Computer implementation methods, computer systems, and computer program products (patient monitoring and treatment using implantable biosensors)

Abstract

To provide a computer system that provides patient monitoring and treatment using implanted biosensors.SOLUTION: Data associated with a target joint of a patient is collected via one or more implanted biosensors. Multiple feature values are extracted from the data. The multiple feature values are processed using a trained classification model to select a recommendation. The recommendation is provided to mitigate hemophilia-related injury to the target joint. Embodiments of the present invention further include a method and a program product for providing patient monitoring and treatment using implanted biosensors in substantially the same manner as the above.SELECTED DRAWING: Figure 6

Claims

1. A computer implementation method for monitoring and treating patients using an implanted biosensor, wherein the computer implementation method is The steps include: collecting data related to the patient's target joint via one or more implanted biosensors; The steps include extracting multiple feature values ​​from the aforementioned data, The process involves processing the multiple feature values ​​using a trained classification model to generate an output indicating the state or recommendation of the target joint based on the multiple feature values, and selecting the recommendation based on the output. The step of providing the recommendations to mitigate the damage to the target joint associated with hemophilia. A computer implementation method comprising the following features.

2. The computer implementation method according to claim 1, wherein the data includes one or more of the following: circulatory system data, mechanical data, and synovial fluid data.

3. Before extracting the aforementioned multiple feature values, A machine learning model is applied to identify the threshold values ​​for one or more parameters of the aforementioned data. Discard any data for each parameter that falls outside the threshold identified for that parameter. The computer implementation method according to claim 1, wherein data cleansing is performed on the data as a result.

4. The computer implementation method according to claim 1, wherein the plurality of feature values ​​extracted from the aforementioned data include one or more from the group of the following: rate of change in osteoarthritis stage, rate of change in temperature, rate of change in cartilage stress distribution, rate of change in synovial fluid pressure, rate of change in antihemophilia factor, rate of change in Bethesda units, rate of change in hemoglobin, and rate of change in blood density in synovial fluid.

5. The computer implementation method according to claim 1, wherein the trained classification model includes an extreme gradient boosting model.

6. The computer implementation method according to claim 1, wherein the recommendations include one or more from the group of physiotherapy procedures, periosteectomy procedures, suggestions to perform surgery on the target joint after a specified time, antihemophilia factor replacement therapy, medical procedures to increase hemoglobin levels, and blood transfusion procedures.

7. The computer implementation method according to any one of claims 1 to 6, further comprising the step of updating the trained classification model based on the results of applying the recommendation to the target joint.

8. A computer system for monitoring and treating patients using an implanted biosensor, wherein the computer system is One or more computer processors, One or more computer-readable storage media, Program instructions for execution by at least one of the one or more computer processors, stored in the one or more computer-readable storage medium. The program instructions include Data related to the patient's target joint is collected via one or more implantable biosensors. Multiple feature values ​​are extracted from the aforementioned data, A pre-trained classification model is used to process the multiple feature values ​​to generate an output indicating the state or recommendation of the target joint based on the multiple feature values, and a recommendation is selected based on the output. The recommendations are provided to mitigate the damage to the target joint associated with hemophilia. A computer system that contains instructions.

9. The computer system according to claim 8, wherein the data includes one or more of circulatory system data, mechanical data, and synovial fluid data.

10. Before extracting the aforementioned multiple feature values, A machine learning model is applied to identify the threshold values ​​for one or more parameters of the aforementioned data. Discard any data for each parameter that falls outside the threshold identified for that parameter. The computer system according to claim 8, wherein data cleansing is performed on the data as a result.

11. The computer system according to claim 8, wherein the plurality of feature values ​​extracted from the aforementioned data include one or more from the group of the following: rate of change in osteoarthritis stage, rate of change in temperature, rate of change in cartilage stress distribution, rate of change in synovial fluid pressure, rate of change in antihemophilia factor, rate of change in Bethesda units, rate of change in hemoglobin, and rate of change in blood density in synovial fluid.

12. The computer system according to claim 8, wherein the trained classification model includes an extreme gradient boosting model.

13. The computer system according to claim 8, wherein the recommendations include one or more from the group of physiotherapy procedures, periosteectomy procedures, suggestions to perform surgery on the target joint after a specified time, antihemophilia factor replacement therapy, medical procedures to increase hemoglobin levels, and blood transfusion procedures.

14. The aforementioned program instructions further include: The computer system according to any one of claims 8 to 13, comprising an instruction to update the trained classification model based on the results of applying the recommendation to the target joint.

15. A computer program for monitoring and treating patients using an implanted biosensor, wherein the computer program comprises one or more computer-readable storage media having a collection of program instructions embodied therewith, and the program instructions, which are executable by the computer, Data related to the patient's target joint is collected via one or more implantable biosensors. Multiple feature values ​​are extracted from the aforementioned data, Using a trained classification model, process the multiple feature values ​​and generate an output indicating the state or recommendation of the target joint based on the multiple feature values, and select the recommendation based on the output. A computer program that provides the recommendations for reducing damage to the target joint associated with hemophilia.

16. The computer program according to claim 15, wherein the data includes one or more of circulatory system data, mechanical data, and synovial fluid data.

17. Before extracting the aforementioned multiple feature values, A machine learning model is applied to identify the threshold values ​​for one or more parameters of the aforementioned data. Discard any data for each parameter that falls outside the threshold identified for that parameter. The computer program according to claim 15, wherein data cleansing is performed on the data as a result.

18. The computer program according to claim 15, wherein the plurality of feature values ​​extracted from the aforementioned data include one or more from the group of the following: rate of change in osteoarthritis stage, rate of change in temperature, rate of change in cartilage stress distribution, rate of change in synovial fluid pressure, rate of change in antihemophilia factor, rate of change in Bethesda units, rate of change in hemoglobin, and rate of change in blood density in synovial fluid.

19. The computer program according to claim 15, wherein the trained classification model includes an extreme gradient boosting model.

20. The computer program according to any one of claims 15 to 19, wherein the recommendations include one or more from the group of physiotherapy procedures, periosteectomy procedures, suggestions to perform surgery on the target joint after a specified time, antihemophilia factor replacement therapy, medical procedures to increase hemoglobin levels, and blood transfusion procedures.

Images