System and method for optimization in a pareto sense of automated abnormal biological event detection and abatement

Patent metadata

Field	Value
Publication number	US-12514490-B2
Application number	US-202318496777-A
Country	US
Kind code	B2
Filing date	Oct 27, 2023
Priority date	Nov 19, 2019
Publication date	Jan 6, 2026
Grant date	Jan 6, 2026

Abstract

A system and method for finding a Pareto-optimal solution for automated detection, warning, and abatement of a medical condition based on a cost of event intervention in a patient is disclosed. The method includes acquiring at least one biological signal from the patient via at least one sensor of a medical device, detecting an abnormal biological event based on changes in the biological signal, and delivering at least one of a therapy and a warning. The method includes logging a set of parameters including at least one of a detection parameter, a therapy parameter, and a therapy modality. The method includes finding an optimal set of parameters that yield a Pareto-optimal cost of event intervention by iteratively determining at least one metric over a time window, determining the cost of event intervention, and modifying at least one parameter, until the cost of event intervention meets an acceptability criteria.

First claim

What is claimed is:

1 . A method for finding a Pareto-optimal solution for automated detection, warning, and abatement of a medical condition based on a cost of event intervention in a patient, the method comprising:
acquiring at least one biological signal from the patient via at least one sensor of a medical device, the at least one biological signal comprising at least one of a cardio-vascular signal, a respiratory signal, a dermal signal, an endocrine signal, a metabolic signal, a kinetic signal, and a cerebral signal; detecting, via the medical device, an abnormal biological event based on changes in the at least one biological signal; delivering, via the medical device, at least one of a therapy and a warning in response to detection of the abnormal biological event; logging to a memory a set of parameters applied as part of detecting, warning, and abating the abnormal biological event, the set of parameters comprising at least one of a detection parameter, a therapy parameter, and a therapy modality; and finding an optimal set of parameters resulting in such that the cost of event intervention being Pareto-optimal, wherein the optimal set of parameters is at least a subset of the set of parameters and is found by iteratively: collecting and determining at least one metric over a time window, determining the cost of event intervention based on the at least one metric, and modifying at least one parameter of the set of parameters, until the cost of event intervention meets an acceptability criteria; wherein the cost of event intervention is based on at least one of a cost of detection, a cost of treatment, and a cost of injuries.

2 . The method of claim 1 , wherein the at least one metric comprises a qualitative assessment of the quality of life of the patient during the time window.

3 . The method of claim 2 , wherein collecting and determining the qualitative assessment of the quality of life comprises sending an inquiry regarding the quality of life to a mobile device associated with the patient and receiving an answer to the inquiry from the patient via the mobile device.

4 . The method of claim 1 , wherein the at least one metric is selected from the group consisting of: a time elapsed between onset of the abnormal biological event and the delivery of the treatment, and an efficacy of the therapy.

5 . The method of claim 1 , wherein the at least one metric is selected from the group consisting of: a false positive detection rate, and a false negative detection rate.

6 . The method of claim 1 , wherein the at least one metric is selected from the group consisting of: an adverse event rate, an adverse event type, an adverse event severity, and an adverse event timestamp.

7 . The method of claim 1 , wherein the at least one metric comprises an optimization efficiency based upon a total number of available treatment modalities.

8 . The method of claim 1 , wherein the cost of event intervention is based on at least one of a warning efficiency, an optimization efficiency, an adaptation efficiency, a seizure burden per unit time, an efficacy of electrical stimulation as a function of total electrical energy delivered/unit time, a time spent in detection, a time spent in warning, and a time spent in treatment.

9 . The method of claim 1 , wherein the abnormal biological event is a seizure, and the medical condition is at least one of cardiac arrhythmia, fainting, and pain.

10 . A medical device system for finding a Pareto-optimal solution for automated detection, warning, and abatement of a medical condition based on a cost of event intervention in a patient, the system comprising:
at least one sensor, a therapy delivery device, and a medical device having an output device, a processor, and a memory, the medical device configured to: acquire at least one biological signal from a patient using the at least one sensor, the at least one biological signal comprising at least one of a cardio-vascular signal, a respiratory signal, a dermal signal, an endocrine signal, a metabolic signal, a kinetic signal, and a cerebral signal; detect an abnormal biological event based on changes in the at least one biological signal; deliver at least one of a therapy using the therapy delivery device and a warning using the output device, in response to detection of the abnormal biological event; log to a memory a set of parameters applied as part of detecting, warning, and abating the abnormal biological event, the set of parameters comprising at least one of a detection parameter, a therapy parameter, and a therapy modality; and find an optimal set of parameters resulting in such that the cost of event intervention being Pareto-optimal, wherein the optimal set of parameters is at least a subset of the set of parameters and is found by iteratively: collecting and determining at least one metric over a time window, determining the cost of event intervention based on the at least one metric, and modifying at least one parameter of the set of parameters, until the cost of event intervention meets an acceptability criteria; wherein the cost of event intervention is based on at least one of a cost of detection, a cost of treatment, and a cost of injuries.

11 . The system of claim 10 , wherein the at least one metric comprises a qualitative assessment of the quality of life of the patient during the time window.

12 . The system of claim 11 :
wherein the medical device is communicatively coupled to a mobile device associated with the patient through a network; and wherein collecting and determining the qualitative assessment of the quality of life comprises sending an inquiry regarding the quality of life to the mobile device and receiving an answer to the inquiry from the patient via the mobile device.

13 . The system of claim 10 , wherein the at least one metric is selected from the group consisting of: a time elapsed between onset of the abnormal biological event and the delivery of the treatment, and an efficacy of the therapy.

14 . The system of claim 10 , wherein the at least one metric is selected from the group consisting of: a false positive detection rate, and a false negative detection rate.

15 . The system of claim 10 , wherein the at least one metric is selected from the group consisting of: an adverse event rate, an adverse event type, an adverse event severity, and an adverse event timestamp.

16 . The system of claim 10 , wherein the at least one metric comprises an optimization efficiency based upon a total number of available treatment modalities.

17 . The system of claim 10 , wherein the cost of event intervention is based on at least one of a warning efficiency, an optimization efficiency, an adaptation efficiency, a seizure burden per unit time, an efficacy of electrical stimulation as a function of total electrical energy delivered/unit time, a time spent in detection, a time spent in warning, and a time spent in treatment.

18 . The system of claim 10 , wherein the abnormal biological event is a seizure, and the medical condition is at least one of cardiac arrhythmia, fainting, and pain.

Assignees

• Osorio Ivan

Inventors

• Osorio Ivan

Classifications

• A61B5/746

  Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms · CPC title

• A61B5/4836

  Diagnosis combined with treatment in closed-loop systems or methods (A61B5/0036 takes precedence) · CPC title

• A61B5/002 Primary

  Monitoring the patient using a local or closed circuit, e.g. in a room or building (A61B5/0017 takes precedence) · CPC title

• A61B5/4094 Primary

  Diagnosing or monitoring seizure diseases, e.g. epilepsy · CPC title