My name is Praveen Kumar, and I was born in Bharat, also known as India. Currently, I work as a Research Assistant Professor at the School of Medicine, University of New Mexico (UNM).
I hold a Bachelor’s degree in Computer Engineering from the National Institute of Technology Surat and both a Master’s and Ph.D. in Computer Science from the University of New Mexico, Albuquerque, USA. After completing my undergraduate degree, I spent 12 years working in the IT industry across the banking, insurance, and travel sectors, holding roles such as Software Engineer, System Analyst, and Associate Project Manager. However, my passion for artificial intelligence (AI) and machine learning (ML) led me to transition into academia. I returned to graduate school to pursue advanced studies, culminating in a Ph.D.
My research expertise lies in health informatics and cheminformatics, focusing on developing AI/ML models and algorithms to extract meaningful insights from complex and noisy data. This includes analyzing patient health data, chemical compound datasets, and biomedical knowledge graphs. I actively engage in collaborative, multidisciplinary projects with researchers from various departments. In health informatics, my work aims to analyze patient data to detect mental health conditions and co-occurring disorders. In cheminformatics, I focus on identifying potential drug compounds through the analysis of chemical datasets. Additionally, my research in biomedical knowledge graphs involves imputing associations between biomedical entities such as genes and diseases. Recently, I have begun developing ML models to facilitate the early detection of patients at risk for diabetes and other chronic diseases.
Beyond my academic research, I have experience teaching and mentoring, primarily gained during my time in the IT industry. There, I was responsible for training new team members in both technical skills and domain-specific knowledge.
Research Publications
Journal Articles
- P. Kumar and C. G. Lambert, “Positive unlabeled learning selected not at random (pulsnar): Class proportion estimation without the selected completely at random assumption”, PeerJ Computer Science, 2024.
- P. Kumar, F. Moomtaheen, S. A. Malec, J. J. Yang, C. G. Bologa, K. A. Schneider, Y. Zhu, M. Tohen,G. Villarreal, D. J. Perkins, E. M. Fielstein, S. E. Davis, M. E. Matheny, and C. G. Lambert, “Detecting opioid use disorder in health claims data with positive unlabeled learning”, IEEE JBHI, 2024.
- M. Ranjbar, J. J. Yang, P. Kumar, D. R. Byrd, E. L. Bearer, and T. I. Oprea, “Autophagy dark genes: Can we find them with machine learning?”, Natural Sciences, e20220067, 2023.
- J. E. Evangelista, D. J. Clarke, Z. Xie, G. B. Marino, V. Utti, S. L. Jenkins, T. M. Ahooyi,C. G. Bologa, J. J. Yang, J. L. Binder, P. Kumar, C. G. Lambert, J. S. Grethe, E. Wenger, D. Taylor,T. I. Oprea, B. d. Bono, and A. Ma’ayan, “Toxicology knowledge graph for structural birth defects”,Communications Medicine, vol. 3, no. 1, p. 98, 2023.
- L. Jarratt, J. Situ, R. D. King, E. Montanez Ramos, H. Groves, R. Ormesher, M. Cossé, A. Raboff,A. Mahajan, J. Thompson, et al., “A comprehensive covid-19 daily news and medical literature briefing to inform health care and policy in new mexico: Implementation study”, JMIR Medical Education, vol. 8, no. 1, e23845, 2022.
- J. Binder, O. Ursu, C. Bologa, S. Jiang, N. Maphis, S. Dadras, D. Chisholm, J. Weick, O. Myers, P. Kumar, et al., “Machine learning prediction and tau-based screening identifies potential alzheimer’s disease genes relevant to immunity”, Communications Biology, vol. 5, no. 1, pp. 1–15, 2022.
- A. Nestsiarovich, P. Kumar, N. R. Lauve, N. G. Hurwitz, A. J. Mazurie, D. C. Cannon, Y. Zhu, S. J. Nelson, A. S. Crisanti, B. Kerner, et al., “Using machine learning imputed outcomes to assess drug-dependent risk of self-harm in patients with bipolar disorder: A comparative effectiveness study”, JMIR mental health, vol. 8, no. 4, e24522, 2021.
- P. Kumar, A. Nestsiarovich, S. J. Nelson, B. Kerner, D. J. Perkins, and C. G. Lambert, “Imputation and characterization of uncoded self-harm in major mental illness using machine learning”, Journal of the American Medical Informatics Association, vol. 27, no. 1, pp. 136–146, 2020.
- G. Zahoranszky-Kohalmi, V. B. Siramshetty, P. Kumar, M. Gurumurthy, B. Grillo, B. Mathew, D. Metaxatos, M. Backus, T. Mierzwa, R. Simon, et al., “A workflow of integrated resources to catalyze network pharmacology driven covid-19 research”, Journal of Chemical Information and Modeling, vol. 62, no. 3, pp. 718–729, 2022.
- J. F. Cavanagh, P. Kumar, A. A. Mueller, S. P. Richardson, and A. Mueen, “Diminished eeg habituation to novel events effectively classifies parkinson’s patients”, Clinical Neurophysiology, vol. 129, no. 2, pp. 409–418, 2018.
Conference Posters
- P. Kumar and V. T. Metzger, “Predicting type 2 diabetes risk: A non-negative matrix factorization approach for feature selection”, in IEEE BHI, 2024.
- P. Kumar, F. Moomtaheen, S. A. Malec, J. J. Yang, C. G. Bologa, K. A. Schneider, Y. Zhu, M. Tohen, G. Villarreal, D. J. Perkins, E. M. Fielstein, S. E. Davis, M. E. Matheny, and C. G. Lambert, “Quantifying the opioid use disorder crisis: Pulsnar finds nearly 3/4 undiagnosed”, in OHDSI Symposium, 2024.
- P. Kumar, V. Metzger, S. Purushotham, P. Kedia, C. G. Lambert, and J. Yang, “Illuminating the druggable genome (idg) scientific use cases powered by the cfde data distillery biomedical knowledge graph, integrating multiple common fund datasets”, in Common Fund Data Ecosystem (CFDE) All-Hands Meeting, 2024.
- P. Kumar and C. G. Lambert, “Improving the detection of behavioral health conditions through positive and unlabeled learning: Opioid use disorder”, in OHDSI Symposium, 2023.
- P. Kumar, J. Tsosie, and C. G. Lambert, “Improving the detection of behavioral health conditions through positive and unlabeled learning: Self-harm and opioid use disorder”, in UNM Brain and Behavioral Health, 2023.
- P. Kumar, S. E. Davis, M. E. Matheny, G. Villarreal, Y. Zhu, M. Tohen, D. J. Perkins, and C. G. Lambert, “Pulsnar: Positive unlabeled learning selected not at random–towards imputing undocumented conditions in ehrs and estimating their incidence”, in OHDSI Symposium, 2022.
- S. E. Davis, P. Kumar, N. R. Lauve, S. K. Parr, D. Park, M. E. Matheny, G. Villarreal, Y. Zhu, M. Tohen, G. Uhl, D. J. Perkins, and C. G. Lambert, “Disparities in coded and imputed post-traumatic stress disorder and self-harm among us veterans”, in AMIA, 2021.
- P. Kumar, N. R. Lauve, S. E. Davis, S. K. Parr, D. Park, M. E. Matheny, G. Villarreal, G. Uhl, Y. Zhu, and M. Tohen, “Detecting ptsd and self-harm among us veterans using positive unlabeled learning”, in OHDSI Symposium, 2021.
- P. Kumar, J. J. Yang, D. Byrd, O. Ursu, C. G. Bologa, S. L. Mathias, J. Berendzen, and T. I. Oprea, “Proteingraphml – predicting disease-to-protein associations from a biomedical knowledge graph”, in FASEB, 2021.
- A. Nestsiarovich, P. Kumar, N. R. Lauve, A. J. Mazurie, N. G. Hurwitz, D. C. Cannon, Y. Zhu, S. J. Nelson, A. S. Crisanti, B. Kerner, M. Tohen, D. J. Perkins, and C. G. Lambert, “Comparing drug-dependent risk of self-harm in bipolar disorder using machine learning imputed outcomes”, in OHDSI Symposium, 2020.
- P. Kumar, A. Nestsiarovich, S. J. Nelson, B. Kerner, D. J. Perkins, and C. G. Lambert, “Visit level machine learning imputation of uncoded self-harm in major mental illness and characterization of incidence of self-harm”, in OHDSI Symposium, 2019.
- P. Kumar, A. Nestsiarovich, A. J. Mazurie, N. G. Hurwitz, S. J. Nelson, and C. G. Lambert, “Visit level suicidality/self-harm phenotyping in bipolar disorder”, in OHDSI Symposium, 2017.
- P. Kumar, Amritansh, and C. G. Lambert, “Transforming the 2.33m-patient medicare synthetic public use files to the omop cdmv5: Etl-cms software and processed data available and feature-complete”, in OHDSI Symposium, 2016.
Conference Talks
- P. Kumar, F. Moomtaheen, S. A. Malec, J. J. Yang, C. G. Bologa, K. A. Schneider, Y. Zhu, M. Tohen,G. Villarreal, D. J. Perkins, E. M. Fielstein, S. E. Davis, M. E. Matheny, and C. G. Lambert, “Detecting opioid use disorder in health claims data with positive unlabeled learning”, in IEEE BHI, 2024.
- P. Kumar, V. Metzger, S. Purushotham, P. Kedia, C. G. Lambert, and J. Yang, “Illuminating the druggable genome (idg) scientific use cases powered by the cfde data distillery biomedical knowledge graph, integrating multiple common fund datasets”, in Common Fund Data Ecosystem (CFDE) All-Hands Meeting, 2024.
- P. Kumar, A. Nestsiarovich, A. J. Mazurie, N. G. Hurwitz, S. J. Nelson, and C. G. Lambert, “Visit level suicidality/self-harm phenotyping in major mental illness”, in AMIA, 2018.
Ph.D. Dissertation
- “Machine learning methods for computational phenotyping using patient healthcare data with noisy labels”, The University of New Mexico, Albuquerque, NM, Dec. 2022.
Colloquium Talk
- “Imputation and characterization of uncoded self-harm in major mental illness using machine learning” – Department of Computer Science, University of New Mexico. 16 September 2020
Peer Review Activities
- Reviewed two posters for American Medical Informatics Association (AMIA 2025) conference
- Reviewed an oral presentation for American Medical Informatics Association (AMIA 2025) conference
- Reviewed a manuscript for Dove Medical Press journal – 2024
- Reviewed a manuscript for PLOS One journal – 2024
- Reviewed a manuscript for International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME 2024)
- Reviewed a manuscript for International Conference on Electrical and Computer Engineering Researches (ICECER 2024)
- Reviewed a manuscript for International Conference on Electrical, Computer and Energy Technologies (ICECET 2024)
Industry Experience
Company | Role | Duration | Location |
Interglobe Inc. | System Analyst/Associate Project Manager | Jul 2011–Aug 2015 | Denver, USA |
Interglobe Ltd. | Lead Software Engineer | May 2007–Jul 2011 | Gurugram, India |
Fiserv Ltd. | System Analyst | Apr 2006–May 2007 | Noida, India |
Computer Sciences Corporation Ltd. | Software Engineer | Dec 2004–Mar 2006 | Noida, India |
Satyam Computer Services Ltd. | Software Engineer | Jul 2003–Dec 2004 | Hyderabad/Pune, India |
Education
Degree | University | Year |
Ph.D. (Computer Science) | University of New Mexico, Albuquerque, NM, USA | 2022 |
M.S. (Computer Science) | University of New Mexico, Albuquerque, NM, USA | 2017 |
B.E. (Computer Engineering) | Sardar Vallabhbhai National Institute of Technology, Surat, Gujarat, India | 2003 |
Technical Skills
- Programming Languages: Python, R, MATLAB, PHP, C, SQL, CQL, HTML, JavaScript, CSS
- Databases: Neo4j, MySQL, and PostgreSQL
- Operating Systems: Windows, and Linux
- Web Servers: Apache, and Nginx
Scholarships and Awards
- OHDSI Top Community Contributor Award at the 2021 OHDSI Symposium (2021)
- Best poster award at the 2016 OHDSI symposium collaborator showcase (2016)
- Received Amigo Scholarship from the University of New Mexico (2015–2017)
- Third prize in the national level open software contest held at the Indian Institute of Technology (IIT) Kharagpur for an open-source C-based software ‘Hindi Notepad’ (2002)
- Third prize in the national level open software contest held at the National Institute of Technology(NIT) Surat for an open-source C-based software ‘Hindi Notepad’ (2002)
Hobbies and Interests
Apart from my research pursuits, I have diverse interests. I am passionate about exploring the ancient history of world civilizations, delving into the mysteries and achievements of past cultures. I am keenly interested in finance and stock market investments, as I enjoy analyzing economic trends. In my free time, I teach mathematics to middle and high school students.