A portable follow-up device for clinical data statistics

Abstract

The present application relates to the technical field of medical auxiliary, in particular to a kind of clinical data statistics with portable follow-up equipment, including intelligent follow-up system, intelligent follow-up system includes data acquisition module, data analysis module and intelligent interaction module;Data acquisition module is used to collect the basic information of patient, case information and physical index;Data analysis module is used to generate regular detection task according to key index;According to abnormal index, generate intelligent inquiry task;Intelligent interaction module is used to inquire and cross-examine to patient, generate follow-up record.The present application can generate targeted regular detection task and intelligent inquiry task according to the condition of patient by the design of data analysis module;And according to the development of patient condition, constantly adjust regular detection task and intelligent inquiry task, so that each follow-up has enough pertinence, and then improve the effectiveness and accuracy of follow-up result.

Description

Technical Field

[0001] This invention relates to the field of medical auxiliary technology, specifically to a convenient follow-up device for clinical data statistics. Background Technology

[0002] Follow-up is a crucial aspect of clinical medicine and scientific research. It refers to the continuous tracking and evaluation of a patient's disease outcome, treatment effectiveness, recovery status, and quality of life by medical staff after the completion of primary inpatient treatment. Effective follow-up not only monitors the patient's recovery process and promptly detects changes in the condition or signs of relapse, providing a basis for adjusting treatment plans, but also accumulates long-term clinical data, which is of great significance for evaluating diagnostic and treatment techniques and conducting medical research.

[0003] To improve follow-up efficiency and reduce labor costs, remote follow-up devices or systems based on artificial intelligence technology have emerged in the market. For example, iFlytek's intelligent follow-up system works as follows: doctors pre-set follow-up plans for patients within the system, including several standardized questions. The system then automatically simulates human intervention by remotely interviewing patients via telephone, SMS, or an application interface, using speech synthesis and recognition technology to collect information such as symptom feedback and medication usage, and automatically generates structured follow-up records. This approach, to some extent, frees doctors from highly repetitive routine inquiries, achieving initial convenience and scalability in follow-up.

[0004] However, existing follow-up systems rely heavily on doctors to pre-set their inquiry logic, content, and identification criteria. Given the significant differences in patients' conditions, a fundamental flaw of existing technologies is the inability to generate tailored follow-up plans based on each patient's specific condition, resulting in severely insufficient effectiveness and accuracy of follow-up results. Therefore, this invention provides a convenient follow-up device for clinical data statistics to address these problems. Summary of the Invention

[0005] To address the aforementioned issues, this invention provides a convenient follow-up device for clinical data statistics. Through the design of a data analysis module, it can generate targeted periodic testing tasks and intelligent inquiry tasks based on the patient's condition. Furthermore, it continuously adjusts the periodic testing tasks and intelligent inquiry tasks according to the progression of the patient's condition, thereby ensuring that each follow-up visit is sufficiently targeted and improving the effectiveness and accuracy of the follow-up results.

[0006] To achieve the above objectives, the technical solution of the present invention is as follows: a convenient follow-up device for clinical data statistics, comprising an intelligent follow-up system, wherein the intelligent follow-up system includes a data acquisition module, a data analysis module, and an intelligent interaction module.

[0007] The data acquisition module is used to collect patients' basic information, medical records, and physical indicators, and to associate and store these information to generate a patient database. The patient database is used for retrieval by the data analysis module and the intelligent interaction module.

[0008] The data analysis module is used to analyze key indicators based on patient case information and physical indicators, generate regular testing tasks based on key indicators, and transmit the regular testing tasks to the data acquisition module; it also generates indicator statistics based on the patient's physical indicators and key indicators, and transmits the indicator statistics to the intelligent interaction module.

[0009] The data analysis module is also used to allow doctors to set range thresholds for key indicators, determine whether key indicators exceed their range thresholds, mark key indicators that exceed their range thresholds as abnormal indicators, generate intelligent inquiry tasks based on abnormal indicators, and transmit the intelligent inquiry tasks to the intelligent interaction module.

[0010] The intelligent interaction module receives intelligent inquiry tasks, conducts inquiries with patients based on these tasks, analyzes the inquiry content, extracts key information, generates preliminary judgment results and treatment suggestions, and generates intelligent follow-up inquiry tasks based on the preliminary judgment results and treatment suggestions. It then conducts follow-up inquiries with patients based on these tasks, analyzes the follow-up inquiry content, extracts key information, updates the judgment results and treatment suggestions, and generates follow-up records.

[0011] The data analysis module is also used to predict a patient's risk of developing a disease based on the patient's physical indicators and follow-up records.

[0012] Furthermore, the intelligent interaction module is also used to allow doctors to view follow-up records and input supplementary inquiry tasks into the data analysis module based on the follow-up records. The intelligent interaction module is used to execute the supplementary inquiry tasks and update the follow-up records.

[0013] Furthermore, the intelligent interaction module is also used to display follow-up records to patients, allowing them to ask questions based on the records, and to provide answers to their questions.

[0014] Furthermore, the intelligent interaction module includes an intelligent question-answering unit, which is used to build an intelligent question-answering model through deep learning algorithms; the intelligent question-answering model is used to perform intelligent inquiry tasks, intelligent follow-up questions tasks, inquiry supplementation tasks, and question answering.

[0015] Furthermore, the intelligent interaction module also includes a doctor interaction unit and a patient interaction unit.

[0016] The doctor interaction unit allows doctors to view patients' basic information, medical records, physical indicators, and follow-up records; it also allows doctors to input supplementary questions, adjust judgment results, and provide treatment suggestions.

[0017] The patient interaction unit allows patients to view their basic information, medical records, physical indicators, and follow-up records; it also allows patients to input questions.

[0018] Furthermore, the patient interaction unit is also used for patients to send doctor-patient interaction invitations to the doctor interaction unit, which are used for doctors and patients to communicate via text, voice, and video.

[0019] Furthermore, the data analysis module includes a task formulation unit, a data statistics unit, and a disease prediction unit.

[0020] The task formulation unit is used to analyze patient case information, identify the patient's condition, analyze key physical indicators related to the patient's condition, and generate periodic testing tasks for key indicators.

[0021] The data statistics unit is used to generate a curve of changes in the patient's historical physical indicators and transmit the curve to the intelligent interaction module.

[0022] The disease prediction unit is used to obtain curves of changes in physical indicators and follow-up records, extract the changes in the patient's physical indicators and keywords in the follow-up records, and build a disease prediction model. The disease prediction model is used to predict the patient's disease risk based on the changes and keywords in the follow-up records, and outputs an emergency risk warning for the patient.

[0023] Furthermore, the data statistics unit is also used to bold key indicators in the change curve and highlight abnormal indicators in the change curve in red.

[0024] Furthermore, the task-setting unit also allows doctors to adjust the content and frequency of routine testing tasks.

[0025] Furthermore, the data acquisition module also includes a chassis, on which a blood analyzer is installed, and on one side of the chassis is a blood pressure monitor; the data acquisition module is used to collect the patient's physical indicators through the blood analyzer and the blood pressure monitor.

[0026] The technical principle of the above solution is as follows:

[0027] The data acquisition module collects patients' basic information, medical records, and physical indicators to generate a patient database. The data analysis module extracts patients' medical records and physical indicators from the database, identifies key indicators based on the medical records, and generates periodic testing tasks and statistical data based on these key indicators. The data analysis module also allows doctors to set threshold ranges for key indicators; when a key indicator exceeds its threshold, it is considered abnormal, and the module generates an intelligent inquiry task based on this abnormality. The intelligent interaction module executes the intelligent inquiry task, asking questions of the patient and following up based on the results, thus providing the patient with corresponding judgments and treatment suggestions, and generating follow-up records. Doctors can use these records to understand the inquiry process and changes in the patient's condition, providing more reasonable judgments and treatment suggestions.

[0028] The above approach has the following beneficial effects:

[0029] 1. This invention automatically identifies key indicators highly correlated with the patient's condition through a data analysis module and continuously monitors them to determine whether they exceed their threshold range. This allows for timely assessment of any abnormalities in the key indicators, enabling the timely detection of potential risks to the patient's health and providing a data foundation for developing targeted follow-up plans.

[0030] 2. Through the design of the intelligent inquiry module, this invention can conduct targeted inquiries on patients based on their abnormal indicators, thereby improving the effectiveness of the inquiry. At the same time, the intelligent interaction module will extract key information from the initial inquiry content and follow up with the patient based on this key information to explore more details and their potential correlation with the condition, thereby generating a more detailed and complete follow-up record, which greatly improves the accuracy and effectiveness of the follow-up.

[0031] 3. In this invention, the data analysis module adjusts the periodic testing tasks according to the changes in the patient's physical indicators, enabling the data collection module to collect data in a targeted manner based on changes in the patient's condition. At the same time, the data statistics unit can automatically generate curves showing changes in physical indicators and highlight key indicators through visualization methods such as bolding and red highlighting, clearly identifying abnormalities in the patient's body. This allows doctors to quickly grasp the development trend of the condition, assist doctors in making decisions, and provide patients with more reasonable judgment results and treatment suggestions. Attached Figure Description

[0032] Figure 1 This is a schematic diagram of the intelligent follow-up system in the portable follow-up device for clinical data statistics of the present invention.

[0033] Figure 2 This is a schematic diagram of the intelligent question-and-answer module in the portable follow-up device for clinical data statistics of the present invention.

[0034] Figure 3 This is a schematic diagram of the data analysis module in the portable follow-up device for clinical data statistics of the present invention.

[0035] Figure 4 This is a flowchart of the intelligent follow-up system in the portable follow-up device for clinical data statistics of the present invention.

[0036] Figure 5 This is a left-side isometric view of the portable follow-up device for clinical data statistics according to the present invention.

[0037] Figure 6 This is a right-side view of the portable follow-up device for clinical data statistics of the present invention.

[0038] Figure 7 This is a top view of the portable follow-up device for clinical data statistics according to the present invention.

[0039] The reference numerals in the accompanying drawings include: 1. Chassis; 2. Touch screen; 3. Blood analyzer; 4. Blood pressure monitor; 5. Radio; 6. Announcer. Detailed Implementation

[0040] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0041] In the description of this invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are used only for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0042] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0043] The following detailed description illustrates the specific implementation method:

[0044] Example 1:

[0045] like Figure 1 and Figure 4 As shown, a portable follow-up device for clinical data statistics includes an intelligent follow-up system, which comprises a data acquisition module, a data analysis module, and an intelligent interaction module; all modules are interconnected.

[0046] The specific functions of each module are as follows:

[0047] The data acquisition module is used to collect patients' basic information, medical records, and physical indicators, and to associate and store these information to generate a patient database. The patient database is used for retrieval by the data analysis module and the intelligent interaction module.

[0048] Specifically, in this embodiment, the data acquisition module is used for patients to independently input their basic information and medical records. At the same time, the data acquisition module is also associated with devices such as blood pressure monitors, blood glucose meters, and uric acid meters in the patient's home to collect various physical indicators of the patient at each test. The basic information includes gender, age, and name; the medical records include past medical history; and the physical indicators include blood glucose, glycated hemoglobin, blood pressure, blood lipids, and uric acid (users can associate other testing devices according to actual follow-up needs to collect and upload specified physical indicators).

[0049] The data analysis module is used to analyze key indicators based on patient case information and physical indicators, generate regular testing tasks based on key indicators, and transmit the regular testing tasks to the data acquisition module; it also generates indicator statistics based on the patient's physical indicators and key indicators, and transmits the indicator statistics to the intelligent interaction module.

[0050] Specifically, the data analysis module contains key indicators (indicator mapping rules, set and entered by doctors) corresponding to different conditions. For example, for diabetes, the key indicators are blood glucose and glycated hemoglobin; for hypertension, the key indicator is blood pressure. The data analysis module will associate the patient's condition with the corresponding key indicators based on the indicator mapping rules.

[0051] Assuming patient A has hypertension, the data analysis module will analyze the patient's key indicator as blood pressure and generate a regular monitoring task: measure blood pressure twice daily, once in the morning and once in the evening. Patient A will then use a blood pressure monitor to measure their blood pressure according to the regular monitoring task, and the data acquisition module will collect the blood pressure results from each measurement.

[0052] The data analysis module also allows doctors to set range thresholds for key indicators (doctors can adjust these thresholds based on individual patient conditions), determine whether key indicators exceed their range thresholds, mark key indicators exceeding their range thresholds as abnormal indicators, generate intelligent inquiry tasks based on the abnormal indicators, and transmit the intelligent inquiry tasks to the intelligent interaction module. The data analysis module includes a task formulation unit.

[0053] The task creation unit is used to analyze patient case information, identify the patient's condition, analyze key physical indicators related to the patient's condition, and generate regular testing tasks for these key indicators. The task creation unit also allows doctors to adjust the content and frequency of these regular testing tasks.

[0054] Specifically, taking patient A as an example, suppose the doctor sets the diastolic blood pressure range threshold to 70-90 mmHg and the systolic blood pressure range threshold to 90-150 mmHg; when patient A's blood pressure is measured at 8 am, his diastolic blood pressure is 98 mmHg and his systolic blood pressure is 162 mmHg, both exceeding the range threshold. At this time, the data analysis module will mark the blood pressure as an abnormal indicator and generate an intelligent inquiry task about hypertension.

[0055] The intelligent interaction module receives intelligent inquiry tasks, conducts inquiries with patients based on these tasks, analyzes the inquiry content, extracts key information, generates preliminary judgment results and treatment suggestions, and simultaneously generates intelligent follow-up inquiry tasks based on the preliminary judgment results and treatment suggestions. The module then conducts follow-up inquiries with patients based on these tasks, analyzes the follow-up inquiry content, extracts key information, updates the judgment results and treatment suggestions, and generates follow-up records.

[0056] Specifically, taking patient A as an example, the intelligent interaction module will execute an intelligent inquiry task, asking patient A: "Hello, the system detected that your blood pressure this morning was 162 / 98 mmHg, which is higher than the control target set by your doctor. To understand the specific situation, please answer the following questions:"

[0057] Did you take your blood pressure medication on time and in the correct dosage this morning?

[0058] Before measuring your blood pressure, were you sitting still and resting for at least 5 minutes?

[0059] Are you currently experiencing dizziness, headache, chest tightness, or palpitations?

[0060] Suppose patient A answers: "I took the medication, and before the measurement, I sat and watched the news for a while, maybe less than 5 minutes. Now I feel a little dizzy."

[0061] The intelligent interaction module extracts keywords such as "treasure taken," "before measurement," "watching the news," and "less than 5 minutes ago," and then asks the patient follow-up questions based on these keywords: "Did the news content cause you emotional fluctuations?"

[0062] Suppose patient A answers, "Yes."

[0063] The intelligent interaction module determines that the patient took the medication on time and in the correct dosage, and that the fluctuation in blood pressure was solely due to emotional fluctuations. It then provides the patient with the following advice: "We suggest you rest in a quiet environment for 10 minutes, and then immediately remeasure and record your blood pressure." After re-recording, patient A's blood pressure returned to within the threshold range, and no new intelligent inquiry task was triggered. Simultaneously, the intelligent interaction module generates a follow-up record based on the inquiry content: "At 8:00 AM, patient A's medication adherence was normal. The first blood pressure measurement was 162 / 98 mmHg, which was abnormal due to emotional fluctuations. A second measurement was performed 10 minutes later, and the blood pressure was 149 / 89 mmHg, which is normal." In this embodiment, the intelligent interaction module implements voice interaction functionality through a speaker 6 and a receiver 5.

[0064] like Figure 2 As shown, the intelligent interaction module includes a doctor interaction unit, a patient interaction unit, and an intelligent question-and-answer unit.

[0065] The doctor interaction unit allows doctors to view follow-up records and input supplementary inquiry tasks into the data analysis module based on these records. The intelligent interaction module executes these supplementary inquiry tasks and updates the follow-up records. In this embodiment, the doctor interaction unit is built on the doctor's computer.

[0066] Specifically, doctors can use the doctor interaction unit to select patient A from the patient list and view the follow-up records automatically generated and updated by the intelligent interaction module. The follow-up records are arranged according to the follow-up timeline and clearly include: the abnormal indicator that triggered this follow-up (blood pressure 162 / 98 mmHg), the complete multi-round question and answer text, the key information extracted by the intelligent interaction module, and the preliminary judgment and treatment suggestions generated by the intelligent interaction module.

[0067] The patient interaction unit allows patients to view their basic information, medical records, physical indicators, and follow-up records; it also allows patients to input questions. The patient interaction unit further allows patients to send doctor-patient interaction invitations to the doctor interaction unit, which are used for communication between doctors and patients via text, voice, and video. In this embodiment, the doctor interaction unit is built based on the patient's mobile phone.

[0068] Specifically, patients can clearly and systematically view their basic information, medical records, past physical indicators, and all historical follow-up records. The interface provides data filtering and search functions, making it easy for patients to track changes in specific time periods or specific indicators.

[0069] Each follow-up record's display page features a prominent "Questions about this record?" entry. Patients can click to enter and then freely input their questions in text or voice format. The questions will be submitted to the intelligent question-and-answer unit for resolution, and the answers will be saved as an appendix to the follow-up record.

[0070] When patients feel that the intelligent answering system cannot meet their needs, or when their condition undergoes an urgent change that requires immediate attention from a doctor, they can initiate a doctor-patient interaction invitation through the "Contact My Doctor" button within the patient interaction unit. This invitation is a structured request that includes the patient's identity, the time of initiation, and a brief, editable reason (such as "urgent consultation regarding this morning's blood pressure record"); the invitation will be pushed to the doctor interaction unit in real time.

[0071] The intelligent question answering unit is used to build an intelligent question answering model using deep learning algorithms; the intelligent question answering model is used to perform intelligent questioning tasks, intelligent follow-up questioning tasks, question supplementation tasks, and question answering tasks.

[0072] Specifically, in this embodiment, the intelligent question-answering model is built on the Transformer architecture. When the intelligent question-answering model receives an intelligent question-answering task from the data analysis module, it will parse the intelligent question-answering task, identify abnormal data, and thus determine the content of the inquiry. When executing the intelligent follow-up question task, the intelligent question-answering model will parse the content of the patient's answer and determine the content of the follow-up question based on the content of the patient's answer.

[0073] The data analysis module also includes a disease prediction unit, which is used to obtain curves of changes in physical indicators and follow-up records, extract the changes in the patient's physical indicators and keywords in the follow-up records, and build a disease prediction model. The disease prediction model is used to predict the patient's disease risk based on the changes and keywords in the follow-up records, and outputs an emergency risk warning for the patient.

[0074] Specifically, the disease prediction unit first obtains the change curves of physical indicators generated by the data statistics unit, and extracts the time-series changes of various key indicators of the patient, such as the diurnal fluctuation range of blood pressure and the slope of the seven-day moving average of blood sugar. At the same time, the disease prediction unit obtains the follow-up records generated by the intelligent question-answering unit, and uses natural language processing technology to perform entity recognition and keyword extraction on the text in the follow-up records. For example, it identifies keywords describing symptoms, medication adherence, and life status, such as "dizziness," "chest tightness," "forgetting to take medication," "insomnia," and "low mood."

[0075] Subsequently, the data fusion subunit within the disease prediction unit structurally correlates the extracted numerical features (indicator changes) with textual features (keywords) to generate a fused feature vector that comprehensively reflects the patient's physiological state and behavioral patterns. For example, this vector may simultaneously contain the correlation information of "systolic blood pressure elevation slope 15%" and "keyword: insomnia".

[0076] The disease prediction model takes historically collected fused feature vectors as input and is trained using pre-set clinical outcomes (such as "hypertensive crisis within one week" or "deterioration of blood sugar control within three months") as labels to learn the intrinsic relationship between feature changes and disease progression. The trained disease prediction model receives the current patient's fused feature vector in real time and outputs a prediction of the future disease condition (the probability of an acute event).

[0077] Doctors use a disease prediction model to preset emergency thresholds for various acute events (such as sudden rise in blood pressure or hypoglycemic coma). When the model analysis determines that the risk of a patient experiencing an acute event within a very short period (e.g., 24-72 hours) exceeds the preset emergency threshold, the disease prediction unit immediately generates an emergency risk warning. This emergency risk warning triggers the intelligent interaction module to initiate an emergency inquiry process, proactively confirming the patient's current status through the speaker 6 and receiver 5, and guiding them to take emergency measures (such as immediate medication, rest, and retesting). Simultaneously, the emergency risk warning is pushed to the doctor's interaction unit in real-time as a highlighted pop-up window, accompanied by an audible alert, ensuring the doctor is informed and intervenes immediately. For example, if the patient's interaction unit's microphone detects a "rapid breathing" vocalization in the patient's voice, combined with a recent blood pressure spike, and the model determines the risk to be extremely high, the aforementioned process will be immediately initiated.

[0078] This embodiment automatically identifies key indicators highly correlated with the patient's condition through a data analysis module and continuously monitors them to determine whether they exceed their threshold range. This allows for timely assessment of any abnormalities in these key indicators, thereby identifying potential risks to the patient's health. The intelligent inquiry module enables targeted questioning based on the patient's abnormal indicators, improving the effectiveness of the inquiry process. Simultaneously, the intelligent interaction module extracts key information from the initial inquiry and uses this information to follow up with further questions, uncovering more details and their potential connection to the patient's condition. This generates more detailed and complete follow-up records, significantly improving the accuracy and effectiveness of the follow-up.

[0079] Example 2:

[0080] The difference from Example 1 is that, as Figure 3As shown, the data analysis module also includes a data statistics unit. This unit generates a curve graph of changes in the patient's historical physical indicators and transmits it to the intelligent interaction module. The data statistics unit also bolds key indicators in the curve graph and highlights abnormal indicators in red.

[0081] Specifically, the horizontal axis of the change curve is time (time axis), and the vertical axis is the indicator value. Whenever the patient enters new indicator data, the chart will automatically expand the time axis and draw new indicator points, thereby achieving real-time updates. This allows doctors and patients to intuitively see the development trend and latest status of the disease.

[0082] The data statistics unit automatically thickens the curves of key indicators in all the change curves it generates, and marks abnormal indicators in red and normal indicators in black, so that doctors and patients can clearly observe abnormal indicators and the time periods in which they occur.

[0083] Example 3:

[0084] The difference from Example 2 is that, as Figure 5 As shown, the data acquisition module also includes a chassis 1, on which a blood analyzer 3 is mounted, and a blood pressure monitor 4 is mounted on one side of the chassis 1. The data acquisition module is used to collect the patient's physical indicators through the blood analyzer 3 and the blood pressure monitor 4.

[0085] like Figure 5 and Figure 7 As shown, in this embodiment, a touch screen 2 is also installed on the top of the chassis 1, and the patient interaction unit realizes data input and display based on the touch screen 2.

[0086] like Figure 5 and Figure 6 As shown, in this embodiment, the loudspeaker 6 and the microphone 5 are bolted to the outer wall of the chassis 1, and the intelligent inquiry module realizes the voice interaction function based on the loudspeaker 6 and the microphone 5.

[0087] Users can achieve multiple functions such as body indicator collection, intelligent Q&A, remote follow-up, data monitoring and query through the integrated design of chassis 1. Moreover, the collected body indicators will be uploaded to the data collection module in real time to avoid data loss, thereby ensuring the accuracy and effectiveness of follow-up.

[0088] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A portable follow-up device for clinical data statistics, characterized in that, This includes an intelligent follow-up system, which comprises a data acquisition module, a data analysis module, and an intelligent interaction module. The data acquisition module is used to collect patients' basic information, medical records, and physical indicators, and to associate and store these information to generate a patient database. The patient database is used for retrieval by the data analysis module and the intelligent interaction module. The data analysis module is used to analyze key indicators based on patient case information and physical indicators, generate regular testing tasks based on key indicators, and transmit the regular testing tasks to the data acquisition module; it also generates indicator statistics based on the patient's physical indicators and key indicators, and transmits the indicator statistics to the intelligent interaction module. The data analysis module is also used to allow doctors to set range thresholds for key indicators, determine whether key indicators exceed their range thresholds, mark key indicators that exceed their range thresholds as abnormal indicators, generate intelligent inquiry tasks based on abnormal indicators, and transmit intelligent inquiry tasks to the intelligent interaction module. The intelligent interaction module is used to receive intelligent inquiry tasks, conduct inquiries with patients based on the intelligent inquiry tasks, analyze the inquiry content, extract key information, generate preliminary judgment results and treatment suggestions, and generate intelligent follow-up inquiry tasks based on the preliminary judgment results and treatment suggestions. The module then conducts follow-up inquiries with patients based on the intelligent follow-up inquiry tasks, analyzes the follow-up inquiry content, extracts key information, updates the judgment results and treatment suggestions, and generates follow-up records. The data analysis module is also used to predict a patient's risk of developing a disease based on the patient's physical indicators and follow-up records.

2. The portable follow-up device for clinical data statistics according to claim 1, characterized in that, The intelligent interaction module is also used to allow doctors to view follow-up records and input supplementary inquiry tasks into the data analysis module based on the follow-up records. The intelligent interaction module is used to execute the supplementary inquiry tasks and update the follow-up records.

3. The portable follow-up device for clinical data statistics according to claim 1, characterized in that, The intelligent interaction module is also used to display follow-up records to patients, allowing them to ask questions based on the records, and to answer those questions.

4. The portable follow-up device for clinical data statistics according to claim 1, characterized in that, The intelligent interaction module includes an intelligent question-answering unit, which is used to build an intelligent question-answering model through deep learning algorithms; the intelligent question-answering model is used to perform intelligent inquiry tasks, intelligent follow-up questions tasks, inquiry supplementation tasks, and question answering.

5. The portable follow-up device for clinical data statistics according to claim 1, characterized in that, The intelligent interaction module also includes a doctor interaction unit and a patient interaction unit; The doctor interaction unit allows doctors to view patients' basic information, medical records, physical indicators, and follow-up records; it also allows doctors to input supplementary questions, adjust judgment results, and treatment suggestions. The patient interaction unit allows patients to view their basic information, medical records, physical indicators, and follow-up records. It is also used for patients to input their questions.

6. The portable follow-up device for clinical data statistics according to claim 5, characterized in that, The patient interaction unit is also used to allow patients to send doctor-patient interaction invitations to the doctor interaction unit, which are used for doctors and patients to communicate via text, voice, and video.

7. The portable follow-up device for clinical data statistics according to claim 1, characterized in that, The data analysis module includes a task setting unit, a data statistics unit, and a disease prediction unit; The task formulation unit is used to analyze patient case information, identify patient conditions, analyze key physical indicators related to the patient's condition, and generate periodic testing tasks for key indicators. The data statistics unit is used to generate a curve of changes in the patient's historical physical indicators and transmit the curve to the intelligent interaction module. The disease prediction unit is used to obtain curves of changes in physical indicators and follow-up records, extract the changes in the patient's physical indicators and keywords in the follow-up records, and build a disease prediction model. The disease prediction model is used to predict the patient's disease risk based on the changes and keywords in the follow-up records, and outputs an emergency risk warning for the patient.

8. The portable follow-up device for clinical data statistics according to claim 7, characterized in that, The data statistics unit is also used to bold key indicators in the change curve and highlight abnormal indicators in the change curve in red.

9. The portable follow-up device for clinical data statistics according to claim 7, characterized in that, The task setting unit also allows doctors to adjust the content and frequency of routine testing tasks.

10. The portable follow-up device for clinical data statistics according to claim 1, characterized in that, The data acquisition module also includes a chassis (1), on which a blood analyzer (3) is installed, and on one side of the chassis (1) a blood pressure monitor (4); the data acquisition module is used to collect the patient's physical indicators through the blood analyzer (3) and the blood pressure monitor (4).

Images