Albert Sean Chiou
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
Research Subjects
Albert Sean Chiou has a total of 265 co-authors. Here are the top co-authors by number of shared publications:
Justin Ko
Department of Dermatology, School of Medicine, Stanford University, Stanford, California
5 shared publications- Kiana Yekrang
Department of Dermatology, Stanford University, CA
5 shared publications - Roxana Daneshjou
Department of Biomedical Data Science, Stanford University School of Medicine, Stanford, CA, USA
5 shared publications - Emmanuel H. During
Department of Neurology, Icahn School of Medicine, New York, USA
4 shared publications - Marius Ardeleanu
Regeneron Pharmaceuticals Inc., Tarrytown, USA
4 shared publications - Olivier Gevaert
Department of Biomedical Data Science Stanford University 94305 Stanford CA USA
4 shared publications
Latest Publications
- Open Access
- 2 September 2026
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 10, e90100
Health Care Professionals’ Perceptions of AI in Clinical Practice: Productivity, Enjoyment, and Pay
Despite widespread discussion of opportunities and risks about AI in medicine, few health care professionals routinely used AI during this study period. Physicians and men were more likely to report frequent AI use, and frequent AI users more often reported positive sentiments about AI’s future impacts on pay, enjoyment, and productivity at work. The youngest professionals (≤29 years) were less engaged and more skeptical about AI’s future benefits. These findings highlight a gap between AI’s promise and medical practice, as adoption varies by role, experience, and demographics.
- 2 September 2026
- Published by JMIR Publications Inc. in JMIR Formative Research
- Vol. 10, e90100
Open AccessHealth Care Professionals’ Perceptions of AI in Clinical Practice: Productivity, Enjoyment, and Pay
Despite widespread discussion of opportunities and risks about AI in medicine, few health care professionals routinely used AI during this study period. Physicians and men were more likely to report frequent AI use, and frequent AI users more often reported positive sentiments about AI’s future impacts on pay, enjoyment, and productivity at work. The youngest professionals (≤29 years) were less engaged and more skeptical about AI’s future benefits. These findings highlight a gap between AI’s promise and medical practice, as adoption varies by role, experience, and demographics.
- Open Access
- 21 January 2026
- Published by Medical Journals Sweden AB in Acta Dermato-Venereologica
- Vol. 106
Patient-reported Itch Outcome Measures for Chronic Pruritus in Dystrophic Epidermolysis Bullosa: Exploratory Analysis of a Phase 2 Randomized Controlled Trial
- 21 January 2026
- Published by Medical Journals Sweden AB in Acta Dermato-Venereologica
- Vol. 106
Open AccessPatient-reported Itch Outcome Measures for Chronic Pruritus in Dystrophic Epidermolysis Bullosa: Exploratory Analysis of a Phase 2 Randomized Controlled Trial
- Top Cited Papers
- 20 January 2026
- Published by Springer Nature in Nature Medicine
- Vol. 32 (3) , 943-951
Holistic evaluation of large language models for medical tasks with MedHELM
While large language models (LLMs) achieve near-perfect scores on medical licensing exams, these evaluations inadequately reflect the complexity and diversity of real-world clinical practice. Here we introduce MedHELM, an extensible evaluation framework with three contributions. First, a clinician-validated taxonomy organizing medical AI applications into five categories that mirror real clinical tasks—clinical decision support (diagnostic decisions, treatment planning), clinical note generation (visit documentation, procedure reports), patient communication (education materials, care instructions), medical research (literature analysis, clinical data analysis) and administration (scheduling, workflow coordination). These encompass 22 subcategories and 121 specific tasks reflecting daily medical practice. Second, a comprehensive benchmark suite of 37 evaluations covering all subcategories. Third, systematic comparison of nine frontier LLMs—Claude 3.5 Sonnet, Claude 3.7 Sonnet, DeepSeek R1, Gemini 1.5 Pro, Gemini 2.0 Flash, GPT-4o, GPT-4o mini, Llama 3.3 and o3-mini—using an automated LLM-jury evaluation method. Our LLM-jury uses multiple AI evaluators to assess model outputs against expert-defined criteria. Advanced reasoning models (DeepSeek R1, o3-mini) demonstrated superior performance with win rates of 66%, although Claude 3.5 Sonnet achieved comparable results at 15% lower computational cost. These results not only highlight current model capabilities but also demonstrate how MedHELM could enable evidence-based selection of medical AI systems for healthcare applications.
- 20 January 2026
- Published by Springer Nature in Nature Medicine
- Vol. 32 (3) , 943-951
Top Cited PapersHolistic evaluation of large language models for medical tasks with MedHELM
While large language models (LLMs) achieve near-perfect scores on medical licensing exams, these evaluations inadequately reflect the complexity and diversity of real-world clinical practice. Here we introduce MedHELM, an extensible evaluation framework with three contributions. First, a clinician-validated taxonomy organizing medical AI applications into five categories that mirror real clinical tasks—clinical decision support (diagnostic decisions, treatment planning), clinical note generation (visit documentation, procedure reports), patient communication (education materials, care instructions), medical research (literature analysis, clinical data analysis) and administration (scheduling, workflow coordination). These encompass 22 subcategories and 121 specific tasks reflecting daily medical practice. Second, a comprehensive benchmark suite of 37 evaluations covering all subcategories. Third, systematic comparison of nine frontier LLMs—Claude 3.5 Sonnet, Claude 3.7 Sonnet, DeepSeek R1, Gemini 1.5 Pro, Gemini 2.0 Flash, GPT-4o, GPT-4o mini, Llama 3.3 and o3-mini—using an automated LLM-jury evaluation method. Our LLM-jury uses multiple AI evaluators to assess model outputs against expert-defined criteria. Advanced reasoning models (DeepSeek R1, o3-mini) demonstrated superior performance with win rates of 66%, although Claude 3.5 Sonnet achieved comparable results at 15% lower computational cost. These results not only highlight current model capabilities but also demonstrate how MedHELM could enable evidence-based selection of medical AI systems for healthcare applications.
- 22 May 2025
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 2 (6)
Multimodal Image Dataset for AI-Based Skin Cancer (MIDAS) Benchmarking
- 22 May 2025
- Published by Massachusetts Medical Society in NEJM AI
- Vol. 2 (6)
Multimodal Image Dataset for AI-Based Skin Cancer (MIDAS) Benchmarking
- Open Access
- 10 November 2024
- Published by Elsevier in JAAD International
- Vol. 18, 145-147
Evaluating the appropriateness of skin cancer prevention recommendations obtained from an online chat-based artificial intelligence model
- 10 November 2024
- Published by Elsevier in JAAD International
- Vol. 18, 145-147
Open AccessEvaluating the appropriateness of skin cancer prevention recommendations obtained from an online chat-based artificial intelligence model
- 30 October 2024
- Published by Elsevier in Journal of Investigative Dermatology
- Vol. 145 (5) , 1205-1208.e4
DDI-2: A Diverse Skin Condition Image Dataset Representing Self-Identified Asian Patients
- 30 October 2024
- Published by Elsevier in Journal of Investigative Dermatology
- Vol. 145 (5) , 1205-1208.e4
DDI-2: A Diverse Skin Condition Image Dataset Representing Self-Identified Asian Patients
- 1 September 2024
- Published by American Medical Association (AMA) in JAMA Dermatology
- Vol. 160 (9) , 972-976
Single-Lesion Skin Cancer Risk Stratification Triage Pathway
Importance: Access to timely dermatologic care remains a challenge, especially for patients with new skin lesions. Assessing the efficiency of new triage pathways may assist in better resource allocation and shorter time to care.Objective: To evaluate whether a rule-based triage system was associated with better skin cancer risk stratification of patients and reduced wait times.Design, Setting, and Participants: This retrospective quality improvement cohort study of patients referred to Stanford University dermatology clinics was conducted between November 2017 and January 2023. A rules-based triage system based on a priori–determined high-risk lesion characteristics was implemented.Exposures: Referral reasons and risk factors of patients provided by their primary care physicians.Main Outcomes and Measures: Biopsy results of patients (diagnosis of any skin cancer and melanoma) at their visit or within 6 months after the visit. Regression models were used to assess the association between risk factors at referral and (1) biopsy outcomes and (2) time to first visit, adjusting for sociodemographic factors.Results: Among 37 478 patients (mean [SD] age, 54 (18) years; 21 292 women [57%]), the rates of aggregate biopsy, malignant biopsy specimens, and melanoma were comparable across patients seen after (n = 12 302) and before (n = 25 176) the implementation of the new triage pathway. Patients seen through the lesion pathway had a higher risk of having malignant biopsy results (adjusted risk ratio [aRR], 1.6; 95% CI, 1.4-1.9) and melanoma (aRR, 2.0; 95% CI, 1.2-3.2) than those not seen through the pathway. Lesions that were concerning to referring clinicians for skin cancer were associated with an increased risk of skin cancer (all skin cancer: aRR, 2.8; 95% CI, 2.2-3.5; melanoma: aRR, 2.02; 95% CI, 1.1-3.7). Patients in the 3 high-risk lesion groups were seen faster in the new triage pathway (mean reduction, 26 days; 95% CI, 18-34 days).Conclusions and Relevance: In this study, a new automated, rules-based referral pathway was implemented that expedited care for patients with high-risk skin cancer. This reform may have contributed to improving patient stratification, reducing the time from referral to first encounter, and maintaining accuracy in identifying malignant lesions. The findings highlight the potential to optimize clinical resource allocation by better risk stratification of referred patients.
- 1 September 2024
- Published by American Medical Association (AMA) in JAMA Dermatology
- Vol. 160 (9) , 972-976
Single-Lesion Skin Cancer Risk Stratification Triage Pathway
Importance: Access to timely dermatologic care remains a challenge, especially for patients with new skin lesions. Assessing the efficiency of new triage pathways may assist in better resource allocation and shorter time to care.Objective: To evaluate whether a rule-based triage system was associated with better skin cancer risk stratification of patients and reduced wait times.Design, Setting, and Participants: This retrospective quality improvement cohort study of patients referred to Stanford University dermatology clinics was conducted between November 2017 and January 2023. A rules-based triage system based on a priori–determined high-risk lesion characteristics was implemented.Exposures: Referral reasons and risk factors of patients provided by their primary care physicians.Main Outcomes and Measures: Biopsy results of patients (diagnosis of any skin cancer and melanoma) at their visit or within 6 months after the visit. Regression models were used to assess the association between risk factors at referral and (1) biopsy outcomes and (2) time to first visit, adjusting for sociodemographic factors.Results: Among 37 478 patients (mean [SD] age, 54 (18) years; 21 292 women [57%]), the rates of aggregate biopsy, malignant biopsy specimens, and melanoma were comparable across patients seen after (n = 12 302) and before (n = 25 176) the implementation of the new triage pathway. Patients seen through the lesion pathway had a higher risk of having malignant biopsy results (adjusted risk ratio [aRR], 1.6; 95% CI, 1.4-1.9) and melanoma (aRR, 2.0; 95% CI, 1.2-3.2) than those not seen through the pathway. Lesions that were concerning to referring clinicians for skin cancer were associated with an increased risk of skin cancer (all skin cancer: aRR, 2.8; 95% CI, 2.2-3.5; melanoma: aRR, 2.02; 95% CI, 1.1-3.7). Patients in the 3 high-risk lesion groups were seen faster in the new triage pathway (mean reduction, 26 days; 95% CI, 18-34 days).Conclusions and Relevance: In this study, a new automated, rules-based referral pathway was implemented that expedited care for patients with high-risk skin cancer. This reform may have contributed to improving patient stratification, reducing the time from referral to first encounter, and maintaining accuracy in identifying malignant lesions. The findings highlight the potential to optimize clinical resource allocation by better risk stratification of referred patients.
- Open Access
Multimodal Image Dataset for AI-based Skin Cancer (MIDAS) Benchmarking
With an estimated 3 billion people globally lacking access to dermatological care, technological solutions leveraging artificial intelligence (AI) have been proposed to improve access 1 . Diagnostic AI algorithms, however, require high-quality datasets to allow development and testing, particularly those that enable evaluation of both unimodal and multimodal approaches. Currently, the majority of dermatology AI algorithms are built and tested on proprietary, siloed data, often from a single site and with only a single image type (i.e., clinical or dermoscopic). To address this, we developed and released the Melanoma Research Alliance Multimodal Image Dataset for AI-based Skin Cancer (MIDAS) dataset, the largest publicly available, prospectively-recruited, paired dermoscopic- and clinical image-based dataset of biopsy-proven and dermatopathology-labeled skin lesions. We explored model performance on real-world cases using four previously published state-of-the-art (SOTA) models and compared model-to-clinician diagnostic performance. We also assessed algorithm performance using clinical photography taken at different distances from the lesion to assess its influence across diagnostic categories. We prospectively enrolled 796 patients through an IRB-approved protocol with informed consent representing 1290 unique lesions and 3830 total images (including dermoscopic and clinical images taken at 15-cm and 30-cm distance). Images represented the diagnostic diversity of lesions seen in general dermatology, with malignant, benign, and inflammatory lesions that included melanocytic nevi (22%; n=234), invasive cutaneous melanomas (4%; n=46), and melanoma in situ (4%; n=47). When evaluating SOTA models using the MIDAS dataset, we observed performance reduction across all models compared to their previously published performance metrics, indicating challenges to generalizability of current SOTA algorithms. As a comparative baseline, the dermatologists performing biopsies were 79% accurate with their top-1 diagnosis at differentiating a malignant from benign lesion. For malignant lesions, algorithms performed better on images acquired at 15-cm compared to 30-cm distance while dermoscopic images yielded higher sensitivity compared to clinical images. Improving our understanding of the strengths and weaknesses of AI diagnostic algorithms is critical as these tools advance towards widespread clinical deployment. While many algorithms may report high performance metrics, caution should be taken due to the potential for overfitting to localized datasets. MIDAS’s robust, multimodal, and diverse dataset allows researchers to evaluate algorithms on our real-world images and better assess their generalizability.
Open AccessMultimodal Image Dataset for AI-based Skin Cancer (MIDAS) Benchmarking
With an estimated 3 billion people globally lacking access to dermatological care, technological solutions leveraging artificial intelligence (AI) have been proposed to improve access 1 . Diagnostic AI algorithms, however, require high-quality datasets to allow development and testing, particularly those that enable evaluation of both unimodal and multimodal approaches. Currently, the majority of dermatology AI algorithms are built and tested on proprietary, siloed data, often from a single site and with only a single image type (i.e., clinical or dermoscopic). To address this, we developed and released the Melanoma Research Alliance Multimodal Image Dataset for AI-based Skin Cancer (MIDAS) dataset, the largest publicly available, prospectively-recruited, paired dermoscopic- and clinical image-based dataset of biopsy-proven and dermatopathology-labeled skin lesions. We explored model performance on real-world cases using four previously published state-of-the-art (SOTA) models and compared model-to-clinician diagnostic performance. We also assessed algorithm performance using clinical photography taken at different distances from the lesion to assess its influence across diagnostic categories. We prospectively enrolled 796 patients through an IRB-approved protocol with informed consent representing 1290 unique lesions and 3830 total images (including dermoscopic and clinical images taken at 15-cm and 30-cm distance). Images represented the diagnostic diversity of lesions seen in general dermatology, with malignant, benign, and inflammatory lesions that included melanocytic nevi (22%; n=234), invasive cutaneous melanomas (4%; n=46), and melanoma in situ (4%; n=47). When evaluating SOTA models using the MIDAS dataset, we observed performance reduction across all models compared to their previously published performance metrics, indicating challenges to generalizability of current SOTA algorithms. As a comparative baseline, the dermatologists performing biopsies were 79% accurate with their top-1 diagnosis at differentiating a malignant from benign lesion. For malignant lesions, algorithms performed better on images acquired at 15-cm compared to 30-cm distance while dermoscopic images yielded higher sensitivity compared to clinical images. Improving our understanding of the strengths and weaknesses of AI diagnostic algorithms is critical as these tools advance towards widespread clinical deployment. While many algorithms may report high performance metrics, caution should be taken due to the potential for overfitting to localized datasets. MIDAS’s robust, multimodal, and diverse dataset allows researchers to evaluate algorithms on our real-world images and better assess their generalizability.
- Open Access
- 10 February 2024
- Published by Elsevier in JAAD Case Reports
- Vol. 46, 5-7
Adult-onset inflammatory linear verrucous epidermal nevus successfully treated with intralesional steroid
- 10 February 2024
- Published by Elsevier in JAAD Case Reports
- Vol. 46, 5-7
Open AccessAdult-onset inflammatory linear verrucous epidermal nevus successfully treated with intralesional steroid
- Open Access
- 10 August 2023
- Published by Oxford University Press (OUP) in British Journal of Dermatology
- Vol. 189 (6) , 685-694
Dupilumab significantly improves sleep in adults with atopic dermatitis: results from the 12-week placebo-controlled period of the 24-week phase IV randomized double-blinded placebo-controlled DUPISTAD study
Background: Sleep disturbance is a prominent symptom of atopic dermatitis (AD) and can result in insomnia, daytime fatigue, drowsiness, reduced productivity and impaired quality of life (QoL). Objectives: The Dupilumab Effect on Sleep in AD Patients (DUPISTAD) phase IV randomized double-blinded placebo-controlled study evaluated the impact of dupilumab treatment on sleep and other patient- and physician-reported outcomes. Methods: Adults with moderate-to-severe AD were randomized 2 : 1 to dupilumab 300 mg once every 2 weeks (q2w) or placebo for 12 weeks; concomitant topical corticosteroids were permitted. Patients subsequently entered an open-label phase and received dupilumab 300 mg q2w for a further 12 weeks. The primary endpoint was the percentage change in sleep quality from baseline to week 12, assessed using a novel numeric rating scale (NRS). Secondary and exploratory endpoints included percentage change in peak pruritus NRS (PP NRS), change in SCORing Atopic Dermatitis (SCORAD), SCORAD sleep visual analogue scale (VAS), Eczema Area and Severity Index, Patient-Reported Outcomes Measurement Information System (PROMIS) sleep-related impairment T-score and the Epworth Sleepiness Scale. Sleep diary and wrist actigraphy measurements were recorded throughout the study. Results: In total, 127 patients received dupilumab and 61 patients received placebo. Demographic and baseline disease characteristics were balanced between groups. Sleep quality NRS significantly improved in patients treated with dupilumab by week 12 vs. placebo [least squares mean of the difference (LSMD) −15.5%, P < 0.001]. PP NRS (LSMD −27.9%, P < 0.001), SCORAD (LSMD −15.1, P < 0.001), SCORAD sleep VAS (LSMD −2.1, P < 0.001) and PROMIS T-score (LSMD −3.6, P < 0.001) were also significantly improved at week 12 with dupilumab vs. placebo. The overall percentage of patients reporting treatment-emergent adverse events was lower in the dupilumab group (56.7%) than in the placebo group (67.2%). Conclusions: Dupilumab significantly improved sleep quality and perception of sleep continuity, itch, metrics of AD severity and QoL in adults with moderate-to-severe AD, with an acceptable safety profile compared with placebo.
- 10 August 2023
- Published by Oxford University Press (OUP) in British Journal of Dermatology
- Vol. 189 (6) , 685-694
Open AccessDupilumab significantly improves sleep in adults with atopic dermatitis: results from the 12-week placebo-controlled period of the 24-week phase IV randomized double-blinded placebo-controlled DUPISTAD study
Background: Sleep disturbance is a prominent symptom of atopic dermatitis (AD) and can result in insomnia, daytime fatigue, drowsiness, reduced productivity and impaired quality of life (QoL). Objectives: The Dupilumab Effect on Sleep in AD Patients (DUPISTAD) phase IV randomized double-blinded placebo-controlled study evaluated the impact of dupilumab treatment on sleep and other patient- and physician-reported outcomes. Methods: Adults with moderate-to-severe AD were randomized 2 : 1 to dupilumab 300 mg once every 2 weeks (q2w) or placebo for 12 weeks; concomitant topical corticosteroids were permitted. Patients subsequently entered an open-label phase and received dupilumab 300 mg q2w for a further 12 weeks. The primary endpoint was the percentage change in sleep quality from baseline to week 12, assessed using a novel numeric rating scale (NRS). Secondary and exploratory endpoints included percentage change in peak pruritus NRS (PP NRS), change in SCORing Atopic Dermatitis (SCORAD), SCORAD sleep visual analogue scale (VAS), Eczema Area and Severity Index, Patient-Reported Outcomes Measurement Information System (PROMIS) sleep-related impairment T-score and the Epworth Sleepiness Scale. Sleep diary and wrist actigraphy measurements were recorded throughout the study. Results: In total, 127 patients received dupilumab and 61 patients received placebo. Demographic and baseline disease characteristics were balanced between groups. Sleep quality NRS significantly improved in patients treated with dupilumab by week 12 vs. placebo [least squares mean of the difference (LSMD) −15.5%, P < 0.001]. PP NRS (LSMD −27.9%, P < 0.001), SCORAD (LSMD −15.1, P < 0.001), SCORAD sleep VAS (LSMD −2.1, P < 0.001) and PROMIS T-score (LSMD −3.6, P < 0.001) were also significantly improved at week 12 with dupilumab vs. placebo. The overall percentage of patients reporting treatment-emergent adverse events was lower in the dupilumab group (56.7%) than in the placebo group (67.2%). Conclusions: Dupilumab significantly improved sleep quality and perception of sleep continuity, itch, metrics of AD severity and QoL in adults with moderate-to-severe AD, with an acceptable safety profile compared with placebo.