CA-3158128-C - SYSTEMS AND METHODS FOR COMPUTER MODELING FOR HEALTHCARE BOTTLENECK PREDICTION AND MITIGATION

Abstract

Systems and methods are disclosed for managing predictive bottleneck models. In one embodiment, a computerized system may comprise a storage medium storing instructions, and a processor in communication with a communications network. The processor may be configured to receive, from a user device, bottleneck data indicating a bottleneck within a facility; compile, based on the received indication, contextual data associated with the bottleneck; analyze the bottleneck data and the contextual data conjunctively; determine a relationship between the bottleneck data and the contextual data; and update a predictive bottleneck model based on the determined relationship.

Inventors

• Anjali Tomer
• Scott Jubeck
• Ratna Divya Kanthi Bejjam

Assignees

• Anjali Tomer
• Scott Jubeck

Dates

Publication Date

20260505

Application Date

20201018

Priority Date

20191018

Claims (20)

1. CLAIMS: 1. A computerized system for managing predictive bottleneck models, the system comprising: one processor in communication with a communications network; and a storage medium comprising instructions that when executed, configure the at least one processor to: receive, from a user device and sensing devices that are located throughout a facility and that monitor one or more conditions of the facility and capture tracking data of a patient throughout the facility, bottleneck data indicating a bottleneck within the facility based upon movement of the patient within the facility as identified from the captured tracking data; confirm, from data gathered from polling the sensing devices, the bottleneck; compile, based on the received indication, contextual data associated with the bottleneck, wherein the contextual data comprises historical data and real time data generated and sourced from sources outside the facility and identifying conditions corresponding to historical bottlenecks and the bottleneck and having at least one similarity to data related to the bottleneck; analyze the bottleneck data and the contextual data conjunctively, wherein the analyzing comprises determining factors that influence the formation and severity of a bottleneck; determine a relationship between the bottleneck data and the contextual data, wherein the determining comprises identifying a statistical correlation between the prevalence of a data element and the formation and severity of a bottleneck; and update a predictive bottleneck model based on the determined relationship.
2. 2. The computerized system of claim 1, wherein the instructions further configure the at least one processor to provide at least one fix to mitigate the bottleneck within the facility.
3. 3. The computerized system of claim 1, wherein the bottleneck data comprises tracking data from sensors indicating movements of patients within the facility. 50 Date Re1rue/Date Received 2024-02-29
4. 4. The computerized system of claim 1, wherein the bottleneck data comprises data indicating an area within the facility is experiencing at least one of: a level of throughput below a predetermined threshold level, a patient query above a threshold level, and an elevated level of delay.
5. 5. The computerized system of claim 1, wherein the instructions further configure the at least one processor to confirm the bottleneck by comparing the bottleneck data to a previously confirmed bottleneck.
6. 6. The computerized system of claim 1, wherein to compile comprises compiling historical data related to previous bottlenecks.
7. 7. The computerized system of claim 1, wherein to analyze comprises determining factors that influence a severity of the bottleneck and determining how the factors influence the severity.
8. 8. The computerized system of claim 1, wherein to determine comprises identifying a statistically recurring prevalence of the bottleneck and at least a portion of the contextual data.
9. 9. The computerized system of claim 1, wherein the predictive model comprises parameters that comprise weights determined utilizing modeling techniques.
10. 10. The computerized system of claim 1, wherein to update comprises automatically modifying parameters of the predictive model based upon the relationships.
11. 11. A computerized method for managing predictive bottleneck models, a system comprising: receiving, from a user device and sensing devices that are located throughout a facility and that monitor one or more conditions of the facility and capture tracking data of a patient throughout the facility, bottleneck data indicating a bottleneck within the facility based upon movement of the patient within the facility as identified from the captured tracking data; confirming, from data gathered from polling the sensing devices, the bottleneck; 51 Date Re1rue/Date Received 2024-02-29 compiling, based on the received indication, contextual data associated with the bottleneck, wherein the contextual data comprises historical data and real time data generated and sourced from sources outside the facility and identifying conditions corresponding to historical bottlenecks and the bottleneck and having at least one similarity to data related to the bottleneck; analyzing the bottleneck data and the contextual data conjunctively, wherein the analyzing comprises determining factors that influence the formation and severity of a bottleneck; determining a relationship between the bottleneck data and the contextual data, wherein the determining comprises identifying a statistical correlation between the prevalence of a data element and the formation and severity of a bottleneck; and updating a predictive bottleneck model based on the determined relationship.
12. 12. The computerized method of claim 11, further comprising providing at least one fix to mitigate the bottleneck within the facility.
13. 13. The computerized method of claim 11, wherein the bottleneck data comprises tracking data from sensors indicating movements of patients within the facility.
14. 14. The computerized method of claim 11, wherein the bottleneck data comprises data indicating an area within the facility is experiencing at least one of: a level of throughput below a predetermined threshold level, a patient query above a threshold level, and an elevated level of delay.
15. 15. The computerized method of claim 11, further comprising confirming the bottleneck by comparing the bottleneck data to a previously confirmed bottleneck.
16. 16. The computerized method of claim 11, wherein the compiling comprises compiling historical data related to previous bottlenecks.
17. 17. The computerized method of claim 11, wherein the analyzing comprises determining factors that influence a severity of the bottleneck and determining how the factors influence the severity. 52 Date Re1rue/Date Received 2024-02-29
18. 18. The computerized method of claim 11, wherein the determining comprises identifying a statistically recurring prevalence of the bottleneck and at least a portion of the contextual data.
19. 19. The computerized method of claim 11, wherein the updating comprises automatically modifying parameters of the predictive model based upon the relationships.
20. 20. A non-transitory computer readable medium storing instructions which, when executed, cause at least one processor to perform operations for managing predictive bottleneck models, the operations comprising: receiving, from a user device and sensing devices that are located throughout a facility and that monitor one or more conditions of the facility and capture tracking data of a patient throughout the facility, bottleneck data indicating a bottleneck within the facility based upon movement of the patient within the facility as identified from the captured tracking data; confirming, from data gathered from polling the sensing devices, the bottleneck; compiling, based on the received indication, contextual data associated with the bottleneck, wherein the contextual data comprises historical data and real time data generated and sourced from sources outside the facility and identifying conditions corresponding to historical bottlenecks and the bottleneck and having at least one similarity to data related to the bottleneck; analyzing the bottleneck data and the contextual data conjunctively, wherein the analyzing comprises determining factors that influence the formation and severity of a bottleneck; determining a relationship between the bottleneck data and the contextual data, wherein the determining comprises identifying a statistical correlation between the prevalence of a data element and the formation and severity of a bottleneck; and updating a predictive bottleneck model based on the determined relationship. 53 Date Re1rue/Date Received 2024-02-29

Description

SYSTEMS AND METHODS FOR COMPUTER MODELING FOR HEALTHCARE BOTTLENECK PREDICTION AND MITIGATION BACKGROUND [001] Modern health care facilities have highly skilled personnel, high-tech patient monitoring systems, employee communication systems, and in some instances, patient and equipment location tracking systems. High efficiency, however, still evades many modern facilities, and many hospitals still fail to deliver the best possible health care to their patients, and fail to operate at maximum possible capacity. There are multiple underlying reasons for inefficiencies. As one example, health care facilities and organizations often have segregated departments and units, causing organizational barriers to providing the best care, especially when the departments and units do not coordinate schedules and their respective roles in caring for a patient. Various pieces of patient data, such as patient flow data, may be segregated across different locations, making it difficult to manage treatment across an entire facility. [002] In many cases, facilities may suffer from various bottlenecks to patient care, which may be caused by caregivers or other staff, such when caregivers bring too many patients to a given location at the same time. In addition, a lack of integration and comprehensive data analysis in traditional systems prevents healthcare systems from operating at the potential capacity. Traditional systems also fail to consider many data points that are observable using the proper equipment. Bottlenecks and/or unforeseen surges in 1 WO 2021/077059 PCT /0S2020/056211 workflow can also increase stress on caregivers, further decreasing the quality of care to patients. [003] In view of the problems facing hospitals and other health care facilities, improved systems and methods for managing patient care bottlenecks are needed. SUMMARY [004] Disclosed embodiments relate to computerized systems and methods for creating and updating predictive bottleneck models, and bottleneck mitigation. [005] Systems and methods are disclosed for configuring predictive bottleneck models, which may predict a possible future bottleneck at a facility or enterprise. Disclosed embodiments also replace subjective analyses of traditional techniques with automatic analyses, which may be rule based, of the aggregated data related to bottlenecks and other contextual sources, using particular rules and mechanisms disclosed herein. Some embodiments of disclosed systems also use arrangements of sensors across one or more facilities in combination with particular database structures to allow for such aggregation and analysis automation and to integrate new types of data into predictive models that could not be collected and analyzed using traditional techniques. Based on the analyses, models for predicting a bottleneck within a facility or enterprise may be modified to better predict future bottlenecks. 2 WO 2021/077059 PCT/0S2020/056211 [006] In addition, the provided systems and methods may predict a future bottleneck and generate interactive graphical user interfaces (GUls) having recommendations based on an analysis of aggregated data and application of a model that determines recommended corrective actions based on real time environment conditions. Some embodiments of the disclosed system further apply one or more rule sets to determine corrective actions based on how such actions may influence other potential bottlenecks. Accordingly, the disclosed embodiments may improve users' experiences with healthcare metric systems, may improve prediction of bottlenecks, may improve the responsiveness to bottlenecks and eliminate inefficiencies, and may increase the efficiency of healthcare systems to allow existing resources to serve more patients. Any or all of these improvements can increase the quality of patient care. [007] Consistent with the present embodiments, a computerized system for managing predictive bottleneck models is disclosed. The system may comprise at least one processor in communication with a communications network; and a storage medium comprising instructions that, when executed, may configure the at least one processor to receive, from a user device, bottleneck data indicating a bottleneck within a facility; compile, based on the received indication, contextual data associated with the bottleneck; analyze the bottleneck data and the contextual data conjunctively; 3 WO 2021/077059 PCT /0S2020/056211 determine a relationship between the bottleneck data and the contextual data; and update a predictive bottleneck model based on the determined relationship. [008] Consistent with the present embodiments, one or more computerized methods are disclosed, corresponding to the exemplary system disclosed above. [009] Consistent with other disclosed embodiments, non-transitory computer readable storage media may store program instructions, which are executed by at least one processor device and perform any of the methods described herein