Will Das

Co-Founder | CTO @ Ocular Diagnostics; I.I. Rabi Scholar @ Columbia University '25; CS + ML researcher.

I.I. Rabi Scholar

CS + Cog Sci

Columbia University

Hello!

My name is Will Das. I’m an ex-founder @ Ocular Diagnostics (venture-backed MedTech startup) and cited neurobehavioral researcher broadly interested in computational medicine, applied machine learning/AI, and SaaS. Currently building in Generative AI.

See my publications and code.

2023 Kleiner Perkins Engineering Fellow.
Co-founded Ocular Diagnostics in 2021—we’re creating a data platform to diagnose neurobehavioral disorders like ADHD, using just your eye movements and performance on a 20 min cognitive test.
Co-founded and led Coding for Impact from 2018-2021, helping deliver tech to underserved NGOs across the globe.
Currently studying CS + Cog Sci @ Columbia University as an I.I. Rabi Research Scholar.

Formerly interned @:

Helix, Inc. (Software Engineer/Applied AI Intern); as Kleiner Perkins Engineering Fellow.
Nokia Bell Labs (Applied AI/ML Software Engineer Intern)
Symbotic, LCC. (ML/Software Engineer Intern)
Icahn School of Medicine at Mount Sinai (under Dr. Li Shen)
New York University Video Lab (under Dr. Yao Wang)

Areas of Interest

Computational Medicine

Computational genomics

Machine/deep learning applications to medicine

Visual Neuroscience

Oculometric analysis (pupil-size, eye-gaze, spontaneous eye blinks)

Time-series based methods

Pupil-size as indicators of cognitive processing (cognitive load, working memory, attention)

Computer Vision

Semantic segmentation/classification of biological structures from 2D/3D medical images (ultrasound)

Mammographic imaging for breast cancer risk prediction

Machine/Deep Learning

Applications to medicine

Analysis of electronic health records

Hybrid ML/DL methods for disease detection

Reach me at whd2108@columbia.edu or williamhdas@gmail.com.

selected publications

A Deep Learning Approach for Segmentation, Classification, and Visualization of 3-D High-Frequency Ultrasound Images of Mouse Embryos

Ziming Qiu, Tongda Xu, Jack Langerman, and 8 more authors

IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 2021

Bib Link

@article{qiu2021deep,
  title = {A Deep Learning Approach for Segmentation, Classification, and Visualization of 3-D High-Frequency Ultrasound Images of Mouse Embryos},
  author = {Qiu, Ziming and Xu, Tongda and Langerman, Jack and Das, William and Wang, Chuiyu and Nair, Nitin and Aristiz{\'a}bal, Orlando and Mamou, Jonathan and Turnbull, Daniel H and Ketterling, Jeffrey A and others},
  journal = {IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control},
  volume = {68},
  number = {7},
  pages = {2460--2471},
  year = {2021},
  publisher = {IEEE},
}

A novel application for the efficient and accessible diagnosis of ADHD using machine learning

Shubh Khanna, and William Das

In 2020 IEEE/ITU International Conference on Artificial Intelligence for Good (AI4G), 2020

Bib Link

@inproceedings{khanna2020novel,
  title = {A novel application for the efficient and accessible diagnosis of ADHD using machine learning},
  author = {Khanna, Shubh and Das, William},
  booktitle = {2020 IEEE/ITU International Conference on Artificial Intelligence for Good (AI4G)},
  pages = {51--54},
  year = {2020},
  organization = {IEEE},
}

A robust machine learning based framework for the automated detection of ADHD using pupillometric biomarkers and time series analysis

William Das, and Shubh Khanna

Scientific reports, 2021

Bib Link PDF

@article{das2021robust,
  title = {A robust machine learning based framework for the automated detection of ADHD using pupillometric biomarkers and time series analysis},
  author = {Das, William and Khanna, Shubh},
  journal = {Scientific reports},
  volume = {11},
  number = {1},
  pages = {1--12},
  year = {2021},
  publisher = {Nature Publishing Group},
  link = {https://www.nature.com/articles/s41598-021-95673-5},
}