ARTIFICIAL INTELLIGENCE powering the future of pharmacy

Duarte is using AI to develop novel methods to identify patients most likely to benefit from preemptive pharmacogenetic testing. Effective targeting of preemptive testing should improve personalization of medication prescribing by assuring genetic information is available to prescribers before a prescription is written.

Gong collaborates with multiple UF faculty in applying AI tools to her pharmacogenomics and precision medicine research. AI technology is assisting her research team in improving the model performance of multiple data sets that are used to advance the clinical implementation of precision medicine.

By using real-world data and AI/machine learning approaches, Guo is developing novel methods to improve health care and health equity by addressing multifaceted social determinants of health. In addition, she leverages causal and counterfactual AI predictions to identify heterogeneity in treatment effects and signals of drug repurposing. Furthermore, She is evaluating fairness and bias of AI applications and exploring new approaches to mitigate the identified bias.

Jiao’s research focuses on investigation of precision medicine that is both applicable for specific diseases and affordable, through the use of advanced study design (i.e. adaptive treatment strategy), cutting-edge statistical methods, and machine learning approaches adopting longitudinal Big Data. As a pharmacoepidemiologist, he has experience in multiple therapeutic areas with a focus on cardiology and pulmonology.

Kim envisions developing AI-assisted imaging analysis and informatics tools that will accelerate the analysis of imaging data and provide insights into better understanding of disease progression. Ultimately, the AI-based tools will help in the rational design of disease prevention and treatment strategies. She is currently focusing on optimizing clinical trial designs for Duchenne muscular dystrophy and type 1 diabetes with other UF investigators.

Li is using computing AI approaches combined with lab experiments to advance the drug discovery process. AI technology is assisting his lab in building a computational small molecule drug design platform to optimize newly developed hit compounds. These compounds could one day lead to new drug therapies to treat pancreatic, lung, colon and breast cancer.

Yanjun Li’s research interests span the fields of deep learning, drug discovery, and precision medicine, with a particular emphasis on AI-driven drug discovery. His work aims to develop innovative AI algorithms to tackle foundational life science challenges with broad scientific impacts and to optimize and automate real-world drug discovery and design pipelines.

Hasan conducts data-driven interdisciplinary research to address complex challenges in public health, contributing to healthcare decision-making, policy, and management. His primary research interests include developing fair, trustworthy and equitable AI-driven and evidence-based Clinical Decision Support Systems to help predict adverse health outcomes; and prescriptive decision analytic models to improve medication adherence and effectiveness of personalized interventions to better manage the chronic health conditions.

Lamba focuses on applying AI and machine learning techniques to advance leukemia research and diagnostics. Her NCI-funded R01s entitled ‘Genomics of AML prognosis’ and ‘Integrated systems biology of pediatric AML’ focus on applying various AI and ML approaches for developing prognostic models for leukemic stem cells using LASSO regression, creating polygenic risk scores with GLM approaches, and employing innovative dimensionality reduction methods such as PaCMAP for diagnostic and prognostic applications in AML.

McDonough is adopting new AI strategies into her data analysis to characterize and predict cardiovascular disease and cardiovascular drug response. Machine learning and AI tools are helping her integrate data from multiple sources and go beyond traditional statistical models in predicting cardiovascular events.

With expertise in pharmacy informatics and pharmacogenomics, Nguyen helps develop clinical decision support tools for UF Health’s electronic medical record system. He envisions using AI technology to develop and implement user-centered health information technology into the medical record system, which will help predict and prevent severe adverse drug reactions in patients.

Rouhizadeh develops machine learning and natural language processing methods with applications to clinical and pharmaceutical outcomes and public health, focusing on three major goals: (a) identifying signs, symptoms, diseases, disorders, and medications from unstructured electronic health records, (b) detecting signals of neurological disorders affecting children and the elderly, and (c) computational models for identifying social and behavioral determinants of health.

Seabra is developing, in collaboration with Dr. Chenglong Li, applications that teach AIs to autonomously design, screen and optimize molecules that attack selected disease targets. The process can speed up the drug discovery process by suggesting molecules to be synthesized and tested with improved chances for success.

Smith uses prediction modeling, including machine learning techniques, to develop improved methods for selecting antihypertensive treatments in patients with chronically high blood pressure. He is also applying similar techniques to improve the value of electronic health record databases in medical research by developing models that differentiate between patients with high and low degrees of data missingness.

Warren integrates AI and machine learning to assess the role neuronal ensembles in drug self-administration. His team applies these technologies to quantifies neuronal activity patterns and associates these measurements with rodent drug-seeking behavior. The incorporation of AI into their research accelerates discoveries and generates novel insights into the dynamics of neural networks in substance use behaviors.

Winterstein’s research concentrates on the evaluation of drug safety and effectiveness in real-world populations with a specific focus on child and maternal health and pediatrics. She employs AI methods to optimize measurement of variables in large health care databases and to develop prediction models for adverse drug effects. Examples of recent work include machine learning-based imputation methods to predict pregnancy onset for the evaluation of teratogenic drug effects and prediction of drug-induced hypoglycemia in hospitalized patients.

Xie is passionate about leveraging AI to understand the natural evolution of enzymes, aiming to advance therapeutic development. He combines AI, computational chemistry, and biochemistry to innovate in protein design and small molecule drug discovery.