Faculty Bibliography

Accessing high-quality, open-access dermatopathology image datasets for learning and cross-referencing is a common challenge for clinicians and trainees. To establish a comprehensive open-access dermatopathology dataset for educational, cross-referencing, and machine-learning purposes, we employed a hybrid workflow to curate and categorize images from the PubMed Central (PMC) repository. We used specific keywords to extract relevant images, and classified them using a novel hybrid method that combined deep learning-based image modality classification with figure caption analyses. Validation on 651 manually annotated images demonstrated the robustness of our workflow, with an F-score of 89.6% for the deep learning approach, 61.0% for the keyword-based retrieval method, and 90.4% for the hybrid approach. We retrieved over 7,772 images across 166 diagnoses and released this fully annotated dataset, reviewed by board-certified dermatopathologists. Using our dataset as a challenging task, we found the current image analysis algorithm from OpenAI inadequate for analyzing dermatopathology images. In conclusion, we have developed a large, peer-reviewed, open-access dermatopathology image dataset, DermpathNet, which features a semi-automated curation workflow.

BACKGROUND:As the incidence of frontal fibrosing alopecia (FFA) continues to rise, there is a need for an optimal treatment algorithm for FFA. OBJECTIVE:To produce an international consensus statement on the treatment modalities and prognostic indicators of FFA. METHODS:Sixty-nine hair experts from six continents were invited to participate in a three-round Delphi process. The final stage was held as a virtual meeting facilitated via Zoom. The consensus threshold was set at ≥66%. RESULTS:Of 365 questions, expert consensus was achieved in 204 (56%) questions following completion of the three rounds. Three additional questions were included at the final meeting. The category with the strongest consensus agreement was disease monitoring (9; 100%). Questions pertaining to physical therapies achieved the least category consensus (15; 40%), followed by systemic therapy (45; 43%). LIMITATIONS/CONCLUSIONS:The study lacked sufficient representation from Africa and South America. CONCLUSION/CONCLUSIONS:SOFFIA highlights areas of agreement and disagreement among experts. Robust research is warranted to provide evidence-based treatment recommendations.

Chemotherapy-induced alopecia and radiation-induced alopecia, the thinning or loss of hair due to cytotoxic chemotherapy and radiation therapy, respectively, are distressing adverse effects of cancer treatment. Chemotherapy, targeted therapies, and radiation therapy used in pediatric oncology often lead to alopecia by damaging hair follicles, with varying degrees of severity depending on the specific treatment type, mechanism of action, and damage-response pathway involved. Pediatric chemotherapy-induced alopecia, radiation-induced alopecia, and permanent alopecia, defined as hair regrowth that remains incomplete 6 months or more after treatment, have significant negative impacts on mental health, self-esteem, and social interactions, highlighting the need for further research into supportive care strategies. There are currently no standard interventions for chemotherapy-induced alopecia or radiation-induced alopecia in children, with most recommendations limited to gentle hair care and camouflaging techniques during treatment. Scalp cooling has demonstrated safety and efficacy in reducing chemotherapy-induced alopecia in adults and is currently under investigation in children and adolescents. Topical and low-dose oral minoxidil have been studied in children for other hair loss disorders and may improve hair regrowth after chemotherapy or radiation. Increased awareness and continued research into management strategies for pediatric chemotherapy-induced alopecia and radiation-induced alopecia are necessary to help mitigate its significant negative impact on quality of life.

The integration of artificial intelligence (AI) in healthcare, known herein as Medical AI, has seen a remarkable increase in attention over the last few years. This study aims to provide a comprehensive analysis of the trends in venture funding in the medical AI sector in comparison to venture funding in healthcare and AI as a whole over the past decade, using data from the Pitchbook financial database, and its implications for the future of healthcare quality and delivery. An extensive review of venture investments in healthcare, AI, and medical AI (the overlap between healthcare and AI) sectors was conducted for a 10-year period from October 7, 2013 to October 6, 2023. The study used Pitchbook"™s database to catalogue deals across various stages, round numbers, and series, inclusive of all ownership models and geographic locations. The analysis focused on completed transactions, extracting descriptive statistics for deal flow, capital flow, and post-funding valuations while analyzing trends. The study found that the medical AI sector experienced a higher year-over-year growth in deal volume (P=0.01 compared to healthcare, P=0.08 compared to AI) and capital flow (P=0.01 compared to healthcare and P=0.03 compared to AI) over this time period, with all sectors witnessing a sharp stimulus during the coronavirus disease 2019 (COVID-19) stimulus period, alongside marked increases at the time of introduction of seminal AI technologies. This was followed by marked drawdowns with the onset of high inflation and high interest rates. Early-stage funding was dominant in medical AI, indicating a market leaning towards emerging technologies. Despite a decrease in total deal volume in recent years, there was a steady increase in median deal sizes and valuations, highlighting the sector"™s resilience and perceived value. The findings suggest that medical AI is a rapidly growing sector with significant investor interest, particularly in early-stage ventures. The findings align with the early stages of a valuation bubble, though the sector thus far has shown resilience and value growth despite broader economic fluctuations and reduced deal volume, indicating a selective yet robust investment environment.