Introduction

Our new Division of Computational Health Sciences is an interdisciplinary academic unit, where faculty, trainees, students and domain experts from diverse backgrounds including data sciences, computing, statistics, epidemiology and human computer interaction. We collect, analyze, and interpret complex, multi-scale real-world data from large-scale and multi-modal data in biomedical research, cohort databases, and clinical care.

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.

Expand all

News

WCCO-TV - Dr. Zhang leads efforts to limit heart issues related to breast cancer treatment using AI

Dr. Zhang was interviewed by CBS News (WCCO) on his research on AI for cardiotoxicity prediction for breast cancer patients.

Detecting synergistic effects of pharmacological and non-pharmacological interventions for Alzheimer's disease and related dementia

Increasing evidence demonstrates that non-pharmacological interventions (NPI), such as sleep, diet, dietary supplements, aerobic exercise, aromtherapy, light therapy, cognitive training, are potentially modifiable and thus offer alternative opportunities for [Alzheimer's disease and related dementia] prevention.

All of Us Risk Modeling

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

U of M researchers receive $1.2M to study role of AI in breast cancer treatment

University of Minnesota-based researchers were recently awarded $1.2 million over the next four years from the National Cancer Institute (NCI).

Research Spotlight: Dr. Zhang Received an R01 Renewal Developing Novel AI Approach to Mine Effective & Safe Use of Dietary Supplements

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

Dr. Zhang Received a New R01 to Research Drug Repurposing for Alzheimer's Disease

Funded by the National Institute on Aging, a new research project will aim to explore non-pharmacological interventions, such as sleep, diet, dietary supplements, etc., for Alzheimer's Disease and related dementia prevention.

Faculty Members

Rui Zhang, PhD

RUI ZHANG, PhD, FAMIA

Division Chief and Associate Professor

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

Follow Dr. Zhang on Social Media! Twitter | LinkedIn

Elizabeth Lusczek, PhD

ELIZABETH R. LUSCZEK , PhD

Associate Professor

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

Brian Steffen, PhD

BRIAN STEFFEN, PhD, MSCR

Assistant Professor

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

Rubina Rizvi, MD, PhD

RUBINA RIZVI, MD, PhD

Assistant Professor

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

Piper Ranallo, PhD

PIPER RANALLO, PhD

Assistant Professor

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

MINGQUAN LIN, PhD

MINGQUAN LIN, PhD

Assistant Professor

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. 

Staff Members / Mentees

Ying Liu, PhD

Ying Liu, PhD, Research Scientist, liux0395@umn.edu

Yu Hou, PhD

Yu Hou, PhD, Research Scientist, hou00127@umn.edu

Mousumi Roy, PhD

Mousumi Roy, PhD, Research Scientist, roy00206@umn.edu 

Dalton Schutte

Dalton Schutte, Lead AI engineer, schut184@umn.edu

Mingchen Li

Mingchen Li, Research Programmer, li003378@umn.edu   

Jeremy Yeung

Jeremy Yeung, Research Programmer, yeung048@umn.edu

Sicheng Zhou

Sicheng Zhou, PhD student, zhou1281@umn.edu

Yongkang Xiao

Yongkang Xiao, PhD student, xiao0290@umn.edu

Huixue Zhou

Huixue Zhou, PhD student, zhou1742@umn.edu

Han Yang

Han Yang, PhD student, yang8597@umn.edu

Research Expertise

  • Omics-based analyses
  • Mendelian randomization
  • Human-computer interactions
  • Mixed method studies
  • Natural language processing
  • Knowledge graph and discovery
  • Machine learning, predictive modeling
  • Terminology and ontology

Job Opportunities

Mentorship / Collaborations

  • Mentees have worked with our faculty and participated in our cutting-edge research projects
  • Mentorship opportunities are open to medical students, residents and fellows, postdoctoral associates, graduate, and undergraduate students;
  • We have previous and ongoing collaboration with internal units (e.g., School of Public Health, Department of Computer Science, Institute for Health informatics, School of Nursing, College of Pharmacy) and external institutions (e.g., Mayo Clinic, University of Florida, Yale University, etc)
  • Contact our faculty or Leah Harman (lharman@umn.edu) for potential collaborations

Projects

A New Computational Framework for Learning from Imbalanced Biomedical Data

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 about 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. The successful implementation of this project would lay a computational foundation for imbalanced learning and can provide more accurate tools for predicting BC CVD outcomes. Check details for this NCI R01 here (PI: Rui Zhang/Ju Sun/ Ying Cui).

Mining minority enriched AllofUs data for innovative ethnic specific risk prediction modeling

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. Due to the genetic heterogeneity and social economic disparity, risk factors may disproportionately impact race/ethnicity (R/E) groups. 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. Check details of this NIH R21 (PI: Rui Zhang/Jinhua Wang/Ju Hou).

Detecting synergistic effects of pharmacological and non-pharmacological interventions for Alzheimer’s disease or related dementia (AD/ADRD)

AD/ADRD is a multifactorial and heterogeneous disorder. Most current studies focus on drug interventions for AD/ADRD and currently none of pharmacological intervention (PI) discovery research has been translated into effective treatments. However, increasing evidence demonstrates that non-pharmacological interventions (NPI), such as sleep, diet, dietary supplements, aerobic exercise, aromatherapy, light therapy, cognitive training, are potentially modifiable and thus offer alternative opportunities for AD/ADRD prevention. Thus, the objective of this project is to develop translational informatics approaches to aggregate, standardize and discover the effects of drug and NPI candidates on AD/ADRD using multi-modal data resources (i.e., biomedical literature, EHR, clinical trials) followed by animal model validation. To achieve our goal, we propose the following aims: 1) constructing a comprehensive Pharmacological And Non- Pharmacological Interventions for Alzheimer's Disease Knowledge Graph (PANIA-KG) from biomedical literature and other knowledge bases; 2) detecting, understanding, and visualization of drug repurposing signals of PIs, NPIs, and their synergistical effects for AD/ADRD using the PANIA-KG; 3) re-ranking and validating individual and synergistical drug repurposing signals using multimodal data sources and animal models. The successful completion of this project will deliver a comprehensive NPI knowledge graph, novel informatics approaches, ranked list of drug and NPI candidates, and validated synergistic intervention using multi-modal data sources. The generated approaches, PANIA-KG and ranked lists can further our clinical investigations and clinical trial design which focuses on synergistic effects of drug and NPIs for AD/ADRD. Dr. Rui Zhang serves as PI and collaborates with University of Texas (MPI: Dr. Hua Xu) as a subaward. (Funding Agency: NIH/NIA 1R01AG078154-01, Project period: 07/2022-06/2027)

Evaluation of the SCALED (SCaling AcceptabLE cDs) Approach for the Implementation of Interoperable CDS system for Venous Thromboembolism Prevention

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. (Funding agency: AHRQ 1R18HS028583-01A1, Project period: 08/2022-07/2025)

An Informatics Framework for Discovery and Ascertainment of Drug-Supplement Interactions

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). (Funding Agency: NIH/NCCIH R01AT009457, Project Dates: 04/01/2017-03/31/2022)

Publications

2022:

  1. Steffen BT, Pankow JS, Norby FL, Lutsey PL, Demmer RT, Guan W, Pankratz N, Li A, Liu G, Matushita K, Tin A, Tang W. Proteomics analysis of genetic liability of abdominal aortic aneurysm identifies plasma neogenin and kit ligand: The Atherosclerosis Risk in Communities Study. ATVB. Accepted for publication.
  2. Steffen BT, Tang W, Lutsey PL, Demmer RT, Selvin E, Matushita K, Morrison AC, Guan W, Rooney MR, Pankratz N, Couper D, Norby FL, Pankow JS. Proteomic analysis of diabetes genetic risk scores identifies complement C2 and neuropilin-2 as predictors of type 2 diabetes: The Atherosclerosis Risk in Communities (ARIC) Study. Diabetologia. 2023 Jan;66(1):105-115.
  3. Steffen BT, Pankow JS, Lutsey PL, Demmer RT, Misialek JR, Guan W, Cowan LT, Coresh J, Norby FL, Tang W. Proteomic Profiling Identifies Novel Proteins for Genetic Risk of Severe COVID-19: the Atherosclerosis Risk in Communities Study. Hum Mol Genet. 2022; ddac024.
  4. Rizvi RF;  VanHouten C; Willis Van; Rosario B; South B; Sands-Lincoln M; Brotman D; Lenert J; Jane Snowdon J;  Jackson Gretchen Understanding a Care Management System’s Role in Influencing a Transitional Aged Youth Program’s Practice – A Mixed Methods Study (Preprint) 2022-05-17 | Preprint DOI: 10.2196/preprints.39646
  5. Emani S, Rui A, Rocha HAL, Rizvi RF, Juaçaba SF, Jackson GP, Bates DW. Physicians' Perceptions of and Satisfaction With Artificial Intelligence in Cancer Treatment: A Clinical Decision Support System Experience and Implications for Low-Middle-Income Countries. JMIR Cancer. 2022 Apr 7;8(2):e31461. doi: 10.2196/31461. PMID: 35389353; PMCID: PMC9030908.
  6. 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. Accepted
  7. Blount, D., Zhang, R., Blaes, A., & Gao, Z. Effects of health wearables on cancer survivors’ health outcomes: A meta-analysis. International Journal of Physical Activity and Health. 2022 (in press) 
  8. 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. 2022. (in press)
  9. 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. PLoS One. 2022;17(6):e0269241. doi: 10.1371/journal.pone.0269241. eCollection 2022. PMID: 35657782; PMCID: PMC9165812.
  10. Nian Y, Hu X, Zhang R, Feng J, Du J, Li F, Bu L, Zhang Y, Chen Y, Tao C. Mining on Alzheimer's diseases related knowledge graph to identify potential AD-related semantic triples for drug repurposing. BMC Bioinformatics. 2022 Sep 30;23(Suppl 6):407. doi: 10.1186/s12859-022-04934-1. PMID: 36180861; PMCID: PMC9523633.
  11. Schutte D, Vasilakes J, Bompelli A, Zhou Y, Fiszman M, Kilicoglu H, Bishop J, Adam T, Zhang RDiscovering novel drug-supplement interactions using SuppKG generated from the biomedical literature. J Biomed Inform. 2022 Jul;131:104120. doi: 10.1016/j.jbi.2022.104120. Epub 2022 Jun 13. PMID: 35709900; PMCID: PMC9335448.
  12. Shen Z, Schutte D, Yi Y, Bompelli A, Yu F, Wang Y, Zhang R. Classifying the lifestyle status for Alzheimer's disease from clinical notes using deep learning with weak supervision. BMC Med Inform Decis Mak. 2022 Jul 7;22(Suppl 1):88. doi: 10.1186/s12911-022-01819-4. PMID: 35799294; PMCID: PMC9261217.
  13. 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. doi: 10.1186/s12911-022-01888-5. PMID: 35799177; PMCID: PMC9264487.
  14. 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. doi: 10.1093/jamia/ocac040. PMID: 35333345; PMCID: PMC9196678.
  15. 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's Clinical Data Repository. AMIA Annu Symp Proc. 2022 May 23;2022:293-302. PMID: 35854717; PMCID: PMC9285162.

 

2021:

  1. Steffen BT, Guan W, Ding J, Nomura SO, Weir NL, Tsai MY. Plasma omega-3 and saturated fatty acids are differentially related to pericardial adipose tissue volume across race/ethnicity: The Multi-Ethnic Study of Atherosclerosis. Eur J Clin Nutr. 2021 Aug;75(8):1237-1244.
  2. Kim JS, Steffen BT, Podolanczuk AJ, Kawut SM, Noth I, Raghu G, Michos ED, Hoffman EA, Axelsson GT, Gudmundsson G, Gudnason V, Gudmundsson EF, Murphy RA, Dupuis J, Xu H, Vasan RS, O'Connor GT, Harris WS, Hunninghake GM, Barr RG, Tsai MY, Lederer DJ. Associations of Omega-3 Fatty acids with Interstitial Lung Disease and Lung Imaging Abnormalities Among Adults. Am J Epidemiol. 2021 Jan 4;190(1):95-108.
  3. Garg PK, Guan W, Karger AB, Steffen BT, Budoff M, Tsai MY. Lipoprotein (a) and risk for calcification of the coronary arteries, mitral valve, and thoracic aorta: The Multi-Ethnic Study of Atherosclerosis. J Cardiovasc Comput Tomogr. 2021 Mar-Apr;15(2):154-160.
  4. 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: 33709928; PMCID: PMC7998322.
  5. Sun Z., Rizvi RF, South B, Scheufele E, Draulis K, Feldman H. Extraction of Ambiguous Phrases Found Within Adverse Drug Event Mentions Using an Artificial Intelligence Annotation tool. Poster abstract, AMIA Annual Symposium 2021.
  6. 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. 2021 Jun 6;9:20503121211022973. doi: 10.1177/20503121211022973. PMID: 34164126; PMCID: PMC8188982.
  7. Thomas Craig KJ, Rizvi RF, Willis VC, Kassler WJ, Jackson GP. Effectiveness of Contact Tracing for Viral Disease Mitigation and Suppression: Evidence-Based Review. JMIR Public Health Surveill. 2021 Oct 6;7(10): e32468. doi: 10.2196/32468. PMID: 34612841; PMCID: PMC8496751.
  8. Emani S, Rui A, Rocha HAL, Rizvi RF, Juaçaba SF, Jackson GP, Bates DW. Physicians' Perceptions of and Satisfaction With Artificial Intelligence in Cancer Treatment: A Clinical Decision Support System Experience and Implications for Low-Middle-Income Countries. JMIR Cancer. 2022 Apr 7;8(2):e31461. doi: 10.2196/31461. PMID: 35389353; PMCID: PMC9030908.
  9. Tao D, Wei D, Rizvi RF, Pandita D, Alghamdi B, Kukhareva P, Sordo M. Gender-Specific Career Development Issues in Biomedical Informatics within Professional Organizations. Panel, AMIA Annual Symposium, 2021.
  10. Silverman G, Sahoo H, Ingraham N, Lupei M, Pusharich M, Usher M, Dries J, Finzel R, Murray E, Sartori J, Simon G, Zhang R, Melton G, Pakhomov S. NLP methods for extraction of symptoms from unstructured data for use in prognostic COVID-19 analytic models. Journal of Artificial Intelligence Research. 2021(72):429-474. https://doi.org/10.1613/jair.1.12631.
  11. 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. https://doi.org/10.34133/2021/9759016.
  12. Wang Y, Zhao Y, Schutte D, Bian J, Zhang R. Deep learning models in detection of dietary supplement adverse event signals from Twitter. JAMIA Open. 2021 Oct;4(4):ooab081. doi: 10.1093/jamiaopen/ooab081. eCollection 2021 Oct. PMID: 34632323; PMCID: PMC8497875.
  13. 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. JAMIA Open. 2021 Aug 7;4(3):ooab070. doi: 10.1093/jamiaopen/ooab070. PMID: 34423261; PMCID: PMC8374371.
  14. Zhang R #, Hristovski D#, Schutte D #, Kastrin A#, Fiszman M, Kilicoglu H. Drug repurposing for COVID-19 via knowledge graph completion. J Biomed Inform. 2021 Mar;115:103696. doi: 10.1016/j.jbi.2021.103696. Epub 2021 Feb 8. PMID: 33571675; PMCID: PMC7869625.
  15. 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. doi: 10.1093/jamia/ocaa218. PMID: 33150942; PMCID: PMC7936508.
  16. He X#Zhang R#, Alpert J, Zhou S, Adam T, Raisa A, Peng Y, Zhang H, Guo Y, Bian J. When text simplication is not enough: could a graph-based visualization facilitate consumers' comprehension of dietary supplement information? JAMIA Open. 2021 Jan;4(1): ooab026. https://doi.org/10.1093/jamiaopen/ooab026.