Medicine Master’s program at University of Minnesota-Duluth

Our mission is to provide novel and compelling insights toward optimizing health and patient outcomes by developing and implementing novel computational tools, including machine learning, natural language processing, computer vision, predictive modeling, human-computer interaction, omics-based frameworks, knowledge representation, and other complementary interdisciplinary methods.

Dr. Rubina Rizvi is one of two recipients of the Minnesota Learning Health System (MN-LHS) Mentored Career Development Award (2024).

The key objective of MN-LHS is to enable Minnesota as a learning health system (LHS) by building a robust workforce with LHS competencies, real world experience, and a support network to be successful. The MN-LHS program receives support through:.

Individualized medicine requires risk prediction tools to guide the use of interventions and preventative measures.

Founding Division Chief of Computational Health Sciences, Dr. Rui Zhang, to develop first-of-its-kind informatics framework for reducing improper dietary supplement use.

Research interests: Real-world data analytics, electronic health records, natural language processing, literature-based discovery, knowledge discovery, social media mining.

Research interests: Metabolomics, biomarker science, data science, precision medicine, circadian rhythms, critical illness.

Research interests: Proteomics of surgical complications and chronic illnesses applying Mendelian randomization to evaluate causality between exposures and health outcomes.

Research expertise: human-computer interaction, usability evaluations and workflow analysis, qualitative research, health equity, and implementation science-related work.

Research interests: knowledge representation, terminology, ontology, real world data analytics, learning health systems, health equity, mental health, and integrating biomedical, behavioral, and social sciences data.

Research Interests: artificial intelligence in medical image analysis, encompassing segmentation, diagnosis, prognosis, and biomarker identification. Additionally, he is interested in multimodal biomedical studies that utilize text, images, clinical variables, and gene data for various tasks.

We have previous and ongoing collaboration with internal units (e.g. Public Health, Computer Science, Institute for Health informatics Nursing, College of Pharmacy) and external institutions (e.g., Mayo Clinic, University of Florida, Yale University, etc).

Advances in cancer prevention, diagnosis, and treatment have dramatically improved long-term survival of those diagnosed with breast cancer. However, this success has been tempered by a parallel increased incidence of chronic conditions in breast cancer survivors, in particular cardiovascular disease (CVD), due at least in part to cardiotoxic treatment regimens. Current evidence-based guidelines for preventing and controlling CVD in breast cancer survivors are broad, and we lack clear guidance for assessing individualized risks of cardiovascular events. Existing CVD risk prediction models focus on the general population and rely only on a limited number of variables. The adoption and integration of electronic health record (EHR) systems has provided a wealth of information individual characteristics at the point of care, including unstructured clinical narratives, imaging data, and structured clinical variables. However, the real-world EHR data is highly imbalanced including the fraction of patients with CVD outcomes and the uniform distribution of time for the CVD development since BC diagnosis. Our overarching goal is to develop solid computational and theoretical foundations for learning from imbalanced real-world data, with an emphasis on BC-CVD outcome risk prediction. Specifically, we will develop a computational framework for imbalanced classification and imbalanced regression tasks on the CVD risk prediction among BC survivors using multimodal EHR data.

Advancement of health equity requires evidence and tools tailored for minority groups. The shift towards individualized precision medicine requires risk prediction tools to guide prevention and intervention. Overall risk prediction constructed from predominantly white populations can perform poorly on other ethnic groups, leading to mis-diagnosis, over-treatment and other adverse health consequences. Efforts on developing R E-specific risk prediction at local healthcare systems are limited by the small sample size caused by inadequate representability of minority populations. To address the gap and to advance precision medicine for non-white patients, it is crucial to harness minority enriched clinical data and develop risk models transferable to point of care. The All of Us (AoU) program offers a wealth of comprehensive multi-modal data on whole genome sequencing (WGS), real-world electronic health records (EHR) and patient reported outcomes (PRO) with enhanced minority participation, providing the common evidence base for learning general R E-specific risk patterns and training risk models for minority populations at local healthcare systems. In this proposal, we develop innovative methods for risk modeling in AoU data tailored for minority populations and its validation on external healthcare data. We will showcase the proposed methods in two use cases: 1) rheumatoid arthritis (RA) genome-wide association study (GWAS) at Mass General Brigham (MGB) focusing on the genetic risk factors 2) cancer cardiotoxicity prediction study at M Health Fairview (MHF) focusing on clinical and social determinants of health (SDoH) risk factors. In Aim 1, we integrate risk factor and disease onset outcome data across WGS, EHR and PRO in AoU data to construct the risk prediction model that yields better risk prediction accuracy, risk factor identification and fairness across R E groups. In Aim 2, we design privacy preserving algorithms to validate the generalizability risk modeling from AoU data on external healthcare data and establish the transfer learning strategy to adapt AoU risk models for local healthcare systems. We intend for the methods to facilitate development of risk modeling using AoU data with focus on minority populations, as well as toe demonstrate the potential impact of the AoU program on improving care at local healthcare.

The project is to provide guideline concordant care to patients with traumatic brain injury with appropriate anticoagulation treatment. Our overall goal is to develop, scale, evaluate, and maintain an interoperable Clinical Practice Guideline-on-Fast Healthcare Interoperability Resources (CPG-on-FHIR) system for COVID-19 venous thromboembolism (VTE) prevention. To investigate, we will conduct a hybrid type 2 randomized stepped wedge trial with multilevel clustering (4 healthcare systems and 9 total sites) across our heterogeneous (both in setting and EHR platform) collaborative CDS network (UMN, Indiana University, Geisinger Health, and UC-Davis). Dr. Rubina Rizvi as a co-investigator, is leading the usability evaluation of the interoperable CDS system based upon the CDS 5 Rights Framework. We plan to complete a rapid cycle CDS evaluation to optimize SMART-on-FHIR workflow integration by conducting a user-driven simulation and expert-driven heuristic usability optimization. Dr. Rizvi is also working closely to help evaluate implementation strategies guided by the Exploration, Preparation, Implementation, and Sustainment (EPIS) framework using a mixed-methods approach.

The objective of this project is to develop an informatics framework to enable the discovery of DSIs by creating a DS terminology and mining scientific evidence from the biomedical literature. Towards these objectives, we propose the following specific aims: (1) Compile a comprehensive DS terminology using online resources and (2) Discover potential DSIs from the biomedical literature. The successful accomplishment of this project will deliver a novel informatics paradigm and resources for identifying most clinically significant DSI signals and their biological mechanisms. One of the outcomes is the integrated Dietary Supplement Knowledge base (iDISK).

Melnik T, Thompson JA, Vasilakes J, Annis T, Zhou S, Schutte D, Melton GB, Pleasants S, Zhang R. Semi-automated clinical content curation of COVID-19 chatbot remote patient monitoring system. 2022 AMIA Symposium.

Blount, D., Zhang, R., Blaes, A., Gao, Z. health outcomes: A meta-analysis. International Journal of Physical Activity and Health. 2022 (in press).

Melnik T, Thompson J, Vasilakes J, Annis T, Zhou S, Schutte D, Melton G, Pleasants S, Zhang R. Semi-automated clinical content curation with COVID-19 remote patient monitoring. AMIA Annual Symposium.

Barrett L, Xing A, Sheffler J, Steidley E, Adam T, Zhang R, He Z. Assessing the use of prescription drugs and dietary supplements in obese respondents in the National Health and Nutrition Examination Survey. 2022 17(6):e0269241. doi: 10.1371 journal.pone.0269241. eCollection 2022. PMID: 35657782 PMCID: PMC9165812.

Shen Z, Schutte D, Yi Y, Bompelli A, Yu F, Wang Y, Zhang R. Classifying the lifestyle status for Alzheimer disease from clinical notes using deep learning with weak supervision. BMC Med Inform Decis Mak. 2022 Jul 7 22(Suppl 1):88. PMID: 35799294 PMCID: PMC9261217.

Singh E, Bompelli A, Wan R, Bian J, Pakhomov S, Zhang R. A conversational agent system for dietary supplements use. BMC Med Inform Decis Mak. 2022 Jul 7 22(Suppl 1):153. PMID: 35799177 PMCID: PMC9264487.

Zhou S, Wang N, Wang L, Liu H, Zhang R. CancerBERT: a cancer domain-specific language model for extracting breast cancer phenotypes from electronic health records. J Am Med Inform Assoc. 2022 Jun 14 29(7):1208-1216. PMID: 35 45 PMCID: PMC9196678.

Kiogou SD, Chi CL, Zhang R, Ma S, Adam TJ. Clinical data cohort quality improvement: The case of the medication data in the University of Minnesota Clinical Data Repository. AMIA Annu Symp Proc. PMID: 35854717 PMCID: PMC9285162.

Rizvi RF, VanHouten C, Bright TJ, McKillop MM, Alevy S, Brotman D, Sands-Lincoln M, Snowdon J, Robinson BJ, Staats C, Jackson GP, Kassler WJ. The Perceived Impact and Usability of a Care Management and Coordination System in Delivering Services to Vulnerable Populations: Mixed Methods Study. J Med Internet Res. 2021 Mar 12 23(3): e24122. doi: 10.2196 24122. PMID: 709928 PMCID: PMC7998322.

Rizvi RF, Craig KJT, Hekmat R, Reyes F, South B, Rosario B, Kassler WJ, Jackson GP. Effectiveness of non-pharmaceutical interventions related to social distancing on respiratory viral infectious disease outcomes: A rapid evidence-based review and meta-analysis. SAGE Open Med. PMID: 34164126 PMCID: PMC8188982.

Thomas Craig KJ, Rizvi RF, Willis VC, Kassler WJ, Jackson GP. JMIR Public Health Surveill. 2021 Oct 6 7(10): e32468. doi: 10.2196 32468. PMID: 34612841 PMCID: PMC8496751.

Bompelli A#, Wang Y#, Wan R, Singh E, Zhou Y, Xu L, Oniani D, Kshatriya BSA, Balls-Berry JE, and Zhang R. Social and behavioral determinants of health in the era of artificial intelligence with electronic health records: A scoping review. Health Data Science. 2021:Article ID 9759016.

Sahoo HS, Silverman GM, Ingraham NE, Lupei MI, Puskarich MA, Finzel RL, Sartori J, Zhang R, Knoll BC, Liu S, Liu H, Melton GB, Tignanelli CJ, Pakhomov SVS. A fast, resource efficient, and reliable rule-based system for COVID-19 symptom identification. 2021 Aug 7 4(3):ooab070. PMID: 34423261 PMCID: PMC8374371.

Fan Y, Zhou S, Li Y, Zhang R. Deep learning approaches for extracting adverse events and indications of dietary supplements from clinical text. J Am Med Inform Assoc. 2021 Mar 1 28(3):569-577. PMID: 150942 PMCID: PMC7936508.

T32: Training the Next Generation of Surgeon-Scientists in Pancreatology.