ASAdrian Serapio

Adrian Serapio

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Adrian Serapio has a total of 28 co-authors. Here are the top co-authors by number of shared publications:

  • Jae Ho Sohn

    Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA

    3 shared publications
  • Masha Bondarenko

    Department of Radiology and Biomedical Imaging, University of California, San Francisco (UCSF), CA

    3 shared publications
  • Ali Nowroozi

    Department of Radiology and Biomedical Imaging, University of California, San Francisco (UCSF), CA

    2 shared publications
  • Yannan Yu

    Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA

    2 shared publications
  • Ali Nowroozi

    Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA

    1 shared publication
  • Alison S Rustagi

    Center for Data to Discovery and Delivery Innovation (3DI), San Francisco VA Health Care System, San Francisco, CA, USA

    1 shared publication

Latest Publications

  • Open Access

    Planner-Executor Style Multimodal Agentic System to Answer Patient Questions in Lung Cancer Screening CT

    by Koharu Sakiyama, Adrian Serapio, Meng Ye, Ali Nowroozi, Masha Bondarenko, Yu-Fu Wu, Kang Qi, Jonathan Liu, Maya Vella, Yannan Yu, et al.

    Background: Accurate patient understanding of lung cancer screening (LCS) results is critical for engagement and follow-up adherence, given the currently low screening uptake. While artificial intelligence (AI) systems show promise in facilitating patient communication, its effective use in clinical settings requires appropriate invocation of imaging tools and self-regulation by deferring certain questions to physicians. To this end, we developed and evaluated a planner-executor style multimodal agentic system to answer simulated patient questions about LCS CT results. Methods: This retrospective study utilized 116 LCS CT reports and images collected from a tertiary academic hospital. The system employed a multi-agent architecture (planner and executor) to mimic clinical reasoning. We developed a large language model (LLM)-based question generation framework to prepare a comprehensive set of 699 simulated patient questions, categorized as answerable and defer-to-doctor to assess self-regulation. Performance was evaluated on tool-calling, self-regulation accuracy (ability to correctly defer out-of-scope questions to a human provider) assessed by LLM-as-a-judge, and clinical quality assessed by a reader performance study with four physicians evaluating a subset of 100 responses. Results: The system demonstrated high overall tool-calling accuracy of 93.1% (646/694; 95% CI: 91.2%, 95.0%) and self-regulation accuracy of 92.6% (462/499; 90.2%, 94.8%). For answerable questions, the percentage of responses receiving perfect 5.0 scores across all readers included 78.9% (180/228) for clinical accuracy (inter-rater agreement: Gwet’s AC2=0.92), and 73.2% (167/228) for patient understandability (0.86). For defer-to-doctor questions, the percentage of responses included 77.3% (133/172) for clinical accuracy (0.80) and 70.3% (121/172) for patient understandability (0.78). Conclusions: The planner-executor style multi-modal agentic system reliably answers patient-specific questions about LCS. Its high tool-calling and self-regulation performance demonstrates its potential as a safe and effective digital communication facilitator in LCS programs.

  • Radiologically Relevant Clinical History Summarization with Large Language Models: A Multireader Performance Study

    by Adrian Serapio, Timothy L. Chen, Brian Tangsombatvisit, Brandon K. K. Fields, Yannan Yu, Yue Guo, Soo Kyung Kim, Brenda Y. Miao, Madhumita Sushil, Christopher P. Hess, et al.

    Proprietary and open-source large language models (LLMs) generated radiologically relevant indications from clinical notes that were more comprehensive and factual than clinician indications, and when generated by the proprietary LLM, were ranked most useful in protocoling and imaging interpretation by radiologists.


  • Open Access

    Pre‐Imaging Clinical Factors Associated With Cardiac MR Image Quality Using Large Language Model‐Enabled Data Extraction

    by Hong Yu, Masha Bondarenko, Ali Nowroozi, Yoo Jin Lee, Adrian Serapio, Punita Kaveti, Jae Ho Sohn

    Background: Poor cardiac MR image quality can prompt repeat examinations and hinder clinical decision‐making. Purpose: To evaluate whether pre‐imaging clinical information, extracted using a large language model (LLM), is independently associated with cardiac MR image quality. Study Type: Retrospective. Population: 1006 adults undergoing clinical cardiac MR examinations. Field Strength/Sequence: 1.5 T and 3 T scanners with cine, black blood, MR angiogram, or late gadolinium enhancement protocols. Assessment: Image quality was categorized per study as excellent, slightly limited, severely limited, or nondiagnostic using institutional reporting conventions finalized by radiologists and cardiologists. A HIPAA‐compliant LLM assigned image quality labels based on radiology reports through an iteratively refined prompt, with reliability confirmed by two radiologists. Labels were binarized as Good (excellent and slightly limited) versus Poor (severely limited and nondiagnostic). A repeat‐imaging‐adjusted image quality label was used in a sensitivity analysis. Pre‐imaging clinical and patient variables were extracted from electronic health records. Associations between variables and image quality labels were investigated. Statistical Tests: Cohen's kappa (κ) for label agreement. Chi‐square and t‐tests for univariate analysis. Variance inflation factor (VIF) and multivariable logistic regression. Significance level: p < 0.05. Results: Binarized image quality labels showed substantial agreement with interpreters' assessments for both the primary dataset (κ = 0.689) and the repeat‐adjusted dataset (κ = 0.879). There was no significant multicollinearity (VIF = 1.01–1.39). Cognitive and communication impairment (OR 1.81, 95% CI [1.30–2.54], p < 0.001) and respiratory issues (1.57 [1.14–2.17], p = 0.006) were independently associated with poor image quality. These associations remained significant in the repeat‐adjusted sensitivity analysis (cognitive and communication impairment (OR 1.75, 95% CI [1.27–2.44], p < 0.001) and respiratory compromise (OR 1.37, 95% CI [1.04–1.82], p = 0.027)). Other clinical variables were not independently associated after adjustment. Data Conclusion: Cognitive/communication impairment and respiratory compromise were independently associated with poor cardiac MR image quality. Level of Evidence: 3. Technical Efficacy: Stage 2.


  • Open Access

    Large language models in radiologic numerical tasks: A thorough evaluation and error analysis

    by Ali Nowroozi, Masha Bondarenko, Adrian Serapio, Tician Schnitzler, Sukhmanjit S Brar, Jae Ho Sohn

    Purpose: To investigate the performance of LLMs in radiology numerical tasks and perform a comprehensive error analysis. Materials and Methods: We defined six tasks: extracting 1-minimum T-score from DEXA report, 2-maximum common bile duct (CBD) diameter from ultrasound report, and 3-maximum lung nodule size from CT report, and judging 1-presence of a highly hypermetabolic region on a PET report, 2-whether a patient is osteoporotic based on a DEXA report, and 3-whether a patient has a dilated CBD based on an ultrasound report. Reports were extracted from the MIMIC III and our institution’s databases, and the ground truths were extracted manually. The models used were Llama 3.1 8b, DeepSeek R1 distilled Llama 8b, OpenAI o1-mini, and OpenAI GPT-5-mini. We manually reviewed all incorrect outputs and performed a comprehensive error analysis. Results: In extraction tasks, while Llama showed relatively variable results (ranging 86%-98.7%) across tasks, other models performed consistently well (accuracies >95%). In judgement tasks, the lowest accuracies of Llama, DeepSeek, o1-mini, and GPT-5-mini were 62.0%, 91.7%, 91.7%, and 99.0%, respectively, while o1-mini and GPT-5-mini did reach 100% performance in detecting osteoporosis. We found no mathematical errors in the outputs of o1-mini and GPT-5-mini. Answer-only output format significantly reduced performance in Llama and DeepSeek but not in o1-mini or GPT-5-mini. Conclusion: True reasoning models perform consistently well in radiology numerical tasks and show no mathematical errors. Simpler non-true reasoning models may also achieve acceptable performance depending on the task.