CN-122004788-A - Cerebral apoplexy risk prediction system and computer device applied to uremic patients

CN122004788ACN 122004788 ACN122004788 ACN 122004788ACN-122004788-A

Abstract

The embodiment of the disclosure provides a cerebral apoplexy risk prediction system and a computer device applied to uremic patients, wherein the cerebral apoplexy risk prediction system and the computer device comprise an acquisition unit, a first prediction unit, a second prediction unit and a switching unit, wherein the acquisition unit is used for respectively acquiring basic physiological index data, first real-time physiological data, dialysis effect data and a second real-time physiological data set, the first prediction unit predicts a first cerebral apoplexy occurrence risk value in a dialysis process through a first prediction model, the second prediction unit is input into a second prediction model to predict a second cerebral apoplexy occurrence risk value, and the switching unit is used for correspondingly switching in response to a switching signal representing the entering or exiting of the dialysis process. By adopting different prediction models in stages, the cerebral apoplexy risk is respectively predicted according to the difference of physiological data changes of uremic patients in the dialysis process and after the dialysis is finished, and further the timeliness and the accuracy of risk prediction are improved.

Inventors

YU CHUNLI
SUN WENJUAN
TAO LINGLING
TANG DINGZHONG
LIU KUN
YAO WEIGUO

Assignees

上海市第六人民医院金山分院(上海健康医学院附属金山区中心医院、上海市金山区中心医院)

Dates

Publication Date: 20260512
Application Date: 20260407

Claims (9)

1. A stroke risk prediction system for uremic patients, comprising: The acquisition unit is used for respectively acquiring basic physiological index data of the uremic patient, which are related to the cerebral apoplexy incidence risk, first real-time physiological data in the dialysis process, dialysis effect data after the dialysis is finished and second real-time physiological data sets in a first preset time period after the dialysis is finished, wherein the first real-time physiological data comprise blood pressure; The first prediction unit is connected with the acquisition unit and is used for predicting a first cerebral apoplexy occurrence risk value of a uremic patient in the dialysis process through a first prediction model according to the basic physiological index data and the first real-time physiological data and sending the first cerebral apoplexy occurrence risk value to a preset user; The second prediction unit is connected with the acquisition unit and is used for inputting the dialysis effect data and the second real-time physiological data set into a second prediction model to predict and obtain a second cerebral apoplexy occurrence risk value of the uremic patient in a prediction time period and send the second cerebral apoplexy occurrence risk value to the preset user, wherein the prediction time period is determined based on the dialysis period of the uremic patient; And the switching unit is respectively connected with the first prediction unit and the second prediction unit, and correspondingly switches the first prediction unit or the second prediction unit to be used in response to a switching signal representing the entering or exiting of the dialysis process.
2. The stroke risk prediction system according to claim 1, wherein the switching unit comprises: the system comprises an interface module, a signal interface, a control module and a control module, wherein the signal interface is directly or indirectly connected with a dialysis machine through a communication link to generate the switching signal based on receiving a start-stop signal of the dialysis machine, or is configured to allow acquisition of the switching signal generated by input actions of a preset user; And the execution module is respectively connected with the interface module, the first prediction unit and the second prediction unit and is used for respectively starting the first prediction unit or starting the second prediction unit according to the switching signal.
3. The stroke risk prediction system of claim 1, wherein the acquiring the base physiological index data of the uremic patient associated with the risk of developing a stroke, the first real-time physiological data during dialysis, the dialysis effect data after dialysis is completed, and the second real-time physiological data set within the first predetermined time period after dialysis is completed comprises: Responding to the acquisition operation of the identification of the uremic patient, and acquiring the basic physiological index data associated with the identification; Responding to the association operation of the identity mark and the dialysis machine, and associating and outputting first real-time physiological data output by the dialysis machine with the identity mark; And after the dialysis process is finished, acquiring the dialysis effect data and the second real-time physiological data output by the real-time acquisition device bound with the identity mark to form the second real-time physiological data set.
4. The stroke risk prediction system according to claim 1, wherein the acquisition unit further comprises a behavior acquisition module, wherein an acquisition range of the behavior acquisition module covers the uremic patient for acquiring state data of the uremic patient, and wherein the state data at least comprises one of posture data of the uremic patient and face data of the uremic patient.
5. The stroke risk prediction system of claim 4, wherein the first real-time physiological data comprises the status data and/or the second real-time physiological data comprises the status data.
6. The stroke risk prediction system of claim 1, wherein the base physiological index data comprises a result of encoding at least one of blood beta 2-microglobulin concentration, frequency of anti-embolic drug use, leukoencephalopathy data, past history of stroke.
7. The stroke risk prediction system of claim 1, wherein the first real-time physiological data further comprises a real-time heart rate and/or the second real-time physiological data further comprises a real-time heart rate.
8. The stroke risk prediction system according to claim 1, wherein the dialysis effect data comprises at least one or more of urea removal index, dialysis adequacy index, electrolyte balance data, total dehydration amount.
9. A computer apparatus, comprising: A processor and a memory; the memory stores program instructions; The processor for executing the program instructions to run a stroke risk prediction system according to any one of claims 1-9.

Description

Cerebral apoplexy risk prediction system and computer device applied to uremic patients Technical Field The present disclosure relates to the field of medical health monitoring, and in particular, to a stroke risk prediction system and a computer device for uremic patients. Background Uremic patients, due to severely impaired renal function, need long-term hemodialysis treatment to maintain stable internal environments. However, the population is also a high-risk population for cerebral apoplexy, and the risk of cerebral apoplexy is obviously higher than that of the common population. Notably, the pathophysiological mechanisms of stroke in uremic patients during dialysis are distinct from those of stroke after dialysis is completed, making it difficult for traditional single risk assessment models to effectively cover full-cycle risk. In the dialysis process, patients often suffer from acute blood pressure fluctuation (such as dialysis hypotension or abnormal hypertension) due to factors such as too fast ultrafiltration, rapid blood volume reduction, impaired blood vessel autonomous regulation function, and the like, thereby causing cerebral perfusion insufficiency or cerebral vascular rupture, and causing ischemic or hemorrhagic cerebral apoplexy. After the end of the dialysis (usually within hours to days after the end of the dialysis), the risk of cerebral apoplexy is mainly caused by factors such as insufficient dialysis sufficiency, residual toxin accumulation, electrolyte rebound, chronic inflammation activation, and circadian rhythm disorder of blood pressure. At this time, stroke risk is more related to the dialysis effect index and dynamic physiological data in a short period after dialysis, and is characterized by accumulation and delay. In the related art, the adaptive prediction logic cannot be automatically switched according to whether the patient is in a dialysis state or a post-dialysis state, so that risk early warning is delayed or misjudgment is caused. Disclosure of Invention In view of the above-described drawbacks of the prior art, an object of the present disclosure is to provide a stroke risk prediction system and a computer for uremic patients, which solve the problems in the related art. A first aspect of the present disclosure provides a stroke risk prediction system for uremic patients, comprising: The acquisition unit is used for respectively acquiring basic physiological index data of the uremic patient, which are related to the cerebral apoplexy incidence risk, first real-time physiological data in the dialysis process, dialysis effect data after the dialysis is finished and second real-time physiological data sets in a first preset time period after the dialysis is finished, wherein the first real-time physiological data comprise blood pressure; The first prediction unit is connected with the acquisition unit and is used for predicting a first cerebral apoplexy occurrence risk value of a uremic patient in the dialysis process through a first prediction model according to the basic physiological index data and the first real-time physiological data and sending the first cerebral apoplexy occurrence risk value to a preset user; The second prediction unit is connected with the acquisition unit and is used for inputting the dialysis effect data and the second real-time physiological data set into a second prediction model to predict and obtain a second cerebral apoplexy occurrence risk value of the uremic patient in a prediction time period and send the second cerebral apoplexy occurrence risk value to the preset user, wherein the prediction time period is determined based on the dialysis period of the uremic patient; And the switching unit is respectively connected with the first prediction unit and the second prediction unit, and correspondingly switches the first prediction unit or the second prediction unit to be used in response to a switching signal representing the entering or exiting of the dialysis process. In an embodiment of the first aspect, the switching unit includes: the system comprises an interface module, a signal interface, a control module and a control module, wherein the signal interface is directly or indirectly connected with a dialysis machine through a communication link to generate the switching signal based on receiving a start-stop signal of the dialysis machine, or is configured to allow acquisition of the switching signal generated by input actions of a preset user; And the execution module is respectively connected with the interface module, the first prediction unit and the second prediction unit and is used for respectively starting the first prediction unit or starting the second prediction unit according to the switching signal. In an embodiment of the first aspect, the acquiring basic physiological index data of the uremic patient associated with a risk of developing cerebral apoplexy, first real-time physiological data during dialysis, dialys