Ivo D. Dinov Ph.D.

Photo of Ivo Dinov

Professor

Henry Philip Tappan Collegiate Professor

Department of Systems, Populations and Leadership Chair

Department

Department of Health Behavior and Clinical Sciences

Department of Systems, Populations and Leadership

University Affiliations

Computational Medicine and Bioinformatics, Medical School

Associate Director for Education and Training, Michigan Institute for Data Science

Contact

[email protected]
Room 4126 NURS2

University of Michigan School of Nursing
426 North Ingalls Street
Ann Arbor, MI 48109-2003
 

Ivo Dinov is accepting new PhD students.


Interests

  • Spacekime and predictive healthcare analytics

  • Foundational and generative artificial intelligence modeling (GAIM)

  • Teaching with technology and blended instruction, augmented intelligence (AuI)

  • Biomedical data science, computational neuroscience, informatics and augmented intelligence

  • Mathematical-physics modeling and statistical inference

Dr. Dinov is the Director of the Statistics Online Computational Resource (SOCR) and is an expert in mathematical modeling, statistical analysis, high-throughput computational processing and scientific visualization of large datasets (Big Data). His applied research is focused on neuroscience, nursing informatics, multimodal biomedical image analysis, and distributed genomics computing. Examples of specific brain research projects Dr. Dinov is involved in include longitudinal morphometric studies of development (e.g., Autism, Schizophrenia), maturation (e.g., depression, pain) and aging (e.g., Alzheimer’s disease, Parkinson’s disease). He leads the AI in Health Initiative, which designs, implements, validates, and disseminates generative AI models supporting research, teaching, learning, clinical decision-making, and translational biomedical science. 

PATENTS:

  • Electronic Medical Record DataSifter: This patent disclosed the development of an innovative technique for desensitizing sensitive data, such as human electronic medical data (US10776516B2)
  • Three-dimensional Cell and Tissue Image Analysis for Cellular and Sub-Cellular Morphological Modeling and Classification: This patent disclosed an automated, efficient, and effective technology for high-throughput specimen collection, image acquisition, data pre-processing, computation of derived biomarkers, modeling, classification and analysis of cancer biopsy samples (US10915729B2)
  • Adaptive Radiotherapy Clinical Decision Support Tool and Related Methods: This patent discloses a novel artificial intelligence method for training a machine learning model of radiotherapy environment

Current Research Grants and Programs

  • NR015331 Center for Complexity and Self-management of Chronic Disease investigates health promotion, illness prevention and the burden of chronic illness burgeons using advanced methods, complexity theory, and data analytics.

  • NSF DUE 1023115 The Distributome Project (https://distributome.org/) is an open-source, open content-development project for exploring, discovering, learning, and computational utilization of diverse probability distributions. Role: Site-Principal Investigator.

  • NSF 2611649: Statistical Methods in Imaging (SMI): A vital hub for bringing together researchers to discuss the rapidly evolving role of statistics, mathematics, and AI in imaging science. From medical scans that detect disease to telescopes that capture distant galaxies, images are fundamental to modern discovery.

  • NIH 1R01CA233487: Optimal Decision Making in Radiotherapy Using Panomics Analytics. The long-term goal of this project is to overcome barriers related to prediction uncertainties and human-computer interactions, which are currently limiting the ability to make personalized clinical decisions for real-time response-based adaptation in radiotherapy from available data. To meet this need and overcome current challenges, we have assembled a multidisciplinary team including: clinicians, medical physicists, data scientists, and human factor experts.

  • NIH 2T32GM141746: The overarching goal of the BIDS-TP is to train a cadre of data-savvy, computationally skilled, and highly motivated biomedical scholars in an intellectually stimulating environment using an effective competency-based curriculum with strong pedagogical emphasis on augmented human-machine intelligence. To enhance their scientific, clinical, and translational abilities, all BIDS-TP students will be trained in collecting, managing, processing, interrogating, and analyzing large amounts of complex high-dimensional biomedical information with focus on rigor, transparency, and reproducibility.

Teaching

Dr. Dinov’s teaching philosophy has evolved and matured over the past two decades from a concept-based instruction to a more pedagogically balanced approach of integrated research, practice and education. He has taught many core and multidisciplinary classes in statistics, mathematics, neuroscience and engineering. Dr. Dinov is developing active learning materials, web-based computational resources, dynamic databases, blended learning materials and electronic instructional resources. The foci of his ongoing educational research are on increasing learners’ motivation, enhancing the learning experiences and improving knowledge retention. As Director of the Statistics Online Computational Resource (SOCR), Dr. Dinov designs, implements and validates novel virtual experiments, web apps for probability, statistics and informatics education, and introduces new multilingual science, technology, engineering and mathematics (STEM) resources.

Notable Awards/Honors

  • World Wide Web Awards™ "Gold" Award, July 2007

  • IEEE Mathematical Methods in Biomedical Image Analysis (MMBIA) Best Paper Award, 2008

  • Runner up, ASA Hands-On Statistics Activity Competition, 2010

  • Elected Member of the Nature Medicine Statistical Advisory Board

Education

  • Postdoc, University of California, Los Angeles, CA, 2001

  • Ph.D., The Florida State University, Tallahassee, FL, 1998

  • M.S., The Florida State University, Tallahassee, FL, 1998

  • M.S., Michigan Technological University, Houghton, MI, 1993

  • B.S., Sofia University, Sofia, Bulgaria, 1991

Publications Highlights

  • Dinov, ID, Ho, ETW, and Ahmed, SE. (2026) Statistical commutators with applications to estimation, inference, and regularization tuning, Statistics and Computing, 36(228), DOI: 10.1007/s11222-026-10991-w.

  • Velev, MV, and Dinov, ID. (2026) Dirac Fields on (3+2)-Dimensional Spacetime with Compact Bi-Time, Kime Coordinates, and Stochastic Kime-Phase, Physica Scripta, 101(23), 235206, DOI: 10.1088/1402-4896/ae7778.

  • Laoye, VE, and Dinov, ID. (2026) Model-based equitable learning framework for high-dimensional biomedical data, APS Open Science, 1(000084), DOI: 10.1103/dgj9-5fck.

  • Dinov, ID. (2025) Back to the future – from nuclear energy to AI, AI Perspectives & Advances, 7(2), DOI: 10.1186/s42467-025-00017-y.

  • Niraula, D., Cuneo, K.C.,Dinov, ID, Gonzalez, BD, Jamaluddin, JB, Jin, JJ, Luo, Y, Matuszak, MM, Haken, RKT, Bryant, AK, Dilling, TJ, Dykstra, MP, Frakes, JM, Liveringhouse, CL, Miller, SR, Mills, MN, Palm, RF, Regan, SN, Rishi, A, Torres-Roca, JF, Yu, HHM, El Naqa, I. (2025) Intricacies of human–AI interaction in dynamic decision-making for precision oncology, Nature Communications, 16(1138), DOI: 10.1038/s41467-024-55259-x.

  • Marino, S., Cassidy, R., Nanni, J. Wang, Y, Liu, Y, Tang, M, Yuan, Y, Chen, T, Sinha, A, Pandian, B, Dinov, ID, & Burn, ML. (2025) Medical data sharing and synthetic clinical data generation – maximizing biomedical resource utilization and minimizing participant re-identification risks, npj Digit. Med. 8, 526 (2025), DOI: 10.1038/s41746-025-01935-1.

  • Dinov, ID. (2023). Data Science and Predictive Analytics: Biomedical and Health Applications using R, 2nd edition, Springer Series in Applied Machine Learning, ISBN 978-3-031-17482-7.

  • Ottom, MA, Abdul Rahman, H, Alazzam, IM and Dinov, ID. (2023). Multimodal Stereotactic Brain Tumor Segmentation Using 3D-Znet, Bioengineering, 10(5):581, DOI: 10.3390/bioengineering10050581.

  • Wang, Y, Shen Y, Deng, D, Dinov, ID. (2022) Determinism, Well-posedness, and Applications of the Ultrahyperbolic Wave Equation in Spacekime, Journal of Partial Differential Equations in Applied Mathematics, 5(100280), DOI: 10.1016/j.padiff.2022.100280.

  • Bobrovnikov, M, Chai, JT, and Dinov, ID. (2022) Interactive Visualization and Computation of 2D and 3D Probability Distributions, SN Computer Science, 3, 327, DOI: 10.1007/s42979-022-01206-w.

  • Zhou, N, Wu, Q, Wu, Z, Marino, S, Dinov, ID. (2022) DataSifterText: Partially Synthetic Text Generation for Sensitive Clinical Notes, Journal of Medical Systems, 46(96):1-14, DOI: 10.1007/s10916-022-01880-6.

  • Zhang, R, Zhang, Y, Liu, Y, Guo, Y, Shen, Y, Deng, D, Qiu, Y, Dinov, ID. (2022) Kimesurface Representation and Tensor Linear Modeling of Longitudinal Data, Neural Computing and Applications Journal, 34:6377–6396, DOI: 10.1007/s00521-021-06789-8.

  • Kalinin, AA, Palanimalai, S, Zhu, J, Wu, W, Devraj, N, Ye, C, Ponaru, N, Husain, SS, and Dinov, ID. (2022) SOCRAT: A Dynamic Web Toolbox for Interactive Data Processing, Analysis and Visualizatino, Journal Information, 13(547):1-24, DOI: 10.3390/info13110547.

  • Dinov, ID and Velev, MV. (2021) Data Science: Time Complexity, Inferential Uncertainty, and Spacekime Analytics, De Gruyter, STEM Series, ISBN 978-3-11-069780-3, DOI 10.1515/9783110697827.

  • Complete List of Publications: http://www.socr.umich.edu/people/dinov/publications.html