US 11,883,228 B2
Smart stethoscopes
Anurag Agarwal, Cambridgeshire (GB); Edmund Kay, Cambridgeshire (GB); and Andrew McDonald, Cambridgeshire (GB)
Assigned to CAMBRIDGE ENTERPRISE LIMITED, Cambridge (GB)
Appl. No. 16/978,932
Filed by Cambridge Enterprise Limited, Cambridgeshire (GB)
PCT Filed Feb. 20, 2019, PCT No. PCT/GB2019/050461
§ 371(c)(1), (2) Date Sep. 8, 2020,
PCT Pub. No. WO2019/171021, PCT Pub. Date Sep. 12, 2019.
Claims priority of application No. 1803805 (GB), filed on Mar. 9, 2018.
Prior Publication US 2021/0169442 A1, Jun. 10, 2021
Int. Cl. A61B 7/04 (2006.01); A61B 5/00 (2006.01)
CPC A61B 7/04 (2013.01) [A61B 5/7264 (2013.01)] 21 Claims
OG exemplary drawing
 
1. A method of processing acoustic heart signal data, the method comprising:
capturing time series acoustic heart signal data from a patient, the time series acoustic heart signal data representing the sound of the patient's heart;
classifying the time series acoustic heart signal data into a plurality of heart sound categories to provide time series sound category data, wherein the time series sound category data comprises, for each of a plurality of time intervals, category probability data representing a probability of the acoustic heart signal for the time interval falling into each of the heart sound categories;
fitting the time series sound category data to a heart state model having a sequence of heart states with associated heart sounds corresponding to the heart sound categories and adjustable durations of the states, to determine timings of the sequence of states;
determining, from the timings of the sequence of states and corresponding category probability data, a confidence value for the model fit; and
outputting one or both of a model fit indication dependent upon the confidence value, and data identifying timings of the sequence of states.