Risk prediction abstention in patient monitoring

EP4771647A1Pending Publication Date: 2026-07-08KONINKLIJKE PHILIPS NV
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
EP · EP
Patent Type
Applications
Current Assignee / Owner
KONINKLIJKE PHILIPS NV
Filing Date
2024-08-21
Publication Date
2026-07-08

AI Technical Summary

Technical Problem

Existing machine learning risk prediction models in patient monitoring struggle with varying reliability of individual predictions due to a predetermined decision threshold calibrated for population-level performance, leading to inconsistent treatment recommendations and fluctuations in prediction confidence over time.

Method used

A computer-implemented method that combines a machine learning risk prediction model with a confidence prediction model to generate a risk score and a confidence interval for each prediction, allowing for real-time determination of whether to include or withhold the risk score from a data series based on the confidence interval and risk classification.

Benefits of technology

This approach enhances the reliability of patient monitoring data series by selectively including or excluding risk scores based on confidence intervals, thereby reducing false positives and false negatives and improving clinical decision-making.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure EP2024073491_06032025_PF_FP_ABST
    Figure EP2024073491_06032025_PF_FP_ABST
Patent Text Reader

Abstract

A method for real time determination as to whether a prediction model output should be included or withheld from a real time data series based on a combination of a confidence interval associated with the prediction model output and a classification of the prediction model output.
Need to check novelty before this filing date? Find Prior Art