Method for predicting a future health status of a patient
CA3329071A1Pending Publication Date: 2025-12-26BITS2BEAT
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CA3329071
- Authority / Receiving Office
- CA · CA
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2025-06-18
- Filing Date
- 2025-06-18
- Publication Date
- 2025-12-26
Abstract
The invention relates to a method for predicting a patient's future health state from at least one signal (rPPG P), comprising the following steps: (E2) classification of the type of noise contained in said signal; (E3) extraction of a data sequence (RR) relating to the heart rhythm by a filtering algorithm parameterized using the result of said noise type classification; (E4, E41, E42, E43) extraction of features (S i,j , DL , P(W)) from multi-scale, lexicographic and data density distribution representations of said data sequence; (E5) classification of the signal into classes (C 1 , CN ) of rhythms from said extracted features; (E6) prediction, according to a given autoregression model (DGP) and from said class (C k ) of the signal, of a probability (P k ) of a future health state of said patient.
Need to check novelty before this filing date? Find Prior Art
