Granted Patent B2

US 12,748,921 · App. 18/193,420 · Granted Sep 29, 2026

Inventor: Robert W. Price (Lockport, IL)

Assignee: MatrixCare, Inc.

G06F40/284G06F40/205G16H10/60G16H40/20G16H50/20G16H50/70

Abstract

Claims (75)

1 . A method comprising:

receiving a patient record for a patient admitted to a healthcare facility, the patient record including social information determined for the patient, wherein the social information comprises (i) a climate of a geographical region of the patient, (ii) an elevation of the geographical region, (iii) an air quality of the geographical region, (iv) a water quality of the geographical region, and (v) a crime rate of the geographical region;

applying a first machine learning model to the patient record to predict a readmission risk profile of the patient;

determining, based on the readmission risk profile, at least one risk factor and at least one underlying factor indicating a reason for the at least one risk factor;

outputting an indication of the readmission risk profile of the patient via a graphical user interface;

determining, based on processing the readmission risk profile using a second machine learning model, one or more remedial actions to be taken for the patient, prior to discharging the patient from the healthcare facility, to reduce a readmission risk level of the patient, wherein the one or more remedial actions comprise providing modified or additional medical treatments or services to the patient; and

in response to determining that the one or more remedial actions have been performed, outputting an indication via the graphical user interface flagging that the one or more remedial actions have been performed.

2 . The method of claim 1 , further comprising:

receiving a plurality of patient records of patients previously discharged from the healthcare facility, the plurality of patient records including social information and readmission information;

training the first machine learning model using training data comprising a first subset of the plurality of patient records; and

validating the first machine learning model using validation data comprising a second subset of the plurality of patient records.

3 . The method of claim 1 , further comprising:

determining that the readmission risk profile indicates that the readmission risk level of the patient exceeds a threshold; and

outputting an indication of the one or more remedial actions.

4 . The method of claim 1 , further comprising:

receiving a plurality of social records from one or more social data sources;

determining the social information for the patient by mapping the patient record to the plurality of social records based on residential information included in the patient record, wherein the social information includes a size of an economy in the geographical region, a measure of economic growth of the geographical region, a measure of availability of health services in the geographical region, a measure of availability of transportation services in the geographical region, and availability of social support services in the geographical region; and

augmenting the patient record to include the social information determined for the patient.

5 . The method of claim 1 , wherein the readmission risk profile includes a categorical readmission risk level determined for the patient.

6 . The method of claim 1 , wherein determining the readmission risk profile comprises:

predicting, for the patient, a plurality of risk levels including a respective risk level of each of a plurality of readmission risk factors; and

determining the readmission risk level based on the plurality of risk levels.

7 . The method of claim 1 , further comprising parsing the patient record by:

tokenizing text in the patient record and normalizing the tokenized text;

converting the tokenized text into an object that is represented numerically using at least one of one-hot encodings or word embedding vectors; and

processing the object using a natural language processing algorithm.

8 . A non-transitory computer-readable medium containing instructions executable to perform an operation comprising:

receiving a patient record for a patient admitted to a healthcare facility, the patient record including social information determined for the patient, wherein the social information comprises (i) a climate of a geographical region of the patient, (ii) an elevation of the geographical region, (iii) an air quality of the geographical region, (iv) a water quality of the geographical region, and (v) a crime rate of the geographical region;

applying a first machine learning model to the patient record to predict a readmission risk profile of the patient;

determining, based on the readmission risk profile, at least one risk factor and at least one underlying factor indicating a reason for the at least one risk factor;

outputting an indication of the readmission risk profile of the patient via a graphical user interface;

determining, based on processing the readmission risk profile using a second machine learning model, one or more remedial actions to be taken for the patient, prior to discharging the patient from the healthcare facility, to reduce a readmission risk level of the patient, wherein the one or more remedial actions comprise providing modified or additional medical treatments or services to the patient; and

in response to determining that the one or more remedial actions have been performed, outputting an indication via the graphical user interface flagging that the one or more remedial actions have been performed.

9 . The non-transitory computer-readable medium of claim 8 , wherein the operation further comprises:

receiving a plurality of patient records of patients previously discharged from the healthcare facility, the plurality of patient records including social information and readmission information;

training the first machine learning model using training data comprising a first subset of the plurality of patient records; and

validating the first machine learning model using validation data comprising a second subset of the plurality of patient records.

10 . The non-transitory computer-readable medium of claim 8 , wherein the operation further comprises:

determining that the readmission risk profile indicates that the readmission risk level of the patient exceeds a threshold; and

outputting an indication of the one or more remedial actions.

11 . The non-transitory computer-readable medium of claim 8 , wherein the operation further comprises:

determining the social information for the patient by mapping the patient record to a plurality of social records based on residential information included in the patient record, wherein the social information includes a size of an economy in the geographical region, a measure of economic growth of the geographical region, a measure of availability of health services in the geographical region, a measure of availability of transportation services in the geographical region, and availability of social support services in the geographical region; and

augmenting the patient record to include the social information determined for the patient.

12 . The non-transitory computer-readable medium of claim 8 , wherein the readmission risk profile includes a categorical readmission risk level determined for the patient.

13 . The non-transitory computer-readable medium of claim 9 , wherein determining the readmission risk profile comprises:

predicting, for the patient, a plurality of risk levels including a respective risk level of each of a plurality of readmission risk factors; and

determining the readmission risk level based on the plurality of risk levels.

14 . A system comprising:

one or more computer processors; and

a memory containing a program executable by the one or more computer processors to perform an operation comprising:

receiving a patient record for a patient admitted to a healthcare facility, the patient record including social information determined for the patient, wherein the social information comprises (i) a climate of a geographical region of the patient, (ii) an elevation of the geographical region, (iii) an air quality of the geographical region, (iv) a water quality of the geographical region, and (v) a crime rate of the geographical region;

applying a first machine learning model to the patient record to predict a readmission risk profile of the patient;

determining, based on the readmission risk profile, at least one risk factor and at least one underlying factor indicating a reason for the at least one risk factor;

outputting an indication of the readmission risk profile of the patient via a graphical user interface;

determining, based on processing the readmission risk profile using a second machine learning model, one or more remedial actions to be taken for the patient, prior to discharging the patient from the healthcare facility, to reduce a readmission risk level of the patient, wherein the one or more remedial actions comprise providing modified or additional medical treatments or services to the patient; and

in response to determining that the one or more remedial actions have been performed, outputting an indication via the graphical user interface flagging that the one or more remedial actions have been performed.

15 . The system of claim 14 , wherein the operation further comprises:

receiving a plurality of patient records of patients previously discharged from the healthcare facility, the plurality of patient records including social information and readmission information;

training the first machine learning model using training data comprising a first subset of the plurality of patient records; and

validating the first machine learning model using validation data comprising a second subset of the plurality of patient records.

16 . The system of claim 14 , wherein the operation further comprises:

determining that the readmission risk profile indicates that the readmission risk level of the patient exceeds a threshold; and

outputting an indication of the one or more remedial actions.

17 . The system of claim 14 , wherein the operation further comprises:

receiving a plurality of social records from one or more social data sources;

determining the social information for the patient by mapping the patient record to the plurality of social records based on residential information included in the patient record, wherein the social information includes a size of an economy in the geographical region, a measure of economic growth of the geographical region, a measure of availability of health services in the geographical region, a measure of availability of transportation services in the geographical region, and availability of social support services in the geographical region; and

augmenting the patient record to include the social information determined for the patient.

18 . The system of claim 14 , wherein the readmission risk profile includes a categorical readmission risk level determined for the patient.

19 . The system of claim 14 , wherein determining the readmission risk profile comprises:

predicting, for the patient, a plurality of risk levels including a respective risk level of each of a plurality of readmission risk factors; and

determining the readmission risk level based on the plurality of risk levels.

20 . The system of claim 14 , wherein the operation further comprises parsing the patient record by:

tokenizing text in the patient record and normalizing the tokenized text;

converting the tokenized text into an object that is represented numerically using at least one of one-hot encodings or word embedding vectors; and

processing the object using a natural language processing algorithm.

Assignments (1)

Continuity (2)

References Cited (11)