# US 12,224,058 B2 · Monitoring, predicting and alerting for census periods in medical inpatient units

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,224,058 B2
- Document ID: US12224058B2
- Status: Granted
- Kind: B2
- Application number: 17/341,949
- Filed: 2021-06-08
- Published: 2021-09-23
- Granted: 2025-02-11
- Earliest claimed: 2019-03-27
- Assignees: General Electric Company
- Applicants: General Electric Company
- Inventors: Bex George Thomas; Vijay K. Veeraghattam; Hong Yang; Gregory Peter Betman
- Web page: https://patentgrep.com/patent/US12224058B2

## CPC

- G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
- G06F 16/9024: {Graphs; Linked lists (G06F16/9027 takes precedence)}
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G06N 3/09: Supervised learning
- G06N 3/0985: Hyperparameter optimisation; Meta-learning; Learning-to-learn
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06N 20/20: Ensemble learning
- G06Q 10/04: Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" (market predictions or forecasting for commercial activities G06Q30/0202)
- G06Q 10/067: Enterprise or organisation modelling
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06N 3/08: Learning methods
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

Systems and techniques for monitoring, predicting and/or alerting for census periods in medical inpatient units are presented. A system can include a grouping component that defines a group of beds at a medical facility based on at least one grouping factor, and a group stability component that determines a measure of occupancy variability for the group based on historical census data for respective beds in the group. The system can further include a model selection component that selects one or more census forecasting models for the group based on the measure of occupancy variability, and a patient census component that applies the one or more census forecasting models to current patient flow data for the medical facility to forecast an expected occupancy level for the group during one or more future periods of time.

## Claims

### Claim 1

A system, comprising:
a memory that stores computer executable components; and
a processor that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
a grouping component that defines a group of beds at a medical facility based on at least one grouping factor;
a training component that learns patterns in historical patient flow data related to historical flow of historical patients in and out of respective beds in the group using one or more machine learning processes and generates one or more census forecasting models trained to predict an expected occupancy level for the group at one or more future time periods based on current patient flow data for the group and the patterns, wherein the historical patient flow data comprises patient journey data tracked for the historical patients regarding respective journeys of the historical patients at the medical facility, and wherein the one or more machine learning processes comprise modeling the respective journeys using heterogeneous graphs and learning the patterns from the heterogenous graphs;
a patient census component that applies the one or more census forecasting model to the current patient flow data to forecast the expected occupancy level for the group during at the one or more future periods of time; and
an alert component that generates and provides an alert to a device associated with an administrator of the medical facility in response to the expected occupancy level satisfying an alert criterion.

### Claim 2 (depends on 1)

The system of claim 1, wherein the computer executable components further comprise:
a group stability component that determines a measure of occupancy variability for the group based on historical census data for the respective beds in the group; and
a model selection component that selects the one or more census forecasting models for the group based on the measure of occupancy variability, wherein a number and type of the one or more census forecasting models varies as a function of the measure of occupancy variability.

### Claim 3 (depends on 2)

The system of claim 2, wherein the one or more census forecasting models comprise a plurality of different forecasting models, and wherein the computer executable components further comprise:
a forecasting optimization component that estimates weights for the different forecasting models and combines outputs of the different forecasting models using the weights to forecast the expected occupancy level.

### Claim 4 (depends on 3)

The system of claim 3, wherein the forecasting optimization component employs a non-convex optimization technique to estimate the weights.

### Claim 5 (depends on 4)

The system of claim 4, wherein the non-convex optimization technique comprises a quadratic programming optimization technique.

### Claim 6 (depends on 1)

The system of claim 1, wherein the computer executable components further comprise:
a forecasting optimization component that tunes one or more parameters of the one or more census forecasting models for the group prior to application by the patient census component to the current patient flow data to forecast the expected occupancy level for the group.

### Claim 7 (depends on 1)

The system of claim 1, wherein the patient journey data comprises information regarding workflow events, conditions of the historical patients, operations of the medical facility and temporal relationships between the workflow events, the conditions of the historical patients, and the operations.

### Claim 8 (depends on 7)

The system of claim 7, wherein learning comprises employing label propagation to infer bed placement patterns from the heterogenous graphs, and wherein the one or more machine learning processes further comprise extracting training features from the heterogenous graphs for input to the one or more census forecasting models that are correlated to the bed placement patterns.

### Claim 9 (depends on 1)

The system of claim 1, wherein the at least one grouping factors comprises a unit grouping factor identifying two or more inpatient units of the medical facility, and wherein the grouping component groups the beds based on association of the beds with the two or more inpatient units.

### Claim 10 (depends on 1)

The system of claim 1, wherein the at least one grouping factor comprises a service line grouping factor identifying at least one service line at the medical facility and wherein the grouping component groups the bed based on association of the beds with the at least one service line.

### Claim 11 (depends on 2)

The system of claim 2, wherein the at least one grouping factor comprises a bed attribute shared by the beds in the group and a time period of the one or more future periods of time, and wherein the group stability component determines the measure of occupancy variability for the time period.

### Claim 12 (depends on 1)

The system of claim 1, wherein the current patient flow data comprises real-time patient data regarding current locations and conditions of current patients at the medical facility, and wherein the computer executable components comprise:
a data collection component that employs a microservices architecture to collect the real-time patient flow from multiple data sources associated with the medical facility and stores the real-time patient data in a machine learning database as tracked patient journey data for the current patients over time.

### Claim 13 (depends on 8)

The system of claim 8, wherein the current patient flow data comprises current patient journey data tracked for current patients at the medical facility regarding respective active journeys of the current patients at the medical facility, and wherein the applying comprises modeling the respective active journeys using new heterogeneous graphs, and employing label propagation to infer runtime features from the new heterogenous graphs for input to the one or more census forecasting models.

### Claim 14

A method, comprising:
defining, by a system comprising a processor, a group of beds at a medical facility based on at least one grouping factor;
employing, by the system, one or more machine learning processes to learn patterns in historical patient flow data related to historical flow of historical patients in and out of respective beds in the group and generate one or more census forecasting models trained to predict an expected occupancy level for the group at one or more future time periods based on current patient flow data for the group and the patterns, wherein the historical patient flow data comprises patient journey data tracked for the historical patients regarding respective journeys of the historical patients at the medical facility, and wherein the employing comprises modeling the respective journeys using heterogeneous graphs and leaning the patterns from the heterogenous graphs;
applying, by the system, the one or more census forecasting models to the current patient flow data to forecast the expected occupancy level for the group at the one or more future periods of time; and
providing, by the system, an alert to a device associated with an administrator of the medical facility in response to the expected occupancy level satisfying an alert criterion.

### Claim 15 (depends on 14)

The method of claim 14, further comprising:
determining, by the system, a measure of occupancy variability for the group based on historical census data for the respective beds in the group; and
selecting, by the system, the one or more census forecasting models for the group based on the measure of occupancy variability, wherein a number and type of the one or more census forecasting models varies as a function of the measure of occupancy variability.

### Claim 16 (depends on 14)

The method of claim 14, wherein the one or more census forecasting models comprise a plurality of different forecasting models, and wherein the method further comprises:
estimating, by the system, weights for the different forecasting models; and
combining, by the system, outputs of the different forecasting models using the weights to forecast the expected occupancy level.

### Claim 17 (depends on 16)

The method of claim 16, wherein the estimating comprises employing a non-convex optimization technique to estimate the weights.

### Claim 18 (depends on 14)

The method of claim 14, wherein the patient journey data comprises information regarding workflow events, conditions of the historical patients, operations of the medical facility and temporal relationships between the workflow events, the conditions of the historical patients, and the operations.

### Claim 19 (depends on 18)

The method of claim 18, wherein learning comprises employing label propagation to infer bed placement patterns from the heterogenous graphs, and wherein the one or more machine learning processes further comprise extracting training features from the heterogenous graphs that are correlated to the bed placement patterns for input to the one or more census forecasting models.

### Claim 20 (depends on 19)

The method of claim 19, wherein the current patient flow data comprises current patient journey data tracked for current patients at the medical facility regarding respective active journeys of the current patients at the medical facility, and wherein the applying comprises modeling the respective active journeys using new heterogeneous graphs, and employing label propagation to infer runtime features from the new heterogenous graphs for input to the one or more census forecasting models.

### Claim 21 (depends on 20)

The method of claim 20, wherein the learning comprises extracting the features from the heterogeneous graphs at different time intervals and replicating conditions in the new heterogeneous graphs at corresponding time intervals of the different time intervals in association with the applying.

### Claim 22

A machine-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:
defining a group of beds at a medical facility based on at least one grouping factor;
employing one or more machine learning processes to learn patterns in historical patient flow data related to historical flow of historical patients in and out of respective beds in the group and generate one or more census forecasting models trained to predict an expected occupancy level for the group at one or more future time periods based on current patient flow data for the group and the patterns, wherein the historical patient flow data comprises patient journey data tracked for the historical patients regarding respective journeys of the historical patients at the medical facility, and wherein the employing comprises modeling the respective journeys using heterogeneous graphs and leaning the patterns from the heterogenous graphs;
applying the one or more census forecasting models to the current patient flow data to forecast the expected occupancy level for the group at the one or more future periods of time; and
providing an alert to a device associated with an administrator of the medical facility in response to the expected occupancy level satisfying an alert criterion.

### Claim 23 (depends on 22)

The machine-readable storage medium of claim 22, wherein the patient journey data comprises information regarding workflow events, conditions of the historical patients, operations of the medical facility and temporal relationships between the workflow events, the conditions of the historical patients, and the operations.

### Claim 24 (depends on 22)

The machine-readable storage medium of claim 22, wherein learning comprises employing label propagation to infer bed placement patterns from the heterogenous graphs, and wherein the one or more machine learning processes further comprise extracting training features from the heterogenous graphs that are correlated to the bed placement patterns for input to the one or more census forecasting models.

### Claim 25 (depends on 24)

The machine-readable storage medium of claim 24, wherein the current patient flow data comprises current patient journey data tracked for current patients at the medical facility regarding respective active journeys of the current patients at the medical facility, and wherein the applying comprises modeling the respective active journeys using new heterogeneous graphs, and employing label propagation to infer runtime features from the new heterogenous graphs for input to the one or more census forecasting models.