
NSF Org: |
CMMI Division of Civil, Mechanical, and Manufacturing Innovation |
Recipient: |
|
Initial Amendment Date: | August 9, 2018 |
Latest Amendment Date: | June 1, 2021 |
Award Number: | 1825761 |
Award Instrument: | Standard Grant |
Program Manager: |
Georgia-Ann Klutke
CMMI Division of Civil, Mechanical, and Manufacturing Innovation ENG Directorate for Engineering |
Start Date: | September 1, 2018 |
End Date: | August 31, 2022 (Estimated) |
Total Intended Award Amount: | $261,055.00 |
Total Awarded Amount to Date: | $302,055.00 |
Funds Obligated to Date: |
FY 2020 = $25,000.00 FY 2021 = $16,000.00 |
History of Investigator: |
|
Recipient Sponsored Research Office: |
4202 E FOWLER AVE TAMPA FL US 33620-5800 (813)974-2897 |
Sponsor Congressional District: |
|
Primary Place of Performance: |
4202 E. Fowler Ave. ENB118 Tampa FL US 33620-9951 |
Primary Place of
Performance Congressional District: |
|
Unique Entity Identifier (UEI): |
|
Parent UEI: |
|
NSF Program(s): |
OE Operations Engineering, COVID-19 Research |
Primary Program Source: |
01002021DB NSF RESEARCH & RELATED ACTIVIT 01002122DB NSF RESEARCH & RELATED ACTIVIT |
Program Reference Code(s): |
|
Program Element Code(s): |
|
Award Agency Code: | 4900 |
Fund Agency Code: | 4900 |
Assistance Listing Number(s): | 47.041 |
ABSTRACT
This Grant Opportunities for Academic Liaison with Industry (GOALI) award will advance the national health by improving the delivery of health-care to the growing sector of the population served by nursing homes. Nursing homes are responsible for caring for the frail and vulnerable population of older adults who suffer from diverse chronic diseases, functional limitations and impairments. They must coordinate distinct caregivers to provide patients with round-the-clock physical and emotional care and assistance. Because of growing demand due to immutable population demographics, rapidly increasing health-care costs, and escalating nursing staff shortage, proper care for nursing home residents is at-risk. The goal of this project is to improve long-term nursing home quality of care and reduce costs using analytical methods and tools to realize proactive, resident-centered staffing plans. This project will improve workforce planning, recruitment and allocation decisions for nursing home managers, reduce stress and burn-out by better balancing workloads for nursing home staff, and enhance health outcomes for nursing home residents by better meeting their diverse care needs. The close involvement of the engineering team with a nursing home operator and national aging health policy experts will also help transform nursing home culture into delivering more resident-centered and home-like care.
The research objectives will be achieved through the development of a set of innovative models, algorithms, and decision tools. A predictive data analytics model and efficient estimation algorithms will be developed to characterize heterogeneous service need trajectories and length-of-stays of nursing home residents for service demand prediction improvement at the resident level. A two-stage stochastic programming model and efficient numerical optimization algorithms will be developed for consistent nursing home staff planning under service demand fluctuation and uncertainty. To maximize the practical relevance of research deliverables, a decision support system will be also developed to evaluate and validate the work in a real-world nursing home setting through our academic-industrial partnership with Greystone Healthcare Management Corporation and industry-scale solution deployment in their facilities.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
PUBLICATIONS PRODUCED AS A RESULT OF THIS RESEARCH
Note:
When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external
site maintained by the publisher. Some full text articles may not yet be available without a
charge during the embargo (administrative interval).
Some links on this page may take you to non-federal websites. Their policies may differ from
this site.
PROJECT OUTCOMES REPORT
Disclaimer
This Project Outcomes Report for the General Public is displayed verbatim as submitted by the Principal Investigator (PI) for this award. Any opinions, findings, and conclusions or recommendations expressed in this Report are those of the PI and do not necessarily reflect the views of the National Science Foundation; NSF has not approved or endorsed its content.
It is well established that nursing home (NH) staffing is critical to resident outcomes and service quality of a NH, which cares the frail and older adults by providing 24/7 personal medical care and daily-living assistance. NH residents often suffer from diverse chronic diseases and functional limitations, and their service needs are highly heterogeneous. So far, NH staffing in practice is either based on administrator experience or based on ?one-size-fits-all? government regulations (e.g., minimum staff-to-resident ratio requirements enforced by federal/state agencies). There is a lack of analytics-based models and decision support tools for informing staffing decisions in meeting with the heterogeneous service demand of NH residents with varied individual characteristics and diverse needs on different types of caregivers. This research aimed at developing advanced analytical methods and tools to realize proactive and resident-centered staffing decisions in meeting with the heterogeneous service demand of NH residents. To achieve the project goal, our research team developed various data-driven prediction models and computational tools for modeling the heterogeneous service demand of NH residents and further informing proactive staffing decisions at reduced labor costs. Specifically, a series of predictive analytics models and efficient estimation algorithms were developed to improve service demand prediction of NH residents by characterizing their heterogeneous length-of-stays and heterogeneous service need trajectories. A predive analytics integrated simulation model and staffing decision support platform were further developed to evaluate different staffing decisions and determine the optimal staffing decisions under different caregiver mix settings and various resident census compositions. The developed models were validated using de-identified real NH data and practical inputs provided by our local NH collaborator. To further investigate the NH workforce shortage and caregiver absenteeism during COVID-19 pandemic, multi-source time-sensitive NH datasets, including survey data and operational detailed staffing data, were collected during COVID-19. The collected caregiver survey data enriched the understanding of various influencing factors in affecting stress and burnout of caregivers during COVID-19. The collected staffing data calibrated and extended the staffing decision support platform developed under normal operating conditions by further considering the uncertainty for caregiver no-shows during COVID-19. Through our studies, we learned that (1) the heterogeneous service demand modeling accuracy of NH residents can be improved by enhancing the prediction accuracy of length-of-stays and/or service need trajectories of individuals; (2) the proposed model-based staffing strategy which considers heterogeneous service demand as well as its fluctuation uncertainty is more cost-saving compared with several existing benchmark strategies under both normal operating conditions and extreme hazard scenarios (e.g., pandemic); (3) there is empirical support indicating that the staffing adequacy and scheduling flexibility are two important factors in reducing the likelihood of a NH caregiver who feels more tired, drained or worn-out after work during COVID-19. Our research team collaborated with long-term care researchers from school of aging studies at the University of South Florida and NH practitioners at Greystone healthcare network, to obtain practical inputs, guidance and feedback for verifying the developed data-driven prediction models and enhancing the usability of the developed staffing decision support platform. The research project partially supported three (3) doctoral students, one (1) master?s student and two (2) undergraduate students. Among them, three (3) are female students. Our collaborative research team published two (2) doctoral dissertations, four (4) journal papers, three (3) conference papers, one (1) book chapter and one (1) technical report. Two (2) journal papers are currently under review and five (5) papers are in preparation. In addition, the research findings from our collaborative research team were disseminated via stakeholder meetings, local events, and twenty-three (23) research presentations at national/international conferences/workshops.
Last Modified: 12/23/2022
Modified by: Mingyang Li
Please report errors in award information by writing to: awardsearch@nsf.gov.