64% Reduction in Vascular Readmissions Using Machine Learning and Big Data
Healthcare Organization Case Study
Patients with peripheral artery disease (PAD) have among the highest rates of avoidable hospital readmissions. This leads to a high rate of complications and healthcare costs.
In an effort to combat the COVID-19 threat, Surgisphere, in partnership with the African Federation of Emergency Medicine (AFEM), created a suite of tools that physicians can use to score symptom severity, determine mortality risk, [...]
COVID-19 Severity Scoring Tool for low resourced settings Scientific Publication / Editorial Background Surgisphere partnered with the African Federation of Emergency Medicine and International Federation of Emergency Medicine [...]
Summary In collaboration with researchers at Harvard Medical School, Baylor College of Medicine, Christ Hospital, and the HCA Research Institute, Surgisphere is pleased to announce the publication of a study on cardiovascular disease, drug [...]
Surgisphere worked with a large hospital system in Chicago to develop a series of data-driven benchmarks and data integration through improved interoperability. We then applied sophisticated machine learning tools to predict which patients were most likely to be readmitted. This led to the development of new clinical management algorithms.
Through an industry-leading predictive model, this hospital system was able to reduce readmissions for their vascular patients by 64%, leading to $1.2 million in direct cost reduction and saving an estimated 18 lives per year.
This successful pilot test is now being expanded throughout the entire hospital system and is expected to lead to more than $4 million in savings throughout FY 2020.