US20220277816A1

US20220277816A1 - Unified data interface and system

Info

Publication number: US20220277816A1
Application number: US17/681,570
Authority: US
Inventors: Michael Winlo; Chris Burchhardt; Kyle McLain; Harsh Pandey; Tayler Cox; Lekan Wang
Original assignee: Palantir Technologies Inc
Current assignee: Palantir Technologies Inc
Priority date: 2015-01-02
Filing date: 2022-02-25
Publication date: 2022-09-01
Also published as: US11302426B1

Abstract

Various systems and methods are provided that aggregate, analyze, and display health data for users. The system aggregates data stored in various databases. For example, the system retrieves data from these databases, maps the data to a set of common terms based on an ontology, and displays such information to an entity accessing the system. Rather than converting the data stored in the databases into a standardized format, the system includes a set of ontologies that provide a correlation between a first set of fields and a second set of fields. The system determines a correlation between a first field in the first set of fields and a second field in the second set of fields using the ontology, stores data retrieved from the database in a second database in association with the second field, and displays the data associated with the first field under the second field.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

This application is a continuation of U.S. patent application Ser. No. 14/975,215, filed on Dec. 18, 2015, which claims priority under 35 U.S.C. § 119(e) to U.S. Provisional Application No. 62/099,321, filed on Jan. 2, 2015, which are hereby incorporated by reference in their entireties.

TECHNICAL FIELD

The present disclosure relates to systems and techniques for data integration, analysis, and visualization.

BACKGROUND

Physical institutions are available to help vulnerable populations, such as foster children, institutionalized patients, those with behavioral health concerns, the homeless, and/or the like. For example, the foster care system provides various wards, group homes, and/or private homes for minors who can no longer live with their biological parents or guardians. As another example, homeless shelters and soup kitchens offer temporary housing and food for those in need. Often, minors in the foster care system may be placed in multiple foster homes within a short period of time (e.g., less than a year) before they find a permanent residence. Similarly, the homeless may pass between different homeless shelters within a short period of time. The same may be true for members of other vulnerable populations as well. Thus, information about a member of a vulnerable population may be lost during this transitory period.

SUMMARY

The systems, methods, and devices described herein each have several aspects, no single one of which is solely responsible for its desirable attributes. Without limiting the scope of this disclosure, several non-limiting features will now be discussed briefly.
As described above, members of vulnerable populations may transition between different locations. As these members transition between locations, important information about the member may be lost. For example, a minor's medical history, hobbies, interests, and/or the like may be lost if the information is not relayed to the guardians of a new foster home. For the medical history in particular, healthcare providers (e.g., physicians, specialists, pharmacists, etc.) often keep detailed records about a patient. However, if the minor transitions from one foster home in a first geographic area to a second foster home in a second geographic area, one or more of the minor's healthcare providers may change. Even if the minor's healthcare records are transferred from an old healthcare provider to a new healthcare provider, such transfers may leave out important information that another healthcare provider knows about the minor. For example, health information related to the minor may be stored in separate databases (e.g., a claims history may be stored in one database, prescription information may be stored in another database, etc.). The separate databases may not be linked or integrated in any way to allow communication of this information among various healthcare providers. Thus, a minor's old pharmacist may be aware of certain medication that the minor is taking, but this information may not be relayed to a new primary care physician. Likewise, information that is helpful for building rapport between a minor and new health professionals (e.g., hobbies, interests and other social factors) is not often captured or preserved. In addition, sharing this information amongst health professionals, foster parents, and the minor can be difficult due to the fact that each of these groups of people should only see the information relevant to their role.
Accordingly, the systems and methods described herein provide an integrated health interface system that collects, aggregates, analyzes, and displays health data for one or more users. For example, the integrated health interface system may collect, aggregate, analyze, and display health data for minors that are a part of the foster care system and/or for any other minor or adult patient. The integrated health interface system may aggregate data stored in various databases. For example, one or more of the various entities may be associated with one or more databases that include information related to the healthcare of a patient. The integrated health interface system may retrieve data from these databases, map the data to a set of common terms based on an ontology, and display such information to an entity accessing the system. In one embodiment, instead of converting data received from each of several sources into a standardized format, the integrated health interface system may include a set of ontologies that provide a correlation between fields of data from the various sources and that contain common data types. For example, the integrated health interface system may determine a correlation between a first column header in a first set of fields from a first data source and a second column header in a second set of fields from a second data source using the ontology, store data retrieved from the second data source in a second, local database in association with the second column header, and then may display in a user interface the data associated with the first column header under the second column header (without modifying the actual data).
The health interface system also provides input options so that clinicians, foster parents, guardians, the minor, and/or others can add detail and/or information to the one or more databases.
One aspect of the disclosure provides a computing system configured to access one or more databases in substantially real-time in order to aggregate patient health information and provide the aggregated information to a user in an interactive user interface. The computing system comprises one or more computer processors. The computing system further comprises a plurality of databases each storing respective datasets. The computing system further comprises a second database comprising retrieved datasets organized in a plurality of first fields. The computing system further comprises a computer readable storage medium storing program instructions configured for execution by the one or more computer processor in order to cause the computing system to: for each database in the plurality of databases, access the dataset stored in the respective database, where the accessed dataset comprises data for a plurality of users, and where each data in the retrieved dataset is associated with a second field in a plurality of second fields; identify a name for each second field in the retrieved dataset; determine a mapping between each identified second field name and a name of a first field in the plurality of first fields; and store the accessed dataset in the second database such that each data in the accessed dataset is stored in association with the first field that maps to the second field that the respective data is associated with; receive a request to access the computing system; determine an identity of a user associated with the request to access the computing system; retrieve from the second database user health data that is associated with the determined user; generate a summary of a medical history of the determined user based on the retrieved user health data; and generate user interface data for rendering the interactive user interface on a computing device.
The computing system of the preceding paragraph can have any sub-combination of the following features: where the interactive user interface includes a first container that comprises an identification of at least one first field in the plurality of first fields, where the first container further comprises the retrieved user health data that corresponds with the at least one first field and the generated summary of the medical history of the determined user; where the retrieved user health data comprises medical claims submitted on behalf of the determined user, and where the computer readable storage medium further stores program instructions that cause the computing system to generate the summary of the medical history of the determined user based on the medical claims; where the computer readable storage medium further stores program instructions that cause the computing system to generate an alert associated with the team member based on the retrieved user health data, where the first container comprises the generated alert; where the computer readable storage medium further stores program instructions that cause the computing system to: receive an indication that the generated alert is selected via the interactive user interface, where the generated alert indicates that the user missed an appointment, and update the user interface data such that the interactive user interface includes a second container comprising a list of selectable appointment times that can be reserved for the user; where the computer readable storage medium further stores program instructions that cause the computing system to: receive an indication that the generated alert is selected via the interactive user interface, where the generated alert indicates that the user is missing a lab test, and update the user interface data such that the interactive user interface includes a second container comprising a map that graphically displays a location of one or more lab facilities located near the user where the lab test can be performed; where the retrieved user health data comprises prescription data, where the team member is a primary care physician, and where the alert is generated based on the prescription data; where the computer readable storage medium further stores program instructions that cause the computing system to generate a risk score associated with the user, where the risk score is generated based on the retrieved user health data; where the risk score is generated based on at least one of a number of missing services associated with the user, a priority of each missing service associated with the user, a likelihood that the user seeks medical services without intervention, or a number of times the user does not comply with a recommended care plan; where the mapping between each identified second field name and a name of a first field in the plurality of first fields is determined based on an ontology; where the interactive user interface further includes a second container that comprises a first alert associated with the team member and a second alert associated with the team member, where the first alert corresponds with the user, and where the second alert corresponds with a second user; where the computer readable storage medium further stores program instructions that cause the computing system to: receive text and a selection of a second team member from the team member, and transmit a message to an account associated with the second team member, where the message comprises the text, and where the second team member can view the message when accessing the computing system; where the team member is one of a primary care physician, a pharmacist, a government agency employee, a guardian, or the user.
Another aspect of the disclosure provides a computer-implemented method of accessing one or more databases in substantially real-time in order to aggregate patient health information and provide the aggregated information to a user in an interactive user interface. The computer-implemented method comprises, as implemented by one or more computer systems comprising computer hardware and memory, the one or more computer systems configured with specific executable instructions, retrieving dataset stored in a first database, where the retrieved dataset comprises data for a plurality of users, and where each data in the retrieved dataset is associated with a second field in a plurality of second fields; identifying a name for each second field in the retrieved dataset; determining a mapping between each identified second field name and a name of a first field in a plurality of first fields; storing the retrieved dataset in a second database such that each data in the retrieved dataset is stored in association with the first field that maps to the second field that the respective data is associated with; receiving a request to access the one or more computer systems; determining an identity of a user associated with the request to access the computing system; retrieving from the second database user health data that is associated with the determined user; and generating user interface data for rendering the interactive user interface on a computing device, the interactive user interface including a first container that comprises an identification of at least one first field in the plurality of first fields, where the first container further comprises the retrieved user health data that corresponds with the at least one first field.
The computer-implemented method of the preceding paragraph can have any sub-combination of the following features: where the interactive user interface includes a first container that comprises an identification of at least one first field in the plurality of first fields, where the first container further comprises the retrieved user health data that corresponds with the at least one first field; where the method further comprises generating a summary of a medical history of the determined user based on the retrieved user health data, where the first container further comprises the generated summary of the medical history of the determined user; where the retrieved user health data comprises medical claims submitted on behalf of the determined user, and where the computer-implemented method further comprises generating the summary of the medical history of the determined user based on the medical claim; where the method further comprises generating an alert associated with the team member based on the retrieved user health data, where the first container comprises the generated alert; where the method further comprises receiving an indication that the generated alert is selected via the interactive user interface, where the generated alert indicates that the user missed an appointment, and updating the user interface data such that the interactive user interface includes a second container comprising a list of selectable appointment times that can be reserved for the user; where the method further comprises receiving an indication that the generated alert is selected via the interactive user interface, where the generated alert indicates that the user is missing a lab test, and updating the user interface data such that the interactive user interface includes a second container comprising a map that graphically displays a location of one or more lab facilities located near the user where the lab test can be performed; where the retrieved user health data comprises prescription data, where the team member is a primary care physician, and where the alert is generated based on the prescription data; and where the method further comprises generating a risk score associated with the user, where the risk score is generated based on the retrieved user health data.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 illustrates a block diagram of a system for aggregating, analyzing, and displaying health data.

FIG. 2 illustrates a user interface displaying an ability to search for patients.

FIG. 3 illustrates a user interface displaying a patient profile.

FIG. 4 illustrates a user interface displaying a patient medical history.

FIG. 5 illustrates a user interface displaying a patient care plan.

FIG. 6 illustrates a user interface displaying a patient health assessment.

FIG. 7 illustrates a user interface displaying a patient clinical evaluation.

FIG. 8 illustrates a user interface displaying alerts and messages for a care team member.

FIG. 9 illustrates a user interface displaying a breakdown of remaining member visits by county.

FIG. 10 illustrates a user interface displaying a breakdown of claims, visits, and costs by diagnoses and facilities.

FIG. 11 illustrates a user interface displaying a graph of weighted care ratio by healthcare provider.

FIGS. 12A-12B illustrate user interfaces displaying a location of care team members.

FIG. 13 illustrates a user interface displaying a location of healthcare providers.

FIG. 14 is a flowchart depicting an illustrative operation of aggregating, analyzing, and displaying health data.

FIG. 15 illustrates a computer system with which certain methods discussed herein may be implemented.

DETAILED DESCRIPTION OF SPECIFIC EMBODIMENTS

Overview

As described above, minors in the foster care system may often be placed in multiple foster homes. As a minor transitions from one foster home to another, important information about the minor may be lost. For example, the minor's medical history, hobbies, interests, and/or the like may be lost if the information is not relayed to the guardians of the new foster home. For the medical history in particular, healthcare providers (e.g., physicians, specialists, pharmacists, etc.) often keep detailed records about a patient. However, if the minor transitions from one foster home in a first geographic area to a second foster home in a second geographic area, one or more of the minor's healthcare providers may change. Even if the minor's healthcare records are transferred from an old healthcare provider to a new healthcare provider, such transfers may leave out important information that another healthcare provider knows about the minor. For example, health information related to the minor may be stored in separate databases (e.g., a claims history may be stored in one database, prescription information may be stored in another database, etc.). The separate databases may not be linked or integrated in any way to allow communication of this information among various healthcare providers. Thus, a minor's old pharmacist may be aware of certain medication that the minor is taking, but this information may not be relayed to a new primary care physician.
In some cases, a care team may manage the healthcare of a minor. For example, the care team may include a care team leader and one or more care team members who monitor whether a minor is receiving proper healthcare. The care team may interact with the minor, the minor's guardians, the minor's physician(s), the minor's specialist(s), the minor's pharmacist, and/or government agencies (e.g., state child welfare agencies). However, each of these entities may store different data related to the minor in different, disparate databases, as described above. Thus, the members of the care team may have trouble finding the appropriate health data to ensure that the minor is receiving proper healthcare.
Accordingly, the systems and methods are described herein provide an integrated health interface system that aggregates, analyzes, and displays health data for one or more users. For example, the integrated health interface system may aggregate, analyze, and display health data for minors that are a part of the foster care system. However, this is not meant to be limiting. The integrated health interface system described herein may aggregate, analyze, and display health data for any patient.
The integrated health interface system may be accessible by a plurality of entities. For example, physicians, specialists, pharmacists, patients, guardians, government agencies, and/or the like may access the integrated health interface system. Each of the various entities may be associated with an access level such that a respective entity can only view data that has been authorized for viewing by the respective entity. Alternatively or in addition, the integrated health interface system can support discover permissions where a physician, specialist, pharmacist, patient, guardian, government agencies, and/or another such user can discover that a piece of data is available, but be notified that the respective user does not have permission to view the available data and must gain special permission in order to view the available data.
The integrated health interface system may aggregate data stored in various databases. For example, one or more of the various entities may be associated with one or more databases that include information related to the healthcare of a patient. The integrated health interface system may retrieve data from these databases, map the data to a set of common terms based on an ontology, and display such information to an entity accessing the system. For example, instead of converting the data stored in the databases into a standardized format, the integrated health interface system may include a set of ontologies that provide a correlation between a first set of fields and a second set of fields. The first set of fields may be column headers in a database. The second set of fields may be a list of common column headers that may be included in the displayed information. The integrated health interface system may determine a correlation between a first column header in the first set of fields and a second column header in the second set of fields using the ontology, store data retrieved from the database in a second, local database in association with the second column header, and then may display in a user interface the data associated with the first column header under the second column header (without modifying the actual data). In this way, new databases can be seamlessly linked to the integrated health interface system such that the integrated health interface system can populate a user interface with data from the new database without having to modify the data to fit a standard format.
In an embodiment, the integrated health interface system generates alerts and/or notifications that are associated with specific entities. For example, the alerts and/or notifications may indicate that a task needs to be performed, a task has already been performed, an appointment was missed, lab results are missing, a prescription was not filled or refilled at the proper time, and/or the like. These alerts and/or notifications may be derived from the data stored in the various databases. In addition, an alert and/or notification directed at one entity may be derived from data stored in a database associated with another entity. When logged into the integrated health interface system, an entity (via a device used to log into the integrated health interface system) may also be able to view alerts and/or notifications that are directed to other entities.
In a further embodiment, the integrated health interface system provides actionable services via a generated user interface. For example, the integrated health interface system may generate a user interface that is then rendered by a device operated by an entity when the entity logs into the integrated health interface system. The integrated health interface system can further generate an alert and/or notification to be displayed in the user interface in response to one of the conditions described herein occurring. The alert and/or notification can indicate to a care team member that a patient missed an appointment, that a patient has a missing lab result, and/or the like. In response to a notification that a patient missing an appointment, the user interface may include an option to view available appointment times and schedule a new appointment. As another example, in response to a notification that a patient has a missing lab result, the user interface may include an option to view the locations of nearby facilities that can perform the relevant lab tests and/or to schedule an appointment.
In some embodiments, the alert and/or notification is automatically transmitted to the device operated by the entity associated with the alert and/or notification. The alert and/or notification can be transmitted at the time that the alert and/or notification is generated or at some determined time after generation of the alert and/or notification. When received by the device, the alert and/or notification can cause the device to display the alert and/or notification via the activation of an application on the device (e.g., a browser, a mobile application, etc.). For example, receipt of the alert and/or notification may automatically activate an application on the device, such as a messaging application (e.g., SMS or MMS messaging application), a standalone application (e.g., a health data monitoring application), or a browser, for example, and display information included in the alert and/or notification. If the device is offline when the alert and/or notification is transmitted, the application may be automatically activated when the device is online such that the alert and/or notification is displayed. As another example, receipt of the alert and/or notification may cause a browser to open and be redirected to a login page generated by the integrated health interface system so that the entity can log in to the integrated health interface system and view the alert and/or notification. Alternatively, the alert and/or notification may include a URL of a webpage (or other online information) associated with the alert and/or notification, such that when the device (e.g., a mobile device) receives the alert, a browser (or other application) is automatically activated and the URL included in the alert and/or notification is accessed via the Internet.

Health Interface System Overview

FIG. 1 illustrates a block diagram of a system 100 for aggregating, analyzing, and displaying health data. The system 100 comprises one or more primary care provider devices 110A, one or more specialist provider devices 110B, one or more other provider devices 110N, a care team device 130, a patient device 150, a foster parent device 160, a pharmacist device 170, a government device 180, a health interface system 140, and/or a network 120.
In the embodiment illustrated in FIG. 1, the one or more primary care provider devices 110A (e.g., operated by a doctor, nurse, hospital or clinic staff, etc.), the one or more specialist provider devices 110B (e.g., operated by a specialist, a specialist's staff, etc.), the one or more other provider devices 110N, the care team device 130 (e.g., operated by a care team member or leader), the patient device 150 (e.g., operated by a patient), the foster parent device 160 (e.g., operated by the guardians of a patient), the pharmacist device 170 (e.g., operated by a pharmacist), and the government device 180 (e.g., operated by a member of a government agency, such as a state child welfare agency), which may each be implemented by one or more first physical computing devices, are communicatively connected to the health interface system 140, which may be implemented by one or more second physical computing devices, over the network 120. In some embodiments, each such physical computing device may be implemented as a computer system including some or all of the components illustrated in the example computing system 1500 of FIG. 15. For example, the one or more primary care provider devices 110A, the one or more specialist provider devices 110B, the one or more other provider devices 110N, the care team device 130, the patient device 150, the foster parent device 160, the pharmacist device 170, and the government device 180 may be implemented in a computer system as a set of program instructions recorded on a machine-readable storage medium.
The one or more primary care provider devices 110A, the one or more specialist provider devices 110B, the one or more other provider devices 110N, the care team device 130, the patient device 150, the foster parent device 160, the pharmacist device 170, and the government device 180 may communicate with the health interface system 140 to access health information related to one or more patients. Each of the various entities may be associated with an access level such that a respective entity can only access and view data that has been authorized for viewing by the respective entity. Alternatively or in addition, the health interface system 140 can support discover permissions where an entity can discover that a piece of data is available, but be notified that the respective entity does not have permission to view the available data and must gain special permission in order to view the available data.
One or more of the primary care provider devices 110A, the specialist provider devices 110B, the other provider devices 110N, the care team device 130, the patient device 150, the foster parent device 160, the pharmacist device 170, and the government device 180 may be associated with one or more databases.
For example, the one or more databases may be associated with and/or maintained by various entities. Such entities may include a health maintenance organization (HMO), a social services or other government agency, and/or a data integration system. The HMO database can include medical claims, pharmacy claims, health risk assessments (e.g., GAIN-SS, PCS-17, etc.), electronic medical records, lab results, vitals (e.g., blood pressure, heart rate, etc.), care plan data (e.g., a patients' primary care and/or treating physicians, current medications, allergies, and/or other clinically relevant information), immunization records, prior authorization information, case management system data, and/or the like. The government agency database can include details about patients' foster parents, guardians, and/or primary care givers, criminal records, school records, and/or the like. The data integration system database can include enriched metrics (e.g., metrics derived from combining data stored in one or more databases). Enriched metrics can include average medical expenditure per month, average pharmacy expenditure per month, average total expenditure (e.g., medical and pharmacy) per month, predicted medical, pharmacy, and/or total expenditure per month, a patient's deviation from expected costs per month, a number of unique prescribers, a number of unique medications (used by one patient or patients in the aggregate), a number of Schedule 2 drugs (as defined by the United States Controlled Substances Act) used by one patient or patients in the aggregate, a costliest diagnosis, an average emergency room utilization rate, an average primary care physician visit rate, a distance to an assigned primary care physician for one or more patients, an average in-patient rate, geo-spatial data about patients, care teams, and/or health facilities, health risk scores, a number of missing medical services for which patients are eligible, and/or the like.
The one or more of the primary care provider devices 110A, the specialist provider devices 110B, the other provider devices 110N, the care team device 130, the patient device 150, the foster parent device 160, the pharmacist device 170, and/or the government device 180 may receive data from the one or more databases via an application programming interface (API) or adaptor, a connection interface, and/or other access point to a transactional or data warehouse system maintained by the HMO and/or government agency. Data can also be stored at a central location (e.g., a server) and delivered to the various entities via a network. Data can also be stored locally on a storage medium (e.g., a hard disk, optical disk, solid state drive, memory, etc.).
The health interface system 140 may aggregate data stored in the various databases. For example, the health interface system 140 may retrieve data from these databases, map the data to a set of common terms based on an ontology, and generate one or more user interfaces to display such information to an entity accessing the health interface system 140, as described in greater detail below. Rather than converting the data stored in the databases into a standardized format, the health interface system 140 may include a set of ontologies that provide a correlation between a first set of fields and a second set of fields. For example, the first set of fields may be column headers in a database and the second set of fields may be a list of common column headers that may be included in the generated user interface. The health interface system 140 may determine a correlation between a first field in the first set of fields and a second field in the second set of fields using the ontology, store data retrieved from the database in a second, local database (e.g., local to the health interface system 140) in association with the second field, and then may display in a user interface the data associated with the first field under the second field (without modifying the actual data). In this way, new databases can be seamlessly linked to the health interface system 140 such that the health interface system 140 can populate a user interface with data from the new database without having to modify the data to fit a standard format.
When executed by one or more processors of the computer system, logic in the health interface system 140 is operable to aggregate, analyze, and display health data according to the techniques described herein. In one embodiment, the health interface system 140 may be implemented in a Java Virtual Machine (JVM) that is executing in a distributed or non-distributed computer system. In other embodiments, the health interface system 140 may be implemented as a combination of programming instructions written in any programming language (e.g. C++ or Visual Basic) and hardware components (e.g., memory, CPU time) that have been allocated for executing the program instructions.
In an embodiment, the network 120 includes any communications network, such as the Internet. The network 120 may be a wired network, a wireless network, or a combination of the two. For example, network 120 may be a local area network (LAN) and/or a wireless area network (WAN).

Example User Interfaces

FIG. 2 illustrates a user interface 200 displaying an ability to search for patients. The interface 200 may be generated by the health interface system 140 and viewable on any of the entities in communication with the health interface system 140. As illustrated in FIG. 2, the interface 200 includes a pane 202. The pane 202 may display data according to a button selected by the user. For example, the user may have selected search button 212. Thus, the pane 202 may include a search box 204 that allows a user to search for a patient. The user may search for a patient by providing the patient's name, identification, social security number, or any other unique identifier. Searching for a patient may bring up information about the patient, such as the patient's profile, which is described below with respect to FIG. 3.
FIG. 3 illustrates a user interface 300 displaying a patient profile. The interface 300 may be generated by the health interface system 140 and viewable on any of the entities in communication with the health interface system 140. As illustrated in FIG. 3, the user has selected profile button 214. Thus, the pane 202 may include various data derived from the linked databases, such as biographical data about the patient, the hobbies and/or interests of the patient, some fun facts about the patient, and/or health data associated with the patient. Some of the data may be retrieved directly from a database and displayed in the pane 202 (after the ontology is used to determine a correlation or mapping between database fields and common fields).
Other data may be generated and displayed based on an analysis of the data retrieved from one or more databases. For example, information displayed in the medical snapshot section may be derived from medical and/or pharmaceutical claims data. Medical claims may include claims that are submitted to insurance companies to receive payment for medical services administered by the healthcare provider. Likewise, pharmaceutical claims may include claims that are submitted to insurance companies to receive payment for drugs distributed by the healthcare provider. Similarly, information related to the most seen primary care provider (PCP) or the last seen specialist in the contacts section may be derived from the medical and/or pharmaceutical claims.
As another example, information displayed in the medical snapshot section may include a map that shows the location of a patient relative to a location of one or more providers and/or health facilities involved in the care of the patient, an average distance traveled by a patient to receive care (e.g., to measure health access friction), a current deviation of a patient's expected or predicted costs, a current deviation from expected costs as a number of standard deviations from a population average, a propensity score predicting the likelihood that a patient's medical costs may deviate by a threshold value in the future, one or more top medical conditions that contribute the most to patient costs (e.g., from aggregated medical claims data), suspected conditions (e.g., conditions suspected to be suffered by a patient based on a mapping of diagnosis codes to conditions assigned to and/or associated with the patient), a number of missing services for which a patient is eligible (e.g., if asthmatic, a determination can be made whether the patient has received a prescription for a preventer medication in the calendar year), a sum of possibly preventable emergency room expenditures (e.g., for emergency room admissions, diagnoses can be assigned a probability that that condition could have been treated in an alternative facility or avoided. The sum of the probability multiplied by the actual treatment expenditure can provide a possibly preventable expenditure value), and/or the like.
In an embodiment, a user can generate a report that includes some or all of the displayed health data in the pane 202 by selecting report button 302. The generated report may be made available to other entities that access the health interface system 140 (e.g., accessible when the other entities log in to the health interface system 140).
The user interface 300 may also provide actionable services. As described above, the health interface system 140 can generate alerts and/or notifications to be displayed in the user interface 300 in response to a determination that a task needs to be performed, a task has already been performed, an appointment was missed, lab results are missing, a prescription was not filled or refilled at the proper time, and/or the like. The generated alerts and/or notifications can be displayed in the user interface 300. For example, the notifications/alerts section in the user interface 300 indicates that the patient missed a service. Other actionable services that can be depicted in the user interface 300 include allowing a user to schedule an appointment if a notification indicates that an appointment was missed, assigning a patient to a specific health intervention (e.g., health coaching) so as to tag the patient and transmit the patient's information to a team for outreach, sending a secure message to any individual of the patient's care team, re-assigning the patient's PCP to another provider (e.g., someone closer to the patient, a provided experienced in the particular condition(s) of the patient, etc.), exporting a summary and/or full report of the patient's medical history (including all patient information) for the purposes of facilitating a hand-off to another provider, sending a reminder for an appointment and/or prescription collection to the patient or a person associated with the patient (e.g., the patient's foster parent, parent, guardian, care giver, etc.), issuing a new patient ID card to a patient if the patient lost one, re-assigning a patient to a new case manager or any other health care provider, and/or the like. Accordingly, the user may select the notification or otherwise indicate that the user would like to schedule an appointment for the patient so that the patient receives the service. In response to a selection of the notification or an indication that the user would like to schedule an appointment, the user interface 300 may display a list of available appointment times to see the relevant provider. In addition, the user interface 300 may display a map to show the geographic location of one or more providers so that the user can choose, for example, the provider nearest to the patient.
In some embodiments, the alert and/or notification is automatically transmitted to an entity in communication with the health interface system 140. The alert and/or notification can be transmitted by the health interface system 140 at the time that the alert and/or notification is generated or at some determined time after generation of the alert and/or notification. When received by the entity, the alert and/or notification can cause the entity to display the alert and/or notification via the activation of an application on the entity (e.g., a browser, a mobile application, etc.). For example, receipt of the alert and/or notification may cause a mobile application to generate a push notification that is displayed. As another example, receipt of the alert and/or notification may cause a browser to open and be redirected to a login page generated by the health interface system 140 so that the entity can log in to the health interface system 140 and view the alert and/or notification via the user interface 300.
FIG. 4 illustrates a user interface 400 displaying a patient medical history. The interface 400 may be generated by the health interface system 140 and viewable on any of the entities in communication with the health interface system 140. As illustrated in FIG. 4, the user has selected medical history button 216. Thus, the pane 202 may include various data derived from the linked databases related to the medical history of the patient, such as past lab results, medications taken by the patient, allergies of the patient, the last visits to see a provider by the patient, and/or the like. For example, the medications data may be derived from the database that stores pharmaceutical claims.
The pane 202 may further include a risk score in the medical profile section. The risk score may represent a propensity for observed medical costs associated with a patient to deviate significantly (e.g., more than a threshold value) from expected medical costs within a time period (e.g., 12 months). The risk score may be based on claims data (e.g., medical and pharmaceutical claims data), coverage data (e.g., patient coverage/eligibility information), patient demographic data, a number of missing services associated with the patient, a priority of each missing service associated with the patient, a likelihood that the patient seeks medical services without intervention, a number of times the patient does not comply with a recommended care plan, a sum of amounts paid on medical claims for a patient (e.g., over a period of time, such as 12 months), an average amount paid on medical claims for a patient (e.g., over a period of time, such as 12 months), a per patient per month medical cost (e.g., over a period of time, such as 12 months), a sum of amounts paid on pharmaceutical claims for a patient (e.g., over a period of time, such as 12 months), an average amount paid on pharmaceutical claims for a patient (e.g., over a period of time, such as 12 months), a per patient per month pharmaceutical cost (e.g., over a period of time, such as 12 months), a per patient per month combined medical and pharmaceutical cost (e.g., over a period of time, such as 12 months), a sum of amounts paid on medical and pharmaceutical claims for a patient (e.g., over a period of time, such as 12 months), a difference between expected cost (e.g., a capitation rate given a set of Hierarchical Condition Categories (HCCs) adjusted for medical loss ratio) and observed cost (e.g., over a period of time, such as 12 months), a population average difference between expected cost and observed cost (e.g., over a period of time, such as 12 months), a population standard deviation of difference between expected cost and observed cost (e.g., over a period of time, such as 12 months), a per-patient deviation from expected costs (e.g., in standard deviations) from the population average (e.g., over a period of time, such as 12 months), a sum of a patient's HCC coefficients (e.g., over a period of time, such as 12 months), a capitation rate given a set of HCCs and a Centers for Medicare and Medicaid Services (CMS) plan rating of at least three and a half stars (e.g., over a period of time, such as 12 months), a capitation rate given a set of HCCs adjusted for medical loss ratio (e.g., over a period of time, such as 12 months), a sum of emergency room encounters (e.g., over a period of time, such as 12 months), a sum of possibly preventable emergency room costs (e.g., over a period of time, such as 12 months), a sum of in-patient encounters (e.g., over a period of time, such as 12 months), a list of unique national drug code (NDC) codes for drugs prescribed (e.g., over a period of time, such as 12 months), a list of unique drug names for drugs prescribed (e.g., over a period of time, such as 12 months), a list of unique pharmacological classes for drugs prescribed (e.g., over a period of time, such as 12 months), a list of unique Drug Enforcement Agency (DEA) Schedules for drugs prescribed (e.g., over a period of time, such as 12 months), a count of unique drugs prescribed (e.g., over a period of time, such as 12 months), flags for different condition categories based on a proprietary mapping of ICD-9, CPT, and HCPCS codes to suspected conditions (e.g., over a period of time, such as 12 months), flags for different HCCs based on CMS mapping of ICD-9 codes to chronic conditions (e.g., over a period of time, such as 12 months), and/or the like. For example, the expected medical costs may be a cost that would be expected given a patient's disease burden and calculated by assigning HCCs to members, summing the capitation premium for those HCCs, and adjusting for medical loss ratio. Observed medical costs can be calculated as per patient per medical costs over eligible months during the relevant time period. The deviation from expected medical costs is then calculated by subtracting observed medical costs from expected medical costs.
The risk factors may be weighted to generate the risk score. For example, some patients may have experienced an acute incident in their recent past that has caused their cost and utilization to spike temporarily. The medical costs associated with these patients may regress to the cost and/or utilization mean and may not benefit significantly from care management resources (as the chronically ill or poorly managed patients would). To address the possibility of regressing to the cost and/or utilization mean, the health interface system 140 can categorize a patient into one of three groups: high-deviation (e.g., observed average monthly medical costs exceed expected average monthly medical costs by a threshold value), chronic (e.g., a patient that has one or more high risk chronic conditions, as suggested by the patient's claim history, but whose observed average monthly medical costs do not exceed expected average monthly medical costs by the threshold value), or non-chronic low-deviation (e.g., a patient that does not have one or more high risk chronic conditions, as suggested by the patient's claim history, and whose observed average monthly medical costs do not exceed the expected average monthly medical costs by the threshold value). Once categorized, the health interface system 140 can train nine different logistic regression models, one for each of the following state transitions: high-deviation to high-deviation, high-deviation to chronic, high-deviation to non-chronic low-deviation, chronic to high-deviation, chronic to chronic, chronic to non-chronic low-deviation, non-chronic low-deviation to high-deviation, non-chronic low-deviation to chronic, and non-chronic low-deviation to non-chronic low-deviation. The training set for each model may include a sample of all eligible patients. The model training can use L1 regularization to address the collinearity between several of the cost metrics by inducing sparseness on the model. For each patient, the health interface system 140 can generate features for a period of time (e.g., 12 months) before and a period of time (e.g., 12 months) after a selected split date. The output of each model training cycle can be a set of feature weights (e.g., coefficients in a logistic regression model) that can be used to compute propensity scores for each of the state transitions listed above.
Once trained, the health interface system 140 can calculate propensity scores (e.g., a likelihood that a patient will move in to or remain in a given state for a period of time, such as 12 months) for a patient for each of the patient's three possible state transitions (e.g., there are three possible state transitions because the patient has already been categorized as starting in one of three categories). For each state transition, features can be weighted according to a trained model. The health interface system 140 can rank some or all patients by a propensity score associated with the transition to a high-deviation state, and the ranking of a patient can be translated into a risk score. In some embodiments, the user interface 400 may provide the option to the user to customize the weighting employed to generate the risk score (e.g., the factors used to generate the risk score, the threshold value that determines whether a patient is categorized as high-deviation, etc.).
The user may select care plan button 402 to view a patient's care plan, as described below with respect to FIG. 5, and the user may select health assessment button 404 to view a patient's health assessment, as described below with respect to FIG. 6.
FIG. 5 illustrates a user interface 500 displaying a patient care plan 502. The interface 500 may be generated by the health interface system 140 and viewable on any of the entities in communication with the health interface system 140. As illustrated in FIG. 5, the user has selected care plan button 218. Thus, the pane 202 displays the care plan 502. The care plan 502 may allow all authorized members of the care team to view the current and past care plans for the patient. Centralized storage of this data via the health interface system 140 may allow care team members and patient's providers access to baseline data in order to gauge the effectiveness and/or progress that a patient has made in any given care plan. The availability of care plans may also allow some or all of the various entities the ability to collaborate on current care plan goals and/or monitor progress.
In some embodiments, the care plan 502 is interactive. For example, the health interface system 140 can receive the care plan via an API such that one or more fields are editable (by an entity with sufficient permissions) when displayed in the user interface 500. The user interface 500 can display relevant input options showing the editable fields when an editable field is selected. If a field is edited, the health interface system 140 can synch the updated care plan 502 with the health plan's case management system. In other embodiments, the care plan 502 is static (e.g., received as a PDF)
FIG. 6 illustrates a user interface 600 displaying a patient health assessment. The interface 600 may be generated by the health interface system 140 and viewable on any of the entities in communication with the health interface system 140. As illustrated in FIG. 6, the user has selected health assessment button 220. Thus, the pane 202 displays a patient health assessment. The health assessment may allow all authorized members of the care team to view the current and/or past health assessments that have been conducted for the patient. The availability of these assessments may enable some or all members of the care team to access information that is critical in addressing each patient's specific needs. In addition to allowing a historical starting measure of the patient, assessment information may also allow the care team to determine when new assessments should be generated.
FIG. 7 illustrates a user interface 700 displaying a patient clinical evaluation. The interface 700 may be generated by the health interface system 140 and viewable on any of the entities in communication with the health interface system 140. As illustrated in FIG. 7, the user has selected vitals button 222. Thus, the pane 202 displays a set of clinical evaluations for the patient. The clinical evaluations may include date-specific recorded vitals signs, such as temperature, pulse, blood pressure, and/or respiratory rate. These vitals may allow providers to view a summary of the patient's health vitals and determine whether it is necessary to determine changes in a health status observed by different providers. Each instance of vitals may allow entities to enter notes regarding dated entries and observations.
FIG. 8 illustrates a user interface 800 displaying alerts and messages for a care team member. The interface 800 may be generated by the health interface system 140 and viewable on any of the entities in communication with the health interface system 140. As illustrated in FIG. 8, the user has selected alert button 224. Thus, the pane 202 displays alerts and/or notifications. The alerts and/or notifications may be for one or more patients that the viewing entity provides services for. The alerts and/or notifications may be derived from data stored in the databases. Example alerts and/or notifications can include a close appointment alert (e.g., a patient has an appointment coming up in the next week, day, hour, etc.), a missed appointment alert (e.g., if a patient missing an appointment), a propensity score shift (e.g., if a patients' propensity or risk score status changes, and the health provider can also be alerted), a recent admission to an emergency room (or a pre-authorization request from a health provider), a recent in-patient event (or pre-authorization request from a health provider), no interaction by the patient with the health interface system 140 for a period of time (e.g., 6 months), reminders for scheduled check-ins with a patient, and/or the like, In some cases, the alerts and/or notifications may be generated based on data associated with an entity that is different than the entity that has logged into the health interface system 140. For example, a pharmacist may have logged into the health interface system 140 and an alert may have been generated for the pharmacist based on data stored in a database associated with a primary care provider.
The notifications may inform an entity of what tasks have been accomplished and what tasks still need to be accomplished. The notifications and/or alerts may be color-coded to indicate an entity associated with the notification and/or alert and/or to indicate an importance of the notification and/or alert (e.g., green may mean the notification and/or alert is not vital, whereas red may mean the notification and/or alert is urgent).
In an embodiment, entities can communicate with each other via the health interface system 140. For example, one entity can send a message to another entity via the health interface system 140. Any messages sent via the health interface system 140 may be viewable in the user interface 800 in the messages section.

Example User Interfaces Depicting Additional Analytics

In some cases, the health interface system 140 can analyze health data at a macro level to, for example, provide insight on the features of a patient population as a whole in a given geographic region. FIG. 9 illustrates a user interface 900 displaying a breakdown of remaining member visits by county. The interface 900 may be generated by the health interface system 140 and viewable on any of the entities in communication with the health interface system 140. As illustrated in FIG. 9, a map 902 indicates a location, by county, of patients that may require a visit (e.g., a well-child visit) within a given period of time (e.g., 90 days). The map 902 may include shading to indicate counties that have a high number of required visits and a low number of required visits. The pane 202 may include a numerical breakdown of the number of required visits by county, medical group, and/or provider.
FIG. 10 illustrates a user interface 1000 displaying a breakdown of claims, visits, and costs by diagnoses and facilities. The interface 1000 may be generated by the health interface system 140 and viewable on any of the entities in communication with the health interface system 140. As illustrated in FIG. 10, the pane 202 includes a list of the top diagnoses by cost associated with emergency room visits for a given patient population.
FIG. 11 illustrates a user interface 1100 displaying a graph 1102 of weighted care ratio by healthcare provider. The interface 1100 may be generated by the health interface system 140 and viewable on any of the entities in communication with the health interface system 140. As illustrated in FIG. 11, the pane 202 includes the graph 1102 and a table that display a provider network as assessed by their care ratio (e.g., the percentage of associated patients who actually received the medical services for which they were eligible), which can be determined by the health interface system 140. The care ratio and the weighted care ratio allow entities to evaluate the character of the provider network when it comes to identifying which providers are best suited to caring for a patient in the patient population.
In an embodiment, a care ratio is a measure of compliance, applicable to providers, and can be specific to a particular medical service. A care ratio can be a percentage of how many patients eligible for a particular service have actually received that service. For example, if a provider has 100 diabetics associated with them, and there is an interest in knowing how many of these diabetics have had an HbA1c test in the last 12 months, the health interface system 140 would take the number of diabetics receiving this test and divide that by the total number of eligible patients. If the number of diabetics receiving this test is 60 and the total number of eligible patients is 100, the provider's care ratio would therefore be 60%.
In an embodiment, a weighted care ratio is a measure of how well a provider is addressing a particular missing service for their assigned patients for the purposes of comparing providers. The weighted care ratio is weighted because the ratio takes into account the number of patients that are assigned to a provider. The care ratios of providers with more patients may contribute proportionally more to the population average for all providers. Providers with very few patients may typically be assigned the average for the population rather than their true care ratio. The weighted care ratio can avoid overemphasizing the care ratio of a provider that has just a few patients. For example, if the care ratio is “percent of membership receiving an HbA1c test in last 12 months” (e.g., a measure applicable to diabetics only), and a provider only has one patient with diabetes and that patient has not had that service, then that provider's care ratio would be 0%. Instead, applying the logic of the weighted care ratio, that provider would receive the average care ratio for the population (e.g., 60%). Thus, this can prevent over-indexing on providers assigned to small populations of patients.

Example User Interfaces Depicting Actionable Services

FIGS. 12A-12B illustrate user interfaces 1200 displaying a location of care team members. The interface 1200 may be generated by the health interface system 140 and viewable on any of the entities in communication with the health interface system 140. As illustrated in FIG. 12A, the location of various care team members in one or more care teams is displayed. For example, the care team members may be shaded to indicate what team the care team member is a member of. The interface 1200 may also an entity to contact a care team member that is selected. For example, care team member John Gold is selected and thus may be contacted via phone or electronic message (e.g., text message).
As illustrated in FIG. 12B, a filter 1202 can be selected such that one or more care team members can be hidden. For example, the entity may select one or more care teams, and those care team members that are not a member of the selected care team may disappear from the interface 1200.
FIG. 13 illustrates a user interface 1300 displaying a location of healthcare providers. The interface 1300 may be generated by the health interface system 140 and viewable on any of the entities in communication with the health interface system 140. As illustrated in FIG. 13, the location of various providers is displayed. For example, the providers nearest to a patient may be displayed. The interface 1300 may also an entity to contact a provider that is selected and/or to schedule an appointment with a selected provider. For example, provider 2 is selected. An entity may contact provider 2 via the phone or may be redirected to a page that allows the entity to schedule an appointment with the provider.

Example Process Flow

FIG. 14 is a flowchart 1400 depicting an illustrative operation of aggregating, analyzing, and displaying health data. Depending on the embodiment, the method of FIG. 14 may be performed by various computing devices, such as by the health interface system 140. Depending on the embodiment, the method of FIG. 14 may include fewer and/or additional blocks and the blocks may be performed in an order different than illustrated.
In block 1402, a health dataset stored in a database is retrieved. For example, the health dataset may include medical and/or pharmaceutical claims data. The health dataset may include a set of second fields (e.g., columns).
In block 1404, a name for each second field in the retrieved health dataset is identified. In block 1406, a mapping between each identified second field name and a name of a first field in a plurality of first fields is determined. The plurality of first fields may include common terms.
In block 1408, the retrieved health dataset is stored in a second database such that each data in the retrieved health dataset is stored in associated with the first field that maps to the second field that the respective data is associated with. For example, the data may be unchanged, however the column headers for the data may be modified.
In block 1410, an identity of a patient for which records are requested is determined. For example, a care team member may desire to view the records of a specific patient.
In block 1412, user interface data is generated for rendering an interactive user interface on a computing device that includes data stored in the second database that is associated with the patient. The interactive user interface may display an identification of the first fields in association with the data.

Implementation Mechanisms

According to one embodiment, the techniques described herein are implemented by one or more special-purpose computing devices. The special-purpose computing devices may be hard-wired to perform the techniques, or may include digital electronic devices such as one or more application-specific integrated circuits (ASICs) or field programmable gate arrays (FPGAs) that are persistently programmed to perform the techniques, or may include one or more general purpose hardware processors programmed to perform the techniques pursuant to program instructions in firmware, memory, other storage, or a combination. Such special-purpose computing devices may also combine custom hard-wired logic, ASICs, or FPGAs with custom programming to accomplish the techniques. The special-purpose computing devices may be desktop computer systems, server computer systems, portable computer systems, handheld devices, networking devices or any other device or combination of devices that incorporate hard-wired and/or program logic to implement the techniques.
Computing device(s) are generally controlled and coordinated by operating system software, such as iOS, Android, Chrome OS, Windows XP, Windows Vista, Windows 7, Windows 8, Windows Server, Windows CE, Unix, Linux, SunOS, Solaris, iOS, Blackberry OS, VxWorks, or other compatible operating systems. In other embodiments, the computing device may be controlled by a proprietary operating system. Conventional operating systems control and schedule computer processes for execution, perform memory management, provide file system, networking, I/O services, and provide a user interface functionality, such as a graphical user interface (“GUI”), among other things.
For example, FIG. 15 is a block diagram that illustrates a computer system 1500 upon which an embodiment may be implemented. For example, any of the computing devices discussed herein, such as the one or more primary care provider devices 110A, the one or more specialist provider devices 110B, the one or more other provider devices 110N, the care team device 130, the patient device 150, the foster parent device 160, the pharmacist device 170, the government device 180, and/or the health interface system 140 may include some or all of the components and/or functionality of the computer system 1500.
Computer system 1500 includes a bus 1502 or other communication mechanism for communicating information, and a hardware processor, or multiple processors, 1504 coupled with bus 1502 for processing information. Hardware processor(s) 1504 may be, for example, one or more general purpose microprocessors.
Computer system 1500 also includes a main memory 1506, such as a random access memory (RAM), cache and/or other dynamic storage devices, coupled to bus 1502 for storing information and instructions to be executed by processor 1504. Main memory 1506 also may be used for storing temporary variables or other intermediate information during execution of instructions to be executed by processor 1504. Such instructions, when stored in storage media accessible to processor 1504, render computer system 1500 into a special-purpose machine that is customized to perform the operations specified in the instructions.
Computer system 1500 further includes a read only memory (ROM) 1508 or other static storage device coupled to bus 1502 for storing static information and instructions for processor 1504. A storage device 1510, such as a magnetic disk, optical disk, or USB thumb drive (Flash drive), etc., is provided and coupled to bus 1502 for storing information and instructions.
Computer system 1500 may be coupled via bus 1502 to a display 1512, such as a cathode ray tube (CRT) or LCD display (or touch screen), for displaying information to a computer user. An input device 1514, including alphanumeric and other keys, is coupled to bus 1502 for communicating information and command selections to processor 1504. Another type of user input device is cursor control 1516, such as a mouse, a trackball, or cursor direction keys for communicating direction information and command selections to processor 804 and for controlling cursor movement on display 1512. This input device typically has two degrees of freedom in two axes, a first axis (e.g., x) and a second axis (e.g., y), that allows the device to specify positions in a plane. In some embodiments, the same direction information and command selections as cursor control may be implemented via receiving touches on a touch screen without a cursor.
Computing system 1500 may include a user interface module to implement a GUI that may be stored in a mass storage device as executable software codes that are executed by the computing device(s). This and other modules may include, by way of example, components, such as software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables.
In general, the word “module,” as used herein, refers to logic embodied in hardware or firmware, or to a collection of software instructions, possibly having entry and exit points, written in a programming language, such as, for example, Java, Lua, C or C++. A software module may be compiled and linked into an executable program, installed in a dynamic link library, or may be written in an interpreted programming language such as, for example, BASIC, Perl, or Python. It will be appreciated that software modules may be callable from other modules or from themselves, and/or may be invoked in response to detected events or interrupts. Software modules configured for execution on computing devices may be provided on a computer readable medium, such as a compact disc, digital video disc, flash drive, magnetic disc, or any other tangible medium, or as a digital download (and may be originally stored in a compressed or installable format that requires installation, decompression or decryption prior to execution). Such software code may be stored, partially or fully, on a memory device of the executing computing device, for execution by the computing device. Software instructions may be embedded in firmware, such as an EPROM. It will be further appreciated that hardware modules may be comprised of connected logic units, such as gates and flip-flops, and/or may be comprised of programmable units, such as programmable gate arrays or processors. The modules or computing device functionality described herein are preferably implemented as software modules, but may be represented in hardware or firmware. Generally, the modules described herein refer to logical modules that may be combined with other modules or divided into sub-modules despite their physical organization or storage
Computer system 1500 may implement the techniques described herein using customized hard-wired logic, one or more ASICs or FPGAs, firmware and/or program logic which in combination with the computer system causes or programs computer system 1500 to be a special-purpose machine. According to one embodiment, the techniques herein are performed by computer system 1500 in response to processor(s) 1504 executing one or more sequences of one or more instructions contained in main memory 1506. Such instructions may be read into main memory 1506 from another storage medium, such as storage device 1510. Execution of the sequences of instructions contained in main memory 1506 causes processor(s) 1504 to perform the process steps described herein. In alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions.
The term “non-transitory media,” and similar terms, as used herein refers to any media that store data and/or instructions that cause a machine to operate in a specific fashion. Such non-transitory media may comprise non-volatile media and/or volatile media. Non-volatile media includes, for example, optical or magnetic disks, such as storage device 1510. Volatile media includes dynamic memory, such as main memory 1506. Common forms of non-transitory media include, for example, a floppy disk, a flexible disk, hard disk, solid state drive, magnetic tape, or any other magnetic data storage medium, a CD-ROM, any other optical data storage medium, any physical medium with patterns of holes, a RAM, a PROM, and EPROM, a FLASH-EPROM, NVRAM, any other memory chip or cartridge, and networked versions of the same.
Non-transitory media is distinct from but may be used in conjunction with transmission media. Transmission media participates in transferring information between nontransitory media. For example, transmission media includes coaxial cables, copper wire and fiber optics, including the wires that comprise bus 802. Transmission media can also take the form of acoustic or light waves, such as those generated during radio-wave and infra-red data communications.
Various forms of media may be involved in carrying one or more sequences of one or more instructions to processor 804 for execution. For example, the instructions may initially be carried on a magnetic disk or solid state drive of a remote computer. The remote computer can load the instructions into its dynamic memory and send the instructions over a telephone line using a modem. A modem local to computer system 1500 can receive the data on the telephone line and use an infra-red transmitter to convert the data to an infra-red signal. An infra-red detector can receive the data carried in the infra-red signal and appropriate circuitry can place the data on bus 1502. Bus 1502 carries the data to main memory 1506, from which processor 1504 retrieves and executes the instructions. The instructions received by main memory 1506 may retrieve and execute the instructions. The instructions received by main memory 1506 may optionally be stored on storage device 1510 either before or after execution by processor 1504.
Computer system 1500 also includes a communication interface 1518 coupled to bus 1502. Communication interface 1518 provides a two-way data communication coupling to a network link 1520 that is connected to a local network 1522. For example, communication interface 1518 may be an integrated services digital network (ISDN) card, cable modem, satellite modem, or a modem to provide a data communication connection to a corresponding type of telephone line. As another example, communication interface 1518 may be a local area network (LAN) card to provide a data communication connection to a compatible LAN (or WAN component to communicated with a WAN). Wireless links may also be implemented. In any such implementation, communication interface 1518 sends and receives electrical, electromagnetic or optical signals that carry digital data streams representing various types of information.
Network link 1520 typically provides data communication through one or more networks to other data devices. For example, network link 1520 may provide a connection through local network 1522 to a host computer 1524 or to data equipment operated by an Internet Service Provider (ISP) 1526. ISP 1526 in turn provides data communication services through the world wide packet data communication network now commonly referred to as the “Internet” 1528. Local network 1522 and Internet 1528 both use electrical, electromagnetic or optical signals that carry digital data streams. The signals through the various networks and the signals on network link 1520 and through communication interface 1518, which carry the digital data to and from computer system 1500, are example forms of transmission media.
Computer system 1500 can send messages and receive data, including program code, through the network(s), network link 1520 and communication interface 1518. In the Internet example, a server 1530 might transmit a requested code for an application program through Internet 1528, ISP 1526, local network 1522 and communication interface 1518.
The received code may be executed by processor 1504 as it is received, and/or stored in storage device 1510, or other non-volatile storage for later execution.

Terminology

Each of the processes, methods, and algorithms described in the preceding sections may be embodied in, and fully or partially automated by, code modules executed by one or more computer systems or computer processors comprising computer hardware. The processes and algorithms may be implemented partially or wholly in application-specific circuitry.
The various features and processes described above may be used independently of one another, or may be combined in various ways. All possible combinations and subcombinations are intended to fall within the scope of this disclosure. In addition, certain method or process blocks may be omitted in some implementations. The methods and processes described herein are also not limited to any particular sequence, and the blocks or states relating thereto can be performed in other sequences that are appropriate. For example, described blocks or states may be performed in an order other than that specifically disclosed, or multiple blocks or states may be combined in a single block or state. The example blocks or states may be performed in serial, in parallel, or in some other manner. Blocks or states may be added to or removed from the disclosed example embodiments. The example systems and components described herein may be configured differently than described. For example, elements may be added to, removed from, or rearranged compared to the disclosed example embodiments.
Conditional language, such as, among others, “can,” “could,” “might,” or “may,” unless specifically stated otherwise, or otherwise understood within the context as used, is generally intended to convey that certain embodiments include, while other embodiments do not include, certain features, elements and/or steps. Thus, such conditional language is not generally intended to imply that features, elements and/or steps are in any way required for one or more embodiments or that one or more embodiments necessarily include logic for deciding, with or without user input or prompting, whether these features, elements and/or steps are included or are to be performed in any particular embodiment.
Any process descriptions, elements, or blocks in the flow diagrams described herein and/or depicted in the attached figures should be understood as potentially representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process. Alternate implementations are included within the scope of the embodiments described herein in which elements or functions may be deleted, executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those skilled in the art.
The term “a” as used herein should be given an inclusive rather than exclusive interpretation. For example, unless specifically noted, the term “a” should not be understood to mean “exactly one” or “one and only one”; instead, the term “a” means “one or more” or “at least one,” whether used in the claims or elsewhere in the specification and regardless of uses of quantifiers such as “at least one,” “one or more,” or “a plurality” elsewhere in the claims or specification.
The term “comprising” as used herein should be given an inclusive rather than exclusive interpretation. For example, a general purpose computer comprising one or more processors should not be interpreted as excluding other computer components, and may possibly include such components as memory, input/output devices, and/or network interfaces, among others.
It should be emphasized that many variations and modifications may be made to the above-described embodiments, the elements of which are to be understood as being among other acceptable examples. All such modifications and variations are intended to be included herein within the scope of this disclosure. The foregoing description details certain embodiments of the invention. It will be appreciated, however, that no matter how detailed the foregoing appears in text, the invention can be practiced in many ways. As is also stated above, it should be noted that the use of particular terminology when describing certain features or aspects of the invention should not be taken to imply that the terminology is being re-defined herein to be restricted to including any specific characteristics of the features or aspects of the invention with which that terminology is associated. The scope of the invention should therefore be construed in accordance with the appended claims and any equivalents thereof.

Claims

What is claimed is:

1. A computing system comprising:

one or more computer processors;

a database that organizes data in a plurality of first columns;

a computer readable storage medium storing program instructions configured for execution by the one or more computer processor in order to cause the computing system to:

for a second database,

access a dataset stored in the second database, wherein the accessed dataset comprises data for a plurality of users organized in a plurality of second columns;

determine a mapping between a name of a second column in the plurality of second columns and a name of a first column in the plurality of first columns; and

cause display of an unmodified version of the data in the accessed dataset corresponding to the name of the second column in a user interface under the name of the first column;

receive a request to access the computing system;

determine an identity of a user associated with the request to access the computing system;

retrieve, from the first database, user health data that is associated with the determined user;

retrieve, from a third database, health claims data associated with the determined user;

categorize the determined user into a first group based on the health claims data;

train one or more models using the health claims data and health claims data associated with one or more other users to produce a set of feature weights associated with the determined user, wherein each of the one or more models corresponds to a state transition from the first group to another group in one or more groups;

determine a likelihood that the determined user will transition from the first group into one of the one or more other groups within a threshold time period using the set of feature weights;

translate the likelihood into a risk score; and

generate user interface data for rendering the user interface on a computing device, wherein the user interface comprises an indication of the risk score.

2. The computing system of claim 1, wherein the user interface includes a first container that comprises an identification of at least one third column in the plurality of first columns, wherein the first container further comprises the retrieved user health data that corresponds with the at least one third column.

3. The computing system of claim 1, wherein the retrieved health claims data comprises medical claims submitted on behalf of the determined user, and wherein the computer readable storage medium further stores program instructions that cause the computing system to generate a summary of a health history of the determined user based on the medical claims.

4. The computing system of claim 1, wherein the retrieved user health data comprises prescription data.

5. The computing system of claim 1, wherein the risk score is based on at least one of a number of missing services associated with the user, a priority of each missing service associated with the user, a likelihood that the user seeks medical services without intervention, or a number of times the user does not comply with a recommended care plan.

6. The computing system of claim 1, wherein the mapping between the name of the second column and the name of the first column is determined based on an ontology.

7. The computing system of claim 1, wherein the user interface further includes a first container that comprises a first alert associated with a team member and a second alert associated with the team member, wherein the first alert corresponds with the user, and wherein the second alert corresponds with a second user.

8. The computing system of claim 1, wherein the computer readable storage medium further stores program instructions that cause the computing system to:

receive text and a selection of a second team member from a first team member; and

transmit a message to an account associated with the second team member, wherein the message comprises the text, and wherein the second team member can view the message when accessing the computing system.

9. The computing system of claim 8, wherein the first team member is one of a primary care physician, a pharmacist, a government agency employee, a guardian, or the user.

10. A computer-implemented method comprising:

as implemented by one or more computer systems comprising computer hardware and memory, the one or more computer systems configured with specific executable instructions,

retrieving a dataset stored in a first database, wherein the retrieved dataset comprises data for a plurality of users organized in a plurality of second columns;

determining a mapping between a name of a second column in the plurality of second columns and a name of a first column in a plurality of first columns;

causing display of an unmodified version of the data in the retrieved dataset corresponding to the name of the second column in a user interface under the name of the first column;

receiving a request to access the one or more computer systems;

determining an identity of a user associated with the request to access the one or more computer systems;

retrieving, from the first database, user health data that is associated with the determined user;

retrieving, from a second database, health claims data associated with the determined user;

categorizing the determined user into a first group based on the health claims data;

training one or more models using the health claims data and health claims data associated with one or more other users to produce a set of feature weights associated with the determined user, wherein each of the one or more models corresponds to a state transition from the first group to another group in one or more groups;

determining a likelihood that the determined user will transition from the first group into one of the one or more other groups within a threshold time period using the set of feature weights;

translating the likelihood into a risk score; and

generating user interface data for rendering the user interface on a computing device, wherein the user interface comprises an indication of the risk score.

11. The computer-implemented method of claim 10, wherein the user interface includes a first container that comprises an identification of at least one third column in the plurality of first columns, wherein the first container further comprises the retrieved user health data that corresponds with the at least one third column.

12. The computer-implemented method of claim 11, further comprising generating a summary of a health history of the determined user based on the retrieved user health data, wherein the first container further comprises the generated summary of the health history of the determined user.

13. The computer-implemented method of claim 12, wherein the retrieved health claims data comprises medical claims submitted on behalf of the determined user, and wherein the computer-implemented method further comprises generating the summary of the health history of the determined user based on the medical claims.

14. The computer-implemented method of claim 10, wherein the retrieved health claims data comprises prescription data.

15. The computer-implemented method of claim 10, further comprising:

receiving text and a selection of a second team member from a first team member; and

transmitting a message to an account associated with the second team member, wherein the message comprises the text, and wherein the second team member can view the message when accessing the computing system.

16. The computer-implemented method of claim 15, wherein the first team member is one of a primary care physician, a pharmacist, a government agency employee, a guardian, or the user.

17. A non-transitory computer-readable storage medium including computer-executable instructions that, when executed by a processor, configure the processor to:

retrieve a dataset stored in a first database, wherein the retrieved dataset comprises data for a plurality of users organized in a plurality of second columns;

determine a mapping between a name of a second column in the plurality of second columns and a name of a first column in a plurality of first columns;

cause display of an unmodified version of the data in the retrieved dataset corresponding to the name of the second column in a user interface under the name of the first column;

receive a request to access one or more computer systems;

determine an identity of a user associated with the request to access the one or more computer systems;

retrieve, from a second database, health claims data associated with the determined user;

translate the likelihood into a risk score; and