Machine Learning in Healthcare | Computational Biology PhD Candidate | Published in Science & Nature Methods
Research Data Scientist with 7+ years of experience leading machine learning initiatives and predictive modeling in healthcare and biomedical domains.
Developing innovative machine learning solutions for healthcare and biomedical challenges.
SLIDE is a novel interpretable machine learning method designed to identify significant interacting latent factors from high-dimensional multiomic datasets, offering theoretical guarantees for inference and strict false discovery rate control without assuming specific data-generating mechanisms. Applied to single-cell and spatial omics, SLIDE outperforms existing methods in both predictive performance and biological interpretability, enabling deeper insights into molecular, cellular, and organismal phenotypes.
Research published in high-impact journals including Science and Nature Methods.
Novel machine learning framework for healthcare data analysis with interpretable outcomes. This approach improved patient stratification accuracy by 35% and has been adopted by multiple research institutions.
View PublicationIntegrated analysis of genomic, proteomic, and clinical data to identify disease mechanisms. This research established new methodologies for biomedical data analysis in tropical diseases.
View PublicationReview of methodologies for integrating diverse biomedical data types. This paper provides a comprehensive overview of current approaches and future directions in multi-omics integration.
View PublicationPredictive modeling framework for clinical applications. This research demonstrated a 27% improvement in prediction accuracy for disease outcomes using electronic medical record data.
View PublicationIdentification of key factors in disease progression using advanced statistical methods. This work was conducted in collaboration with the midwest pediatric nephrology consortium.
View PublicationTechnical and domain expertise in data science, machine learning, and healthcare analytics.
Academic and professional journey in data science and healthcare analytics.
2018 - Expected July 2025
Dissertation: "Machine Learning Approaches for Interpretable Healthcare Analytics and Clinical Decision Support"
Relevant Coursework: Advanced Machine Learning, Statistical Learning Theory, Computational Genomics, Healthcare Data Science
September 2018 – Present
Led development of SLIDE, a novel machine learning framework for healthcare data analysis, resulting in publication in Nature Methods and adoption by three research institutions.
Managed a team of 4 graduate students on multi-omics data integration projects, providing technical mentorship and strategic direction.
2015 - 2017
Thesis: "Statistical Methods for Biomedical Data Analysis"
Relevant Coursework: Regression Analysis, Categorical Data Analysis, Multivariate Statistics, Experimental Design
August 2015 – August 2017
Designed and delivered comprehensive statistics curriculum to undergraduate students, maintaining a 4.8/5.0 instructor rating.
Mentored 30+ students in statistical methods and data analysis techniques, with 5 students pursuing advanced degrees in data science.
2005 - 2009
Focus: Operations Research and Systems Engineering
Relevant Coursework: Operations Research, Systems Engineering, Probability & Statistics, Optimization
June 2009 – December 2010
Implemented optimization models for healthcare delivery systems, reducing operational costs by 18%.
Analyzed complex system requirements and translated them into technical specifications for engineering teams.
Interested in collaboration or have questions about my research? Get in touch.
javad@pitt.edu
Pittsburgh, PA
Available after July 15, 2025