US 12,339,873 B2
Incremental clustering and hierarchy formation system for clinical decision support (CDS) system development and method of operation thereof
Ali Akbar Ahmad Samadani, Cambridge, MA (US); Taiyao Wang, Cambridge, MA (US); and Cornelis van Zon, Cambridge, MA (US)
Assigned to Koninklijke Philips N.V., Eindhoven (NL)
Filed by KONINKLIJKE PHILIPS N.V., Eindhoven (NL)
Filed on Nov. 1, 2022, as Appl. No. 17/978,482.
Claims priority of provisional application 63/291,528, filed on Dec. 20, 2021.
Prior Publication US 2023/0197287 A1, Jun. 22, 2023
Int. Cl. G06F 17/00 (2019.01); G06F 16/28 (2019.01); G06F 18/23 (2023.01); G06F 18/2413 (2023.01); G16H 10/60 (2018.01); G16H 50/70 (2018.01)
CPC G06F 16/285 (2019.01) [G06F 18/23 (2023.01); G06F 18/24147 (2023.01); G16H 10/60 (2018.01); G16H 50/70 (2018.01)] 20 Claims
OG exemplary drawing
 
1. A clinical decision support (CDS) system, comprising:
at least one controller, the at least one controller including at least one microprocessor and being configured to communicate with a plurality of hospital servers, the at least one controller being further configured to:
extract, via the plurality of hospital servers, electronic health records (EHRs) of a plurality of hospitals of an initial hospital group (IHG) in accordance with at least one of a selected target patient population (TPP) and selected physiological measurements of interest (SMs) to form a target patient dataset;
compute patient level features of the target patient dataset capturing a time interval between each subsequent record for each of the measurements defined by the SMs;
compute hospital level features of the target patient dataset comprising statistics descriptive of the distribution of the captured time intervals for each of the measurements defined by the SM in the computed patient level features;
cluster the plurality of hospitals of the IHG in accordance with the computed hospital level features into a plurality of clusters (CL);
determine whether another hospital is within a threshold distance (d) to a closest one of the plurality of clusters;
place the other hospital in the closest cluster when it is determined that the other hospital is within the threshold distance to the closest one of the plurality of clusters; and
place the other hospital in a new cluster of the plurality of clusters when it is determined that the other hospital is not within the threshold distance to the closest one of the plurality of clusters.