Md Mahmudul Hasan

Md Mahmudul Hasan, Ph.D.

Assistant Professor

Department: Pharmaceutical Outcomes & Policy
Business Phone: (352) 273-6276
Business Email:

About Md Mahmudul Hasan

Md Mahmudul Hasan, Ph.D. is an assistant professor in the Department of Pharmaceutical Outcomes and Policy (POP) with a joint appointment in the department of Information Systems and Operations Management (ISOM) at the University of Florida. He is also the Assistant Director and the Faculty Lead of the Medical Marijuana Research Repository for the Florida state-funded Consortium for Medical Marijuana Clinical Outcomes Research. His appointment is a part of the UF’s larger AI initiative. Prior to joining the faculty at UF, Dr. Hasan worked as an Oak Ridge Institute for Science and Education (ORISE) Postdoctoral Fellow of Drug Safety and Artificial Intelligence Methods in the Center for Drug Evaluation and Research (CDER) at the United States Food and Drug Administration (FDA). Dr. Hasan has completed PhD and worked as a postdoctoral research scientist at the Decision Analytics Lab at Northeastern University, Boston, Massachusetts. He was also an active member of Northeastern’s Center for Health Policy and Healthcare Research.

Dr. Hasan conducts data-driven interdisciplinary research to address complex challenges in public health, contributing to healthcare decision-making, policy, and management. Funded by CDC in collaboration with Massachusetts Department of public health (MDPH), he has collaborated in several interdisciplinary research projects that address critical issues surrounding opioid use disorder and opioid overdose epidemic. His current research lies in the intersection of pharmaceutical outcomes and health service utilization with a focus on substance use and mental health disorder, opioid related adverse drug events, and chronic diseases. His primary research interests include developing (i) fair, trustworthy, and equitable AI-driven and evidence-based Clinical Decision Support Systems (CDSS) to help predict adverse health outcomes; and (ii) prescriptive decision analytic models to improve medication adherence and effectiveness of personalized interventions to better manage the chronic health conditions. From a methodological standpoint, Dr. Hasan leverages data science, in particular AI/machine learning, statistical modeling, and management science techniques.

Teaching Profile

Courses Taught
PHA6910 Supervised Research
QMB7933 Seminar in Information Systems and Operations Management
PHA6265 Introduction to Pharmaceutical Outcomes and Policy I
PHA7979 Advanced Research
QMB5305 Advanced Managerial Statistics

Research Profile

Open Researcher and Contributor ID (ORCID)



Advancing Equity in Opioid Use Disorder Prediction: A Bias Mitigation Algorithm for Accurate and Fair Outcomes
JMIR AI(under review)).
An Explainable Machine Learning Framework for Predicting the Risk of Buprenorphine Treatment Discontinuation among Commercially Insured Individuals for Opioid Use Disorder
Computers in Biology and Medicine (Under review). [DOI]
The Clinical Value of Counseling as a Complement to Buprenorphine Treatment for Opioid Use Disorder: A Retrospective Observational Study
The American Journal of Drug and Alcohol Abuse (Tentative submission)).
Patient outcomes following buprenorphine treatment for opioid use disorder: The influence of patient- and prescriber-level characteristics
Addiction (Under review).
Physician Practice Migration and Changes in Practice Style: A Study of Low-Value Diagnostic Imaging
Production and Operations Management (POMS) (Under second review).
Treatment Experiences for Patients Receiving Buprenorphine/Naloxone for Opioid Use Disorder: A Qualitative Study of Patients’ Perceptions and Attitudes
Substance Use & Misuse. 58(4):512-519 [DOI] 10.1080/10826084.2023.2177111.
Long-term patient outcomes following buprenorphine/naloxone treatment for opioid use disorder: a retrospective analysis in a commercially insured population
The American Journal of Drug and Alcohol Abuse. 1-11 [DOI] 10.1080/00952990.2022.2065638.
Optimizing return and secure disposal of prescription opioids to reduce the diversion to secondary users and black market
Socio-Economic Planning Sciences. [DOI] 10.1016/j.seps.2022.101457.
A machine learning based two-stage clinical decision support system for predicting patients’ discontinuation from opioid use disorder treatment: retrospective observational study
BMC Medical Informatics and Decision Making. 21(1) [DOI] 10.1186/s12911-021-01692-7. [PMID] 34836524.
A machine learning framework to predict the risk of opioid use disorder
Machine Learning with Applications. 6 [DOI] 10.1016/j.mlwa.2021.100144.
A possibility distribution‐based multicriteria decision algorithm for resilient supplier selection problems
Journal of Multi-Criteria Decision Analysis. 27(3-4):203-223 [DOI] 10.1002/mcda.1696.
Hospital Readmissions to Nonindex Hospitals: Patterns and Determinants Following the Medicare Readmission Reduction Penalty Program
Journal for Healthcare Quality. 42(1):e10-e17 [DOI] 10.1097/jhq.0000000000000199.
Patterns of buprenorphine/naloxone prescribing: an analysis of claims data from Massachusetts
The American Journal of Drug and Alcohol Abuse. 46(2):216-223 [DOI] 10.1080/00952990.2019.1674863.
Resilient supplier selection in logistics 4.0 with heterogeneous information
Expert Systems with Applications. 139 [DOI] 10.1016/j.eswa.2019.07.016.
A Systematic Review on Healthcare Analytics: Application and Theoretical Perspective of Data Mining
Healthcare. 6(2) [DOI] 10.3390/healthcare6020054. [PMID] 29882866.
Multiple criteria supplier selection: a fuzzy approach
International Journal of Logistics Systems and Management. 20(4) [DOI] 10.1504/ijlsm.2015.068488.


2022 · Northeastern University

Contact Details

(352) 273-6276
Business Street: