Bio

Asad is a research data analyst in the Integrative Biomedical Imaging Informatics (IBIIS) group at Stanford. His work involves the development of artificial intelligence (AI) algorithms for applications in medical imaging, biomedical informatics, and deep learning.

Supervisors

Honors & Awards

  • ECE Outstanding Student Award, The University of Texas at Austin (2024)

Education & Certifications

  • MS, The University of Texas at Austin, Electrical & Computer Engineering (2024)
  • MS, The University of Texas at Austin, Information Technology (2022)
  • BS (Honors), Lahore University of Management Sciences, Accounting & Finance (2019)

Contact

  • Work
    asadaali@stanford.edu
    University - Staff Department: Rad/Integrative Biomedical Imaging Informatics at Stanford Position: Research Data Analyst

Additional Info

Links

All Publications

  • Adapted large language models can outperform medical experts in clinical text summarization. Nature medicine Van Veen, D., Van Uden, C., Blankemeier, L., Delbrouck, J. B., Aali, A., Bluethgen, C., Pareek, A., Polacin, M., Reis, E. P., Seehofnerová, A., Rohatgi, N., Hosamani, P., Collins, W., Ahuja, N., Langlotz, C. P., Hom, J., Gatidis, S., Pauly, J., Chaudhari, A. S. 2024

    Abstract

    Analyzing vast textual data and summarizing key information from electronic health records imposes a substantial burden on how clinicians allocate their time. Although large language models (LLMs) have shown promise in natural language processing (NLP) tasks, their effectiveness on a diverse range of clinical summarization tasks remains unproven. Here we applied adaptation methods to eight LLMs, spanning four distinct clinical summarization tasks: radiology reports, patient questions, progress notes and doctor-patient dialogue. Quantitative assessments with syntactic, semantic and conceptual NLP metrics reveal trade-offs between models and adaptation methods. A clinical reader study with 10 physicians evaluated summary completeness, correctness and conciseness; in most cases, summaries from our best-adapted LLMs were deemed either equivalent (45%) or superior (36%) compared with summaries from medical experts. The ensuing safety analysis highlights challenges faced by both LLMs and medical experts, as we connect errors to potential medical harm and categorize types of fabricated information. Our research provides evidence of LLMs outperforming medical experts in clinical text summarization across multiple tasks. This suggests that integrating LLMs into clinical workflows could alleviate documentation burden, allowing clinicians to focus more on patient care.

    View details for DOI 10.1038/s41591-024-02855-5

    View details for PubMedID 38413730

    View details for PubMedCentralID 5593724

  • Solving Inverse Problems with Score-Based Generative Priors learned from Noisy Data 57th Asilomar Conference on Signals, Systems, and Computers Aali, A., Arvinte, M., Kumar, S., Tamir, J. I. 2023: 837-843

    View details for DOI 10.1109/IEEECONF59524.2023.10477042

https://orcid.org/0009-0008-2120-5722