WO2024001695A1 - 数据采集方法、装置、系统及计算机可读存储介质 - Google Patents

数据采集方法、装置、系统及计算机可读存储介质 Download PDF

Info

Publication number
WO2024001695A1
WO2024001695A1 PCT/CN2023/098645 CN2023098645W WO2024001695A1 WO 2024001695 A1 WO2024001695 A1 WO 2024001695A1 CN 2023098645 W CN2023098645 W CN 2023098645W WO 2024001695 A1 WO2024001695 A1 WO 2024001695A1
Authority
WO
WIPO (PCT)
Prior art keywords
interest
question
topic
data
label
Prior art date
Application number
PCT/CN2023/098645
Other languages
English (en)
French (fr)
Inventor
张坤
周国新
Original Assignee
苏州景昱医疗器械有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 苏州景昱医疗器械有限公司 filed Critical 苏州景昱医疗器械有限公司
Publication of WO2024001695A1 publication Critical patent/WO2024001695A1/zh

Links

Classifications

    • GPHYSICS
    • G16INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
    • G16HHEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
    • G16H10/00ICT specially adapted for the handling or processing of patient-related medical or healthcare data
    • G16H10/20ICT specially adapted for the handling or processing of patient-related medical or healthcare data for electronic clinical trials or questionnaires
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/35Clustering; Classification
    • G06F16/355Class or cluster creation or modification
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/30Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
    • G06F16/38Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00Handling natural language data
    • G06F40/10Text processing
    • G06F40/166Editing, e.g. inserting or deleting
    • G06F40/174Form filling; Merging
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/04Architecture, e.g. interconnection topology
    • G06N3/045Combinations of networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06NCOMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00Computing arrangements based on biological models
    • G06N3/02Neural networks
    • G06N3/08Learning methods
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02ATECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
    • Y02A90/00Technologies having an indirect contribution to adaptation to climate change
    • Y02A90/10Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation

Definitions

  • This application relates to the technical field of automatic form generation and data collection, for example, to data collection methods, devices, systems and computer-readable storage media.
  • Clinical Trial refers to any systematic study of drugs in humans (patients or healthy volunteers) to confirm or reveal the effects, adverse reactions and/or absorption, distribution, metabolism and excretion of the test drug, The purpose is to determine the efficacy and safety of the experimental drug.
  • Relevant clinical trial data collection and recording methods mainly rely on paper forms, or different clinical trials collect data through different systems. This will cause data to be easily lost, inconvenient to save, and data processing caused by multiple forms and multiple systems will be inconvenient. Convenient question.
  • Patent CN113918699A discloses a method for generating a questionnaire, which includes: receiving a user-triggered questionnaire generation request carrying user information, and performing identity verification on the user based on the user information; if the identity verification passes, based on the The user information performs authority verification on the user; if the authority verification passes, a preset questionnaire configuration interface is displayed; wherein, the questionnaire configuration interface includes a survey question menu, and the survey question menu includes a variety of survey question types; receive The user-triggered selection operation on the survey question menu in the questionnaire configuration interface obtains the corresponding target survey question type; displaying the question editor corresponding to the target survey question type in the questionnaire configuration interface area; wherein, the topic editing area includes a topic title editing block and a topic content editing block; based on the editing operation input by the user in the topic editing area, a target survey question corresponding to the target survey question type is obtained ; Generate a corresponding target questionnaire based on the target survey question and the preset questionnaire template.
  • the above method can improve the intelligence and flexibility of questionnaire
  • this application provides a data collection method, device, system and computer-readable storage medium to solve the problems existing in the above related technologies.
  • the purpose of this application is to provide data collection methods, devices, systems and computer-readable storage media, customize the required data collection forms according to different clinical trial orientations, and solve the problems caused by easy data loss, inconvenient storage, and multiple forms and multiple systems.
  • this application provides a data collection method for data collection during clinical trials.
  • the method includes include:
  • the multiple topics of interest include multiple sensing topics and multiple non-sensing topics;
  • the data collection form includes a portion to be filled corresponding to each topic of interest, and the topic information includes a topic description and a topic type;
  • a sensing device to sense the patient's bioelectrical signals to obtain data to be filled corresponding to multiple sensing questions of the patient
  • the data to be filled corresponding to each topic of interest of the patient is used to fill the portion to be filled corresponding to each topic of interest in the data collection form.
  • determining multiple topics of interest to the user includes:
  • the topics of interest to all doctors among the users are removed to obtain multiple topics of interest to the users.
  • determining multiple topics of interest to the user includes:
  • Each topic in the topic database corresponds to one or multiple tags
  • obtaining the label similarity between each topic in the topic database and the user includes:
  • the training process of the label similarity model includes:
  • the training set includes a plurality of training data, each of the training data includes a label of a first sample object, a label of a second sample object, and the first sample object and the second sample object.
  • the user selects multiple topics with the highest tag similarity from the topic database as the user A number of topics of interest, including:
  • N is an integer greater than 1;
  • the question type of each question of interest is text box, text field, radio choice, multi-selection, drop-down box or attachment upload;
  • the question type of the question of interest is a text box
  • the part to be filled in the question of interest adopts a text box
  • the question type of the question of interest is a text field
  • the part to be filled in the question of interest adopts a text field
  • the question type of the question of interest is a radio button
  • the part to be filled in the question of interest uses a radio button box
  • the part to be filled in the question of interest uses a check box
  • the part to be filled in the question of interest uses a drop-down box
  • the part to be filled in the question of interest uses an attachment upload control.
  • obtaining data to be filled corresponding to multiple non-sensing questions of the patient includes:
  • Keyword extraction is performed on the patient's disease information to obtain data to be filled corresponding to multiple non-sensing questions of the patient.
  • this application provides a data collection device for collecting data during a clinical trial.
  • the device includes a processor, and the processor is configured to:
  • the multiple topics of interest include multiple sensing topics and multiple non-sensing topics;
  • the data collection form includes a portion to be filled corresponding to each topic of interest, and the topic information includes a topic description and a topic type;
  • a sensing device to sense the patient's bioelectrical signals to obtain data to be filled corresponding to multiple sensing questions of the patient
  • the data to be filled corresponding to each topic of interest of the patient is used to fill the portion to be filled corresponding to each topic of interest in the data collection form.
  • the processor is further configured to determine multiple topics of interest to the user in the following manner:
  • the topics of interest to all doctors among the users are removed to obtain multiple topics of interest to the users.
  • the processor is further configured to determine multiple topics of interest to the user in the following manner:
  • Each topic in the topic database corresponds to one or multiple tags
  • the processor is further configured to obtain the tag similarity between each question in the question library and the user in the following manner:
  • the training process of the label similarity model includes:
  • the training set includes a plurality of training data, each of the training data includes a label of a first sample object, a label of a second sample object, and the first sample object and the second sample object.
  • the processor is further configured to obtain multiple topics of interest to the user in the following manner:
  • N is an integer greater than 1;
  • the question type of each question of interest is text box, text field, radio choice, multi-selection, drop-down box or attachment upload;
  • the question type of the question of interest is a text box
  • the part to be filled in the question of interest adopts a text box
  • the question type of the question of interest is a text field
  • the part to be filled in the question of interest adopts a text field
  • the question type of the question of interest is a radio button
  • the part to be filled in the question of interest uses a radio button box
  • the part to be filled in the question of interest uses a check box
  • the part to be filled in the question of interest uses a drop-down box
  • the part to be filled in the question of interest uses an attachment upload control.
  • the processor is further configured to obtain data to be filled corresponding to multiple non-sensing questions of the patient in the following manner:
  • Keyword extraction is performed on the patient's disease information to obtain data to be filled corresponding to multiple non-sensing questions of the patient.
  • this application provides a data collection system, which includes:
  • the sensing device is used for sensing bioelectrical signals of the patient.
  • the present application provides a computer-readable storage medium that stores a computer program.
  • the computer program When the computer program is executed by a processor, it implements the steps of any of the above methods or implements any of the above methods. function of the device.
  • sensing questions that is, questions related to sensed bioelectric signals
  • non-sensing questions questions that have nothing to do with bioelectric signals
  • question information based on the above-mentioned topics of interest (including question description and question type ) automatically generates a (clinical trial) data collection form corresponding to the user.
  • the generated data collection form includes a to-be-filled section corresponding to each topic of interest; during the clinical trial process, sensing equipment is used to sense the patient's bioelectrical signals.
  • Different clinical trials correspond to different users.
  • the user here is, for example, a doctor corresponding to the clinical trial or a user composed of multiple doctors.
  • a general form cannot cover the clinical trial needs of all users (the data that need to be collected for depression and Parkinson's disease are obviously different). Therefore, for different users, it can be based on different clinical trial research topics and doctors' needs.
  • the same clinical trial can have multiple different clinical trial centers, that is, the same clinical trial can correspond to multiple users, thus corresponding to multiple sets of questions of interest, that is, Corresponds to multiple data collection forms.
  • Set a section to be filled in each topic of interest, and fill the data to be filled in for sensing and non-sensing questions into the data collection form, realizing the function of data collection during clinical trials.
  • Figure 1 shows a structural block diagram of a data collection system provided by this application.
  • Figure 2 shows a schematic flow chart of a data collection method provided by this application.
  • FIG. 3 shows a schematic flowchart of determining multiple topics of interest to a user provided by this application.
  • FIG. 4 shows another schematic flowchart of determining multiple topics of interest to a user provided by this application.
  • Figure 5 shows a structural block diagram of a data collection device provided by this application.
  • Figure 6 shows a schematic structural diagram of a program product provided by this application.
  • At least one means one or more, and “plurality” means two or more.
  • “And/or” describes the association of associated objects, indicating that there can be three relationships, for example, A and/or B, which can mean: A exists alone, A and B exist simultaneously, and B exists alone, where A, B can be singular or plural.
  • the character “/” generally indicates that the related objects are in an “or” relationship.
  • “At least one of the following” or similar expressions thereof refers to any combination of these items, including any combination of a single item (items) or a plurality of items (items).
  • At least one of a, b or c can mean: a, b, c, a and b, a and c, b and c, a and b and c, where a, b and c can It can be single or multiple. It is worth noting that "at least one item (item)” can also be interpreted as “one item (item) or multiple items (item)”.
  • Implantable medical systems include implantable nerve electrical stimulation systems, implantable cardiac electrical stimulation systems (also known as pacemakers), implantable drug delivery systems (I DDS for short) and lead transfer systems. Connect to the system, etc.
  • Implantable neuroelectric stimulation systems include, for example, Deep Brain Stimulation (DBS), Cortical Nerve Stimulation (CNS), and Spinal Cord. Stimulation, referred to as SCS), implanted sacral nerve electrical stimulation system (Sacral Nerve Stimulation, referred to as SNS), implanted vagus nerve electrical stimulation system (Vagus Nerve Stimulation, referred to as VNS), etc.
  • the implantable neuroelectric stimulation system includes a stimulator implanted in the patient's body (i.e., an implantable neurostimulator, a nerve stimulation device) and a programmable device installed outside the patient's body. That is, a stimulator is an implant, or the implant includes a stimulator.
  • a stimulator is an implant, or the implant includes a stimulator.
  • Relevant neuromodulation technology mainly involves implanting electrodes (electrodes, for example, in the form of electrode wires) in specific parts of the body's tissues (i.e., target points) through stereotaxic surgery, and sending electrical pulses to the target points through the electrodes to regulate the corresponding neural structures. and the electrical activity of the network and its functions, from And improve symptoms and relieve pain.
  • the stimulator can include an IPG, an extension wire, and an electrode wire.
  • the IPG (implantable pulse generator) is installed in the patient's body. In response to the program-controlled instructions sent by the program-controlled device, it relies on sealed batteries and circuits to provide energy to the body's tissues. Controllable electrical stimulation energy. IPG delivers one or more controllable specific electrical stimulations to specific areas of tissue in the body by extending wires and electrodes.
  • the extension lead is used in conjunction with the IPG as a transmission medium for electrical stimulation signals to transmit the electrical stimulation signals generated by the IPG to the electrode leads. Electrode leads deliver electrical stimulation to specific areas of tissue in the body through multiple electrode contacts.
  • the stimulator is provided with one or more electrode leads on one or both sides, and multiple electrode contacts are provided on the electrode leads.
  • the electrode contacts can be arranged evenly or non-uniformly in the circumferential direction of the electrode leads. As an example, the electrode contacts may be arranged in an array of 4 rows and 3 columns (12 electrode contacts in total) in the circumferential direction of the electrode lead.
  • the electrode contacts may include stimulation electrode contacts and/or collection electrode contacts.
  • the electrode contacts may be in the shape of, for example, a sheet, a ring, a dot, or the like. If necessary, the same electrode contact can perform both stimulation and acquisition tasks.
  • the stimulated in vivo tissue may be the patient's brain tissue, and the stimulated site may be a specific part of the brain tissue.
  • the stimulated parts are generally different, the number of stimulation contacts used (single source or multiple sources), one or more channels (single channel or multi-channel) specific electrical stimulation signals
  • the application and stimulation parameter data are also different.
  • the embodiments of this application do not limit the applicable disease types, which may be the disease types applicable to deep brain stimulation (DBS), spinal cord stimulation (SCS), pelvic stimulation, gastric stimulation, peripheral nerve stimulation, and functional electrical stimulation.
  • DBS diseases that DBS can be used to treat or manage
  • diseases include, but are not limited to: spastic diseases (eg, epilepsy), pain, migraine, mental illness (eg, major depressive disorder (MDD)), bipolar disorder, anxiety disorder, Post-traumatic stress disorder, mild depression, obsessive-compulsive disorder (OCD), behavioral disorders, mood disorders, memory disorders, mental status disorders, mobility disorders (e.g., essential tremor or Parkinson's disease), Huntington's disease, Alzheimer's disease Alzheimer's disease, drug addiction, autism or other neurological or psychiatric diseases and impairments.
  • spastic diseases eg, epilepsy
  • pain migraine
  • mental illness eg, major depressive disorder (MDD)
  • bipolar disorder e.g., anxiety disorder, Post-traumatic stress disorder, mild depression, obsessive-compulsive disorder (OCD)
  • OCD obsessive-compulsive disorder
  • behavioral disorders e.g., mood disorders, memory disorders, mental status
  • the program-controlled device when the program-controlled device and the stimulator establish a program-controlled connection, can be used to adjust the stimulation parameters of the stimulator (or the stimulation parameters of the pulse generator, different stimulation parameters correspond to different electrical stimulation signals), and also
  • the patient's electrophysiological activity can be sensed by the stimulator to collect electrophysiological signals, and the stimulation parameters of the stimulator can be continuously adjusted through the collected electrophysiological signals.
  • the stimulation parameters may include at least one of the following: electrode contact identification used to deliver electrical stimulation (for example, it can be 2# electrode contact and 3# electrode contact), frequency (for example, the number of electrical stimulation pulse signals within 1 s per unit time). Number, unit is Hz), pulse width (duration of each pulse, unit is ⁇ s), amplitude (generally expressed in voltage, that is, the intensity of each pulse, unit is V), timing (for example, it can be continuous or cluster Hair bursts refer to discontinuous temporal behaviors composed of multiple processes), stimulation modes (including one or more of current mode, voltage mode, timing stimulation mode and cyclic stimulation mode), upper and lower limits controlled by doctors ( The range that can be adjusted by the doctor) and the upper and lower limits of patient control (the range that the patient can adjust independently)
  • each stimulation parameter of the stimulator can be adjusted in current mode or voltage mode.
  • the program-controlled equipment may be a doctor-programmed equipment (that is, a program-controlled equipment used by a doctor) or a patient-programmed equipment (that is, a program-controlled equipment used by a patient).
  • Doctor program-controlled equipment can be, for example, tablet computers, laptop computers, desktop computers, mobile phones and other smart devices equipped with program-controlled software. capable terminal equipment.
  • the patient's program-controlled equipment can be, for example, tablet computers, laptops, desktop computers, mobile phones and other intelligent terminal devices equipped with program-controlled software.
  • the patient's program-controlled equipment can also be other electronic equipment with program-controlled functions (such as chargers, data sets with program-controlled functions). collection equipment, etc.).
  • the embodiments of this application do not limit the data interaction between the doctor's program-controlled equipment and the stimulator.
  • the doctor remotely programs the device
  • the doctor's program-controlled equipment can interact with the stimulator through the server and the patient's program-controlled equipment.
  • the doctor performs face-to-face programming with the patient offline
  • the doctor's program-controlled equipment can interact with the stimulator through the patient's program-controlled equipment, and the doctor's program-controlled equipment can also directly interact with the stimulator.
  • the patient programming device may include a host (in communication with the server) and a slave (in communication with the stimulator), the host and slave being communicatively connected.
  • the doctor's program-controlled equipment can interact with the server through the 3G/4G/5G network
  • the server can interact with the host through the 3G/4G/5G network
  • the host can interact with the slave through the Bluetooth protocol/WIFI protocol/USB protocol.
  • the slave machine can interact with the stimulator through the 401MHz-406MHz operating frequency band/2.4GHz-2.48GHz operating frequency band
  • the doctor's program-controlled equipment can directly conduct data with the stimulator through the 401MHz-406MHz operating frequency band/2.4GHz-2.48GHz operating frequency band. Interaction.
  • this application can also be applied to other technical fields of medical devices and even non-medical devices.
  • This application does not set a limit to this and can be applied to any situation involving real-time collection and storage of data.
  • the clinical trials in this application can be the above-mentioned clinical trials involving implantable devices, or other clinical trials.
  • Figure 1 shows a structural block diagram of a data collection system provided by this application.
  • This application provides a data collection system, which includes:
  • Sensing device 20 the sensing device is used for sensing bioelectrical signals of the patient.
  • the data collection system i.e. clinical trial electronic data collection system
  • the data collection system is a system provided to clinicians. It can flexibly customize data collection forms according to different trial research topics. It is a multi-clinical and multi-center electronic data collection system. By creating different users (i.e., clinical trial teams, which can include one or more doctors), multiple clinical research trials can be established, and the same clinical trial can have multiple different clinical trial centers.
  • the data collection system can provide highly flexible data collection forms (or data collection questionnaires, clinical trial questionnaires) that allow users to customize them according to different clinical trials, such as depression trials, obsessive-compulsive disorder trials, adult For addiction disease trials, etc., you can customize the form title, enter the title description, select the title type, and customize the form according to the doctor's needs.
  • the data collection system can provide a variety of question types, such as text boxes, text fields, radio choices, multiple choices, drop-down boxes, attachment uploads, etc. It basically covers all question types commonly used in forms. Preset formats can be generated immediately after confirmation.
  • the form page is convenient, fast and easy to operate.
  • Doctors can read the corresponding form questions through different tags in the management background of the data collection system for modular management. Clinicians can conduct multi-clinical and multi-clinical testing for multiple different clinical trials or multiple different centers of the same clinical trial. If the center's data collection operations find areas that do not comply with process specifications during clinical trials, the preset forms can also be adjusted to achieve the purpose of the clinical trial.
  • sensing device 20 may include, for example, one or more of a stimulator, an in vitro collection device, an electrode cap, a smart bracelet, a smart watch, a smart vest, smart shorts, a smart physical therapy instrument, and a smart massage chair. kind.
  • the above-mentioned products use electrode sheets or electrode contacts to sense bioelectrical signals inside or outside the human body in real time. That is to say, the bioelectrical signals of the human body can be sensed in real time through the sensing device 20 and stored, so as to facilitate the user based on their own Select one or more suitable sensing devices 20 based on performance requirements and cost requirements to complete the collection of bioelectric signals.
  • the sensing device is a stimulator implanted in the human body.
  • the data collection device 10 can be configured to implement the steps of the data collection method.
  • the data collection method will be described below, and then the data collection device 10 will be described.
  • Figure 2 shows a schematic flow chart of a data collection method provided by this application.
  • This application provides a data collection method for data collection during clinical trials.
  • the method includes:
  • Step S101 Determine multiple topics of interest to the user.
  • the multiple topics of interest include multiple sensing topics and multiple non-sensing topics;
  • Step S102 Generate a data collection form corresponding to the user based on the topic information of multiple topics of interest.
  • the data collection form includes a portion to be filled corresponding to each topic of interest.
  • the topic information includes a topic description and a topic type. ;
  • Step S103 Use a sensing device to sense the patient's bioelectrical signals to obtain data to be filled corresponding to multiple sensing questions of the patient;
  • Step S104 Obtain data to be filled corresponding to multiple non-sensing questions of the patient
  • Step S105 Based on the question type of each topic of interest in the data collection form, use the data to be filled corresponding to each topic of interest of the patient to fill in the data corresponding to each topic of interest in the data collection form. Part to be filled.
  • the required data collection forms are customized according to different clinical trial orientations, and the collected electronic data is filled into the data collection forms. It is highly flexible and solves the problem of easy data loss, inconvenient storage, and problems caused by multiple forms and multiple systems. It solves the problem of inconvenient data processing and greatly reduces the cost of storing clinical data.
  • sensing questions i.e. Questions related to sensed bioelectrical signals
  • non-sensing questions requests unrelated to bioelectrical signals
  • the generated data collection form includes the parts to be filled corresponding to each topic of interest; during the clinical trial process, the sensing device is used to sense the patient's bioelectrical signal to obtain the patient's multiple data.
  • Different clinical trials correspond to different users.
  • the user here is, for example, a doctor corresponding to the clinical trial or a user composed of multiple doctors.
  • a general form cannot cover the clinical trial needs of all users (the data that need to be collected for depression and Parkinson's disease are obviously different). Therefore, for different users, it can be based on different clinical trial research topics and doctors' needs.
  • the same clinical trial can have multiple different clinical trial centers, that is, the same clinical trial can correspond to multiple users, thus corresponding to multiple sets of questions of interest, that is, Corresponds to multiple data collection forms.
  • Set a section to be filled in each topic of interest, and fill the data to be filled in for sensing and non-sensing questions into the data collection form, realizing the function of data collection during clinical trials.
  • Multiple in this application refers to more than 1, including 2 and more than 2.
  • This application does not limit the number of interesting topics, which may be, for example, 2, 3, 5, 8, 10, 15, 20, 30, 50, 100, 150, 200 , 1000 etc.
  • This application does not limit the number of sensing questions and non-sensing questions, and the sum of the two is equal to the number of interesting questions.
  • the sensing topics in this application refer to topics related to the sensed physiological electrical signals, such as the voltage amplitude, pulse width, frequency, type, corresponding physiological state, corresponding pain score, and corresponding physiological electrical signals. Disease status, etc.
  • the voltage amplitude of the physiological electrical signal is, for example, 30 ⁇ V, 60 ⁇ V, 80 ⁇ V, etc. on the order of microvolts
  • the pulse width may be, for example, 50 ⁇ s, 60 ⁇ s, 70 ⁇ s, etc.
  • the frequency may be, for example, 100 Hz, 130 Hz, 150 Hz, etc.
  • the types of physiological electrical signals may be, for example, brain electrical signals, electrocardiographic signals, myoelectric signals, electrooculogram signals, etc.
  • the physiological state corresponding to the physiological electrical signal may be, for example, onset, normal, after meals, during exercise, sleep, etc.
  • the pain score corresponding to the physiological electrical signal can be, for example, on a percentage scale, which can be, for example, 78, 85, 99, etc. The larger the value, the stronger the pain the patient feels.
  • the disease state corresponding to the physiological electrical signal may be, for example, onset or non-onset, or may be classified into mild, moderate, severe, etc.
  • non-sensing questions refer to questions that have nothing to do with physiological electrical signals (or have no direct relationship), such as the patient's name, ID number, age, gender, ethnicity, address, blood type, chief complaint, symptoms, and medical history information. , rating scales, follow-up records, family genetic disease information, mood, comfort level, diet records, medication records, follow-up records, opinions and suggestions to doctors, etc.
  • the rating scale may be, for example, the Unified Parkinson's Disease Rating Scale or the UPD Rating Scale.
  • Unified Parkinson's disease rating scale The full text is called The unified Parkinson's disease rating scale, also known as UPDRS rating scale or UPD rating scale), which is an assessment scale used to longitudinally measure the development of Parkinson's disease.
  • UPD rating scale (English: rating scale) is the most commonly used rating scale in clinical research on Parkinson's disease.
  • rating scales can also be set for other disease types or other application scenarios.
  • the Rapid Self-Rating Depression Symptoms Scale for depression the Insomnia Severity Index (ISI) for insomnia, the Childhood Autism Rating Scale (CARS) for autism, and the Hamilton Anxiety Scale for anxiety disorders.
  • Table (HAMA) Simple Prediabetes Screening Scale for Adults (PRISQ Score) for Diabetes, Obstructive Sleep Apnea Screening Scale for Sleep Apnea (NoSAS Score), Patient Self-Care Ability Assessment Scale for Self-Care Ability wait.
  • step S104 may include: using an interactive device to receive an input operation, and in response to the input operation, obtaining data to be filled corresponding to multiple non-sensing questions of the patient; or,
  • an interactive device to receive an import operation, and in response to the import operation, import data to be filled corresponding to multiple non-sensing questions of the patient from local, cloud or external storage devices; or,
  • patient data may include, for example, all data generated by the same patient that can be queried in the networked system, including text data, medical image data, image data collected by cameras, program-controlled records, data collection records, etc.
  • step S105 may include: based on the question type of each sensing question in the data collection form, filling each item in the data collection form with the data to be filled corresponding to each sensing question of the patient. The portion to be filled corresponding to each sensing question;
  • Figure 3 shows a schematic flow chart of determining multiple topics of interest to a user provided by this application.
  • step S101 may include:
  • Step S201 Obtain topics of interest to each doctor among the users to obtain topics of interest to all doctors among the users;
  • Step S202 Eliminate duplicate topics of interest to all doctors among the users to obtain multiple topics of interest to the user.
  • FIG. 4 shows another schematic flowchart of determining multiple topics of interest for a user provided by this application.
  • step S101 may include:
  • Step S301 Obtain one or more tags of the user
  • Step S302 Based on the label of each topic in the topic database and the label of the user, obtain the label similarity between each topic in the topic database and the user.
  • Each topic in the topic database Corresponds to one or more tags;
  • Step S303 Select multiple topics with the highest tag similarity from the topic database as multiple topics of interest to the user.
  • a label is set for the user, and a label is set for each question in the question bank.
  • the label similarity between each question and the user is evaluated using label matching, and then the label similarity is selected from the question bank.
  • the top topics are multiple topics of interest to users, with a high degree of matching and low maintenance difficulty. Questions in the question bank can be reused without requiring each user to re-edit and generate question information each time, and data collection forms can be quickly generated.
  • the user's label can be manually set, for example, “mental illness”, “drug detoxification”, “obsessive-compulsive disorder”, “depression”, “psychiatry”, “gastroenterology”, “general surgery” “, “Stomatology”, “Rehabilitation Medicine”, “Hospital A”, “Hospital B”, “Hospital C”, “Hospital D”, etc.
  • the user's label can also be intelligently set based on each doctor's label or doctor information. For example, when the user is a team of doctors and the doctors in the team are all psychiatrists, "psychiatry" can be used as the user. Tag of.
  • the labels of the questions can be intelligently matched or manually set, such as "patient basic information” or “depression”.
  • the label "Basic patient information" can correspond to multiple topics, such as filling in the patient's name, ID number, contact address, contact number, email, age, gender, ethnicity, political affiliation, workplace, and medical insurance type non-sensing questions.
  • the user's tag includes the tag "Basic Patient Information”
  • the above non-sensing questions corresponding to the tag can be automatically included in the data collection form.
  • the label “DBS” can correspond to the obsessive-compulsive disorder clinical trial team, depression clinical trial team, addictive disease clinical trial team, etc.
  • the label “DBS” can also correspond to multiple sensing questions, such as the number of electrode leads used to fill the patient (for example, 1 or 2), the implantation location (left brain and/or right brain) , target (such as the nucleus accumbens and/or the forelimb of the internal capsule), data collection time, data collection duration, EEG signal voltage amplitude, EEG signal pulse width, and EEG signal frequency.
  • the tag similarity can be a numerical value represented by a percentage such as 50%, 88%, 95%, etc.
  • the label similarity may be, for example, 100%.
  • the user detoxification team and the label of question A01 are both "detoxification”.
  • step S302 may include:
  • the training process of the label similarity model includes:
  • the training set includes a plurality of training data, each of the training data includes a label of a first sample object, a label of a second sample object, and the first sample object and the second sample object.
  • the label similarity model can be trained by a large amount of training data, and can predict the corresponding output data (ie, the label similarity of two objects) for different input data (ie, the labels of two objects), and has a wide range of applications. , high level of intelligence.
  • design establish an appropriate number of neuron computing nodes and multi-layer computing hierarchies, select appropriate input layers and output layers, and then you can obtain a preset deep learning model.
  • preset deep learning model Through the learning and tuning of the preset deep learning model, Establish a functional relationship from input to output. Although the functional relationship between input and output cannot be found 100%, it can approximate the realistic relationship as much as possible.
  • the label similarity model trained thus can be based on each topic and use The user's label is used to obtain the similarity of each topic and the user's label respectively, and the calculation results are highly accurate and reliable.
  • this application can use the above training process to train a label similarity model. In other optional implementations, this application can use a pre-trained label similarity model.
  • historical data may be data mined to obtain training data.
  • the labels of the first sample object and the second sample object can also be automatically generated using the generation network of the GAN model.
  • the GAN model is a Generative Adversarial Network, which consists of a generative network and a discriminative network.
  • the generative network randomly samples from the latent space as input, and its output results need to imitate the real samples in the training set as much as possible.
  • the input of the discriminant network is a real sample or the output of the generative network, and its purpose is to distinguish the output of the generative network from the real sample as much as possible.
  • the generative network must deceive the discriminant network as much as possible.
  • the two networks compete with each other and constantly adjust parameters. The ultimate goal is to make the discriminant network unable to judge whether the output results of the generating network are true.
  • the GAN model can be used to generate classification information of multiple sample organisms, which can be used in the training process of the label similarity model. It can effectively reduce the amount of original data collected and greatly reduce the number of data collected. The cost of data collection and annotation.
  • This application does not limit the method of obtaining the annotated data.
  • manual annotation, automatic annotation, or semi-automatic annotation may be used.
  • This application does not limit the training process of the label similarity model.
  • the training method of the above-mentioned supervised learning can be used, or the training method of semi-supervised learning can be used, or the training method of unsupervised learning can be used.
  • This application does not limit the preset training end condition. For example, it can be that the number of training times reaches the preset number of times (the preset number of times is, for example, 1 time, 3 times, 10 times, 100 times, 1000 times, 10000 times, etc.), or it can The training data in the training set have completed one or more trainings, or the total loss value obtained in this training is not greater than the preset loss value.
  • step S303 may include:
  • N is an integer greater than 1;
  • the number of questions N can be set manually, and the user can set the number of questions through the interactive device to determine the number of questions of interest. That is to say, after using the intelligent method of label matching to obtain the similarity between each question in the question bank and the user's label, and then combining the manually set number of questions to determine multiple interesting questions, this intelligence and artificial intelligence
  • the combined method can have the advantages of high processing efficiency and closeness to actual needs.
  • a simplified version of the data collection form and a complete version of the data collection form can be generated respectively to meet the needs of practical applications. diverse needs.
  • the number of questions N may be, for example, 2, 3, 5, 8, 10, 15, 20, 30, 50, 100, 150, 200, 1000, etc.
  • This application does not limit the interactive device, which may be, for example, a mobile phone, a tablet, a laptop, a desktop computer, a smart wearable device, or other intelligent terminal device, or the interactive device may be a workstation or a console.
  • This application does not limit the manner in which interactive devices are used to receive various (manual) operations.
  • Operations are divided according to input methods, which may include, for example, text input operations, audio input operations, video input operations, key operations, mouse operations, keyboard operations, smart stylus pen operations, etc.
  • step S303 may include:
  • the preset quantity is a preset quantity, for example, it can be 2, 3, 5, 8, 10, 15, 20, 30, 50, 100, 150, 200 , 1000 etc.
  • the types of questions are different, the filling methods of the data to be filled corresponding to the topics of interest are different, and the corresponding forms of the parts to be filled are different.
  • the question type of each question of interest can be a text box, text field, radio choice, multiple choice, drop-down box or attachment upload;
  • the question type of the question of interest is a text box
  • the part to be filled in the question of interest adopts a text box
  • the question type of the question of interest is a text field
  • the part to be filled in the question of interest adopts a text field
  • the question type of the question of interest is a radio button
  • the part to be filled in the question of interest uses a radio button box
  • the part to be filled in the question of interest uses a check box
  • the part to be filled in the question of interest uses a drop-down box
  • the part to be filled in the question of interest uses an attachment upload control.
  • the method of filling the data to be filled into the part to be filled can be automatic filling or manual filling.
  • the question type of the sensing question is a text box or text field
  • the question description is, for example:
  • the topic of interest is a non-sensing topic
  • the question type of the sensing question is a text box or text field
  • the question description is, for example:
  • the average pulse width of the collected physiological electrical signals is:
  • the topic of interest is a sensing topic
  • the question type of the sensing question is single choice, and the question description is, for example:
  • the collected physiological electrical signals are:
  • the topic of interest is a sensing topic
  • the question type of the sensing question is check (one or more options can be selected), and the question description is, for example:
  • the patient's illnesses include:
  • the topic of interest is a non-sensing topic
  • the question type of the sensing question is a drop-down box
  • the question description is, for example:
  • Drop-down box options Male; Female.
  • the topic of interest is a non-sensing topic
  • the question type of the sensing question is attachment upload
  • the question description is, for example:
  • the topic of interest is a sensing topic
  • obtaining data to be filled corresponding to multiple non-sensing questions of the patient includes:
  • Keyword extraction is performed on the patient's disease information to obtain data to be filled corresponding to multiple non-sensing questions of the patient.
  • the patient's disease information is used to extract keywords to obtain the data to be filled corresponding to the patient's non-sensing questions.
  • these data can be obtained through automatic extraction without manual filling, which further improves the It improves the speed of electronic data collection for clinical trials, has a high degree of intelligence and provides a good user experience.
  • disease information which may include, for example, one or more of the patient's basic information, medical history information, medical imaging information, pre-recorded video information, real-time video information, program-controlled records, and audio and video records.
  • the medical imaging information in this application may include, for example, CT data, MR data, PET data, X-ray data, PET-CT data, PET-MR data, etc.
  • the medical scanning equipment used may be, for example, CT equipment, MR equipment, PET equipment, X-ray equipment, PET-CT equipment, PET-MR equipment, etc.
  • CT Computed Tomography
  • MR Magnetic Resonance
  • PET Positron Emission Tomography
  • This application also provides a data collection device, the specific implementation of which is consistent with the implementation and technical effects achieved described in the implementation of the above method, and part of the content will not be described again.
  • This application also provides a data collection device for data collection during clinical trials.
  • the device includes a processor, and the processor is configured to:
  • the multiple topics of interest include multiple sensing topics and multiple non-sensing topics;
  • the data collection form includes a portion to be filled corresponding to each topic of interest, and the topic information includes a topic description and a topic type;
  • a sensing device to sense the patient's bioelectrical signals to obtain data to be filled corresponding to multiple sensing questions of the patient
  • the data to be filled corresponding to each topic of interest of the patient is used to fill the portion to be filled corresponding to each topic of interest in the data collection form.
  • the processor is further configured to determine multiple topics of interest to the user in the following manner:
  • the topics of interest to all doctors among the users are removed to obtain multiple topics of interest to the users.
  • the processor is further configured to determine multiple topics of interest to the user in the following manner:
  • Each topic in the topic database corresponds to one or multiple tags
  • the processor is further configured to obtain the tag similarity between each question in the question library and the user in the following manner:
  • the training process of the label similarity model includes:
  • the training set includes a plurality of training data, each of the training data includes a label of a first sample object, a label of a second sample object, and the first sample object and the second sample object.
  • the processor is further configured to obtain multiple topics of interest to the user in the following manner:
  • N is an integer greater than 1;
  • the question type of each question of interest is text box, text field, radio choice, multiple choice, drop-down box or attachment upload;
  • the question type of the question of interest is a text box
  • the part to be filled in the question of interest adopts a text box
  • the question type of the question of interest is a text field
  • the part to be filled in the question of interest adopts a text field
  • the question type of the question of interest is a radio button
  • the part to be filled in the question of interest uses a radio button box
  • the part to be filled in the question of interest uses a check box
  • the part to be filled in the question of interest uses a drop-down box
  • the part to be filled in the question of interest uses an attachment upload control.
  • the processor is further configured to obtain data to be filled corresponding to multiple non-sensing questions of the patient in the following manner:
  • Keyword extraction is performed on the patient's disease information to obtain data to be filled corresponding to multiple non-sensing questions of the patient.
  • Figure 5 shows a structural block diagram of a data collection device 200 provided by this application.
  • the data acquisition device 200 may include, for example, at least one memory 210, at least one processor 220, and a bus 230 connecting different platform systems.
  • Memory 210 may include readable media in the form of volatile memory, such as random access memory (RAM) 211 and/or cache memory 212, and may further include read only memory (ROM) 213.
  • RAM random access memory
  • ROM read only memory
  • the memory 210 also stores a computer program, and the computer program can be executed by the processor 220, so that the processor 220 realizes the function of any of the above data collection methods.
  • the specific implementation method is the same as the implementation method described in the above method implementation. The technical effects achieved are the same, and some contents will not be repeated again.
  • Memory 210 may also include a utility 214 having at least one program module 215, such program modules 215 including, but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some of these examples. This combination may include the implementation of a network environment.
  • the processor 220 can execute the above-mentioned computer program, and can execute the utility tool 214.
  • the processor 220 may adopt one or more Application Specific Integrated Circuits (ASICs), DSPs, Programmable Logic Devices (PLDs), Complex Programmable Logic Devices (CPLDs), Field-Programmable Gate Array (FPGA, Field-Programmable Gate Array) or other electronic components.
  • ASICs Application Specific Integrated Circuits
  • DSPs Digital Signal processors
  • PLDs Programmable Logic Devices
  • CPLDs Complex Programmable Logic Devices
  • FPGA Field-Programmable Gate Array
  • FPGA Field-Programmable Gate Array
  • Bus 230 may be a local bus representing one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or any bus structure using a variety of bus structures.
  • the data collection device 200 can also communicate with one or more external devices 240 such as keyboards, pointing devices, Bluetooth devices, etc., and can also communicate with one or more devices capable of interacting with the data collection device 200, and/or with devices that enable the data collection device 200 to communicate with other devices.
  • Data collection device 200 can communicate with any device (eg, router, modem, etc.) that communicates with one or more other computing devices. This communication may occur through the input/output interface 250.
  • the data collection device 200 can also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN) and/or a public network, such as the Internet) through the network adapter 260.
  • Network adapter 260 can communicate with other modules of data collection device 200 through bus 230.
  • data acquisition device 200 may be used in conjunction with the data acquisition device 200, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID systems, tapes Drives and data backup storage platforms, etc.
  • This application also provides a computer-readable storage medium, which stores a computer program.
  • the computer program When the computer program is executed by a processor, the function of any one of the above devices or the method of realizing any one of the above methods is realized.
  • the specific implementation methods are consistent with the implementation methods and technical effects achieved described in the implementation methods of the above methods, and some of the contents will not be repeated.
  • Figure 6 shows a schematic structural diagram of a program product provided by this application.
  • the program product may take the form of a portable compact disk read-only memory (CD-ROM) and include program code, and may be run on a terminal device, such as a personal computer.
  • the program product of the present invention is not limited thereto.
  • the readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, apparatus or device.
  • the Program Product may take the form of one or more readable media in any combination.
  • the readable medium may be a readable signal medium or a readable storage medium.
  • the readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof.
  • readable storage media include: electrical connection with one or more conductors, portable disk, hard disk, random access memory (RAM), read only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • RAM random access memory
  • ROM read only memory
  • EPROM or flash memory erasable programmable read-only memory
  • CD-ROM compact disk read-only memory
  • magnetic storage device or any suitable combination of the above.
  • a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave carrying the readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a readable storage medium may also be any readable medium that can transmit, propagate, or transport the program for use by or in connection with an instruction execution system, apparatus, or device.
  • Program code contained on a readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.
  • Program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented Programming languages such as Java, C++, etc.
  • the program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server execute on.
  • the remote computing device may be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device, such as provided by an Internet service. (business comes via Internet connection).
  • LAN local area network
  • WAN wide area network

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Computational Linguistics (AREA)
  • Biomedical Technology (AREA)
  • Mathematical Physics (AREA)
  • Software Systems (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Databases & Information Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Epidemiology (AREA)
  • Medical Informatics (AREA)
  • Library & Information Science (AREA)
  • Primary Health Care (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Public Health (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Medical Treatment And Welfare Office Work (AREA)

Abstract

本申请提供了数据采集方法、装置、系统及计算机可读存储介质,用于在临床试验过程中进行数据采集,所述方法包括:确定使用者的多个感兴趣题目;基于多个感兴趣题目的题目信息生成所述使用者对应的数据采集表单;利用感测设备感测患者的生物电信号,以获取所述患者的多个感测题目对应的待填充数据;获取所述患者的多个非感测题目对应的待填充数据;基于所述数据采集表单中的每个感兴趣题目的题目类型,利用所述患者的每个感兴趣题目对应的待填充数据填充所述数据采集表单中的每个感兴趣题目对应的待填充部分。根据不同的临床试验定向定制所需要的数据采集表单,解决数据易丢失、不方便保存以及多表格多系统带来的数据处理不方便的问题。

Description

数据采集方法、装置、系统及计算机可读存储介质
本申请要求于2022年6月30日提交的申请号为202210762218.5的中国专利的优先权,上述中国专利通过全文引用的形式并入。
技术领域
本申请涉及自动生成表单和数据采集的技术领域,例如涉及数据采集方法、装置、系统及计算机可读存储介质。
背景技术
临床试验(Clinical Trial),指任何在人体(病人或健康志愿者)进行药物的系统性研究,以证实或揭示试验药物的作用、不良反应及/或试验药物的吸收、分布、代谢和排泄,目的是确定试验药物的疗效与安全性。相关的临床试验数据采集记录方式主要还是依靠纸质表格收集,或者,不同的临床试验通过不同的系统采集数据,这样会造成数据易丢失、不方便保存以及多表格多系统带来的数据处理不方便的问题。
专利CN113918699A公开了一种调查问卷的生成方法,包括:接收用户触发的携带有用户信息的调查问卷生成请求,并根据所述用户信息对所述用户进行身份验证;若身份验证通过,基于所述用户信息对所述用户进行权限验证;若权限验证通过,展示预设的调查问卷配置界面;其中,所述调查问卷配置界面包括调查题目菜单,所述调查题目菜单包括多种调查题目类型;接收所述用户触发的对于所述调查问卷配置界面中所述调查题目菜单的选择操作,得到对应的目标调查题目类型;在所述调查问卷配置界面中展示与所述目标调查题目类型对应的题目编辑区域;其中,所述题目编辑区域包括题目标题编辑区块与题目内容编辑区块;基于所述用户在所述题目编辑区域输入的编辑操作,得到与所述目标调查题目类型对应的目标调查题目;基于所述目标调查题目与预设的调查问卷模板,生成对应的目标调查问卷。上述方法能提高调查问卷生成的智能性与灵活性,但是每次生成新问卷的过程都需要重新编辑题目信息,使用起来较为不便。
基于此,本申请提供了数据采集方法、装置、系统及计算机可读存储介质,以解决上述相关技术中存在的问题。
发明内容
本申请的目的在于提供数据采集方法、装置、系统及计算机可读存储介质,根据不同的临床试验定向定制所需要的数据采集表单,解决数据易丢失、不方便保存以及多表格多系统带来的数据处理不方便的问题。
本申请的目的采用以下技术方案实现:
第一方面,本申请提供了一种数据采集方法,用于在临床试验过程中进行数据采集,所述方法包 括:
确定使用者的多个感兴趣题目,多个感兴趣题目包括多个感测题目和多个非感测题目;
基于多个感兴趣题目的题目信息生成所述使用者对应的数据采集表单,所述数据采集表单包括每个感兴趣题目对应的待填充部分,所述题目信息包括题目描述和题目类型;
利用感测设备感测患者的生物电信号,以获取所述患者的多个感测题目对应的待填充数据;
获取所述患者的多个非感测题目对应的待填充数据;
基于所述数据采集表单中的每个感兴趣题目的题目类型,利用所述患者的每个感兴趣题目对应的待填充数据填充所述数据采集表单中的每个感兴趣题目对应的待填充部分。
在一些可能的实现方式中,所述确定使用者的多个感兴趣题目,包括:
获取所述使用者中的每个医生的感兴趣题目,以获取所述使用者中的所有医生的感兴趣题目;
对所述使用者中的所有医生的感兴趣题目进行去重,以获取所述使用者的多个感兴趣题目。
在一些可能的实现方式中,所述确定使用者的多个感兴趣题目,包括:
获取所述使用者的一个或多个标签;
基于题目库中的每个题目的标签与所述使用者的标签,获取所述题目库中的每个题目与所述使用者的标签相似度,所述题目库中的每个题目对应一个或多个标签;
从所述题目库中选择标签相似度最高的多个题目作为所述使用者的多个感兴趣题目。
在一些可能的实现方式中,所述基于题目库中的每个题目的标签与所述使用者的标签,获取所述题目库中的每个题目与所述使用者的标签相似度,包括:
针对所述题目库中的每个题目,执行以下处理:
将所述题目的标签与所述使用者的标签输入标签相似度模型,以得到所述题目与所述使用者的标签相似度;
其中,所述标签相似度模型的训练过程包括:
获取训练集,所述训练集包括多个训练数据,每个所述训练数据包括第一样本对象的标签、第二样本对象的标签以及所述第一样本对象和所述第二样本对象的标签相似度的标注数据;
针对所述训练集中的每个训练数据,执行以下处理:
将所述训练数据中的第一样本对象的标签和第二样本对象的标签输入预设的深度学习模型,以得到所述第一样本对象和所述第二样本对象的标签相似度的预测数据;
基于所述第一样本对象和所述第二样本对象的标签相似度的预测数据和标注数据,对所述深度学习模型的模型参数进行更新;
检测是否满足预设的训练结束条件;若是,则将训练出的深度学习模型作为所述标签相似度模型;若否,则利用下一个所述训练数据继续训练所述深度学习模型。
在一些可能的实现方式中,所述从所述题目库中选择标签相似度最高的多个题目作为所述使用者 的多个感兴趣题目,包括:
利用交互设备获取所述使用者对应的题目数量N,N是大于1的整数;
从所述题目库中选择标签相似度最高的N个题目作为所述使用者的多个感兴趣题目。
在一些可能的实现方式中,每个感兴趣题目的题目类型是文本框、文本域、单选、多选、下拉框或者附件上传;
当所述感兴趣题目的题目类型是文本框时,所述感兴趣题目的待填充部分采用文本框;
当所述感兴趣题目的题目类型是文本域时,所述感兴趣题目的待填充部分采用文本域;
当所述感兴趣题目的题目类型是单选时,所述感兴趣题目的待填充部分采用单选框;
当所述感兴趣题目的题目类型是多选时,所述感兴趣题目的待填充部分采用复选框;
当所述感兴趣题目的题目类型是下拉框时,所述感兴趣题目的待填充部分采用下拉框;
当所述感兴趣题目的题目类型是附件上传时,所述感兴趣题目的待填充部分采用附件上传控件。
在一些可能的实现方式中,所述获取所述患者的多个非感测题目对应的待填充数据,包括:
获取所述患者的疾病信息;
对所述患者的疾病信息进行关键词提取,以获取所述患者的多个非感测题目对应的待填充数据。
第二方面,本申请提供了一种数据采集装置,用于在临床试验过程中进行数据采集,所述装置包括处理器,所述处理器被配置成:
确定使用者的多个感兴趣题目,多个感兴趣题目包括多个感测题目和多个非感测题目;
基于多个感兴趣题目的题目信息生成所述使用者对应的数据采集表单,所述数据采集表单包括每个感兴趣题目对应的待填充部分,所述题目信息包括题目描述和题目类型;
利用感测设备感测患者的生物电信号,以获取所述患者的多个感测题目对应的待填充数据;
获取所述患者的多个非感测题目对应的待填充数据;
基于所述数据采集表单中的每个感兴趣题目的题目类型,利用所述患者的每个感兴趣题目对应的待填充数据填充所述数据采集表单中的每个感兴趣题目对应的待填充部分。
在一些可能的实现方式中,所述处理器被进一步配置成采用以下方式确定使用者的多个感兴趣题目:
获取所述使用者中的每个医生的感兴趣题目,以获取所述使用者中的所有医生的感兴趣题目;
对所述使用者中的所有医生的感兴趣题目进行去重,以获取所述使用者的多个感兴趣题目。
在一些可能的实现方式中,所述处理器被进一步配置成采用以下方式确定使用者的多个感兴趣题目:
获取所述使用者的一个或多个标签;
基于题目库中的每个题目的标签与所述使用者的标签,获取所述题目库中的每个题目与所述使用者的标签相似度,所述题目库中的每个题目对应一个或多个标签;
从所述题目库中选择标签相似度最高的多个题目作为所述使用者的多个感兴趣题目。
在一些可能的实现方式中,所述处理器被进一步配置成采用以下方式获取所述题目库中的每个题目与所述使用者的标签相似度:
针对所述题目库中的每个题目,执行以下处理:
将所述题目的标签与所述使用者的标签输入标签相似度模型,以得到所述题目与所述使用者的标签相似度;
其中,所述标签相似度模型的训练过程包括:
获取训练集,所述训练集包括多个训练数据,每个所述训练数据包括第一样本对象的标签、第二样本对象的标签以及所述第一样本对象和所述第二样本对象的标签相似度的标注数据;
针对所述训练集中的每个训练数据,执行以下处理:
将所述训练数据中的第一样本对象的标签和第二样本对象的标签输入预设的深度学习模型,以得到所述第一样本对象和所述第二样本对象的标签相似度的预测数据;
基于所述第一样本对象和所述第二样本对象的标签相似度的预测数据和标注数据,对所述深度学习模型的模型参数进行更新;
检测是否满足预设的训练结束条件;若是,则将训练出的深度学习模型作为所述标签相似度模型;若否,则利用下一个所述训练数据继续训练所述深度学习模型。
在一些可能的实现方式中,所述处理器被进一步配置成采用以下方式获取所述使用者的多个感兴趣题目:
利用交互设备获取所述使用者对应的题目数量N,N是大于1的整数;
从所述题目库中选择标签相似度最高的N个题目作为所述使用者的多个感兴趣题目。
在一些可能的实现方式中,每个感兴趣题目的题目类型是文本框、文本域、单选、多选、下拉框或者附件上传;
当所述感兴趣题目的题目类型是文本框时,所述感兴趣题目的待填充部分采用文本框;
当所述感兴趣题目的题目类型是文本域时,所述感兴趣题目的待填充部分采用文本域;
当所述感兴趣题目的题目类型是单选时,所述感兴趣题目的待填充部分采用单选框;
当所述感兴趣题目的题目类型是多选时,所述感兴趣题目的待填充部分采用复选框;
当所述感兴趣题目的题目类型是下拉框时,所述感兴趣题目的待填充部分采用下拉框;
当所述感兴趣题目的题目类型是附件上传时,所述感兴趣题目的待填充部分采用附件上传控件。
在一些可能的实现方式中,所述处理器被进一步配置成采用以下方式获取所述患者的多个非感测题目对应的待填充数据:
获取所述患者的疾病信息;
对所述患者的疾病信息进行关键词提取,以获取所述患者的多个非感测题目对应的待填充数据。
第三方面,本申请提供了一种数据采集系统,所述数据采集系统包括:
上述任一项数据采集装置;
感测设备,所述感测设备用于感测患者的生物电信号。
第四方面,本申请提供了一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时实现上述任一项方法的步骤或者实现上述任一项装置的功能。
采用本申请提供的数据采集方法、装置、系统及计算机可读存储介质,至少具有以下优点:
根据不同的临床试验定向定制所需要的数据采集表单,并将采集得到的电子数据填充至数据采集表单中,灵活性高,解决数据易丢失、不方便保存以及多表格多系统带来的数据处理不方便的问题,大大减少了临床数据的保存成本。
首先,以临床试验对应的医生个人或者医生团队作为使用者,确定使用者的多个感兴趣题目(如果感兴趣题目只有1个则自动生成表单带来的效率提升有限),这些感兴趣题目中部分是感测题目(即与感测到的生物电信号相关的题目),部分是非感测题目(与生物电信号无关的题目);基于上述感兴趣题目的题目信息(包括题目描述和题目类型)自动生成使用者对应的(临床试验)数据采集表单,所生成的数据采集表单包括每个感兴趣题目对应的待填充部分;在临床试验过程中,利用感测设备感测患者的生物电信号,从而获取该患者的多个感测题目对应的待填充数据;再获取该患者的非感测题目对应的待填充数据;在得到所有感兴趣题目对应的待填充数据后,填充数据采集表单中的每个感兴趣题目对应的待填充部分。
不同的临床试验所对应的使用者不同,此处使用者例如是该临床试验对应的一个医生或者多个医生组成的使用者。通用表单无法覆盖所有使用者的临床试验需求(针对抑郁症和帕金森病所需要采集的数据显然是不同的),因此,针对不同的使用者,可根据临床试验研究课题的不同,根据医生需求灵活性地自动生成定制化的数据采集表单(或者说问卷),适用于多中心临床试验(Multi-regional clinical trial),方便快捷,智能化程度高,定制化服务满足多样性需求。通过创建不同的使用者(对应不同的使用者),同一个临床试验可以有多个不同的临床试验中心,即同一个临床试验可以对应多个使用者,从而对应多套感兴趣题目,也即对应多个数据采集表单。在每个感兴趣题目设置待填充部分,将感测题目和非感测题目的待填充数据填充至数据采集表单,实现了在临床试验过程中进行数据采集的功能。
附图说明
下面结合附图和实施方式对本申请进一步说明。
图1示出了本申请提供的一种数据采集系统的结构框图。
图2示出了本申请提供的一种数据采集方法的流程示意图。
图3示出了本申请提供的一种确定使用者的多个感兴趣题目的流程示意图。
图4示出了本申请提供的另一种确定使用者的多个感兴趣题目的流程示意图。
图5示出了本申请提供的一种数据采集装置的结构框图。
图6示出了本申请提供的一种程序产品的结构示意图。
具体实施方式
下面将结合本申请的说明书附图以及具体实施方式,对本申请中的技术方案进行描述,需要说明的是,在不相冲突的前提下,以下描述的各实施方式之间或各技术特征之间可以任意组合形成新的实施方式。
在本申请中,“至少一个”是指一个或者多个,“多个”是指两个或两个以上。“和/或”,描述关联对象的关联关系,表示可以存在三种关系,例如,A和/或B,可以表示:单独存在A,同时存在A和B,单独存在B的情况,其中A,B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。“以下至少一项(个)”或其类似表达,是指的这些项中的任意组合,包括单项(个)或复数项(个)的任意组合。例如,a,b或c中的至少一项(个),可以表示:a,b,c,a和b,a和c,b和c,a和b和c,其中a、b和c可以是单个,也可以是多个。值得注意的是,“至少一项(个)”还可以解释成“一项(个)或多项(个)”。
还需说明的是,本申请中,“示例性的”或者“例如”等词用于表示作例子、例证或说明。本申请中被描述为“示例性的”或者“例如”的任何实施方式或设计方案不应被解释为比其他实施方式或设计方案更优选或更具优势。确切而言,使用“示例性的”或者“例如”等词旨在以具体方式呈现相关概念。
下面,首先对本申请的其中一个应用领域(即植入式器械)进行简单说明。
植入式医疗系统包括植入式神经电刺激系统、植入式心脏电刺激系统(又称心脏起搏器)、植入式药物输注系统(Implantable Drug Delivery System,简称I DDS)和导线转接系统等。植入式神经电刺激系统例如是脑深部电刺激系统(Deep Brain Stimulation,简称DBS)、植入式脑皮层电刺激系统(Cortical Nerve Stimulation,简称CNS)、植入式脊髓电刺激系统(Spinal Cord Stimulation,简称SCS)、植入式骶神经电刺激系统(Sacral Nerve Stimulation,简称SNS)、植入式迷走神经电刺激系统(Vagus Nerve Stimulation,简称VNS)等。
植入式神经电刺激系统包括植入患者体内的刺激器(即植入式神经刺激器,一种神经刺激装置)以及设置于患者体外的程控设备。也就是说,刺激器是一种植入物,或者说,植入物包括刺激器。相关的神经调控技术主要是通过立体定向手术在生物体的组织的特定部位(即靶点)植入电极(电极例如是电极导线的形式),经电极向靶点发放电脉冲,调控相应神经结构和网络的电活动及其功能,从 而改善症状、缓解病痛。其中,刺激器可以包括IPG、延伸导线和电极导线,IPG(implantable pulse generator,植入式脉冲发生器)设置于患者体内,响应于程控设备发送的程控指令,依靠密封电池和电路向体内组织提供可控制的电刺激能量。IPG通过延伸导线和电极导线,为体内组织的特定区域递送一路或多路可控制的特定电刺激。延伸导线配合IPG使用,作为电刺激信号的传递媒体,将IPG产生的电刺激信号,传递给电极导线。电极导线通过多个电极触点,向体内组织的特定区域递送电刺激。刺激器设置有单侧或双侧的一路或多路电极导线,电极导线上设置有多个电极触点,电极触点可以均匀排列或者非均匀排列在电极导线的周向上。作为一个示例,电极触点可以以4行3列的阵列(共计12个电极触点)排列在电极导线的周向上。电极触点可以包括刺激电极触点和/或采集电极触点。电极触点例如可以采用片状、环状、点状等形状。如有需要,同一电极触点可以既执行刺激任务,又执行采集任务。
在一些实施例中,受刺激的体内组织可以是患者的脑组织,受刺激的部位可以是脑组织的特定部位。当患者的疾病类型不同时,受刺激的部位一般来说是不同的,所使用的刺激触点(单源或多源)的数量、一路或多路(单通道或多通道)特定电刺激信号的运用以及刺激参数数据也是不同的。本申请实施例对适用的疾病类型不做限定,其可以是脑深部刺激(DBS)、脊髓刺激(SCS)、骨盆刺激、胃刺激、外周神经刺激、功能性电刺激所适用的疾病类型。其中,DBS可以用于治疗或管理的疾病类型包括但不限于:痉挛疾病(例如,癫痫)、疼痛、偏头痛、精神疾病(例如,重度抑郁症(MDD))、躁郁症、焦虑症、创伤后压力心理障碍症、轻郁症、强迫症(OCD)、行为障碍、情绪障碍、记忆障碍、心理状态障碍、移动障碍(例如,特发性震颤或帕金森氏病)、亨廷顿病、阿尔茨海默症、药物成瘾症、孤独症或其他神经学或精神科疾病和损害。
本申请实施例中,程控设备和刺激器建立程控连接时,可以利用程控设备调整刺激器的刺激参数(或者说脉冲发生器的刺激参数,不同的刺激参数所对应的电刺激信号不同),也可以通过刺激器感测患者的电生理活动以采集得到电生理信号,并可以通过所采集到的电生理信号来继续调整刺激器的刺激参数。
刺激参数可以包括以下至少一种:用于递送电刺激的电极触点标识(例如可以是2#电极触点和3#电极触点)、频率(例如是单位时间1s内的电刺激脉冲信号个数,单位为Hz)、脉宽(每个脉冲的持续时间,单位为μs)、幅值(一般用电压表述,即每个脉冲的强度,单位为V)、时序(例如可以是连续或者簇发,簇发是指多个过程组成的不连续的时序行为)、刺激模式(包括电流模式、电压模式、定时刺激模式和循环刺激模式中的一种或多种)、医生控制上限及下限(医生可调节的范围)和患者控制上限及下限(患者可自主调节的范围)
在一个具体应用场景中,可以在电流模式或者电压模式下对刺激器的各刺激参数进行调节。
程控设备可以是医生程控设备(即医生使用的程控设备)或者患者程控设备(即患者使用的程控设备)。医生程控设备例如可以是搭载有程控软件的平板电脑、笔记本电脑、台式计算机、手机等智 能终端设备。患者程控设备例如可以是搭载有程控软件的平板电脑、笔记本电脑、台式计算机、手机等智能终端设备,患者程控设备还可以是其他具有程控功能的电子设备(例如是具有程控功能的充电器、数据采集设备等)。
本申请实施例对医生程控设备和刺激器的数据交互不进行限制,当医生远程程控时,医生程控设备可以通过服务器、患者程控设备与刺激器进行数据交互。当医生线下和患者面对面进行程控时,医生程控设备可以通过患者程控设备与刺激器进行数据交互,医生程控设备还可以直接与刺激器进行数据交互。
在一些实施例中,患者程控设备可以包括(与服务器通信的)主机和(与刺激器通信的)子机,主机和子机可通信地连接。其中,医生程控设备可以通过3G/4G/5G网络与服务器进行数据交互,服务器可以通过3G/4G/5G网络与主机进行数据交互,主机可以通过蓝牙协议/WIFI协议/USB协议与子机进行数据交互,子机可以通过401MHz-406MHz工作频段/2.4GHz-2.48GHz工作频段与刺激器进行数据交互,医生程控设备可以通过401MHz-406MHz工作频段/2.4GHz-2.48GHz工作频段与刺激器直接进行数据交互。
除了上述植入式器械的应用领域,本申请还可以应用于其他医疗器械甚至非医疗器械的技术领域,本申请不对此设限,只要涉及实时采集和存储数据的场合均可应用。也就是说,本申请中的临床试验,可以是上述涉及植入式器械的临床试验,也可以是其他临床试验。
系统实现方式
参见图1,图1示出了本申请提供的一种数据采集系统的结构框图。
本申请提供了一种数据采集系统,所述数据采集系统包括:
数据采集装置10;
感测设备20,所述感测设备用于感测患者的生物电信号。
数据采集系统(即临床试验电子数据采集系统)是一套提供给临床医生使用的系统,可根据试验研究课题的不同,灵活性定制数据采集表单,是一个多临床多中心的电子数据采集系统。通过创建不同的使用者(即临床试验团队,临床试验团队可以包括一个或多个医生),可以建立多临床的研究试验,同一个临床试验可以有多个不同的临床试验中心。
该数据采集系统可以提供具有高度灵活性、允许用户自定义的数据采集表单(或者说数据采集问卷、临床试验问卷),使用者可以根据不同的临床试验,如抑郁症试验、强迫症试验、成瘾性疾病试验等,自定义设置表单题目,输入题目描述,选择题目类型,根据医生需求定制化表单。该数据采集系统能够提供多种题目类型,如文本框、文本域、单选、多选、下拉框、附件上传等,基本涵盖了常用于表单的所有题目类型,确认后可立即生成预设格式的表单页面,方便快捷便于操作。
医生可在该数据采集系统的管理后台通过不同的标签,读取对应的表单题目进行模块化管理,临床医生可以对多个不同临床试验或者同个临床试验的多个不同中心,进行多临床多中心的数据采集操作,如果在临床试验中发现不符合流程规范的地方,也可以对预设表单进行调整,以便达到临床试验的目的。
本申请对感测设备20不作限定,其例如可以包括刺激器、体外采集仪、电极帽、智能手环、智能手表、智能背心、智能短裤、智能理疗仪、智能按摩椅中的一种或多种。
上述产品使用电极片或者电极触点实时感测人体体内或体外的生物电信号,也就是说,可以通过感测设备20实时感测人体的生物电信号,并进行存储,方便用户个人基于自身的性能需求和成本需求选择适合的一种或多种感测设备20,以完成生物电信号的采集。
在一些实施例中,所述感测设备是刺激器,所述刺激器植入于人体体内。
本申请中,所述数据采集装置10可以被配置成实现数据采集方法的步骤,下文将先对数据采集方法进行说明,再对数据采集装置10进行说明。
方法实现方式
参见图2,图2示出了本申请提供的一种数据采集方法的流程示意图。
本申请提供了一种数据采集方法,用于在临床试验过程中进行数据采集,所述方法包括:
步骤S101:确定使用者的多个感兴趣题目,多个感兴趣题目包括多个感测题目和多个非感测题目;
步骤S102:基于多个感兴趣题目的题目信息生成所述使用者对应的数据采集表单,所述数据采集表单包括每个感兴趣题目对应的待填充部分,所述题目信息包括题目描述和题目类型;
步骤S103:利用感测设备感测患者的生物电信号,以获取所述患者的多个感测题目对应的待填充数据;
步骤S104:获取所述患者的多个非感测题目对应的待填充数据;
步骤S105:基于所述数据采集表单中的每个感兴趣题目的题目类型,利用所述患者的每个感兴趣题目对应的待填充数据填充所述数据采集表单中的每个感兴趣题目对应的待填充部分。
由此,根据不同的临床试验定向定制所需要的数据采集表单,并将采集得到的电子数据填充至数据采集表单中,灵活性高,解决数据易丢失、不方便保存以及多表格多系统带来的数据处理不方便的问题,大大减少了临床数据的保存成本。
首先,以临床试验对应的医生个人或者医生团队作为使用者,确定使用者的多个感兴趣题目(如果感兴趣题目只有1个则自动生成表单带来的效率提升有限),这些感兴趣题目中部分是感测题目(即 与感测到的生物电信号相关的题目),部分是非感测题目(与生物电信号无关的题目);基于上述感兴趣题目的题目信息(包括题目描述和题目类型)自动生成使用者对应的(临床试验)数据采集表单,所生成的数据采集表单包括每个感兴趣题目对应的待填充部分;在临床试验过程中,利用感测设备感测患者的生物电信号,从而获取该患者的多个感测题目对应的待填充数据;再获取该患者的非感测题目对应的待填充数据;在得到所有感兴趣题目对应的待填充数据后,填充数据采集表单中的每个感兴趣题目对应的待填充部分。
不同的临床试验所对应的使用者不同,此处使用者例如是该临床试验对应的一个医生或者多个医生组成的使用者。通用表单无法覆盖所有使用者的临床试验需求(针对抑郁症和帕金森病所需要采集的数据显然是不同的),因此,针对不同的使用者,可根据临床试验研究课题的不同,根据医生需求灵活性地自动生成定制化的数据采集表单(或者说问卷),适用于多中心临床试验(Multi-regional clinical trial),方便快捷,智能化程度高,定制化服务满足多样性需求。通过创建不同的使用者(对应不同的使用者),同一个临床试验可以有多个不同的临床试验中心,即同一个临床试验可以对应多个使用者,从而对应多套感兴趣题目,也即对应多个数据采集表单。在每个感兴趣题目设置待填充部分,将感测题目和非感测题目的待填充数据填充至数据采集表单,实现了在临床试验过程中进行数据采集的功能。
本申请中的多个,是指大于1个,包括2个和大于2个的情况。
本申请对感兴趣题目的数量不作限定,其例如可以是2个、3个、5个、8个、10个、15个、20个、30个、50个、100个、150个、200个、1000个等。
本申请对感测题目、非感测题目的数量不作限定,二者之和等于感兴趣题目的数量。
本申请中的感测题目是指与感测到的生理电信号有关的题目,例如是生理电信号的电压幅值、脉宽、频率、类型、对应的生理状态、对应的疼痛评分、对应的发病状态等。
生理电信号的电压幅值例如是微伏数量级的30μV、60μV、80μV等,脉宽例如可以是50μs、60μs、70μs等,频率例如可以是100Hz、130Hz、150Hz等。
生理电信号的类型例如可以是脑电信号、心电信号、肌电信号、眼电信号等。
生理电信号对应的生理状态例如可以是发病、正常、饭后、运动中、睡眠等。
生理电信号对应的疼痛评分例如可以采用百分制,其例如可以是78、85、99等,数值越大表明患者的疼痛感越强烈。
生理电信号对应的发病状态例如可以是发病、未发病,又例如可以分为轻度、中度、重度等。
相应的,非感测题目是指与生理电信号无关(或者说无直接关系)的题目,例如是患者的姓名、身份证号、年龄、性别、民族、住址、血型、主诉、症状、病史信息、评分量表、随访记录、家族遗传病信息、心情、舒适程度、饮食记录、用药记录、复诊记录、对医生的意见和建议等。
评分量表例如可以是统一帕金森氏症评定量表或者UPD评分量表。统一帕金森氏症评定量表(英 文全称为The unified Parkinson's disease rating scale,也被称为UPDRS评分量表或UPD评分量表),是用来纵向衡量帕金森氏症发展情形的估量表。UPD评分量表(英语:rating scale)是临床研究帕金森氏症中最常用的评分量表。
除了帕金森病对应的上述两种评分量表,针对其他疾病类型或者其他应用场景也可以设置有对应的评分量表。例如针对抑郁症的抑郁症症状快速自评量表,针对失眠的失眠严重程度指数量表(ISI),针对孤独症的儿童孤独症评定量表(CARS),针对焦虑症的汉密顿焦虑量表(HAMA),针对糖尿病的成人糖尿病前期人群筛查简易评分表(PRISQ评分),针对睡眠呼吸暂停的阻塞性睡眠呼吸暂停筛查评分表(NoSAS评分),针对自理能力的患者自理能力评估表等。
本申请中,步骤S104可以包括:利用交互设备接收输入操作,响应于所述输入操作,获取所述患者的多个非感测题目对应的待填充数据;或者,
利用交互设备接收导入操作,响应于所述导入操作,从本地、云端或者外部存储设备中导入所述患者的多个非感测题目对应的待填充数据;或者,
获取所述患者的患者数据,对所述患者的患者数据进行关键词提取,以得到所述患者的多个非感测题目对应的待填充数据。
其中,患者数据例如可以包括联网系统中可以查询得到的同一患者产生的所有数据,包括文本数据、医学影像数据、摄像头采集得到的图像数据、程控记录、数据采集记录等。
本申请中,步骤S105可以包括:基于所述数据采集表单中的每个感测题目的题目类型,利用所述患者的每个感测题目对应的待填充数据填充所述数据采集表单中的每个感测题目对应的待填充部分;
基于所述数据采集表单中的每个非感测题目的题目类型,利用所述患者的每个非感测题目对应的待填充数据填充所述数据采集表单中的每个非感测题目对应的待填充部分。
参见图3,图3示出了本申请提供的一种确定使用者的多个感兴趣题目的流程示意图。
在一些实施例中,所述步骤S101可以包括:
步骤S201:获取所述使用者中的每个医生的感兴趣题目,以获取所述使用者中的所有医生的感兴趣题目;
步骤S202:对所述使用者中的所有医生的感兴趣题目进行去重,以获取所述使用者的多个感兴趣题目。
由此,分别获取每个医生的感兴趣题目,从而获取所有医生的感兴趣题目,再对其进行去重,就能够得到使用者的多个感兴趣题目。这种感兴趣题目的获取方式简单快捷,效率高。
参见图4,图4示出了本申请提供的另一种确定使用者的多个感兴趣题目的流程示意图。
在一些实施例中,所述步骤S101可以包括:
步骤S301:获取所述使用者的一个或多个标签;
步骤S302:基于题目库中的每个题目的标签与所述使用者的标签,获取所述题目库中的每个题目与所述使用者的标签相似度,所述题目库中的每个题目对应一个或多个标签;
步骤S303:从所述题目库中选择标签相似度最高的多个题目作为所述使用者的多个感兴趣题目。
由此,为使用者设置标签,并分别为题目库中的每个题目设置标签,采用标签匹配的方式评价每个题目和使用者之间的标签相似度,再从题目库中选择标签相似度最高的一些题目作为使用者的多个感兴趣题目,匹配程度高,维护难度低。题目库中的题目可以实现复用,而不需要每个使用者每次重新编辑生成题目信息,数据采集表单得以快速生成。
本申请中,使用者的标签可以是人工设定的,例如是“精神类疾病”、“戒毒”、“强迫症”、“抑郁症”、“精神科”、“消化内科”、“普通外科”、“口腔科”、“康复医学”、“A医院”、“B医院”、“C医院”、“D医院”等。使用者的标签也可以是根据各个医生的标签或医生信息智能设定的,例如当使用者是医生团队,且团队内的医生都是精神科医生时,可以将“精神科”作为该使用者的标签。
题目库中,题目的标签可以是智能匹配的或者人工设定的,例如是“患者基本信息”或“抑郁症”。
例如,“患者基本信息”这一标签,可以对应多个题目,例如用于填充患者姓名、身份证号、联系地址、联系电话、邮箱、年龄、性别、民族、政治面貌、工作单位、医保类型的非感测题目。当使用者的标签中包含“患者基本信息”这一标签时,可以自动将该标签对应的上述非感测题目列入数据采集表单中。
又例如,“DBS”这一标签,可以对应强迫症临床试验团队、抑郁症临床试验团队、成瘾性疾病临床试验团队等。“DBS”这一标签,还可以对应多个感测题目,例如是用于填充患者植入电极导线的数量(例如是1个或2个)、植入位置(左脑和/或右脑)、靶点(例如是伏隔核和/或内囊前肢)、数据采集时刻、数据采集时长、脑电信号电压幅值、脑电信号脉宽、脑电信号频率的题目。
作为示例,标签相似度可以是50%、88%、95%等百分比表示的数值。
当使用者和题目的标签完全一致时,标签相似度例如可以是100%。例如使用者戒毒团队和题目A01的标签都是“戒毒”。
本申请中,只要更改使用者和/或题目的标签,就可以更改使用者和题目之间的对应关系,因此维护简单,并且能够实现已有题目的复用。此处复用是指同样的题目可以用于生成多个临床试验团队的数据采集表单。例如新创建了一个“戒毒临床试验团队”,当为其添加“患者基本信息”这一标签时,则其对应的数据采集表单中包括具有“患者基本信息”这一标签的题目。
在一些实施例中,所述步骤S302可以包括:
针对所述题目库中的每个题目,执行以下处理:
将所述题目的标签与所述使用者的标签输入标签相似度模型,以得到所述题目与所述使用者的标签相似度;
其中,所述标签相似度模型的训练过程包括:
获取训练集,所述训练集包括多个训练数据,每个所述训练数据包括第一样本对象的标签、第二样本对象的标签以及所述第一样本对象和所述第二样本对象的标签相似度的标注数据;
针对所述训练集中的每个训练数据,执行以下处理:
将所述训练数据中的第一样本对象的标签和第二样本对象的标签输入预设的深度学习模型,以得到所述第一样本对象和所述第二样本对象的标签相似度的预测数据;
基于所述第一样本对象和所述第二样本对象的标签相似度的预测数据和标注数据,对所述深度学习模型的模型参数进行更新;
检测是否满足预设的训练结束条件;若是,则将训练出的深度学习模型作为所述标签相似度模型;若否,则利用下一个所述训练数据继续训练所述深度学习模型。
由此,标签相似度模型可以由大量的训练数据训练得到,能够针对不同的输入数据(即两个对象的标签)预测得到相应的输出数据(即两个对象的标签相似度),适用范围广,智能化水平高。通过设计,建立适量的神经元计算节点和多层运算层次结构,选择合适的输入层和输出层,就可以得到预设的深度学习模型,通过该预设的深度学习模型的学习和调优,建立起从输入到输出的函数关系,虽然不能100%找到输入与输出的函数关系,但是可以尽可能地逼近现实的关联关系,由此训练得到的标签相似度模型,可以基于每个题目和使用者的标签分别获取每个题目和使用者的标签相似度,且计算结果准确性高、可靠性高。
在一些实施例中,本申请可以采用上述训练过程训练得到标签相似度模型,在另一些可选的实施方式中,本申请可以采用预先训练好的标签相似度模型。
在一些实施例中,例如可以对历史数据进行数据挖掘,以获取训练数据。当然,第一样本对象、第二样本对象的标签也可以是利用GAN模型的生成网络自动生成的。
其中,GAN模型即生成对抗网络(Generative Adversarial Network),由一个生成网络与一个判别网络组成。生成网络从潜在空间(latent space)中随机采样作为输入,其输出结果需要尽量模仿训练集中的真实样本。判别网络的输入则为真实样本或生成网络的输出,其目的是将生成网络的输出从真实样本中尽可能分辨出来。而生成网络则要尽可能地欺骗判别网络。两个网络相互对抗、不断调整参数,最终目的是使判别网络无法判断生成网络的输出结果是否真实。使用GAN模型可以生成多个样本生物体的分类信息,用于标签相似度模型的训练过程,能有效降低原始数据采集的数据量,大大降低数 据采集和标注的成本。
本申请对标注数据的获取方式不作限定,例如可以采用人工标注的方式,也可以采用自动标注或者半自动标注的方式。
本申请对标签相似度模型的训练过程不作限定,其例如可以采用上述监督学习的训练方式,或者可以采用半监督学习的训练方式,或者可以采用无监督学习的训练方式。
本申请对预设的训练结束条件不作限定,其例如可以是训练次数达到预设次数(预设次数例如是1次、3次、10次、100次、1000次、10000次等),或者可以是训练集中的训练数据都完成一次或多次训练,或者可以是本次训练得到的总损失值不大于预设损失值。
在一些实施例中,所述步骤S303可以包括:
利用交互设备获取所述使用者对应的题目数量N,N是大于1的整数;
从所述题目库中选择标签相似度最高的N个题目作为所述使用者的多个感兴趣题目。
由此,题目数量N可以采用人工设定的方式,使用者可以通过交互设备进行题目数量的设定操作,从而确定感兴趣题目的数量。也就是说,在利用标签匹配的智能方式匹配得到题目库中的每个题目与使用者的标签相似度后,再结合人工设定的题目数量来确定多个感兴趣题目,这种智能和人工相结合的方式能够兼具处理效率高、贴近实际需求的优点,当使用者人工设定不同的题目数量时,可以分别生成简化版的数据采集表单和完整版的数据采集表单,满足实际应用中的多样性需求。
本申请中,题目数量N例如可以是2个、3个、5个、8个、10个、15个、20个、30个、50个、100个、150个、200个、1000个等。
本申请对交互设备不作限定,其例如可以是手机、平板电脑、笔记本电脑、台式计算机、智能穿戴设备等智能终端设备,或者,交互设备可以是工作站或者控制台。
本申请对利用交互设备接收各种(人工)操作的方式不作限定。按照输入方式划分操作,例如可以包括文本输入操作、音频输入操作、视频输入操作、按键操作、鼠标操作、键盘操作、智能触控笔操作等。
在另一些可选的实施方式中,所述步骤S303可以包括:
从所述题目库中选择标签相似度最高的预设数量的题目作为所述使用者的多个感兴趣题目。
其中,预设数量是预先设定的数量,例如可以是2个、3个、5个、8个、10个、15个、20个、30个、50个、100个、150个、200个、1000个等。
本申请中,题目类型不同,感兴趣题目对应的待填充数据的填充方式不同,所对应的待填充部分的形式不同。
在一些实施例中,每个感兴趣题目的题目类型可以是文本框、文本域、单选、多选、下拉框或者附件上传;
当所述感兴趣题目的题目类型是文本框时,所述感兴趣题目的待填充部分采用文本框;
当所述感兴趣题目的题目类型是文本域时,所述感兴趣题目的待填充部分采用文本域;
当所述感兴趣题目的题目类型是单选时,所述感兴趣题目的待填充部分采用单选框;
当所述感兴趣题目的题目类型是多选时,所述感兴趣题目的待填充部分采用复选框;
当所述感兴趣题目的题目类型是下拉框时,所述感兴趣题目的待填充部分采用下拉框;
当所述感兴趣题目的题目类型是附件上传时,所述感兴趣题目的待填充部分采用附件上传控件。
由此,涵盖了问卷的多种题目类型,确认后可立即生成预设格式的问卷表单页面,方便快捷便于操作。
本申请中,将待填充数据填充至待填充部分的方式可以采用自动填充的方式,也可以采用人工填充的方式。
作为一个示例,感测题目的题目类型是文本框或文本域,题目描述例如是:
患者姓名:
(该感兴趣题目为非感测题目)
作为另一个示例,感测题目的题目类型是文本框或文本域,题目描述例如是:
所采集的生理电信号的平均脉宽是:
(该感兴趣题目为感测题目)
作为又一个示例,感测题目的题目类型是单选,题目描述例如是:
所采集的生理电信号是:
A、脑电信号;B、心电信号;C、眼电信号;D、肌电信号。
(该感兴趣题目为感测题目)
作为又一个示例,感测题目的题目类型是复选(可以选择其中一个或多个选项),题目描述例如是:
患者的疾病包括:
A、抑郁症;B、强迫症;C、成瘾性疾病;D、帕金森病。
(该感兴趣题目为非感测题目)
作为又一个示例,感测题目的题目类型是下拉框,题目描述例如是:
患者性别:
下拉框选项:男;女。
(该感兴趣题目为非感测题目)
作为又一个示例,感测题目的题目类型是附件上传,题目描述例如是:
请上传患者的生理电信号数据文件。
(该感兴趣题目为感测题目)
在一些实施例中,所述获取所述患者的多个非感测题目对应的待填充数据,包括:
获取所述患者的疾病信息;
对所述患者的疾病信息进行关键词提取,以获取所述患者的多个非感测题目对应的待填充数据。
由此,利用患者的疾病信息进行关键词提取,以获取该患者的非感测题目对应的待填充数据,也就是说,这些数据可以采用自动提取的方式获取,而不需要人工填写,进一步提升了临床试验电子数据采集的速度,智能化程度高,用户体验佳。
本申请对疾病信息不作限定,其例如可以包括患者的基本信息、病史信息、医学影像信息、预先录制视频信息、实时视频信息、程控记录和音视频记录中的一个或多个。
本申请中的医学影像信息例如可以包括CT数据、MR数据、PET数据、X光数据、PET-CT数据、PET-MR数据等。相应的,所使用的的医学扫描设备例如可以是CT设备、MR设备、PET设备、X光设备、PET-CT设备、PET-MR设备等。其中,CT(Computed Tomography)即电子计算机断层扫描,MR(Magnetic Resonance)即磁共振,PET(Positron Emission Tomography)即正电子发射断层扫描。
装置实现方式
本申请还提供了一种数据采集装置,其具体实现方式与上述方法实现方式中记载的实现方式、所达到的技术效果一致,部分内容不再赘述。
本申请还提供了一种数据采集装置,用于在临床试验过程中进行数据采集,所述装置包括处理器,所述处理器被配置成:
确定使用者的多个感兴趣题目,多个感兴趣题目包括多个感测题目和多个非感测题目;
基于多个感兴趣题目的题目信息生成所述使用者对应的数据采集表单,所述数据采集表单包括每个感兴趣题目对应的待填充部分,所述题目信息包括题目描述和题目类型;
利用感测设备感测患者的生物电信号,以获取所述患者的多个感测题目对应的待填充数据;
获取所述患者的多个非感测题目对应的待填充数据;
基于所述数据采集表单中的每个感兴趣题目的题目类型,利用所述患者的每个感兴趣题目对应的待填充数据填充所述数据采集表单中的每个感兴趣题目对应的待填充部分。
在一些实施例中,所述处理器被进一步配置成采用以下方式确定使用者的多个感兴趣题目:
获取所述使用者中的每个医生的感兴趣题目,以获取所述使用者中的所有医生的感兴趣题目;
对所述使用者中的所有医生的感兴趣题目进行去重,以获取所述使用者的多个感兴趣题目。
在一些实施例中,所述处理器被进一步配置成采用以下方式确定使用者的多个感兴趣题目:
获取所述使用者的一个或多个标签;
基于题目库中的每个题目的标签与所述使用者的标签,获取所述题目库中的每个题目与所述使用者的标签相似度,所述题目库中的每个题目对应一个或多个标签;
从所述题目库中选择标签相似度最高的多个题目作为所述使用者的多个感兴趣题目。
在一些实施例中,所述处理器被进一步配置成采用以下方式获取所述题目库中的每个题目与所述使用者的标签相似度:
针对所述题目库中的每个题目,执行以下处理:
将所述题目的标签与所述使用者的标签输入标签相似度模型,以得到所述题目与所述使用者的标签相似度;
其中,所述标签相似度模型的训练过程包括:
获取训练集,所述训练集包括多个训练数据,每个所述训练数据包括第一样本对象的标签、第二样本对象的标签以及所述第一样本对象和所述第二样本对象的标签相似度的标注数据;
针对所述训练集中的每个训练数据,执行以下处理:
将所述训练数据中的第一样本对象的标签和第二样本对象的标签输入预设的深度学习模型,以得到所述第一样本对象和所述第二样本对象的标签相似度的预测数据;
基于所述第一样本对象和所述第二样本对象的标签相似度的预测数据和标注数据,对所述深度学习模型的模型参数进行更新;
检测是否满足预设的训练结束条件;若是,则将训练出的深度学习模型作为所述标签相似度模型;若否,则利用下一个所述训练数据继续训练所述深度学习模型。
在一些实施例中,所述处理器被进一步配置成采用以下方式获取所述使用者的多个感兴趣题目:
利用交互设备获取所述使用者对应的题目数量N,N是大于1的整数;
从所述题目库中选择标签相似度最高的N个题目作为所述使用者的多个感兴趣题目。
在一些实施例中,每个感兴趣题目的题目类型是文本框、文本域、单选、多选、下拉框或者附件上传;
当所述感兴趣题目的题目类型是文本框时,所述感兴趣题目的待填充部分采用文本框;
当所述感兴趣题目的题目类型是文本域时,所述感兴趣题目的待填充部分采用文本域;
当所述感兴趣题目的题目类型是单选时,所述感兴趣题目的待填充部分采用单选框;
当所述感兴趣题目的题目类型是多选时,所述感兴趣题目的待填充部分采用复选框;
当所述感兴趣题目的题目类型是下拉框时,所述感兴趣题目的待填充部分采用下拉框;
当所述感兴趣题目的题目类型是附件上传时,所述感兴趣题目的待填充部分采用附件上传控件。
在一些实施例中,所述处理器被进一步配置成采用以下方式获取所述患者的多个非感测题目对应的待填充数据:
获取所述患者的疾病信息;
对所述患者的疾病信息进行关键词提取,以获取所述患者的多个非感测题目对应的待填充数据。
参见图5,图5示出了本申请提供的一种数据采集装置200的结构框图。
数据采集装置200例如可以包括至少一个存储器210、至少一个处理器220以及连接不同平台系统的总线230。
存储器210可以包括易失性存储器形式的可读介质,例如随机存取存储器(RAM)211和/或高速缓存存储器212,还可以进一步包括只读存储器(ROM)213。
其中,存储器210还存储有计算机程序,计算机程序可以被处理器220执行,使得处理器220实现上述任一项数据采集方法的功能,其具体实现方式与上述方法实现方式中记载的实现方式、所达到的技术效果一致,部分内容不再赘述。
存储器210还可以包括具有至少一个程序模块215的实用工具214,这样的程序模块215包括但不限于:操作系统、一个或者多个应用程序、其它程序模块以及程序数据,这些示例的每一个或某种组合中可能包括网络环境的实现。
相应的,处理器220可以执行上述计算机程序,以及可以执行实用工具214。
处理器220可以采用一个或多个应用专用集成电路(ASIC,Application Specific Integrated Circuit)、DSP、可编程逻辑器件(PLD,Programmable Logic Device)、复杂可编程逻辑器件(CPLD,Complex Programmable Logic Device)、现场可编程门阵列(FPGA,Field-Programmable Gate Array)或其他电子元件。
总线230可以为表示几类总线结构的一种或多种,包括存储器总线或者存储器控制器、外围总线、图形加速端口、处理器或者使用多种总线结构的任意总线结构的局域总线。
数据采集装置200也可以与一个或多个外部设备240例如键盘、指向设备、蓝牙设备等通信,还可与一个或者多个能够与该数据采集装置200交互的设备通信,和/或与使得该数据采集装置200能与一个或多个其它计算设备进行通信的任何设备(例如路由器、调制解调器等)通信。这种通信可以通过输入输出接口250进行。并且,数据采集装置200还可以通过网络适配器260与一个或者多个网络(例如局域网(LAN),广域网(WAN)和/或公共网络,例如因特网)通信。网络适配器260可以通过总线230与数据采集装置200的其它模块通信。应当明白,尽管图中未示出,可以结合数据采集装置200使用其它硬件和/或软件模块,包括但不限于:微代码、设备驱动器、冗余处理器、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储平台等。
介质实现方式
本申请还提供了一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时实现上述任一项装置的功能或者实现上述任一项方法的步骤,其具体实现方式与上述方法实现方式中记载的实现方式、所达到的技术效果一致,部分内容不再赘述。
参见图6,图6示出了本申请提供的一种程序产品的结构示意图。
程序产品可以采用便携式紧凑盘只读存储器(CD-ROM)并包括程序代码,并可以在终端设备,例如个人电脑上运行。然而,本发明的程序产品不限于此,在本申请中,可读存储介质可以是任何包含或存储程序的有形介质,该程序可以被指令执行系统、装置或者器件使用或者与其结合使用。程序产品可以采用一个或多个可读介质的任意组合。可读介质可以是可读信号介质或者可读存储介质。可读存储介质例如可以为但不限于电、磁、光、电磁、红外线、或半导体的系统、装置或器件,或者任意以上的组合。可读存储介质的更具体的例子(非穷举的列表)包括:具有一个或多个导线的电连接、便携式盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。
计算机可读存储介质可以包括在基带中或者作为载波一部分传播的数据信号,其中承载了可读程序代码。这种传播的数据信号可以采用多种形式,包括但不限于电磁信号、光信号或上述的任意合适的组合。可读存储介质还可以是任何可读介质,该可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。可读存储介质上包含的程序代码可以用任何适当的介质传输,包括但不限于无线、有线、光缆、RF等,或者上述的任意合适的组合。可以以一种或多种程序设计语言的任意组合来编写用于执行本发明操作的程序代码,程序设计语言包括面向对象的 程序设计语言诸如Java、C++等,还包括常规的过程式程序设计语言诸如C语言或类似的程序设计语言。程序代码可以完全地在用户计算设备上执行、部分地在用户设备上执行、作为一个独立的软件包执行、部分在用户计算设备上部分在远程计算设备上执行、或者完全在远程计算设备或服务器上执行。在涉及远程计算设备的情形中,远程计算设备可以通过任意种类的网络,包括局域网(LAN)或广域网(WAN),连接到用户计算设备,或者,可以连接到外部计算设备(例如利用因特网服务提供商来通过因特网连接)。

Claims (16)

  1. 一种数据采集方法,用于在临床试验过程中进行数据采集,所述方法包括:
    确定使用者的多个感兴趣题目,多个感兴趣题目包括多个感测题目和多个非感测题目;
    基于多个感兴趣题目的题目信息生成所述使用者对应的数据采集表单,所述数据采集表单包括每个感兴趣题目对应的待填充部分,所述题目信息包括题目描述和题目类型;
    利用感测设备感测患者的生物电信号,以获取所述患者的多个感测题目对应的待填充数据;
    获取所述患者的多个非感测题目对应的待填充数据;
    基于所述数据采集表单中的每个感兴趣题目的题目类型,利用所述患者的每个感兴趣题目对应的待填充数据填充所述数据采集表单中的每个感兴趣题目对应的待填充部分。
  2. 根据权利要求1所述的数据采集方法,其中,所述确定使用者的多个感兴趣题目,包括:
    获取所述使用者中的每个医生的感兴趣题目,以获取所述使用者中的所有医生的感兴趣题目;
    对所述使用者中的所有医生的感兴趣题目进行去重,以获取所述使用者的多个感兴趣题目。
  3. 根据权利要求1所述的数据采集方法,其中,所述确定使用者的多个感兴趣题目,包括:
    获取所述使用者的一个或多个标签;
    基于题目库中的每个题目的标签与所述使用者的标签,获取所述题目库中的每个题目与所述使用者的标签相似度,所述题目库中的每个题目对应一个或多个标签;
    从所述题目库中选择标签相似度最高的多个题目作为所述使用者的多个感兴趣题目。
  4. 根据权利要求3所述的数据采集方法,其中,所述基于题目库中的每个题目的标签与所述使用者的标签,获取所述题目库中的每个题目与所述使用者的标签相似度,包括:
    针对所述题目库中的每个题目,执行以下处理:
    将所述题目的标签与所述使用者的标签输入标签相似度模型,以得到所述题目与所述使用者的标签相似度;
    其中,所述标签相似度模型的训练过程包括:
    获取训练集,所述训练集包括多个训练数据,每个所述训练数据包括第一样本对象的标签、第二样本对象的标签以及所述第一样本对象和所述第二样本对象的标签相似度的标注数据;
    针对所述训练集中的每个训练数据,执行以下处理:
    将所述训练数据中的第一样本对象的标签和第二样本对象的标签输入预设的深度学习模型,以得到所述第一样本对象和所述第二样本对象的标签相似度的预测数据;
    基于所述第一样本对象和所述第二样本对象的标签相似度的预测数据和标注数据,对所述深度学习模型的模型参数进行更新;
    检测是否满足预设的训练结束条件;若是,则将训练出的深度学习模型作为所述标签相似度模型;若否,则利用下一个所述训练数据继续训练所述深度学习模型。
  5. 根据权利要求3所述的数据采集方法,其中,所述从所述题目库中选择标签相似度最高的多 个题目作为所述使用者的多个感兴趣题目,包括:
    利用交互设备获取所述使用者对应的题目数量N,N是大于1的整数;
    从所述题目库中选择标签相似度最高的N个题目作为所述使用者的多个感兴趣题目。
  6. 根据权利要求1所述的数据采集方法,其中,每个感兴趣题目的题目类型是文本框、文本域、单选、多选、下拉框或者附件上传;
    当所述感兴趣题目的题目类型是文本框时,所述感兴趣题目的待填充部分采用文本框;
    当所述感兴趣题目的题目类型是文本域时,所述感兴趣题目的待填充部分采用文本域;
    当所述感兴趣题目的题目类型是单选时,所述感兴趣题目的待填充部分采用单选框;
    当所述感兴趣题目的题目类型是多选时,所述感兴趣题目的待填充部分采用复选框;
    当所述感兴趣题目的题目类型是下拉框时,所述感兴趣题目的待填充部分采用下拉框;
    当所述感兴趣题目的题目类型是附件上传时,所述感兴趣题目的待填充部分采用附件上传控件。
  7. 根据权利要求1所述的数据采集方法,其中,所述获取所述患者的多个非感测题目对应的待填充数据,包括:
    获取所述患者的疾病信息;
    对所述患者的疾病信息进行关键词提取,以获取所述患者的多个非感测题目对应的待填充数据。
  8. 一种数据采集装置,其中,用于在临床试验过程中进行数据采集,所述装置包括处理器,所述处理器被配置成:
    确定使用者的多个感兴趣题目,多个感兴趣题目包括多个感测题目和多个非感测题目;
    基于多个感兴趣题目的题目信息生成所述使用者对应的数据采集表单,所述数据采集表单包括每个感兴趣题目对应的待填充部分,所述题目信息包括题目描述和题目类型;
    利用感测设备感测患者的生物电信号,以获取所述患者的多个感测题目对应的待填充数据;
    获取所述患者的多个非感测题目对应的待填充数据;
    基于所述数据采集表单中的每个感兴趣题目的题目类型,利用所述患者的每个感兴趣题目对应的待填充数据填充所述数据采集表单中的每个感兴趣题目对应的待填充部分。
  9. 根据权利要求8所述的数据采集装置,其中,所述处理器被进一步配置成采用以下方式确定使用者的多个感兴趣题目:
    获取所述使用者中的每个医生的感兴趣题目,以获取所述使用者中的所有医生的感兴趣题目;
    对所述使用者中的所有医生的感兴趣题目进行去重,以获取所述使用者的多个感兴趣题目。
  10. 根据权利要求8所述的数据采集装置,其中,所述处理器被进一步配置成采用以下方式确定使用者的多个感兴趣题目:
    获取所述使用者的一个或多个标签;
    基于题目库中的每个题目的标签与所述使用者的标签,获取所述题目库中的每个题目与所述使用者的标签相似度,所述题目库中的每个题目对应一个或多个标签;
    从所述题目库中选择标签相似度最高的多个题目作为所述使用者的多个感兴趣题目。
  11. 根据权利要求10所述的数据采集装置,其中,所述处理器被进一步配置成采用以下方式获取所述题目库中的每个题目与所述使用者的标签相似度:
    针对所述题目库中的每个题目,执行以下处理:
    将所述题目的标签与所述使用者的标签输入标签相似度模型,以得到所述题目与所述使用者的标签相似度;
    其中,所述标签相似度模型的训练过程包括:
    获取训练集,所述训练集包括多个训练数据,每个所述训练数据包括第一样本对象的标签、第二样本对象的标签以及所述第一样本对象和所述第二样本对象的标签相似度的标注数据;
    针对所述训练集中的每个训练数据,执行以下处理:
    将所述训练数据中的第一样本对象的标签和第二样本对象的标签输入预设的深度学习模型,以得到所述第一样本对象和所述第二样本对象的标签相似度的预测数据;
    基于所述第一样本对象和所述第二样本对象的标签相似度的预测数据和标注数据,对所述深度学习模型的模型参数进行更新;
    检测是否满足预设的训练结束条件;若是,则将训练出的深度学习模型作为所述标签相似度模型;若否,则利用下一个所述训练数据继续训练所述深度学习模型。
  12. 根据权利要求10所述的数据采集装置,其中,所述处理器被进一步配置成采用以下方式获取所述使用者的多个感兴趣题目:
    利用交互设备获取所述使用者对应的题目数量N,N是大于1的整数;
    从所述题目库中选择标签相似度最高的N个题目作为所述使用者的多个感兴趣题目。
  13. 根据权利要求8所述的数据采集装置,其中,每个感兴趣题目的题目类型是文本框、文本域、单选、多选、下拉框或者附件上传;
    当所述感兴趣题目的题目类型是文本框时,所述感兴趣题目的待填充部分采用文本框;
    当所述感兴趣题目的题目类型是文本域时,所述感兴趣题目的待填充部分采用文本域;
    当所述感兴趣题目的题目类型是单选时,所述感兴趣题目的待填充部分采用单选框;
    当所述感兴趣题目的题目类型是多选时,所述感兴趣题目的待填充部分采用复选框;
    当所述感兴趣题目的题目类型是下拉框时,所述感兴趣题目的待填充部分采用下拉框;
    当所述感兴趣题目的题目类型是附件上传时,所述感兴趣题目的待填充部分采用附件上传控件。
  14. 根据权利要求8所述的数据采集装置,其中,所述处理器被进一步配置成采用以下方式获取所述患者的多个非感测题目对应的待填充数据:
    获取所述患者的疾病信息;
    对所述患者的疾病信息进行关键词提取,以获取所述患者的多个非感测题目对应的待填充数据。
  15. 一种数据采集系统,所述数据采集系统包括:
    权利要求8-14任一项所述的数据采集装置;
    感测设备,所述感测设备用于感测患者的生物电信号。
  16. 一种计算机可读存储介质,所述计算机可读存储介质存储有计算机程序,所述计算机程序被处理器执行时实现权利要求1-7任一项所述方法的步骤或者实现权利要求8-14任一项所述装置的功能。
PCT/CN2023/098645 2022-06-30 2023-06-06 数据采集方法、装置、系统及计算机可读存储介质 WO2024001695A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210762218.5A CN114842930B (zh) 2022-06-30 2022-06-30 数据采集方法、装置、系统及计算机可读存储介质
CN202210762218.5 2022-06-30

Publications (1)

Publication Number Publication Date
WO2024001695A1 true WO2024001695A1 (zh) 2024-01-04

Family

ID=82574641

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/098645 WO2024001695A1 (zh) 2022-06-30 2023-06-06 数据采集方法、装置、系统及计算机可读存储介质

Country Status (2)

Country Link
CN (1) CN114842930B (zh)
WO (1) WO2024001695A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114842930B (zh) * 2022-06-30 2022-09-27 苏州景昱医疗器械有限公司 数据采集方法、装置、系统及计算机可读存储介质

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170109610A1 (en) * 2013-03-13 2017-04-20 Kofax, Inc. Building classification and extraction models based on electronic forms
CN109389427A (zh) * 2018-09-26 2019-02-26 中国平安人寿保险股份有限公司 问卷推送方法、装置、计算机设备和存储介质
CN110245213A (zh) * 2019-05-08 2019-09-17 平安科技(深圳)有限公司 调查问卷生成方法、装置、设备和存储介质
CN113918699A (zh) * 2021-10-12 2022-01-11 平安国际智慧城市科技股份有限公司 调查问卷的生成方法、装置、计算机设备和存储介质
CN114842930A (zh) * 2022-06-30 2022-08-02 苏州景昱医疗器械有限公司 数据采集方法、装置、系统及计算机可读存储介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114072782A (zh) * 2020-05-29 2022-02-18 京东方科技集团股份有限公司 问题推荐方法及装置、系统和电子设备、可读存储介质
CN112434151A (zh) * 2020-11-26 2021-03-02 重庆知识产权大数据研究院有限公司 一种专利推荐方法、装置、计算机设备及存储介质
CN113822427A (zh) * 2021-07-29 2021-12-21 腾讯科技(深圳)有限公司 一种模型训练的方法、图像匹配的方法、装置及存储介质
CN114328910A (zh) * 2021-11-23 2022-04-12 合肥讯飞数码科技有限公司 文本聚类方法以及相关装置
CN114528494A (zh) * 2022-02-28 2022-05-24 北京高途云集教育科技有限公司 一种信息推送方法、装置、设备及存储介质

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170109610A1 (en) * 2013-03-13 2017-04-20 Kofax, Inc. Building classification and extraction models based on electronic forms
CN109389427A (zh) * 2018-09-26 2019-02-26 中国平安人寿保险股份有限公司 问卷推送方法、装置、计算机设备和存储介质
CN110245213A (zh) * 2019-05-08 2019-09-17 平安科技(深圳)有限公司 调查问卷生成方法、装置、设备和存储介质
CN113918699A (zh) * 2021-10-12 2022-01-11 平安国际智慧城市科技股份有限公司 调查问卷的生成方法、装置、计算机设备和存储介质
CN114842930A (zh) * 2022-06-30 2022-08-02 苏州景昱医疗器械有限公司 数据采集方法、装置、系统及计算机可读存储介质

Also Published As

Publication number Publication date
CN114842930A (zh) 2022-08-02
CN114842930B (zh) 2022-09-27

Similar Documents

Publication Publication Date Title
US10974049B1 (en) Artificial intelligence systems for quantifying movement disorder symptoms and adjusting treatment based on symptom quantification
US11759642B1 (en) Movement disorder therapy and brain mapping system and methods of tuning remotely, intelligently and/or automatically
US8805514B2 (en) Systems and methods for interacting with an implantable medical device
EP3886692B1 (en) Data processing system for generating predictions of cognitive outcome in patients
WO2024021960A1 (zh) 脉冲发生器、医疗系统及计算机可读存储介质
US20130023950A1 (en) Method and system to facilitate neurostimulator programming based on pre-existing therapy profiles
EP2892419A1 (en) Movement disorder therapy system, devices and methods, and intelligent methods of tuning
Matsushita et al. A fully implantable wireless ECoG 128-channel recording device for human brain–machine interfaces: W-HERBS
US20100268057A1 (en) Computational systems and methods for health services planning and matching
US20100241449A1 (en) Computational systems and methods for health services planning and matching
WO2024001695A1 (zh) 数据采集方法、装置、系统及计算机可读存储介质
Ayo-Farai et al. Engineering innovations in healthcare: a review of developments in the USA
WO2024001723A1 (zh) 控制设备、医疗系统及计算机可读存储介质
WO2023005353A1 (zh) 基于多模态数据的配置信息获取装置及相关设备
CN115501481A (zh) 应急程控设备、医疗系统及计算机可读存储介质
WO2024041496A1 (zh) 充电提醒装置、植入式神经刺激系统及存储介质
Uddin et al. Development of a wearable cardiac monitoring system for behavioral neurocardiac training: a usability study
Grew et al. Wireless heart patients and the quantified self
WO2024083193A1 (zh) 脉冲发生器、刺激器、医疗系统及计算机可读存储介质
CN115211816A (zh) 监护方法及监护系统
WO2023185410A1 (zh) 刺激电极导线的成像识别方法及相关装置
WO2023024881A1 (zh) 慢性病患者视频追溯方法及相关装置
CN114849063A (zh) 体外充电器、程控系统和计算机可读存储介质
Shaikhouni et al. Computers and neurosurgery
CN114817168A (zh) 数据存储方法、装置、系统及计算机可读存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23829879

Country of ref document: EP

Kind code of ref document: A1