Andrew Heusser
Managing Partner at Cognitive Insight Consulting, LLC
Greater Boston United States
Summary
🤩
Rockstar🎓
Top SchoolAndrew Heusser is a cognitive neuroscientist-turned-data scientist and founder who specializes in translating rigorous science into regulatory-grade digital health products. With a decade of experience building ML-powered features and clinical evidence pipelines, he led data science at Akili and helped secure FDA De Novo clearance for EndeavorRx, the first video game therapeutic. He now runs Cognitive Insight Consulting to design metrics, build probabilistic models, and navigate De Novo/510(k) pathways for cognitive, psychiatric, and neurological products. Andrew combines academic depth—a PhD in cognitive neuroscience and postdoc work on computational models of learning—with hands-on engineering, including open-source contributions like enhancing visualization and dimensionality tools in hypertools. He balances product impact (marketing lift, conversion gains, and shipping features) with rigorous clinical validation, making him fluent across research, product, and regulatory domains.
11 years of coding experience
11 years of employment as a software developer
Doctor of Philosophy (PhD), Cognitive Neuroscience, Human Memory, Doctor of Philosophy (PhD), Cognitive Neuroscience, Human Memory at New York UniversityBachelor of Science (BSc), Psychology, minor in Philosophy, Bachelor of Science (BSc), Psychology, minor in Philosophy at Northeastern University
English
Stackoverflow
1reputation
0reached
0answers
0questions
Github Skills (9)
scikit-learn10
data-visualizations10
data-transformation10
machine-learning10
pca10
data-visualization10
data-visualisation10
python10
scikit10
Programming languages (7)
Github contributions (5)
ContextLab/hypertools
Sep 2016 - Aug 2018
A Python toolbox for gaining geometric insights into high-dimensional data
Role in this project:
Data Scientist
Data ScientistContributions:16 releases, 1084 commits, 28 PRs in 1 year 10 months
Contributions summary:Andrew primarily focused on implementing the `plot` function, which includes features such as text vectorization using a `CountVectorizer`, topic modeling using `LatentDirichletAllocation`, data reduction with `IncrementalPCA`, and the visual presentation of data. The user also made improvements to the internal structuring and organization of the plotting code, including changes to make the animation smoother. Finally, the user developed features for the `DataGeometry` class to provide easier access to the data within plots, and added support for different reduction models.
pythondata-visualizationhigh-dimensional-datatopic-modelingtext-vectorization
ContextLab/tubeTopics
Sep 2016 - Oct 2016
Contributions:31 commits, 29 pushes, 1 branch in 1 month
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.