Bio

Shriti is an Assistant Research Professor in Stanford’s Center for Biomedical Informatics Research and a Junior Faculty Fellow at the Institute for Human-Centered AI. Her research focuses on developing and evaluating human-centered decision-support techniques to help patients and clinicians make health data and algorithms actionable. She is particularly interested in creating tools to support the use of wearable health data and studying their impact on chronic condition management.

Academic Appointments

  • Assistant Professor (Research), Medicine - Biomedical Informatics Research

Professional Education

  • B.Tech., Indian Institute of Technology, Computer Science (2011)
  • MS, University of California Irvine, Information and Computer Science (2015)
  • Ph.D., University of Michigan, Information (2022)

Contact

  • Academic
    shritir@stanford.edu
    University - Faculty Department: Med/BMIR Position: Non-Tenure Line - Research Line Assistant Professor

Additional Info

2024-25 Courses

Stanford Advisees

All Publications

  • Red teaming ChatGPT in medicine to yield real-world insights on model behavior. NPJ digital medicine Chang, C. T., Farah, H., Gui, H., Rezaei, S. J., Bou-Khalil, C., Park, Y. J., Swaminathan, A., Omiye, J. A., Kolluri, A., Chaurasia, A., Lozano, A., Heiman, A., Jia, A. S., Kaushal, A., Jia, A., Iacovelli, A., Yang, A., Salles, A., Singhal, A., Narasimhan, B., Belai, B., Jacobson, B. H., Li, B., Poe, C. H., Sanghera, C., Zheng, C., Messer, C., Kettud, D. V., Pandya, D., Kaur, D., Hla, D., Dindoust, D., Moehrle, D., Ross, D., Chou, E., Lin, E., Haredasht, F. N., Cheng, G., Gao, I., Chang, J., Silberg, J., Fries, J. A., Xu, J., Jamison, J., Tamaresis, J. S., Chen, J. H., Lazaro, J., Banda, J. M., Lee, J. J., Matthys, K. E., Steffner, K. R., Tian, L., Pegolotti, L., Srinivasan, M., Manimaran, M., Schwede, M., Zhang, M., Nguyen, M., Fathzadeh, M., Zhao, Q., Bajra, R., Khurana, R., Azam, R., Bartlett, R., Truong, S. T., Fleming, S. L., Raj, S., Behr, S., Onyeka, S., Muppidi, S., Bandali, T., Eulalio, T. Y., Chen, W., Zhou, X., Ding, Y., Cui, Y., Tan, Y., Liu, Y., Shah, N., Daneshjou, R. 2025; 8 (1): 149

    Abstract

    Red teaming, the practice of adversarially exposing unexpected or undesired model behaviors, is critical towards improving equity and accuracy of large language models, but non-model creator-affiliated red teaming is scant in healthcare. We convened teams of clinicians, medical and engineering students, and technical professionals (80 participants total) to stress-test models with real-world clinical cases and categorize inappropriate responses along axes of safety, privacy, hallucinations/accuracy, and bias. Six medically-trained reviewers re-analyzed prompt-response pairs and added qualitative annotations. Of 376 unique prompts (1504 responses), 20.1% were inappropriate (GPT-3.5: 25.8%; GPT-4.0: 16%; GPT-4.0 with Internet: 17.8%). Subsequently, we show the utility of our benchmark by testing GPT-4o, a model released after our event (20.4% inappropriate). 21.5% of responses appropriate with GPT-3.5 were inappropriate in updated models. We share insights for constructing red teaming prompts, and present our benchmark for iterative model assessments.

    View details for DOI 10.1038/s41746-025-01542-0

    View details for PubMedID 40055532

    View details for PubMedCentralID 10564921

  • Augmenting clinicians' analytical workflow through task-based integration of data visualizations and algorithmic insights: a user-centered design study. Journal of the American Medical Informatics Association : JAMIA Scholich, T., Raj, S., Lee, J., Newman, M. W. 2024

    Abstract

    To understand healthcare providers' experiences of using GlucoGuide, a mockup tool that integrates visual data analysis with algorithmic insights to support clinicians' use of patientgenerated data from Type 1 diabetes devices.This qualitative study was conducted in three phases. In Phase 1, 11 clinicians reviewed data using commercial diabetes platforms in a think-aloud data walkthrough activity followed by semistructured interviews. In Phase 2, GlucoGuide was developed. In Phase 3, the same clinicians reviewed data using GlucoGuide in a think-aloud activity followed by semistructured interviews. Inductive thematic analysis was used to analyze transcripts of Phase 1 and Phase 3 think-aloud activity and interview.3 high level tasks, 8 sub-tasks, and 4 challenges were identified in Phase 1. In Phase 2, 3 requirements for GlucoGuide were identified. Phase 3 results suggested that clinicians found GlucoGuide easier to use and experienced a lower cognitive burden as compared to the commercial diabetes data reports that were used in Phase 1. Additionally, GlucoGuide addressed the challenges experienced in Phase 1.The study suggests that the knowledge of analytical tasks and task-specific visualization strategies in implementing features of data interfaces can result in tools that lower the perceived burden of engaging with data. Additionally, supporting clinicians in contextualizing algorithmic insights by visual analysis of relevant data can positively influence clinicians' willingness to leverage algorithmic support.Task-aligned tools that combine multiple data-driven approaches, such as visualization strategies and algorithmic insights, can improve clinicians' experience in reviewing device data.

    View details for DOI 10.1093/jamia/ocae183

    View details for PubMedID 39003519

https://orcid.org/0000-0001-5484-9980