Q&A: A roadmap for revolutionizing health care through data-driven innovation
The healthcare sector stands on the cusp of a profound transformation, driven by the strategic application of data-driven innovation. A new book, “The Analytics Edge in Healthcare,” co-authored by MIT’s Vice Provost for Open Learning, Dimitris Bertsimas, alongside his former students Agni Orfanoudaki PhD ’21 and Holly Wiberg PhD ’22, offers a comprehensive roadmap for leveraging data to revolutionize patient care and hospital operations.
This timely publication serves as a practical introduction to healthcare analytics, blending foundational concepts in machine learning and optimization with real-world case studies across various clinical specialties. It builds upon the success of its predecessor, “The Analytics Edge,” further demonstrating how data and models can lead to better decisions and add significant value within the medical field.
Professor Bertsimas, also the Associate Dean of Business Analytics and the Boeing Leaders for Global Operations Professor of Management at the MIT Sloan School of Management, is the visionary behind MITx’s highly popular course, 15.071 (The Analytics Edge). In a recent discussion, he shed light on how analytics are already reshaping healthcare and hinted at the surprising ways these tools are being deployed in hospitals globally.
Addressing the fundamental shift, Bertsimas emphasized his long-standing aspiration to bridge academic research with practical application. This vision culminated in the founding of Holistic Hospital Optimization (H2O), an initiative dedicated to optimizing hospital operations through machine learning. “We have developed a variety of tools at MIT and implemented them at hospitals around the world,” Bertsimas stated. These innovations include managing patient length of stay, predicting clinical deterioration using advanced indexes, optimizing nurse allocation, and streamlining surgery schedules. “This is the beginning of a change where analytics and AI methods are now being utilized quite widely. My hope would be that this work and this book will accelerate the effect of using these tools.”
He further highlighted the crucial role of education in this paradigm shift. Through a nine-lecture course taught with Orfanoudaki and Wiberg at the Hartford Hospital System, Bertsimas realized the immense potential of demonstrating these analytics methods—typically not part of medical school curricula—to healthcare practitioners including physicians, nurses, and administrators. This aligns perfectly with his role at MIT Open Learning, where the objective is to educate a global audience, exemplified by the upcoming Universal AI program focused on comprehensive artificial intelligence knowledge for the evolving job market.
The impact of analytics is already yielding remarkable results. Bertsimas shared compelling examples from Hartford Hospital, where the application of analytics led to a reduction in patients’ average length of stay from 5.67 days to a mere five days. This was achieved by an algorithm that predicts patient discharge probability, allowing doctors to prioritize and prepare patients for earlier release. “This means that the hospital can treat far more patients, and the patients stay in the hospital less time,” he explained.
During the challenging period of the Covid-19 pandemic, as nurse turnover surged, H2O developed an analytics system that considered equity and fairness, significantly reducing overtime costs and decreasing overall nurse turnover by optimizing preferred slots for staff. These are just two instances where an analytical approach has made a tangible, material difference in healthcare.
Looking to the future, Bertsimas sees artificial intelligence profoundly shaping healthcare. “We use machine learning to make better predictions, but generative AI can explain them,” he noted, signaling a movement towards more transparent and interpretable AI systems. He underscored the life-saving potential, recalling an instance at Hartford Hospital where analytics predicted a patient’s worsening condition, leading to an early diagnosis of sepsis that ultimately saved the patient’s life. “This made an actual difference in saving a person’s life,” he stated.
Describing “The Analytics Edge in Healthcare” in a few words, Bertsimas calls it “a phased transition in health care.” He believes the book is capable of affecting the health care sector in an unprecedented way, encapsulating a decade of his impactful work in healthcare applications.
