Quantitative Health Sciences Calendar

Description: This talk will explore the development and application of an AI-powered image analysis pipeline designed to classify at-home COVID-19 rapid antigen test results. By employing machine learning techniques, including image matching and transfer learning, this method aims to address common issues with human interpretation, such as faint test lines and people suffering from visual impairments. We will discuss the system’s architecture, its performance across various test brands, and how it improves diagnostic accuracy in real-world, non-laboratory settings. The potential of AI to standardize rapid test interpretations and enhance public health outcomes will also be highlighted.  

Bio: Dr. Xian Du is an Associate Professor at UMass Amherst, with research focusing on high-resolution, large-area, and fast-speed sensing, machine vision, and pattern recognition technologies for flexible and wearable electronics printing, as well as personalized health monitoring. He earned his Ph.D. in Innovation of Manufacturing Systems and Technology from the Singapore-MIT Alliance. Before joining UMass, Dr. Du was a research scientist at MIT, where he invented concentric circular trajectory scanning and super-resolution techniques for large area imaging. He is the recipient of NSF CAREER Award and a senior member of IEEE, ASME, and OSA.  

Bio: Meysam Safarzadeh is a PhD candidate at the Intelligent Sensing Lab, specializing in deep learning and smart health monitoring technologies. At the University of Massachusetts Amherst, he has played a key role in developing AI-driven health diagnostics. His work spans multiple projects focused on integrating advanced computational techniques with healthcare innovations to enhance medical diagnostics and patient care. 

Click here to join or call  1 301 715 8592, Meeting ID: 948 2951 6040 password: 202286

Description: Type 2 diabetes imposes a significant economic burden on healthcare systems. Interdisciplinary healthcare teams can offer patient-centered care by integrating medical, behavioral, and social support services. This research evaluated the cost-effectiveness of a clinical pharmacist and community health worker team-based mobile health intervention for diabetes adherence support (mDAS) among African American and Latinx individuals with elevated hemoglobin A1c (HbA1c). Cost-effectiveness was assessed in terms of cost per quality-adjusted life year gained, compared to usual care, using a cohort transition Markov model from a health system perspective. 

Bio: Mrinmayee Joshi is a PhD Candidate in the Department of Pharmacy Systems, Outcomes and Policy at the University of Illinois Chicago (UIC) College of Pharmacy. She has completed fellowships at AbbVie Inc, in their Health Economics and Outcomes Research - Oncology team, and at the FDA Center for Drug Evaluation and Research – Office of New Drugs. Her primary research interests include evaluating the safety, effectiveness and value of health care interventions, including pharmaceuticals and clinical pharmacy services. 

Click here to join or call  1 301 715 8592, Meeting ID: 948 2951 6040 password: 202286