About

Mark Lee is an Industry Assistant Professor of Technology Management in the NYU Tandon School of Engineering People Analytics group. He joined NYU as a full-time faculty member in 2025 after serving as an adjunct professor for ten years, during which he taught courses in People Analytics, Statistics, Human Factors Engineering, Workplace Design, and the Management of Human Capital Systems. Mark's industry experience includes roles at various organizations such as Underwriters Laboratories, where he was the Head of Research, Analytics, and Business Development for the ComplianceWire business unit serving the Life Sciences industry. His professional background also encompasses positions at AT&T, Lockheed Martin, NCR, Pitney Bowes, Siemens, iThreat, Certara, and Medidata (Dassault Systems). Prior to his industry career, Mark was a faculty member at Old Dominion University and was a NASA ASEE fellowship recipient. He earned his doctorate in Engineering Psychology with a minor in Industrial Engineering from Georgia Tech, where he is also a Ramblin' Wreck. His research interests include People Analytics, Learning, Perception, Human and Computer Interaction, Life Sciences (Clinical, PK/PD, Manufacturing), and Artificial Intelligence.

Research topics

• Computer Science
• Artificial Intelligence
• Medicine
• Biology
• Political Science
• Pathology
• Data Mining
• Machine Learning
• Physics
• Geography
• Radiology
• Business
• Cancer research
• Marketing
• Oncology
• Law
• Psychology
• Engineering
• Virology
• Data science

Selected publications

• Two-Stage Training Framework Using Multicontrast MRI Radiomics for <i>IDH</i> Mutation Status Prediction in Glioma

  Radiology Artificial Intelligence · 2024 · 16 citations

  • Medicine
  • Oncology
  • Biology

  Published under a CC BY 4.0 license. See also commentary by Moassefi and Erickson in this issue.

  PublisherDOI

• MRI-Based Deep Learning Method for Classification of IDH Mutation Status

  Bioengineering · 2023 · 22 citations

  • Artificial Intelligence
  • Computer Science
  • Biology

  , a T2w-image-only network (T2-net) and a multi-contrast network (MC-net). Each network was separately trained using TCIA (227 subjects) or TCIA + EGD data (683 subjects combined). The networks were trained to classify IDH mutation status and implement single-label tumor segmentation simultaneously. The trained networks were tested on over 1100 held-out datasets including 360 cases from UT Southwestern Medical Center, 136 cases from New York University, 175 cases from the University of Wisconsin-Madison, 456 cases from EGD (for the TCIA-trained network), and 495 cases from the University of California, San Francisco public database. A receiver operating characteristic curve (ROC) was drawn to calculate the AUC value to determine classifier performance. Results: T2-net trained on TCIA and TCIA + EGD datasets achieved an overall accuracy of 85.4% and 87.6% with AUCs of 0.86 and 0.89, respectively. MC-net trained on TCIA and TCIA + EGD datasets achieved an overall accuracy of 91.0% and 92.8% with AUCs of 0.94 and 0.96, respectively. We developed reliable, high-performing deep learning algorithms for IDH classification using both a T2-image-only and a multi-contrast approach. The networks were tested on more than 1100 subjects from diverse databases, making this the largest study on image-based IDH classification to date.

  PublisherOA PDFDOI

• Federated learning enables big data for rare cancer boundary detection

  Nature Communications · 2022 · 326 citations

  • Computer Science
  • Computer Science
  • Machine Learning

  Although machine learning (ML) has shown promise across disciplines, out-of-sample generalizability is concerning. This is currently addressed by sharing multi-site data, but such centralization is challenging/infeasible to scale due to various limitations. Federated ML (FL) provides an alternative paradigm for accurate and generalizable ML, by only sharing numerical model updates. Here we present the largest FL study to-date, involving data from 71 sites across 6 continents, to generate an automatic tumor boundary detector for the rare disease of glioblastoma, reporting the largest such dataset in the literature (n = 6, 314). We demonstrate a 33% delineation improvement for the surgically targetable tumor, and 23% for the complete tumor extent, over a publicly trained model. We anticipate our study to: 1) enable more healthcare studies informed by large diverse data, ensuring meaningful results for rare diseases and underrepresented populations, 2) facilitate further analyses for glioblastoma by releasing our consensus model, and 3) demonstrate the FL effectiveness at such scale and task-complexity as a paradigm shift for multi-site collaborations, alleviating the need for data-sharing.

  DOI

• Comparative transmissibility of SARS-CoV-2 variants Delta and Alpha in New England, USA

  Cell Reports Medicine · 2022 · 199 citations

  • Political Science
  • Virology
  • Biology

  The SARS-CoV-2 Delta variant rose to dominance in mid-2021, likely propelled by an estimated 40%-80% increased transmissibility over Alpha. To investigate if this ostensible difference in transmissibility is uniform across populations, we partner with public health programs from all six states in New England in the United States. We compare logistic growth rates during each variant's respective emergence period, finding that Delta emerged 1.37-2.63 times faster than Alpha (range across states). We compute variant-specific effective reproductive numbers, estimating that Delta is 63%-167% more transmissible than Alpha (range across states). Finally, we estimate that Delta infections generate on average 6.2 (95% CI 3.1-10.9) times more viral RNA copies per milliliter than Alpha infections during their respective emergence. Overall, our evidence suggests that Delta's enhanced transmissibility can be attributed to its innate ability to increase infectiousness, but its epidemiological dynamics may vary depending on underlying population attributes and sequencing data availability.

  DOI

• Aligning implementation science with improvement practice: a call to action

  Implementation Science Communications · 2021 · 107 citations

  • Computer Science
  • Computer Science
  • Business

  BACKGROUND: In several recent articles, authors have called for aligning the fields of implementation and improvement science. In this paper, we call for implementation science to also align with improvement practice. Multiple implementation scholars have highlighted the importance of designing implementation strategies to fit the existing culture, infrastructure, and practice of a healthcare system. Worldwide, healthcare systems are adopting improvement models as their primary approach to improving healthcare delivery and outcomes. The prevalence of improvement models raises the question of how implementation scientists might best align their efforts with healthcare systems' existing improvement infrastructure and practice. MAIN BODY: We describe three challenges and five benefits to aligning implementation science and improvement practice. Challenges include (1) use of different models, terminology, and methods, (2) a focus on generalizable versus local knowledge, and (3) limited evidence in support of the effectiveness of improvement tools and methods. We contend that implementation science needs to move beyond these challenges and work toward greater alignment with improvement practice. Aligning with improvement practice would benefit implementation science by (1) strengthening research/practice partnerships, (2) fostering local ownership of implementation, (3) generating practice-based evidence, (4) developing context-specific implementation strategies, and (5) building practice-level capacity to implement interventions and improve care. Each of these potential benefits is illustrated in a case study from the Centers for Disease Control and Prevention's Cancer Prevention and Control Research Network. CONCLUSION: To effectively integrate evidence-based interventions into routine practice, implementation scientists need to align their efforts with the improvement culture and practice that is driving change within healthcare systems worldwide. This paper provides concrete examples of how researchers have aligned implementation science with improvement practice across five implementation projects.

  DOI

Frequent coauthors

• Rajan Jain

  NYU Langone Health

  27 shared

• Daniel Rueckert

  23 shared

• Ben Glocker

  Imperial College London

  21 shared

• Adam P. Dicker

  Methodist Hospital

  19 shared

• Enzo Ferrante

  19 shared

• Adam E. Flanders

  Universidade Federal de São Paulo

  19 shared

• Sarah Parisot

  17 shared

• Jill S. Barnholtz‐Sloan

  17 shared

Education

• Neuroradiology Fellow, Radiology

  NYU Grossman School of Medicine

  2025

• Resident Physician, Radiology

  NYU Grossman School of Medicine

  2024

• Intern, Internal Medicine

  Baylor College of Medicine

  2020

• MD

  The Warren Alpert Medical School of Brown University

  2019

• Bachelor of Science, Neuroscience

  Brown University

  2015

Awards & honors

• NASA ASEE fellowship recipient

Similar researchers at New York University

• Dan R. Littmanh-240
• Jef D. Boekeh-160
• Eliseo Guallarh-151
• Douglas Kondziolkah-144
• Yann LeCunh-144