Program areas at Association for Health Learning and Inference
The 2nd annual Machine Learning for Health (ML4H) Symposium was held as a hybrid event on November 28, 2022 in New Orleans, LA, United States and virtually. The purpose of the symposium was to bring together machine learning researchers, clinicians, and healthcare data experts. In this years program, invited speakers and attendees discussed the utility and challenges of explainable artificial intelligence (XAI) as well as paths to practice for ML in healthcare. The two focus sessions were accompanied by 3 keynotes as well as 13 interactive research roundtables, two poster sessions, 28 accepted research papers, and 52 extended abstracts. The program included 3 mentorship programs and had 391 registrations with a 90% attendance rate.
Predicting High Risk Breast Cancer: Nightingale, Association for Health Learning & Inference (AHLI) and Providence St. Joseph Health hosted a High Risk Breast Cancer Prediction Contest with support from the Gordon and Betty Moore Foundation that ended in May 2023. Every year, 40 million women get a mammogram; some go on to have an invasive biopsy to better examine a concerning area. To advance medical knowledge on identifying features of cancers that will metastasize, we hosted an earlier machine contest to identify the cancer stage from more than 72,000 biopsy slides provided by Providence Oncology. Based on our findings from the first contest, we hosted a second high risk breast cancer contest on a balanced subset in terms of the race and ethnicity of patients as well as cancer stages. Thirty (30) teams entered this contest, and awards were given to the top 2 teams that submitted the winning models. To support repeatable science and collaborative research, the win
The 4th annual Conference on Health, Inference, and Learning (CHIL) was held on June 22-24, 2023 in Cambridge, Massachusetts, USA. The goal of the conference is to bring together a variety of disciplines at the intersection of machine learning and health. CHIL is designed to spark insight-driven dialogue on new and emerging ideas. To facilitate discussion and collaboration, we target a cross-disciplinary representation of clinicians and researchers, from industry and academia, in machine learning, health policy, epidemiology, statistics, economics, and other related areas. CHIL 2023 featured seven keynotes, three invited talks, three panel discussions, five research roundtables, three debates, 12 oral talks, and poster sessions for accepted papers and doctoral works, and five lightning talks. Thirty-three (33) papers were accepted into the proceedings. In total, 198 people registered for the event, and 190 people attended in-person, reflecting a high (96%) attendanc