BCBrian Chu

Brian Chu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Brian Chu has a total of 115 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Agentic AI in Dermatology: A Call to Action

    by Brian Chu, Heather Shen, Ivy Lee, Jules B Lipoff

    Artificial intelligence (AI) tools are shifting from passive, user-initiated tools to proactive agentic AI systems that are capable of autonomous, multi-step actions. These agents can independently gather information, execute sequential tasks, and collaborate with humans or other agents without requiring constant prompting from humans. Early adopters in health care have demonstrated early feasibility across multiple specialties and clinical settings. Dermatology is well-positioned to benefit given its high patient volumes, administrative burdens, and clinicopathological workflows. To guide responsible adoption of agentic AI, we propose a risk-stratification framework based on clinical risk and task reversibility. Barriers to widespread adoption of agentic AI include limitations in model reliability, interoperability across health records, and unresolved questions around liability, privacy, and regulation. Dermatologists must proactively engage via professional organizations and industry partnerships to ensure that agentic AI is developed safely, equitably, and in alignment with our values.

  • Cutaneous Manifestations of Vasculitis: A Cross‐Sectional Analysis From an International Cohort

    by Robert G. Micheletti, William B. Song, Brian Chu, Lynne Allen‐Taylor, Joel M. Gelfand, Peter C. Grayson, Cristina Ponte, Joanna C. Robson, Ravi Suppiah, Raashid A. Luqmani, et al.

  • Open Access

    Agentic AI in Dermatology: A Call to Action (Preprint)

    by Brian Chu, Heather Shen, Ivy Lee, Jules Lipoff

    UNSTRUCTURED Artificial intelligence tools are shifting from passive, user-initiated tools to proactive agentic AI systems that are capable of autonomous, multi-step actions. These agents can independently gather information, execute sequential tasks, and collaborate with humans or other agents without requiring constant prompting from humans. Early adopters in healthcare have demonstrated early feasibility across multiple specialties and clinical settings. Dermatology is well-positioned to benefit given its high patient volumes, administrative burdens, and clinicopathological workflow. To guide responsible adoption of agentic AI, we propose a risk-stratification framework based on clinical risk and task reversibility. Barriers to widespread adoption of agentic AI include limitations in model reliability, interoperability across health records, and unresolved questions around liability, privacy, and regulation. Dermatologists must proactively engage via professional organizations and industry partnerships to ensure that agentic AI is developed safely, equitably, and in alignment with our values.

  • Open Access

    Evaluation of ChatGPT Dermatology Responses to Common Patient Queries

    by Alana L Ferreira, Brian Chu, Jane M Grant-Kels, Temitayo Ogunleye, Jules B Lipoff

    Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). N/A


  • Open Access

    Evaluation of ChatGPT Dermatology Responses to Common Patient Queries (Preprint)

    by Alana L Ferreira, Brian Chu, Jane M Grant-Kels, Temitayo Ogunleye, Jules B Lipoff

    UNSTRUCTURED Our evaluation of ChatGPT’s dermatology-related advice revealed a predominance of appropriate responses, as well as areas for improvement and the importance of professional consultations.

  • Open Access

    Penicillin allergy evaluation in hospitalized patients with hematologic malignancy

    by Vima M. Patel, Brian Chu, Keith W. Hamilton, Cassandra Bellamy, Christina Harker, Joshua S. Bryer, Bridget Shields, Rebecca L. Hirsh, Olajumoke O. Fadugba, Robert G. Micheletti

    A penicillin allergy testing service (PATS) assessed penicillin allergy in patients with hematologic malignancies; 17 patients who met criteria had negative skin testing. Patients who underwent penicillin challenge passed and were delabeled. Of delabeled patients, 87% received and tolerated β-lactams during follow-up. Providers found the PATS valuable.


  • Open Access

    Quality of Life and Physical Activity in 629 Individuals With Sarcoidosis: Prospective, Cross-sectional Study Using Smartphones (Sarcoidosis App)

    by Brian Chu, Daniel M O'Connor, Marilyn Wan, Ian Barnett, Haochang Shou, Marc Judson, Misha Rosenbach

    Background: Large gaps exist in understanding the symptomatic and functional impact of sarcoidosis, a rare multisystem granulomatous disease affecting fewer than 200,000 individuals in the United States. Smartphones could be used for prospective research, especially for rare diseases where organizing large cohorts can be challenging, given their near ubiquitous ownership and ability to track objective and subjective data with increasingly sophisticated technology. Objective: We aimed to investigate whether smartphones could assess the quality of life (QoL) and physical activity of a large cohort of individuals with sarcoidosis. Methods: We developed a mobile app (Sarcoidosis App) for a prospective, cross-sectional study on individuals with sarcoidosis. The Sarcoidosis App was made available on both Apple and Android smartphones. Individuals with sarcoidosis were recruited, consented, and enrolled entirely within the app. Surveys on sarcoidosis history, medical history, and medications were administered. Patients completed modules from the Sarcoidosis Assessment Tool, a validated patient-reported outcomes assessment of physical activity, fatigue, pain, skin symptoms, sleep, and lungs symptoms. Physical activity measured by smartphones was tracked as available. Results: From April 2018 to May 2020, the App was downloaded 2558 times, and 629 individuals enrolled (404, 64.2% female; mean age 51 years; 513, 81.6% White; 86, 13.7% Black). Two-thirds of participants had a college or graduate degree, and more than half of them reported an income greater than US $60,000. Both QoL related to physical activity (P<.001, ρ=0.250) and fatigue (P<.01, ρ=–0.203) correlated with actual smartphone-tracked physical activity. Overall, 19.0% (98/517) of participants missed at least 1 week of school or work in an observed month owing to sarcoidosis, and 44.4% (279/629) reported that finances “greatly” or “severely” affected by sarcoidosis. Furthermore, 71.2% (437/614) of participants reported taking medications for sarcoidosis, with the most common being prednisone, methotrexate, hydroxychloroquine, and infliximab. Moreover, 46.4% (244/526) reported medication side effects, most commonly due to prednisone. Conclusions: We demonstrate that smartphones can prospectively recruit, consent, and study physical activity, QoL, and medication usage in a large sarcoidosis cohort, using both passively collected objective data and qualitative surveys that did not require any in-person encounters. Our study’s limitations include the study population being weighted toward more educated and wealthier individuals, suggesting that recruitment was not representative of the full spectrum of patients with sarcoidosis in the United States. Our study provides a model for future smartphone-enabled clinical research for rare diseases and highlights key technical challenges that future research teams interested in smartphone-based research for rare diseases should anticipate.


  • Open Access

    Moderate Colitis Not Requiring Intravenous Steroids Is Associated with Improved Survival in Stage IV Melanoma after Anti-CTLA4 Monotherapy, But Not Combination Therapy

    by Emily J Anstadt, Brian Chu, Nikhil Yegya-Raman, Xiaoyan Han, Abigail Doucette, Kendra Poirier, Jahan J Mohiuddin, Amit Maity, Andrea Facciabene, Ravi K Amaravadi, et al.

    Background: For patients with melanoma, gastrointestinal immune-related adverse events are common after receipt of anti-CTLA4 therapy. These present difficult decision points regarding whether to discontinue therapy. Detailing the situations in which colitis might predict for improved survival and how this is affected by discontinuation or resumption of therapy can help guide clinical decision-making. Materials and Methods: Patients with stage IV melanoma receiving anti-CTLA4 therapy from 2008 to 2019 were analyzed. Immune-related colitis treated with ≥50 mg prednisone or equivalent daily or secondary immunosuppression was included. Moderate colitis was defined as receipt of oral glucocorticoids only; severe colitis was defined as requiring intravenous glucocorticoids or secondary immunosuppression. The primary outcome was overall survival (OS). Results: In total, 171 patients received monotherapy, and 91 received dual checkpoint therapy. In the monotherapy group, 25 patients developed colitis and a nonsignificant trend toward improved OS was observed in this group. Notably, when colitis was categorized as none, moderate or severe, OS was significantly improved for moderate colitis only. This survival difference was not present after dual checkpoint therapy. There were no differences in known prognostic variables between groups, and on multivariable analysis neither completion of all ipilimumab cycles nor resumption of immunotherapy correlated with OS, while the development of moderate colitis did significantly affect OS. Conclusion: This single-institution retrospective series suggests moderate colitis correlates with improved OS for patients with stage IV melanoma treated with single-agent anti-CTLA4, but not dual agent, and that this is true regardless of whether the immune-checkpoint blockade is permanently discontinued.


  • Open Access

    Patterns of Promotional Content by Dermatology Influencers on TikTok

    by Varun K Ranpariya, Ramie Fathy, Brian Chu, Sonia Wang, Jules B Lipoff

    Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author). N/A


  • Open Access

    The Sarcoidosis App: A national prospective study of quality of life and physical activity in 629 individuals with sarcoidosis using smartphones (Preprint)

    by Brian Chu, Daniel M O'COnnor, Marilyn T Wan, Ian Barnett, Haochang Shou, Marc A Judson, Misha Rosenbach

    BACKGROUND Large gaps exist in understanding the symptomatic and functional impact of sarcoidosis. Smartphones could be used for prospective research, especially for rare diseases where organizing large cohorts can be challenging, given their near ubiquitous ownership and ability to track objective and subjective data. OBJECTIVE We investigate whether smartphones could assess quality of life (QoL) and physical activity of a large cohort of individuals with sarcoidosis. METHODS We developed a mobile application (“Sarcoidosis App") for prospective, cross-sectional study of individuals with sarcoidosis. Individuals were recruited, consented, and enrolled entirely within the App. Surveys of sarcoidosis history, medical history, and medications were administered. Patients completed modules from the Sarcoidosis Assessment Tool, a validated patient-reported outcomes assessment of physical activity, fatigue, pain, skin symptoms, sleep, and lungs symptoms. Physical activity measured by smartphones was tracked as available. RESULTS From April 2018 to May 2020, the App was downloaded 2,558 times, and 629 enrolled (64.2% female, mean age 51 years, 81.6% white, 13.7% black). Both QoL related to physical activity (p<0.001, ρ=0.250) and fatigue (p<0.01, ρ=-0.203) correlated with actual smartphone-tracked physical activity. Nineteen percent of participants missed at least one week of school or work in an observed month due to sarcoidosis, and 44% reported finances “greatly” or “severely” affected by sarcoidosis. Sixty-three percent reported medication side effects. CONCLUSIONS We demonstrate that smartphones can prospectively recruit, consent, and study physical activity, QoL, and medication usage in a large sarcoidosis cohort, using both passively collected objective data and qualitative surveys. Our study provides a model for future smartphone-enabled clinical research for rare diseases and highlights key technical challenges.