20) selects on the displayed screen an option that corresponds to the selection of one of the users (10) that must be evaluated. With this selection, the terminal (110) generates the form generation request (50) and sends it to the server (100). When the server (100) receives the form generation request (50), steps b) to e) are executed. In these stages, the server (100) executes an ORM-type process in which it queries the tables of the database (200) (eg, project table (210), user table (220), diagnostic tools table ( 230), and table of risk estimation rules (240)) following the relationships between them to determine which are the questions that the diagnostic questionnaire (300) must have in order to collect the necessary information for the project. In this example, the diagnostic questionnaire (300) contains questions from the Morinsky tests to detect if the user (10) adheres to his prescribed treatment, MINI CHAL test to detect if the user (10) has symptoms related to hypertension , which can trigger episodes and complications in diabetic patients, such as kidney and heart failure, and other tests that allow early detection of a patient's risk.

In this example, the operator (20) calls the user (10) by telephone and begins to apply the diagnostic questionnaire (300), and while the user (10) answers the questions asked by the operator (20), the The operator (20) fills in some values on a response entry screen displayed by the terminal (110). After the application of the diagnostic questionnaire (300) is finished, the terminal (110) generates the response data (350) and sends it to the server (100) for processing according to steps g) to i) and the value of the risk score data (500) is obtained.

The server (100) in steps g) to i) qualifies the user responses (10) recorded in the response data (350), again following the relationships between the tables of the database (200). Particularly, the server (100) relates the diagnostic tool data (370) with the rule data (242) of the record (241) related to the questionnaire data (232) of the record (231) obtained in step d) . In other words, the server (100) from the ORM-type process can consult the rules in the rule data (242) that allow to qualify the answers obtained from the user (10), and based on that qualification, the value of the risk score data is determined (500), which can be quantitative (eg, score on a scale of 1-10, 1-100) or categorical (eg, high/low, high/medium/low, false, negative, meets/does not meet).

Glossary:

Some of the terms used are described below, in some modalities of the method and system disclosed throughout the Descriptive Chapter:

Data: Data will be understood in this disclosure as a symbolic representation that can be numerical, alphabetic, algorithmic, logical, and/or vector that encodes information.

A piece of data can have a structure or frame made up of blocks of characters or bits that represent different types of information. Each block is made up of strings of characters, numbers, logical symbols, among others.

A piece of data can also be made up of only bits (strings in binary language), made up of characters formed one by one by a combination of bits, made up of fields, records or tables made up of fields and records, or made up of interchange files. data (formats such as csv, json, xls, among others). Furthermore, a data item can be a matrix of n rows by m columns. In turn, a data can contain several data.

For example, when the data has a frame structure, the frame may have a block of identifying characters, generally known as a header, which contains information related to a computing device or processor that sends the data, and may contain information related to a computing device or processor that receives the data. Preferably, if data has a frame format, the frame contains blocks related to layers according to the OSI reference model.

Likewise, the frame can have a block of tail characters (or simply tail), or "tail" in English, which allows identifying a computing unit or server that is the end of the data, that is, that after that block information contained in the data previously identified by the computing unit or server with the "header" is no longer found. In addition, the data has between the "header" block and the "tail" block one or more blocks of characters that represent statistics, numbers , descriptors, words, letters, logical values (e.g. booleans) and combinations of these.

Database: In this disclosure, a database will be understood as a series of data organized and related to each other, and a set of programs that allow users to access and modify said data. Additionally, a database can be a collection of information configured to facilitate data retrieval, modification, reorganization, and deletion.

Examples of databases are relational databases and non-relational databases. For example, relational databases are used to store and manage structured data, which, for example, may be arranged in table formats, or equivalent formats (e.g., CVS, XLS). These relational database structures can be divided into fields and records. However, said data structures that make up relational databases can be related to other similar data structures. For example, in the method of the present invention relationships between tables are taken into account. These relationships allow handling different data tables simultaneously, without the need to replicate them in the event that the same table is needed for two different processes.

Some examples of relational databases may be configured to be edited, modified, and managed by servers and compute modules configured to execute one or more methods, processes, steps, routines, and combinations thereof, which may be written in programming languages. such as Java, Javascript, Perl, PHP and C++, #C, Python, SQL, Swift, Ruby, Delphi, Visual Basic, D, HTML, HTML5, CSS, and other programming languages known to a person moderately versed in the matter.

In some of the modalities of the method disclosed here, in which one or more tables with relationships among themselves are used, the database (200) can be a relational database that is taken as input for an ORM-type process. One of the advantages of these modalities is the scalability that it provides to the system and the flexibility that it provides to the telecare service during the execution of the method.

In an example of the method disclosed here, the database (200) can include up to 63 tables classified into type tables, and relational tables, which are connected by key data (804) (eg, primary and foreign keys) and support tables that obey cardinality depending on the module (Mainly talking about many-to-many relationships where you can create new tables that keep both primary keys under the role of foreign, thus creating a single primary or primary id) such tables are closely related and therefore the process of executing queries to the database is facilitated, since through the unions (v.g. JOINS in SQL language) it is possible to identify the desired queries taking into account the tables involved in order to have more optimal results and precise.

ORM-type process: In this disclosure, the ORM-type process (object-relational mapping, in English - object-relational mapping, in Spanish) will be understood as a process implemented by a computer based on object-oriented programming, a key technology for implementing systems. complex, providing benefits of reusability, robustness, and ease of maintenance and administration of relational databases. The ORM-like process is a bridge between the two allowing applications to access relational data in an object-oriented manner. Additionally, the ORM-type process provides scalability and ease for queries to the databases (200) and allows efficient use of the system modules and the method disclosed here. Classification process: in this disclosure, the classification process will be understood as any process that allows data to be grouped into classes, among which are artificial intelligence and machine learning processes, such as linear classification processes ( (eg, logistic regression, Naive Bayes classification, Fisher's linear discriminant), support vector machines, least-squares support vector machines, quadratic classification processes, kernel estimation, k-th neighborhood, trees of decision, random forests, neural networks (eg supervised, backpropagation, forwardpropagation), learning vector quantization, and other machine learning techniques known to one of ordinary skill in the art.

Machine learning may involve performing a plurality of machine learning tasks using machine learning systems, such as supervised learning. Supervised learning can include presenting a set of example inputs and desired outputs to machine learning systems.

In addition, the machine learning can include a plurality of other tasks based on an output from the machine learning system. Such tasks can also be classified as machine learning problems, such as classification, regression, clustering, density estimation, dimensionality reduction, anomaly detection, and the like. Machine learning can include a variety of mathematical and statistical techniques.

Learning algorithms may include decision tree learning, association rule learning, deep learning, artificial neural networks, genetic learning algorithms, inductive logic programming, support vector machines (SVMs), Bayesian network, reinforcement, representation learning, rule-based machine learning, sparse dictionary learning, similarity and metric learning, learning classification systems (LCS), logistic regression, random forest, K means, gradient reinforcement and adaboost, nearest neighbors to K (KNN), a priori algorithms and the like. Also, a classification process can have one or more stages based on steps of genetic algorithms, which can be used in computational intelligence systems, machine vision, natural language processing (NLP), recommender systems, reinforcement learning, construction of graphic models and the like. Machine learning systems can be used in natural language processing, search engines, pattern matching, and the like.

Demographic data: In this disclosure, demographic data will be understood as one or more data that has information corresponding to and inherent to the characteristics of communities and human beings.

This general information of groups of people usually includes attributes such as age, gender, city, socioeconomic status, place of residence, as well as social characteristics such as occupation, family situation or income. In analytical processes, demographic data is used to provide a deeper insight into a population, study its behavior and find patterns.

Computing device or computing device: In this disclosure, computing device or computing device shall be understood as all those devices in which communication can be established with one or more computing devices, terminals, and/or servers to exchange data, labels, and commands over a communications network. A particular case of a computing device or computing device is a terminal, where the terminal can be configured to establish constant communication with a server, for example, through a specific communication protocol (eg, VPN networks, LAN networks, WAN, protocols HTTPS, REST, SOAP, API-REST, and combinations thereof).

Communications module: In this disclosure, a communications module will be understood as a hardware element attached to a computing unit, processing unit, or processing module of a computing device, terminal, or server, which allows communication to be established between one or more devices computers, terminals or servers to exchange data, commands and/or labels.

For example, the communication module may be selected from the group consisting of wired communication modules, wireless communication modules, and wired and wireless communication modules.

Examples of wireless communication modules use a wireless communication technology selected from the group consisting of Bluetooth, WiFi, Radio Frequency RF ID (Radio Frequency Identification), UWB (Ultra Wide B -and), GPRS, Konnex or KNX, DMX (Digital Multiplex), WiMax and equivalent wireless communication technologies that are known by a person moderately versed in the matter and combinations of the above.

Examples of wired communications modules have a wired connection port that allows communication with external devices through a communications bus, which is selected, among others, from the group made up of I2C (from the acronym IIC Inter-Integrated Circuit), CAN (Controller Area Network), Ethernet, SPI (Serial Peripheral Interface), SCI (Serial Communication Interface), QSPI (Quad Serial Peripheral Interface), 1-Wire, D2B (Domestic Digital Bus), Profibus and others known to a person moderately versed in the matter, and combinations thereof.

Human Interface Device (HID): It will be understood in the present invention that a Human Interface Device (HID) can be any device capable of allowing a user to input data into the computing unit, server or terminal. Examples of Human Interface Devices (HID) include, without limitation, keyboard, mouse, trackball, touchpad, pointing device, joystick, touch screen, microphones coupled to voice data generation and recognition modules, cameras, and other voice capture devices. image coupled to recognition and generation modules by gestures, among other devices capable of allowing a user to enter data into the computing unit of the device and combinations thereof.

Display device: A display device is any device that can be connected to a computing unit, server or terminal and display its output, is selected from among others CRT (Cathode Ray Tube) monitor, flat screen LCD, Liquid Crystal Display, Active Matrix LCD, Passive Matrix LCD, LED Displays, Screen Projectors, TV (4KTV, HDTV, Plasma TV, Smart TV) , OLED (Organic Light Emitting Diode) displays, AMOLED (Active Matrix Organic Light Emitting Diode) displays, QD (Quantic Display) quantum dot displays, of segments, among other devices capable of displaying data to a user, known to those skilled in the art, and combinations thereof.

Server: In the present invention, a server will be understood as a device that has a processing unit configured to execute a series of instructions corresponding to stages or steps of methods, routines, or processes. The server may install and/or run a computer program that may be written in Java, Javascript, Perl, PHP, and C++, #C, Python, SQL, Swift, Ruby, Delphi, Visual Basic, D, HTML, HTML5, CSS , and other programming languages known by a person moderately versed in the matter.

In addition, the server has a communications module that allows connection to other servers or computing devices.

Additionally, servers can connect with each other, and connect with other computing devices through web services architectures and communicate by communication protocols such as SOAP, REST, HTTP/HTML/TEXT, HMAC, HTTP/S, RPC, SP and others. communication protocols known by a person moderately versed in the matter. Similarly, the servers mentioned in the Descriptive Chapter of the present invention can be interconnected through networks such as the Internet, VPN networks, LAN networks, WAN, other equivalent or similar networks known by a person moderately versed in the matter and combinations of the same. These same networks can connect one or more computing devices or terminals (110) to one or more servers (100).

Some of the servers mentioned in the Descriptive Chapter of the present invention may be virtual servers or web servers.

Any of the servers of the present invention may include a memory module configured to store instructions that, when executed by the server, execute part, or all of one or more steps of any of the methods disclosed herein.

In some embodiments of the present invention, one or more of the servers may be physical servers or virtual servers with a backup architecture or clustered architecture in which one or more replacement servers are configured to ensure high availability.

Terminal (110): in the present invention, terminal (110) shall be understood as any computational device capable of processing digital data and intended to be used by a user or operator through a user interface, for example, a computer, a server , a Tablet, a smartphone, and similar and equivalent computing devices known by a person moderately versed in the matter. The terminal (110) may have installed one or more software applications configured to establish communication with the server (100). The communication with the server (100) can be done through a communication protocol selected among API, API-REST, RESTfile, SOAP, HTTPS, SSH, TCP, and combinations thereof. The terminal (110) preferably includes a human interface device (HID) and a display device that allow the operator to enter and view commands, requests, and generally interact with the terminal (110). Computer network (620): In the present invention, a computer network (620) or communications network will be understood as a set of technical means and/or hardware and software elements configured to allow remote communication between computer devices, terminals, servers, and equivalent technical elements known by a person moderately versed in the matter. Normally it is about transmitting data by electromagnetic waves through various media (air, vacuum, copper cable, fiber optics, etc.). Non-limiting examples of a computer network are the Internet, WAN, and LAN. It will be understood that the method and system disclosed herein can employ any type of equivalent computer network known to a person of ordinary skill in the art.

It must be understood that the present invention has not been limited to the modalities described and illustrated, since as will be evident to a person versed in the art, there are possible variations and modifications that do not depart from the spirit of the invention, which is only found defined by the following claims.

Claims

1. A method for obtaining risk score data (500) from a user (10), executed by a server (100) comprising the following steps: a) accessing a database (200) that has a project table (210), a user table (220), a diagnostic tools table (230) and a risk estimation rules table (240), where the project table (210) contains at least one record (211) with a first field with project data (212), where said user table (220) contains at least one record (221) with a first field that includes user identification data (222), a second field that includes a pathology data (223) and a third field that relates the project data (212) from the project table (210), where the diagnostic tools table (230) contains at least one record (231 ) with a first field with a questionnaire data (232), a second field with a question data (233), a third field with an assessment data (234) and a fourth field that relates to the pathology data (223). of the user table (220), and where the table of risk estimation rules (240) contains at least one record (241) with a first field with a rule data (242), a second field that relates the data questionnaire (232) from the diagnostic tools table (230) and a third field that relates the project data (212) from the project table (210); b) receiving a form generation request (50) from a terminal (110), which includes user identification data (55); c) obtain the record (221) of the user table (220) whose user identification data (222) corresponds to the user identification data (55) of the form generation request (50); d) obtaining the record (231) of the diagnostic tools table (230) from the pathology data list (223) of the record (221) obtained in step c); e) obtaining a diagnostic questionnaire (300) from the question data (233) of the record (231) obtained in step d); f) transmit the diagnostic questionnaire (300) to the terminal (110) for its corresponding processing; g) receiving response data (350) related to the question data (233) of the diagnostic questionnaire (300) from the terminal (110); h) obtaining diagnostic tool data (370) by relating the response data (350) received in step g) with the evaluation data (234) of the record (231) obtained in step d); yi) obtain the risk score data (500) by relating the diagnostic tool data (370) with the rule data (242) of the registry (241) related to the questionnaire data (232) of the registry (231) obtained in step d).

2. The method of Claim 1, where stage a) of accessing a database (200) through a server (100) includes: al) accessing a database (200) of one or more institutions providing health, medical centers, patient portals, medical record systems and health professionals.

3. The method of Claim 0, further comprising:

I) select through the server (100) at least one intervention plan data stored in the database (200) based on the value of the risk score data (500) of the user (10); where the intervention plan data includes one or more instructions to reduce the value of the risk score data (500) of the user (10).

4. The method of Claim 0, which also comprises: obtaining through the server (100) a group risk score data of a group of users from the risk score data (500) of the records (221) of the user table (220).

5. The method of Claim 0, further comprising:

JA) receiving in the server (100) an alert data packet (710) from the terminal (110); where the data packet (710) has early warning data (710) and user identification data (720);

JB) register through the server (100) the early warning data (710) in the record (211) of the user table (220) whose user identification data (222) is related to the user identification data ( 720) of the alert data packet (710).

6. The method of Claim 5, wherein the early warning data (710) includes an alert type data, and a priority data.

7. A system for obtaining risk score data (500) from a user (10), comprising:

- a server (100) configured to execute the instructions of the method of Claim 0; and

- a terminal (110) that communicates via a computer network (620) with the server (100).

8. A method for obtaining risk score data (500) from a user (10), executed by a server (100) comprising the steps:

A) receive a process start command (800) from a terminal (20) that includes a process data value (801) equal to "assessment

B) load a record (802) from a user-project table (803), belonging to a main database (820), where the record (802) includes a process data value (801) equal to "assessment" ;

C) loading a plurality of response data values (350) associated with a project to which the user (10) belongs; where the response data values (350) are obtained by relating a key data (804) of the user's record (802) (10) and to consult in a table of responses-questionnaires (805) the response data values ( 350) associated with the user (10);

D) obtain at least one risk score data (500) from the user (10) by executing at least one qualification process (806) that takes as input the response data (350) where the qualification process (806) is a rule-based process (807); where each rule (807) corresponds to an evaluation test that measures a psychosocial, medical, physiological, health variable of the user (10); and where each rule (807) is consulted relating the key data (804) of the registry (802) of the user (10).

9. The method of Claim 8, which also comprises a step E) of assigning to the record (802) at least one risk class data (808) by means of a classification process (809) that takes as input the at least one risk score data (500), where the risk class data (808) has values associated with psychosocial, medical, physiological, or health risks of the user (10) that are assigned based on the magnitude of the value of at least a risk data (500).

10. The method of Claim 9, wherein the risk class data (808) stores a qualitative variable configured to rank the risk score data value (500) on a predetermined scale.

11. The method of Claim 8, further comprising a stage AA) prior to stage A) of obtaining an updated main database (820) by means of a data feed process (810) that takes a first database as input. of data (200) received from a computational device (811), where the data feeding process (810) includes the sub-steps:

AA1) obtaining a set of affected records (812) including at least one record from the first database (200) by means of a data preprocessing method (813) taking the first database (200) as input; AA2) obtaining an alert data (831) that includes a plurality of identification data "ID" of the records of the group of affected records (812);

AA3) storing in the main database (820) the records that do not belong to the group of affected records (812); and

AA4) assign to each record added to the main database (820) a process data value (801) equal to "retrieve", and status data value (814) equal to "call pending", where the records added to the main database (820) are stored in at least one user table (824) having a plurality of fields storing key data (804) configured to relate the user table (824) to a plurality of tables of the main database (820).

12. The method of Claim 8, where the response data values (350) associated with a project to which the user (10) belongs are obtained before step A) in the following steps:

BB) receiving from a terminal (20) a process start command (800) that includes a process data value (801) equal to "assessment"; and

CC) execute a user call process (815) that includes the sub-steps:

CC1) upload a record from a user-project table (816) belonging to the main database (820), where the uploaded record is associated with a user (10) and where the uploaded record includes a process data value (801) equal to "valuation";

CC2) identifying a status data value (814) in the register loaded in substep CC1);

CC3) obtain ID data (817) from diagnostic questionnaires (300) pending response associated with a project to which the user belongs (10) and associated with the value of the status data (814) identified in substage CC2) , where the ID data (817) is obtained by relating a key data (804) of the loaded record and querying the questionnaire-responses table (805) the response data values (350) associated with the user (10) having a "null"value;

CC4) obtaining a first screen generation data (819) that includes a form with a plurality of questions extracted from the diagnostic questionnaires (300) associated with the ID data (817);

CC5) sending to the terminal (20) the first screen generation data (819) configured so that the terminal (20) displays a first screen (821) with the form;

CC6) receiving from the terminal (20) at least one response data (350) that includes the responses to the form that the operator (20) obtains when calling the user (10);

CC7) record the at least one response data (350) in the response-questionnaire table (805); and

CC8) modifying the value of the process data (801) or the status data (814) by means of a first comparison process (833) that validates the number of responses from the user (10) against a number of responses required to change the value of the status data (814); and

CC9) repeat step CC1) loading a record from a different user (10).

13. The method according to Claim 8, further comprising before step A) the following steps:

DD) receive from a terminal (110) a command to start the process (800) that includes a process data value (801) equal to "capture" and a status data (814) equal to "diagnosis confirmation pending ”;

EE) verify a diagnostic data value (821) from the user (10) that includes the sub-steps:

EE1) receiving a drug data value (822) that is supplied by a user (10) during a call with the operator (20) of the terminal (110);

EE2) compare the value of the drug data (822) with a pathology data (223) associated with the user (10), and that is included in a table of types of drugs (823) that belongs to the main database ( 820); where the table of types of medicines (823) is related to the table of users-projects (816) by means of a key data (804); and where the comparison is made by a second comparison process (834) based on rules provided by an expert;

EE3) obtain a diagnosis confirmation data (825) if the drug data value (822) coincides with a predetermined drug data value (825) associated with the pathology data (223) and finish step EE), of otherwise, obtain diagnostic alert data (826) and proceed to sub-step EE4);

EE4) assign a value of "healthy user" in the user record (10), if the medication data (822) has a null value, otherwise, assign a value of "pending program change" in the record of the user (10), if the medication data (822) is equal to a predetermined medication data value (825) associated with a pathology data (823) different from the pathology data (823) stored in the user record ( 10).

14. The method of Claim 8, which further comprises a stage I) of assigning to the user record (10) an intervention plan data by means of a classification process (831) that takes as input the value of the score data of risk (500) of the user (10); where the intervention plan data includes one or more instructions configured to reduce or contain the value of the risk score data (500) of the user (10).

15. A system for obtaining risk score data (500) from a user (10), comprising:

- a server (100) configured to execute the method of Claim 8; and

16. The system of Claim 15, wherein the server (100) is connected to a computer network (620) to establish a service-based communications protocol (835) that interconnects the server (100) with at least one call server. (828) configured to: allow communication between a first communications device (829) of the operator (20) and a second communications device (830) of the user (10); and exchange data with the server (100) related to the calls made by each operator (20).

17. A computer-readable medium that includes instructions that, when interpreted by a server (100), allows the method according to any of Claims 1 to 13 to be executed.

18. A computer program that includes instructions that, when interpreted by a server (100), allows the execution of the method according to any of Claims 1 to 13.