A5069278500- Cutaneous Melanoma Detection and Management
- AI in cancer detection
- Artificial Intelligence in Healthcare and Education
- Telemedicine and Telehealth Implementation
- Hidradenitis Suppurativa and Treatments
- Cutaneous lymphoproliferative disorders research
- Machine Learning in Healthcare
- Nonmelanoma Skin Cancer Studies
- Mobile Health and mHealth Applications
- RNA regulation and disease
- melanin and skin pigmentation
- Topic Modeling
- Chemotherapy-related skin toxicity
- COVID-19 and healthcare impacts
- Oral Health Pathology and Treatment
- Genetic and rare skin diseases.
- Polyomavirus and related diseases
- Autoimmune and Inflammatory Disorders
- Clinical Reasoning and Diagnostic Skills
- Nail Diseases and Treatments
- Cell Image Analysis Techniques
- Wound Healing and Treatments
- Aquaculture disease management and microbiota
- Urban Green Space and Health
- Skin Diseases and Diabetes
Stanford University
2022-2025
Université de Montréal
2020-2024
Center for Clinical Research (United States)
2023
Stanford Medicine
2023
Centre Hospitalier Universitaire Sainte-Justine
2020-2022
Centre Hospitalier de l’Université de Montréal
2019-2020
The risk of subsequent primary cancers after a diagnosis cutaneous Merkel cell carcinoma (MCC) is not well established.
Introduction Stevens-Johnson syndrome and toxic epidermal necrolysis are severe cutaneous drug eruptions characterized by detachment. Pembrolizumab is a monoclonal antibody that binds to the programmed death-1 receptor, it has been associated with numerous adverse side-effects, including syndrome. Case report We describe 63-year-old male metastatic lung adenocarcinoma who developed rapidly progressing maculopapular rash three days after first dose of pembrolizumab. On day 16, affected more...
Abstract The integration of Large Language Models (LLMs) like GPT-4 and GPT-3.5 into clinical diagnostics has the potential to transform patient-doctor interactions. However, readiness these models for real-world application remains inadequately tested. This paper introduces Conversational Reasoning Assessment Framework Testing in Medicine (CRAFT-MD), a novel approach evaluating LLMs. Unlike traditional methods that rely on structured medical exams, CRAFT-MD focuses natural dialogues, using...
Despite the proliferation and clinical deployment of artificial intelligence (AI)-based medical software devices, most remain black boxes that are uninterpretable to key stakeholders including patients, physicians, even developers devices. Here, we present a general model auditing framework combines insights from experts with highly expressive form explainable AI leverages generative models, understand reasoning processes We then apply this generate first thorough, medically interpretable...
Building trustworthy and transparent image-based medical AI systems requires the ability to interrogate data models at all stages of development pipeline: from training post-deployment monitoring. Ideally, associated could be described using terms already familiar physicians, but this datasets densely annotated with semantically meaningful concepts. Here, we present a foundation model approach, named MONET (
Background The COVID-19 pandemic rapidly changed the landscape of clinical practice in United States; telehealth became an essential mode health care delivery, yet many components use remain unknown years after disease’s emergence. Objective We aim to comprehensively assess and its associated factors States. Methods This cross-sectional study used a nationally representative survey (Health Information National Trends Survey) administered US adults (≥18 years) from March 2022 through November...
Soft tissue sarcomas (STS) are rare and heterogeneous, with cutaneous STS (CSTS) lacking recent epidemiological data. This study analyses CSTS incidence from 2000 to 2019 using SEER data, identifying 18 181 cases. was more common in men non-Hispanic Whites, Kaposi sarcoma (KS) dermatofibrosarcoma protuberans (DFSP) being predominant. The overall 11.2 per 1 000 person-years, KS having the highest rate. reveals a 1.4% annual decline rates highlights ethnic disparities, especially among...
Background: Patterned cutaneous hypopigmentation (PCH) can be associated with an array of extracutaneous findings. Objective: Determine clinical and genetic characteristics patients PCH involvement. Method: Thirty were identified, eight neurological involvement agreed to participate in this study. They reassessed collect anomalies their PCH. Exome sequencing was performed on patient blood lesional skin biopsies as well from both parents when available. Array comparative genomic hybridization...
Indoor tanning beds cause more than 450,000 new skin cancers each year, yet their use remains common, with a global indoor prevalence of 10.4%. Social media provides an opportunity for cost-effective, targeted public health messaging. We sought to direct Instagram users at high risk accurate information about the risks and reduce bed use.
RHOA-related neuroectodermal syndrome is characterised by linear skin hypopigmentation along Blaschko's lines associated with alopecia, leukoencephalopathy, facial and limb hypoplasia, ocular, dental, acral anomalies. Herein, we report a patient patterned cutaneous similar phenotype due to novel postzygotic RHOA variant (c.210G>T; p.Arg70Ser). This illustrates that the complexity of orchestration morphogenesis organogenesis can be affected different variants in same gene.
Abstract With an estimated 3 billion people globally lacking access to dermatological care, technological solutions leveraging artificial intelligence (AI) have been proposed improve 1 . Diagnostic AI algorithms, however, require high-quality datasets allow development and testing, particularly those that enable evaluation of both unimodal multimodal approaches. Currently, the majority dermatology algorithms are built tested on proprietary, siloed data, often from a single site with only...
Informal caregivers of people with Alzheimer's disease and related dementias (ADRD) are at risk poor mental health. This study aimed to investigate the feasibility validity studying caregivers' stressors using online caregiving forum data (March 2018–February 2022) natural language processing machine learning (NLP/ML). NLP/ML topic modeling generated eight prominent topics, which we compared qualitatively defined themes existing framework assess validity. Among a total 60,182 posts, 5848...
Deep granuloma annulare is an uncommon benign granulomatous skin disorder that presents almost exclusively in the paediatric population. It as asymptomatic subcutaneous nodule with normal overlying on distal extremities, scalp, or forehead. shows a deep palisading areas of central necrobiosis histologic examination. Due to its self-limited nature, clinical follow-up recommended over surgical interventions. We present case cephalic healthy 5-year-old girl who remains free recurrence after...
Pyoderma gangrenosum is often associated with a systemic disease. Cocaine-induced pyoderma gangrenosum, most probably caused by levamisole, has been described recently and typically presents as multiple, large cribriform ulcers. Peri-nuclear antineutrophil cytoplasmic antibody the common serological finding. A strong counseling for cocaine cessation, combined wound care immunosuppressive therapy, mainstay of treatment. We present two cases cocaine-induced correlate their findings typical...
For the deployment of artificial intelligence (AI) in high-risk settings, such as healthcare, methods that provide interpretability/explainability or allow fine-grained error analysis are critical. Many recent for and use concepts, which meta-labels semantically meaningful to humans. However, there only a few datasets include concept-level most these relevant natural images do not require domain expertise. Densely annotated medicine focused on single disease melanoma. In dermatology, skin is...
We developed a digital tool for home-based monitoring of skin disease, our tool. In the current observational pilot study, we found that DORA is feasible to use in practice, as it has high patient compliance, retention and satisfaction. Clinicans rated photos generally good quality or perfect quality. These results show health can easily be used by patients send their dermatologist, which could reduce unnecessary clinical visits. It may also other settings where literacy barriers unequal...