About Abdullah Al-Mamun
Dr. Abdullah Al-Mamun is an Assistant Professor in the Department of Pharmaceutical Systems and Policy in the School of Pharmacy. He received his PhD in Computing and Information Sciences from the University of Northumbria at Newcastle, UK.
- West Virginia University School of Pharmacy
- Pharmaceutical Systems & Policy
- PhD, University of Northumbria, Newcastle, UK
1322: CLINICAL CHARACTERISTICS AND OUTCOMES OF ACUTE KIDNEY INJURY IN CRITICALLY ILL ADULTS
T Brothers, M Al-Mamun
Critical Care Medicine 50 (1), 662
Evaluating the Association and Predictability of Complex Medication Regimen Scores with Clinical Outcomes Among the Critically Ill
MA Al-Mamun, J Strock, Y Sharker, R Schmidt, K Shawwa, D Slain, ...
Survival and recovery modeling of acute kidney injury in critically ill adults
842: Machine Learning Models to Validate a Medication Regimen Complexity Scoring Tool
The full publications list can be found here
ResearchGate profile can be found here
Dr. Al-Mamun has taught the following courses.
1. PHAR 786: Health Svcs Res/Sec Databases, Spring 2022
2. PHAR 769: Adv Hlth Service Rsrch Methods, Fall 2022
3. PHAR 788: Grad Sem-Hlth Outcomes Rsrch, Fall 2022
About Abdullah Al-Mamun
Dr. Abdullah Al-Mamun is an Assistant Professor in the Department of Pharmaceutical Systems and Policy in the School of Pharmacy at West Virginia University (WVU). He received his PhD in Computing and Information Sciences from the University of Northumbria at Newcastle, UK. Prior to joining WVU, he worked as a Health Outcomes Data Science faculty in the College of Pharmacy at the University of Rhode Island. He completed two postdoctoral fellowships in Epidemiology of Microbial Diseases in the Department of Population Medicine & Diagnostic Sciences at Cornell University and in the Yale School of Public Health at Yale University.
In training, he is a health data scientist specializing in the areas of health outcomes, data science and epidemiology. He brings interdisciplinary research experiences in building mathematical modeling and health data science tools (predictive models, machine learning) to understand disease dynamics at both individual- and population level. His research provides cutting-edge methods and tools to interpret and address the research questions related to health outcomes, big data, and epidemiological surveillance systems. His current research is expanded on three themes: (1) understanding polysubstance use among the people who use opioids using state- and national-level surveillance datasets, (2) understanding medication regimen complexity among critically ill patients using the intensive care unit data, and (3) understanding spatiotemporal dynamics of vector-borne diseases (West Nile and Eastern Equine Encephalitis Viruses) in the USA using national-level surveillance datasets.
HealBig - Health Outcomes and BigData Informatics
Dr. Al-Mamun’s research lab name is HealBig- Health Outcomes and BigData Informatics. HealBig mainly focuses on understanding complex data problems in health outcomes and services-related research problems. HealBig develops and improves methods like mathematical and agent-based models, decision support systems, data mining, and machine learning within the health outcomes research domain. The overarching goal of HealBig is to develop health data science tools through interdisciplinary collaboration among health data scientists, physicians, clinical pharmacists, and other healthcare professionals.
Acute Kidney Injury (AKI) and Chronic Kidney Disease (CKD)
HealBig develops new and novel methods and tools to understand AKI among hospitalized patients. AKI occurred in over 1 of 5 hospitalizations in the U.S. Acute kidney injury (AKI) is a common and severe clinical event affecting up to 15.0% of hospitalized patients and up to 50.0% of intensive care unit patients. AKI can sometimes lead to chronic kidney disease (CKD). The existing epidemiology studies identify AKI as an independent risk factor for CKD, including End Stage Renal Disease (ESRD). In our lab, we utilized a range of datasets (e.g., EHR data, hospitalization data, national-level clinical and survey data) to understand the correlates of AKI and CKD among different populations. The existing projects related to AKI and CKD are provided below.
- AKI among the critically ill patients
- CKD progression and Clinical outcomes
- Impact of nephrotoxic medications
- Complex medication regimens and polypharmacy
Polysubstance Use and Opioid Epidemic
West Virginia (WV) is currently the 8th highest opioid prescribing state but has the highest opioid overdose fatality rate. Most fatal overdoses involved synthetic illicit opioids such as fentanyl or fentanyl analogs, usually with multiple drugs, including other opioids, benzodiazepines, methamphetamine/other stimulants, or antidepressants. However, polysubstance involvement in fatal and non-fatal WV overdoses is unpredictable and poorly characterized. Thus, it is important to address multiple substance use in overdose response programs and opioid misuse treatment. Our project team works on multiple projects to develop data mining and machine learning tools to understand the patterns of polysubstance use and
correlates of fatal and non-fatal drug overdoses. We utilized state-level datasets from WVOCME: West Virginia Office of Chief Medical Examiner - Forensic Drug Database [FDD]), WV CSMP: West Virginia Board of Pharmacy Controlled Substance Monitoring Program, and TriNetx: an electronic health records dataset consisting of 2 million unique patient records.
The HealBig created a project team consisting of clinicians, pharmacists and nurses to understand the diagnosis delays and correlates to multiple rare diseases. So far, we have investigated two rare diseases: Transthyretin Amyloid Cardiomyopathy (ATTR-CM) and Merkel Cell Carcinoma (MCC). Our goal is to develop prognostic and prediction tools to identify rare diseases timely promptly.
- Digital Health
- Clinical Decision Support System
- Health Outcomes
- Health Resource Utilizations
- Health Outcomes Data Science
- Machine Learning
- Fatal and non-fatal drug overdoses
- Rare Diseases
- Infectious Diseases
- Mathematical modeling (infectious disease, agent-based, cellular automata, and dynamic models)
- Statistical modeling (regressions, time series models )
- Data mining (association rule mining, clustering)
- Machine learning
Google Scholar link https://scholar.google.com/citations?user=9Ga2RnYAAAAJ&hl=en
ResearchGate link https://www.researchgate.net/profile/Mohammad-Al-Mamun-5