Methods and systems for patient baseline estimation

Patent metadata

Field	Value
Publication number	US-11925474-B2
Application number	US-202016919154-A
Country	US
Kind code	B2
Filing date	Jul 2, 2020
Priority date	Aug 22, 2019
Publication date	Mar 12, 2024
Grant date	Mar 12, 2024

Abstract

The present disclosure is directed to systems and methods for developing an individual-specific patient baseline for a target patient. An exemplary method involves: determining one or more acuity scores for the target patient; identifying patient health data corresponding to one or more low acuity time periods; storing retrospective clinical data from a group of patients in a second database; comparing the patient health data corresponding to the one or more low acuity time periods with retrospective clinical data from a group of patients by identifying one or more patient subgroups; determining the individual-specific patient baseline using an adaptive baseline selection algorithm, wherein the adaptive baseline selection algorithm is used to determine whether to determine the individual-specific patient baseline using patient health data or using retrospective clinical data from one or more patient subgroups; and displaying, using a user interface, the individual-specific patient baseline.

First claim

The invention claimed is:

1. A computer implemented method for developing an individual-specific patient baseline for a target patient, comprising:
determining one or more acuity scores for the target patient, wherein the one or more acuity scores vary based on time;
identifying one or more low acuity time periods corresponding to one or more low acuity scores;
retrieving patient health data from the target patient regarding one or more health factors;
identifying, from the retrieved patient health data, patient health data corresponding to the one or more low acuity time periods;
storing the patient health data identified as corresponding to the one or more low acuity time periods in a first database;
storing retrospective clinical data from a group of patients regarding at least the one or more health factors in a second database;
comparing the patient health data identified as corresponding to the one or more low acuity time periods with retrospective clinical data from a group of patients regarding the one or more health factors by identifying one or more patient subgroups, wherein the one or more patient subgroups are subgroups of the group of patients;
determining the individual-specific patient baseline using an adaptive baseline selection algorithm based on the patient health data or the retrospective clinical data, wherein the adaptive baseline selection algorithm determines whether to calculate the individual-specific patient baseline using the patient health data or using the retrospective clinical data from one or more patient subgroups; and
displaying, using a user interface, the individual-specific patient baseline.

2. The method of claim 1 , wherein the one or more acuity scores are determined using general acuity scoring systems or disease specific scoring systems.

3. The method of claim 1 , wherein one or more patient subgroups are identified using patient similarity measures or generic clustering algorithms.

4. The method of claim 1 , wherein the individual-specific patient baseline is determined using retrospective clinical data from one or more patient subgroups by averaging baselines from the one or more patient subgroups or by computing a weighted average baseline from two or more patient subgroups.

5. The method of claim 1 , wherein the adaptive baseline selection algorithm utilizes an average length of medical treatment amongst members of the one or more patient subgroups as a factor to determine whether to determine the individual-specific patient baseline using patient health data or using retrospective clinical data from the one or more patient subgroups.

6. The method of claim 5 , wherein if a length of medical treatment of the target patient is more than 25 percent of the average length of medical treatment amongst members of the one or more patient subgroups, the individual-specific patient baseline is determined using patient health data.

7. The method of claim 1 ,
wherein the individual-specific patient baseline is determined using the patient health data if a variance in the retrospective clinical data of the one or more subgroups is less than a variance threshold or wherein the individual-specific patient baseline is determined using the patient health data if a population size of the one or more subgroups is less than a size threshold.

8. The method of claim 1 , wherein the individual-specific patient baseline is determined using the patient health data if a difference between a centroid of a patient subgroup of the one or more patient subgroups and a centroid of a neighboring subgroup is less than a centroid threshold, wherein the neighboring subgroup is a neighboring cluster on a similarity clustering graph.

9. A system for developing individual-specific patient baselines for a target patient, comprising:
a first database in which patient health data corresponding to one or more low acuity time periods corresponding to one or more low acuity scores is stored;
a second database in which retrospective clinical data from a group of patients regarding at least one or more health factors is stored;
a processor configured to:
compare the patient health data corresponding to the one or more low acuity time periods with the retrospective clinical data from the group of patients regarding the one or more health factors by identifying one or more patient subgroups, wherein the one or more patient subgroups are subgroups of the group of patients; and
determine the individual-specific patient baseline using an adaptive baseline selection algorithm based on the patient health data or the retrospective clinical data, wherein the adaptive baseline selection algorithm determines whether to calculate the individual-specific patient baseline using the patient health data or using the retrospective clinical data from one or more patient subgroups; and

a user interface configured to display the individual-specific patient baseline.

10. The system of claim 9 , wherein the one or more acuity scores are determined using general acuity scoring systems or disease specific scoring systems.

11. The system of claim 9 , wherein the processor is further configured to identify patient subgroups using patient similarity measures or generic clustering algorithms.

12. The system of claim 9 , wherein the processor is further configured to determine the individual-specific patient baseline using the retrospective clinical data from the one or more patient subgroups by averaging baselines from the one or more patient subgroups or by computing a weighted average baseline from two or more patient subgroups.

13. The system of claim 9 , wherein the processor is further configured to use an adaptive baseline selection algorithm utilizing an average length of medical treatment amongst members of the one or more patient subgroups as a factor to determine whether to determine the individual-specific patient baseline using patient health data or using the retrospective clinical data from the one or more patient subgroups.

14. The system of claim 9 , wherein the processor is further configured to determine the individual-specific patient baseline using the patient health data if a variance in the retrospective clinical data of the one or more subgroups is less than a variance threshold or determine the individual-specific patient baseline using the patient health data if a population size of the one or more subgroups is less than a size threshold.

15. The system of claim 9 , wherein the processor is further configured to determine individual-specific patient baseline using the patient health data if a difference between a centroid of a patient subgroup of the one or more patient subgroups and a centroid of a neighboring subgroup is less than a centroid threshold, wherein the neighboring subgroup is a neighboring cluster on a similarity clustering graph.

Assignees

• Koninklijke Philips Nv

Inventors

• Zhao Claire Yunzhu
• Conroy Bryan
• Sorower Mohammad Shahed
• Noren David Paul
• Swaminathan Kailash
• Kulkarni Chaitanya
• Feng Ting
• Tgavalekos Kristen
• Schwager Emma Holdrich
• Ghosh Erina
• Kumar Vinod
• Shivanna Vikram
• Hariharan Srinivas
• Mcfarlane Daniel Craig

Classifications

• A61B5/4842 Primary

  Monitoring progression or stage of a disease · CPC title

• A61B5/7225

  Details of analogue processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation (input circuits for detecting, measuring, or recording bioelectric or biomagnetic signals A61B5/30; specific diagnostic methods using bioelectric or biomagnetic signals A61B5/316) · CPC title

• A61B5/742

  using visual displays (displays for heart-related electrical signals, e.g. ECG, A61B5/339) · CPC title

• G16H10/60

  for patient-specific data, e.g. for electronic patient records · CPC title

• G16H50/20

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title