What if the data could help predict the prognosis of a patient, rationalize hospital operations or optimize human resources in medicine? A book fresh out of the shelves, “The advantage of analysis in health care», Show that this already happens and shows how to evolve it.
Written by Dimitris Bertsimas, Vice -Prévôt of open learning of the MIT, as well as two of the former students of Bertsimas – Agni Orfanoudaki Phd ‘1, Associate Professor for Management of Operations at the University of Oxford, Saïd Business School, and Holly Wiberg Phd ’22, deputy professor of public research on health care in Carnegie Mellon Analytics. By emphasizing the applications of the real world, the first part of the book establishes technical foundations – covering learning and machine optimization – while the second part of the book presents integrated case studies that cover various clinical specialties and types of problems using descriptive, predictive and normative analyzes.
Part of a larger series, “The Analytics Edge in Healthcare” shows how to take advantage of data and models to make better decisions in the health care sector, while its predecessor, “The analysis edge», Plunges into the science of data use to create models, improve decisions and add value to institutions and individuals.
Bertsimas, who is also the dean partner of business analysis and the Boeing World Operations Management Professor at MIT Sloan School of Management, is the innovator behind 15.071 (The Analytics Edge)A course on the MIT Open Learning’s Mitx This attracted hundreds of thousands of learners online and served as inspiration behind the book series. Bertsimas has taken a break in research and his work in Mit Open Learning to discuss how the field of analysis transforms the health care system and sharing surprising ways of analyzes that are already used in hospitals.
Q: How does the field of analysis change the way hospitals provide care and manage their operations?
A: As an agademic, I have always suited to educate, write publications and use what we do in practice. Therefore, I founded Holistic optimization of the hospital (H20) in order to optimize hospital operations with automatic learning to improve patient care. We have developed a variety of tools at the MIT and implemented them in hospitals around the world. For example, we manage the duration of the patient’s stay and their deterioration indices (a computerized tool which predicts the risk of clinical deterioration of a patient); We manage the optimization of nurses and how hospitals can allocate human resources appropriately; And we optimize the blocks for surgeries. This is the start of a change where analysis and AI methods are now used quite widely. I hope this work and this book accelerate the effect of using these tools.
In addition, I taught A course of nine conferences Twice with Agni and Holly in the Hartford hospital system, where I realized that these analysis methods – which are generally not taught in medical schools – can be demonstrated for health practitioners, including doctors, nurses and administrators. To have an impact, you must have appropriate methods, implement them and apply them, but you must also educate people on how to use them. This is well linked to my role in Open Learning, where our goal is to educate learners worldwide. In fact, open learning is launched this AI universal autumn, a dynamic online learning experience that provides complete knowledge of artificial intelligence, preparing a global public of employment learners on our rapidly evolving labor market.
Q: What are the surprising ways whose analyzes are used in the health care most people would not expect?
A: Using the analysis, we have reduced the duration of the patient’s stay at Hartford hospital from 5.67 days to five days. We have an algorithm that predicts the probability of patients to be released; Therefore, doctors prioritize patients with the greatest probability, preparing them at the exit. This means that the hospital can treat many more patients and that patients stay in hospital less time.
In addition, when hospitals have increased in the renewal of nurses during the COVVI-19 pandemic, we have developed an analysis system which takes into account equity and equity and decreases the costs of overtime, giving preferred slots to nurses and considerably reducing overall turnover. These are only two examples; There are many others where an analytical perspective for health care and medicine has made a material difference.
Q: For the future, how do you see artificial intelligence shaping the future of health care?
A: In a very significant way – we use automatic learning to make better predictions, but generative AI can explain them. I already see a movement in this direction. It is really the evolution of the AI that made it possible, and it is exciting. It is also important for the world, due to its ability to improve care and save lives.
For example, thanks to our program to the Hartford hospital system, we discovered that a patient is getting worse and predicted by the analysis that he would still worsen. After our prediction, doctors examined the patient more closely and discovered that the patient had an early case of sepsis, a fatal affection in which the body reacts badly to an infection. If we had not detected septicemia earlier, the patient could have died. It made a real difference in the rescue of a person’s life.
Q: If you had to describe “the advantage of analysis in health care” in one or two words, what would they be and why?
A: The book is a progressive transition in health care because it is able to affect the health care sector in a way that has never been done before. The book really describes my work in health care and its applications in the past decade.