Researchers in the Mayo Clinic Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery's Data Science Program have expertise in in a wide range of mathematical, statistical and machine learning methodologies. They lead the development and integration of artificial intelligence- and machine learning-based solutions that are a hallmark of the center's unique, practice-transforming work. Their work includes developing and guiding the infrastructure needed for fast, efficient integration of data and information technology-based tools.
The center's Data Science Program is focused on:
- Developing, implementing and evaluating artificial intelligence and machine learning models for clinical applications
- Implementing artificial intelligence algorithms into practice workflows
- Bayesian modeling for complex problems
- Designing evaluations for testing the impact of artificial intelligence-based tools in practice
- Developing, piloting and supporting implementation of virtual reality tools for medical applications
Control Tower: Innovation framework for patient care support
The Control Tower project provides a support tool for health care providers in the inpatient setting. Built on Mayo Clinic's unified data platform and incorporating engineering, design, knowledge management and analytics capabilities, the framework provides the elements essential to building both a physical interface and the artificial intelligence to power proposed solutions.
The first proof-of-concept case for the innovation framework was developed and tested by researchers from the Mayo Clinic Kern Center for the Science of Health Care Delivery and Mayo's Center for Palliative Medicine. Researchers used machine learning techniques to develop a novel risk score, a real-time dashboard and alerts.
This tool predicts the potential need for a patient to receive palliative care support, allowing palliative care specialists to proactively offer consults. The tool has decreased the time to palliative care consultations with patients by more than 40%. Implementation has reduced 60-day readmissions by more than 25%.
Related news story:
- Murphree DH, Wilson PM, Asai SW, Quest DJ, Lin Y, Mukherjee P, Chhugani Nirmal, Strand JJ, Demuth G, Mead D, Wright B, Harrison A, Soleimani J, Herasevich V, Pickering BW, Storlie CB. Improving the delivery of palliative care through predictive modeling and healthcare informatics. Journal of the American Medical Informatics Association (JAMIA). 2021; doi: 10.1093/jamia/ocaa211.
In support of local, regional and state pandemic response, the Mayo Clinic Kern Center for the Science of Health Care Delivery's Data Science Program developed a Bayesian Susceptible-Exposed-Infected-Recovered (SEIR) model to predict COVID-19 cases and hospitalizations across the country for internal and external collaborators. The project included a publicly accessible COVID-19 map.
Related work led to a hospital census prediction model, which was later expanded to encompass numerous patient services across Mayo Clinic's hospitals and clinics in Arizona, Florida, Minnesota and Wisconsin.
Related news story:
- Khokhar A, Spaulding A, Niazi Z, Ailawadhi S, Manochakian R, Chanan-Khan A, Niazi S, Sher T. A panel evaluation of the changes in the general public's social-media-following of United States' public health departments during COVID-19 pandemic. Journal of Primary Care & Community Health. 2021; doi:10.1177/2150132721995450.
- Mayo Clinic COVID-19 Predictive Analytics Task Force, Pollock BD, Carter RE, Dowdy SC, Dunlay SM, Habermann EB, Kor DJ, Limper AH, Liu H, Franco PM, Neville MR, Noe KH, Poe JD, Sampathkumar P, Storlie CB, Ting HH, Shah ND. Deployment of an interdisciplinary predictive analytics task force to inform hospital operational decision-making during the COVID-19 pandemic. Mayo Clinic Proceedings. 2021; doi:10.1016/j.mayocp.2020.12.019.
- Ryu AJ, Romero-Brufau S, Shahraki N, Zhang J, Qian R, Kingsley TC. Practical development and operationalization of a 12-hour hospital census prediction algorithm. Journal of the American Medical Informatics Association (JAMIA). 2021; doi:10.1093/jamia/ocab089.
- Storlie CB, Pollock BD, Rojas RL, Demuth GO, Johnson PW, Wilson PM, Heinzen EP, Liu H, Carter RE, Habermann EB, Kor DJ, Neville MR, Limper AH, Noe KH, Bydon M, Franco PM, Sampathkumar P, Shah ND, Dunlay SM, Dowdy SC. Quantifying the importance of COVID-19 vaccination to our future outlook. Mayo Clinic Proceedings. 2021; doi:10.1016/j.mayocp.2021.04.012.
Complex patient identification algorithm
With internal and external collaborators, Data Science Program researchers are developing an algorithm based on health insurance administrative claim data to identify patients with complex disease who may need to see a specialty practice at a tertiary medical center. The team plans to use the tool primarily to support the care of patients with complex and serious conditions.
Sometimes these patients "churn," or move around the health care system, in less-than-ideal care patterns. Ideally, the algorithm will improve continuity of care, reduce the time to develop correct diagnoses and treatment plans, and improve both experiences and outcomes for patients.