Thomas Lew

All Publications

• Physician-Reported Safety Outcomes of AI-Generated Hospital Course Summaries. JAMA network open Grolleau, F., Liang, A. S., Keyes, T., Ma, S. P., Lew, T., Huynh, T. R., Steele, N., Chung, P., Qin, P., Chandra, G., Wang, S. F., Mullen, E., Carpenter, L., Hoppenfeld, M., Morrin, M., Kyerematen, B. A., Ambers, N., Kotecha, N., Alsentzer, E., Hom, J., Shah, N. H., Schulman, K., Chen, J. H. 2026; 9 (5): e2616556

  Abstract

  High-quality discharge summaries are essential for safe care transitions but contribute substantially to clinician documentation burden and burnout. While retrospective studies suggest that large language models (LLMs) can generate clinical summaries of comparable quality to those by physicians, prospective data on their safety, utility, and association with clinician well-being in clinical environments are lacking.To evaluate the safety, use, and association with clinician burden of MedAgentBrief, an LLM-based agentic workflow for generating hospital course summaries, during prospective clinical deployment.This single-arm prospective pilot quality improvement study encompassed hospital discharges at 1 academic inpatient medicine unit from August 1 to October 11, 2025, with baseline comparisons drawn from April 9 to July 31, 2025.A custom agentic LLM workflow using Gemini 2.5 Pro generated draft hospital course summaries nightly using patient history and physical and daily progress notes. Drafts were securely emailed to physicians daily for review and optional use.The primary outcome was physician-reported potential for and severity of harm from unedited summaries (Agency for Healthcare Research and Quality Common Format Harm Scale). Secondary outcomes included use rate, error types (omissions, inaccuracies, and hallucinations), time spent in discharge summaries (electronic health record logs), and changes in cognitive burden (NASA Task Load Index; score range, 0-100, with higher scores indicating greater cognitive burden) and burnout (Stanford Professional Fulfillment Index Work Exhaustion Scale; score range, 0-4, with higher scores indicating greater burnout).Among 384 hospital discharges, the system generated 1274 summaries. Physicians used artificial intelligence (AI) content in 219 cases (57.0%). Feedback on 100 summaries (88 of 219 used summaries [40.2%] and 12 of 165 unused summaries [7.3%]) noted omissions (25 summaries [25.0%]) and inaccuracies (20 summaries [20.0%]) but rare hallucinations (2 summaries [2.0%]). Physicians rated 88 unedited summaries (88.0%) as having no harm potential and 1 (1.0%) as likely to cause moderate harm; no severe harm was reported. Mean physician burnout scores decreased significantly from before to after the intervention (1.75; 95% CI, 1.16-2.34 vs 1.20; 95% CI, 0.71-1.69; P = .03). Time savings were heterogeneous, with 5 of 7 physicians with matched baseline data (71.4%) seeing reductions in median documentation time; changes from baseline to pilot were up to 2.9 minutes, which was a nonsignificant difference (10.7 minutes; 95% CI, 7.4-13.3 minutes vs 7.8 minutes; 95% CI, 5.1-11.7 minutes; P = .13).In this study, an LLM-based agentic workflow produced hospital course summaries that were frequently used with minimal risk of harm identified. The intervention was associated with a reduction in physician burnout, supporting the viability of AI summarization to mitigate documentation burden.

  View details for DOI 10.1001/jamanetworkopen.2026.16556

  View details for PubMedID 42101844

• Point-of-Care Ultrasound Predicts Clinical Outcomes in Patients With COVID-19. Journal of ultrasound in medicine : official journal of the American Institute of Ultrasound in Medicine Kumar, A., Weng, I., Graglia, S., Lew, T., Gandhi, K., Lalani, F., Chia, D., Duanmu, Y., Jensen, T., Lobo, V., Nahn, J., Iverson, N., Rosenthal, M., Gordon, A. J., Kugler, J. 2021

  Abstract

  OBJECTIVES: Point-of-care ultrasound (POCUS) detects the pulmonary manifestations of COVID-19 and may predict patient outcomes.METHODS: We conducted a prospective cohort study at four hospitals from March 2020 to January 2021 to evaluate lung POCUS and clinical outcomes of COVID-19. Inclusion criteria included adult patients hospitalized for COVID-19 who received lung POCUS with a 12-zone protocol. Each image was interpreted by two reviewers blinded to clinical outcomes. Our primary outcome was the need for intensive care unit (ICU) admission versus no ICU admission. Secondary outcomes included intubation and supplemental oxygen usage.RESULTS: N=160 patients were included. Among critically ill patients, B-lines (94 vs 76%; P<.01) and consolidations (70 vs 46%; P<.01) were more common. For scans collected within 24hours of admission (N=101 patients), early B-lines (odds ratio [OR] 4.41 [95% confidence interval, CI: 1.71-14.30]; P<.01) or consolidations (OR 2.49 [95% CI: 1.35-4.86]; P<.01) were predictive of ICU admission. Early consolidations were associated with oxygen usage after discharge (OR 2.16 [95% CI: 1.01-4.70]; P=.047). Patients with a normal scan within 24hours of admission were less likely to require ICU admission (OR 0.28 [95% CI: 0.09-0.75]; P<.01) or supplemental oxygen (OR 0.26 [95% CI: 0.11-0.61]; P<.01). Ultrasound findings did not dynamically change over a 28-day scanning window after symptom onset.CONCLUSIONS: Lung POCUS findings detected within 24hours of admission may provide expedient risk stratification for important COVID-19 clinical outcomes, including future ICU admission or need for supplemental oxygen. Conversely, a normal scan within 24hours of admission appears protective. POCUS findings appeared stable over a 28-day scanning window, suggesting that these findings, regardless of their timing, may have clinical implications.

  View details for DOI 10.1002/jum.15818

  View details for PubMedID 34468039

• COVID fallout: Biden wants to stop, not stoke, racism against Asian Americans like me Lew, T. USA Today. 2021
• Severe coronavirus is more likely if you neglect your health. Preventative care is key Lew, T. USA Today. 2020
• COVID doctor: Herd immunity rests on naive and faulty logic. In practice, people will die Lew, T. USA Today. 2020
• Recurrent Multifocal Mycoplasma orale Infection in an Immunocompromised Patient: A Case Report and Review. Case reports in infectious diseases Ketchersid, J., Scott, J., Lew, T., Banaei, N., Kappagoda, S. 2020; 2020: 8852115

  Abstract

  A young woman with mixed connective tissue disease complicated by erosive arthritis, secondary hypogammaglobulinemia due to rituximab, and a history of many infectious complications developed multiple nonhealing wounds, polyarticular joint pain, and leukocytosis. Radiographic studies demonstrated multiple scattered areas of osteomyelitis and complex abscesses. Purulent fluid drained from multiple sites did not yield a microbiologic diagnosis by standard culture technique, but Mycoplasma orale was ultimately identified using 16S ribosomal RNA gene amplification and sequencing. We describe this unique case and review the literature.

  View details for DOI 10.1155/2020/8852115

  View details for PubMedID 32850161

• Take it from a physician treating COVID-19 patients, 'Frontline Doctors' video is dangerous Lew, T. USA Today. 2020
• Young doctor; I have coronavirus advice for people my age. Step back, stay healthy Lew, T. K. USA Today. 2020
• Lean-Based Redesign of Multidisciplinary Rounds on General Medicine Service. Journal of hospital medicine Kane, M. n., Rohatgi, N. n., Heidenreich, P. n., Thakur, A. n., Winget, M. n., Shum, K. n., Hereford, J. n., Shieh, L. n., Lew, T. n., Horn, J. n., Chi, J. n., Weinacker, A. n., Seay-Morrison, T. n., Ahuja, N. n. 2018

  Abstract

  Multidisciplinary rounds (MDR) facilitate timely communication amongst the care team and with patients. We used Lean techniques to redesign MDR on the teaching general medicine service.To examine if our Lean-based new model of MDR was associated with change in the primary outcome of length of stay (LOS) and secondary outcomes of discharges before noon, documentation of estimated discharge date (EDD), and patient satisfaction.This is a pre-post study. The preperiod (in which the old model of MDR was followed) comprised 4000 patients discharged between September 1, 2013, and October 22, 2014. The postperiod (in which the new model of MDR was followed) comprised 2085 patients between October 23, 2014, and April 30, 2015.Lean-based redesign of MDR.LOS, discharges before noon, EDD, and patient satisfaction.There was no change in the mean LOS. Discharges before noon increased from 6.9% to 10.7% (P < .001). Recording of EDD increased from 31.4% to 41.3% (P < .001). There was no change in patient satisfaction.Lean-based redesign of MDR was associated with an increase in discharges before noon and in recording of EDD.

  View details for PubMedID 29394300

• Acute, Unilateral Breast Toxicity From Gemcitabine in the Setting of Thoracic Inlet Obstruction. Journal of oncology practice / American Society of Clinical Oncology Weiskopf, K., Creighton, D., Lew, T., Caswell, J. L., Ouyang, D., Shah, A. T., Hofmann, L. V., Neal, J. W., Telli, M. L. 2016; 12 (8): 763-764

  View details for DOI 10.1200/JOP.2016.014241

  View details for PubMedID 27511721

• MedFactEval and MedAgentBrief: A Framework and Workflow for Generating and Evaluating Factual Clinical Summaries. Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Grolleau, F., Alsentzer, E., Keyes, T., Chung, P., Swaminathan, A., Aali, A., Hom, J., Huynh, T., Lew, T., Liang, A., Chu, W., Steele, N., Lin, C., Yang, J., Black, K., Ma, S., Haredasht, F. N., Shah, N. H., Schulman, K., Chen, J. H. 2026; 31: 388-399

  Abstract

  Evaluating factual accuracy in Large Language Model (LLM)-generated clinical text is a critical barrier to adoption, as expert review is unscalable for the continuous quality assurance these systems require. We address this challenge with two complementary contributions. First, we introduce MedFactEval, a framework for scalable, fact-grounded evaluation where clinicians define high-salience key facts and an "LLM Jury"-a multi-LLM majority vote-assesses their inclusion in generated summaries. Second, we present MedAgentBrief, a model-agnostic, multi-step workflow designed to generate high-quality, factual discharge summaries. To validate our evaluation framework, we established a gold-standard reference using a seven-physician majority vote on clinician-defined key facts from inpatient cases. The MedFactEval LLM Jury achieved almost perfect agreement with this panel (Cohen's κ = 81%), a performance statistically non-inferior to that of a single human expert (κ = 67%, P < 0.001). Our work provides both a robust evaluation framework (MedFactEval) and a high-performing generation workflow (MedAgentBrief), offering a comprehensive approach to advance the responsible deployment of generative AI in clinical workflows.

  View details for DOI 10.1142/9789819824755_0027

  View details for PubMedID 41758155

• The benefits of telehealth in promoting equity in blood cancer care - results of a multi-stakeholder forum and narrative review. Journal of medical economics Mikhael, J., Darlington, D., Howell, B., Hydren, J., Hernandez, T., Werner, S., Iraca, T., Arnett, M., Gonzalez, V., Peschin, S., Balch, A. J., Moran, D., , Banjo, O., Obeng, G. D., , Kawuo, S., Tukur, A. M., Mohammed, I., Obeng, A. P., Csanádi, M., Lew, T., Choon-Quinones, M. 2025: 1-27

  Abstract

  Aims Therapeutic advancements have significantly improved patient outcomes in blood cancers. However, stark racial and ethnic disparities persist in treatment and access to care. Telehealth offers a promising solution to these disparities by using electronic and telecommunication technologies to deliver healthcare services remotely. Ensuring access to telehealth depends not just on the technologies, but on the broader enabling environment, especially policy harmonization, communications infrastructure, and skills.This paper aims to advocate for the expanded use of telehealth in blood cancer management, highlighting its potential to improve equity and outcomes.Materials and methods An expert forum discussion results informed this narrative review which was performed to better understand the applied Telehealth solutions and the expected benefits. The forum discussion and the literature review findings were aggregated and reviewed by subject-matter experts and patient advocates with personal experience in blood cancer.Results Our review of the literature yielded 18 relevant papers. Studies included patients from various disease areas; some studies used broader definitions of cancer to include more patients (i.e., acute leukemias and malignant lymphomas), while others were more specific to a particular condition. The identified Telehealth solutions were classified into two groups: solutions focusing on electronic consultation (n = 10) and solutions focusing on a specific intervention to improve patients' health status (n = 8). A larger variety of outcomes were found in these studies, including quality of life, patient and clinicians' acceptance, adherence, costs, and resource use.Conclusions Initial findings demonstrate that telehealth can potentially improve patient outcomes for people living with blood cancer, including improved patient quality of life, increased clinician acceptance, better adherence, and reduced costs and resource use to the health system. While evidence for virtual consultations show promising results, further research is needed due to the variety of study settings evaluated in this review. Providers and health systems need additional data on the positive economic impact of Telehealth related to the diagnostic journey and access to treatment.

  View details for DOI 10.1080/13696998.2024.2438561

  View details for PubMedID 40340653

• Don't get lulled by COVID-19 vaccine. Stay careful and free up hospital space for others Lew, T. USA Today. 2021
• Why celebrity mental health matters Lew, T. USA Today. 2021
• If you saw my COVID patients, you’d know we’re still in danger. Don’t be a vaccine straggler Lew, T. USA Today. 2021
• My patient got COVID and died. He thought life was back to normal, but we aren't there yet Lew, T. USA Today. 2021
• COVID vaccines save lives. Get one even if your own life isn't back to normal overnight Lew, T. USA Today. 2021
• Fake news about the coronavirus is hazardous to your health. Don’t fall for it: Doctor Lew, T. USA Today. 2020
• Don’t let COVID-19 fears stop you from seeking medical treatment Lew, T. San Jose Mercury. 2020
• Opinion: Don’t believe nonsense that COVID-19 deaths are vastly overstated Lew, T. San Jose Mercury. 2020
• Toxic outside, contagious inside: Fire and COVID rage all around me. Can't we do better? Lew, T. USA Today. 2020
• Mr. President, people with COVID-19 are somebody to me, not 'nobody' Lew, T. USA Today. 2020
• Trump hit with COVID-19: Anyone can get sick. Anyone can spread the deadly disease Lew, T. USA Today. 2020
• Getting COVID-19 didn't help Trump evolve his thinking Lew, T. USA Today. 2020
• Doctor: Settle for virtual holidays this year amid COVID-19, starting with Thanksgiving Lew, T. USA Today. 2020
• Please don't cave to COVID-19 fatigue. Cases are exploding and we need your help. Again Lew, T. USA Today. 2020
• We failed Thanksgiving and COVID is surging. For Christmas, let's stay home and stay safe Lew, T. USA Today. 2020
• My COVID-19 vaccine was like a flu shot. I got one and went right back to work Lew, T. USA Today. 2020