Better Than Humans: Building AI That Is Less Prejudiced, More Fair

January 21, 2022 | 12pm (PST)

Speaker: Dr. Leo Anthony Celi, Clinical Research Director and Principal Research Scientist, MIT Laboratory for Computational Physiology; Staff Physician, Beth Israel Deaconess Medical Center (BIDMC)

Title: Better than Humans: Building AI that is less prejudiced, more fair

Abstract: Artificial intelligence (AI) in healthcare is a codification of clinical practice and the medical knowledge system, as it is developed from their digital exhaust. It is an encryption of a clinical practice that leads to outcome disparities, and a medical knowledge system that is derived from research that disproportionately represents a majoritized population. ​​When we train a model to predict or optimize an outcome from a set of features pertaining to the patient and the disease, we assume that treatment decisions are the same across similar patients. But they are not. For example, Black patients are less likely than white patients to receive pain medication for the same symptoms, a pattern of disparate treatment that holds even for children. Using audio-recorded outpatient encounters from urban primary care physicians, a study found that doctors spend less time and build less emotional rapport with obese patients compared to normal weight patients. A 2015 survey of 28,000 trans individuals in the US revealed a third of respondents had a negative encounter with a healthcare provider, including being refused treatment. Women with heart attacks have worse outcomes when cared for by male cardiologists. For those in this exciting field of medical AI, we need to remind ourselves that data routinely collected in the process of care are heavily influenced by long-standing social, cultural, and institutional biases, as well as provider subjectivity in decision-making. It is therefore not surprising to discover AI models developed in the healthcare domain exhibiting bias against those who already have worse outcomes to begin with.

Bio: As clinical research director and principal research scientist at the MIT Laboratory for Computational Physiology (LCP), and as a practicing intensive care unit (ICU) physician at the Beth Israel Deaconess Medical Center (BIDMC), Leo brings together clinicians and data scientists to support research using data routinely collected in the process of care. His group built and maintains the publicly-available Medical Information Mart for Intensive Care (MIMIC) database and the Philips-MIT eICU Collaborative Research Database, with more than 25,000 users from around the world. In addition, Leo is one of the course directors for HST.936 – global health informatics to improve quality of care, and HST.953 – collaborative data science in medicine, both at MIT. He is an editor of the textbook for each course, both released under an open access license. "Secondary Analysis of Electronic Health Records" has been downloaded more than a million times, and has been translated to Mandarin, Spanish, Korean and Portuguese. He is the inaugural editor of PLOS Digital Health.