BCH AI and Machine Learning Work Group: Contemporary Symbolic Regression Methods for Interpretable Machine Learning

Speaker: William La Cava, PhD, at Boston Children's Hospital

Date: September 17, 2021 at 09:30AM - 10:30AM

Most interpretable machine learning research focuses on explaining the outputs of black-box models. A different, and promising, approach is to use machine learning to find the simplest possible model that meets certain performance criteria; this is the pursuit of symbolic regression. In this talk I will discuss the concepts of interpretability and explainability, and how they are used in the machine learning world. I will then discuss a pre-print that will be published in the Neurips Datasets and Benchmarks track later this year. In it, we attempt to benchmark many different approaches to symbolic regression on hundreds of problems in order to determine the strengths and weaknesses of current methods. I will discuss what lies ahead and implications for how clinicians and patients receive and process models that increasingly appear in the health system.  

This event is only open to Boston Children's staff. If you would like to attend the Zoom details, please email CHIP@childrens.harvard.edu. 

William La Cava is a new member of the faculty in CHIP. He received his PhD from UMass Amherst and did his postdoctoral work at University of Pennsylvania as part of the Institute for Biomedical Informatics. His work concerns the interpretability and fairness of predictive health models. 


Publications

Levy S, Wisk LE, Chadi N, Lunstead J, Shrier LA, Weitzman ER. Validation of a single question for the assessment of past three-month alcohol consumption among adolescents. Drug and alcohol dependence 2021.

Wu F, Xiao A, Zhang J, Moniz K, Endo N, Armas F, Bonneau R, Brown MA, Bushman M, Chai PR, Duvallet C, Erickson TB, Foppe K, Ghaeli N, Gu X, Hanage WP, Huang KH, Lee WL, Matus M, McElroy KA, Nagler J, Rhode SF, Santillana M, Tucker JA, Wuertz S, Zhao S, Thompson J, Alm EJ. SARS-CoV-2 RNA concentrations in wastewater foreshadow dynamics and clinical presentation of new COVID-19 cases. The Science of the total environment 2021.

Weber GM, Zhang HG, L'Yi S, Bonzel CL, Hong C, Avillach P, Gutiérrez-Sacristán A, Palmer NP, Tan AL, Wang X, Yuan W, Gehlenborg N, Alloni A, Amendola DF, Bellasi A, Bellazzi R, Beraghi M, Bucalo M, Chiovato L, Cho K, Dagliati A, Estiri H, Follett RW, García-Barrio N, Hanauer DA, Henderson DW, Ho YL, Holmes JH, Hutch MR, Kavuluru R, Kirchoff K, Klann JG, Krishnamurthy AK, Le TT, Liu M, Loh NHW, Lozano-Zahonero S, Luo Y, Maidlow S, Makoudjou A, Malovini A, Moal B, Morris M, Mowery DL, Murphy SN, Neuraz A, Ngiam KY, Okoshi MP, Omenn GS, Patel LP, Pedrera-Jiménez M, Prudente RA, Samayamuthu MJ, Sanz J, Schriver ER, Schubert P, Serrano-Balazote P, Tan BW, Tanni SE, Tibollo V, Visweswaran S, Wagholikar KB, Xia Z, Zöller D, Kohane IS, Cai T, South AM, Brat GA. International Changes in COVID-19 Clinical Trajectories Across 315 Hospitals and 6 Countries: a 4CE Consortium Study. Journal of medical Internet research 2021.

Mandl KD, Perakslis ED. HIPAA and the Leak of "Deidentified" EHR Data. Reply. The New England journal of medicine 2021.

Rees CA, Monuteaux MC, Herdell V, Fleegler EW, Bourgeois FT. Correlation Between National Institutes of Health Funding for Pediatric Research and Pediatric Disease Burden in the US. JAMA pediatrics 2021.