Joshua Cohen

PhD in Physics Applies Scientific Expertise to Develop ML Models for Diverse Applications

Cincinnati, Ohio, United States of America

About

I am a highly motivated individual with expertise in various artificial intelligence (AI) tools, including machine learning (ML) and natural language processing (NLP). Over the course of my academic and professional career, I have developed a strong skill set in these areas, and have applied them to various domains, including mental health. At Clarigent Health, I have played a key role in developing and improving machine learning models that analyze patient speech to identify mental health concerns such as depression, anxiety, and suicide risk. In addition, I have been the principal investigator on a NIMH SBIR grant investigating machine learning model performance across different patient characteristics and settings. Moreover, I have experience in developing and implementing customer-facing dashboards using tools like PowerBI, which enable clients to interact with and derive insights from complex data sets. Through my work at Clarigent Health, I have been able to leverage my expertise in ML, NLP, and other AI-related tools to drive innovation and improve mental health outcomes through data-driven solutions.

Education

Tufts University

Ph.D., Physics / July, 2018

Medford, Massachusetts, United States of America

Experience

Clarigent Health

Chief Scientific Officer / January, 2022Present

•Leads team's scientific and technical efforts for company focused on identifying mental health risks from speech data •Direct clinical mental health data collection for machine learning model development, validation, and utility assessment •Heads communication of scientific achievements through peer-reviewed publications and conference presentations

Director of Data Science / September, 2020January, 2022

•Invented novel quantitative methods to drive product changes and improve end-to-end customer experience (e.g., automatic speaker identification, transcript quality assessments, and on-topic speech detection) •Developed customer facing dashboard and data model in Microsoft PowerBI to communicate sensitive patient data •Published 2 first author articles validating machine learning models and presented findings at international conference •Principal Investigator for Phase I NIH SBIR grant investigating and mitigating machine learning model bias •Oversaw interviewing, onboarding, training, and daily tasks of 5 data scientists

Senior Data Scientist / September, 2019September, 2020

Developed and deployed ML models in Python to identify suicidal risk, depression, and anxiety from speech data •Experimented with various ML approaches (e.g., SVM, RF, and ANN) to improve model performance •Utilized advanced NLP (e.g., word embeddings and sentiment analysis) to extract meaningful features and improve accuracy •Designed and implemented ETL pipelines to efficiently extract, transform, and load large volumes of speech data

Freelance

Data Scientist / January, 2019September, 2019

Developed models to predict mouse sleep states (sleep, REM, wake) from brain and muscle signals with 96% accuracy

UES at Air Force Research Labs

Research Scientist / August, 2018September, 2019

•Lead R&D program for medical countermeasures of directed energy in 711th HPW/Force Health Protection Branch •Principal Investigator: Feasibility of Deployed Medical System Hardening to Directed Energy, In-Vitro Cellular Response to Directed Energy, Rapid Environmental Site Assessment with Readily Available Biomaterials •Characterized emissions from ammunition causing health issues with microscopic, spectroscopic, and statistical analysis

Tufts University

Research Assistant / July, 2014July, 2018

Designed and executed original surface science experiments to probe fundamental features of nanoscale materials •Performed statistical analysis on data sets and developed complex models using Mathematica and MS Excel •Published 2 first author articles and presented findings at international conference

Publications

A Feasibility Study Using a Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in Adolescent Therapy Sessions

International Journal of Environmental Research and Public Health / Nov 05, 2020

Cohen, J., Wright-Berryman, J., Rohlfs, L., Wright, D., Campbell, M., Gingrich, D., Santel, D., & Pestian, J. (2020). A Feasibility Study Using a Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in Adolescent Therapy Sessions. International Journal of Environmental Research and Public Health, 17(21), 8187. https://doi.org/10.3390/ijerph17218187

Integration and Validation of a Natural Language Processing Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in the Emergency Department

Frontiers in Digital Health / Feb 02, 2022

Cohen, J., Wright-Berryman, J., Rohlfs, L., Trocinski, D., Daniel, L., & Klatt, T. W. (2022). Integration and Validation of a Natural Language Processing Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in the Emergency Department. Frontiers in Digital Health, 4. https://doi.org/10.3389/fdgth.2022.818705

CO adsorption on nanoislands: Ni on Au(111)

The Journal of Chemical Physics / Jun 14, 2018

Cohen, J. I., & Tobin, R. G. (2018). CO adsorption on nanoislands: Ni on Au(111). The Journal of Chemical Physics, 148(22), 224702. https://doi.org/10.1063/1.5030862

Effects of ordered islands on surface resistivity: Ni on Au(111)

The Journal of Chemical Physics / Apr 14, 2017

Cohen, J. I., & Tobin, R. G. (2017). Effects of ordered islands on surface resistivity: Ni on Au(111). The Journal of Chemical Physics, 146(14), 144703. https://doi.org/10.1063/1.4979846

Links & Social Media

Research Interests

Public Health, Environmental and Occupational Health
General Medicine
Physical and Theoretical Chemistry
General Physics and Astronomy
Join Josh on NotedSource!

At NotedSource, we believe that professors, post-docs, scientists and other researchers have deep, untapped knowledge and expertise that can be leveraged to drive innovation within companies. NotedSource is committed to bridging the gap between academia and industry by providing a platform for collaboration with industry and networking with other researchers.

For industry, NotedSource identifies the right academic experts in 24 hours to help organizations build and grow. With a platform of thousands of knowledgeable PhDs, scientists, and industry experts, NotedSource makes connecting and collaborating easy.

For academic researchers such as professors, post-docs, and Ph.D.s, NotedSource provides tools to discover and connect to your colleagues with messaging and news feeds, in addition to the opportunity to be paid for your collaboration with vetted partners.

Expert Institutions
NotedSource has experts from Stanford University
Expert institutions using NotedSource include Oxfort University
Experts from McGill have used NotedSource to share their expertise
University of Chicago experts have used NotedSource
MIT researchers have used NotedSource
Proudly trusted by
Microsoft uses NotedSource for academic partnerships
Johnson & Johnson academic research projects on NotedSource
ProQuest (Clarivate) uses NotedSource as their industry academia platform
Slamom consulting engages academics for research collaboration on NotedSource
Omnicom and OMG find academics on notedsource
Phoenix Tailings finds academic collaborations on NotedSource
Unilever research project have used NotedSource to engage academic experts

Connect with researchers and scientists like Joshua Cohen on NotedSource to help your company with innovation, research, R&D, L&D, and more.