Intae Moon

itmoon@mit.edu

Hello! My name is Intae (pronounced IN-teh) and I'm currently pursuing a PhD in Electrical Engineering and Computer Science at Massachusetts Institute of Technology (MIT). I've been advised by Professor Alexander Gusev at the Dana-Farber Cancer Institute and Harvard Medical School and Professor Marzyeh Ghassemi at CSAIL, MIT. Before starting my current PhD thesis work, I was advised by Professor David Perreault at MIT Research Laboratory of Electronics (RLE) and worked on electrical energy conversion and control for my master's thesis. I received B.S. in electrical and computer engineering from the University of Illinois, Urbana-Champaign.

At the intersection of medicine and AI, my research is focused on harnessing the depth of clinical data to develop evidence-based decision support tools in medicine, while mitigating potential harms from biased AI algorithms.

CV / LinkedIn / Google Scholar / GitHub / Twitter

Announcements

11/4/23: I presented our recent work titled "Robust and fair time-to-event framework for predicting cancer-associated Venous Thromboembolism (VTE) using routinely-collected clinical and panel-sequencing data" at American Society of Human Genetics (ASHG) 2023 in Washington DC! See our extended abstract and poster below.
8/7/23: I’m excited to share that our work "Machine learning for genetics-based classification and treatment response prediction in cancer of unknown primary" has been published in Nature Medicine!
5/9/23: I’m happy to announce that I will be presenting our recent work SurvLatent ODE (see paper and poster) as a poster at Symposium on Artificial Intelligence for Learning Health Systems (SAIL) conference in Puerto Rico!
12/27/22: I’m excited to share our work "Utilizing Electronic Health Records (EHR) and Tumor Panel Sequencing to Demystify Prognosis of Cancer of Unknown Primary (CUP) patients". See here for the pre-print.
10/25/22: I’m excited to announce that I've been selected as a predoctoral semifinalist for the 2022 Charles J. Epstein Trainee Awards for Excellence in Human Genetics Research, presented by the American Society of Human Genetics (ASHG). 60 semifinalist and 18 finalist were chosen among over 700 applicants.
6/15/22: I’m excited to share that I won the 2022 Carlton E. Tucker Award for teaching excellence, thanks to the fantastic teaching staff and students of Machine Learning for Healthcare at MIT. All teaching materials are available at this link.
5/30/22: I’m excited to announce that I'll be working with Google Health AI team over Summer (full-time) and Fall 2022 (part-time).
5/22/22: I’ll be presenting "Utilizing Electronic Health Records (EHR) and Tumor Panel Sequencing to Demystify Prognosis of Cancer of Unknown Primary (CUP) patients" in the poster session (5/23/22) at Symposium on Artificial Intelligence for Learning Health Systems (SAIL). We'll post the pre-print soon.
4/20/22: I’m excited to share our work on a new generative, Neural ODE based time-to-event model for longitudinal data with competing risks, SurvLatent ODE. See here for the pre-print.

Selected Publications

Please see my Google Scholar page for a full list of my publications.

Robust and fair time-to-event framework for predicting cancer-associated Venous Thromboembolism (VTE) using routinely-collected clinical and panel-sequencing data

Intae Moon, Hyewon Jeong, Alexander Gusev, and Marzyeh Ghassemi

American Society of Human Genetics (ASHG), 2023: [extended abstract], [poster]
Machine learning for genetics-based classification and treatment response prediction in cancer of unknown primary

Intae Moon, Jaclyn LoPiccolo, Sylvan C. Baca, Lynette M. Sholl, Kenneth L. Kehl, Michael J. Hassett, David Liu, Deborah Schrag, and Alexander Gusev

Nature Medicine, 2023: [manuscript], [codes]

Featured on MIT News and DFCI News!

We have also published a Research Briefing in Nature Medicine.
SurvLatent ODE: A Neural ODE based time-to-event model with competing risks for longitudinal data improves cancer-associated Venous Thromboembolism (VTE) prediction

Intae Moon, Stefan Groha, and Alexander Gusev

Proceedings of Machine Learning Research (PMLR), Machine Learning for Healthcare 2022:

[manuscript], [codes]
Utilizing Electronic Health Records (EHR) and Tumor Panel Sequencing to Demystify Prognosis of Cancer of Unknown Primary (CUP) patients

Intae Moon, Sylvan C. Baca, Kenneth L. Kehl, and Alexander Gusev

Symposium on Artificial Intelligence for Learning Health Systems (SAIL), 2022: [abstract]
A high-performance 65 w universal ac-dc converter using a variable-inverter-rectifier-transformer with improved step-down capability

Intae Moon, Mike K. Ranjram, Sombuddha Chakraborty, and David J. Perreault

IEEE Energy Conversion Congress and Exposition (ECCE) 2019: [paper link]
A wide operating range converter using a variable-inverter-rectifier-transformer with improved step-down capability

Intae Moon, Mike K. Ranjram, Sombuddha Chakraborty, and David J. Perreault

IEEE Applied Power Electronics Conference and Exposition (APEC) 2019: [paper link]
Variable-inverter-rectifier-transformer: A hybrid electronic and magnetic structure enabling adjustable high step-down conversion ratios

Mike K. Ranjram, Intae Moon, and David J. Perreault

IEEE Transactions on Power Electronics 2018: [paper link]
Design and implementation of a 1.3 kW, 7-level flying capacitor multilevel AC-DC converter with power factor correction

Intae Moon, Carl F Haken, Erik K Saathoff, Ethan Bian, Yutian Lei, Shibin Qin, Derek Chou, Steven Sedig, Won Ho Chung, and Robert CN Pilawa-Podgurski

IEEE Applied Power Electronics Conference and Exposition (APEC) 2017: [paper link]

Teaching

In Spring 2022, I taught 6.871 : Machine Learning for Healthcare at MIT as a teaching assistant. I created weekly recitation content and developed Python-based problem sets, in order to improve students' understanding of real-world healthcare applications of machine learning. I also coordinated collaborations between clinical researchers from MIT and Harvard, and students for course projects, and provided mentorship on student projects, leading to notable publications. I received the Carlton E. Tucker Award for Teaching Excellence (overall instructor rating: 6.8/7.0).
In Spring 2019, I was a TA for 6.004 : Computation Structures at MIT. I helped design and build new laboratory assignments and course materials in a RISC-V assembly and hardware description language called Bluespec.

Awards

Charles J. Epstein Trainee Awards for Excellence in Human Genetics Research
Location: American Society of Human Genetics (ASHG), Los Angeles, CA, August 2022
Details: Predoctoral semifinalist; chosen as one of the 60 semi-finalists out of over 700 applicants.
Carlton E. Tucker Award for Teaching Excellence
Location: MIT Electrical Engineering and Computer Science, Cambridge, MA, June 2022
Details: Annual department teaching award.
Best Innovation Award
Location: IEEE International Future Energy Challenge, National Taiwan University, Taipei, Taiwan, July 2016
Details: Team Leader; led the team of undergraduate students to design and build a successful 1.3 kW power converter for an efficient data center power delivery architecture.