{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,11]],"date-time":"2026-08-11T06:38:03Z","timestamp":1786430283225,"version":"build-2736575974"},"reference-count":7,"publisher":"The Ewha Medical Journal, Ewha Womans University College of Medicine","issue":"3","license":[{"start":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T00:00:00Z","timestamp":1753142400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/3.0\/"}],"content-domain":{"domain":["e-emj.org"],"crossmark-restriction":true},"short-container-title":["Ewha Med J"],"published-print":{"date-parts":[[2025,7,31]]},"abstract":"<jats:p>Purpose: This study developed and validated a deep learning model for the automated early detection of androgenetic alopecia (AGA) using trichoscopic images, and evaluated the model\u2019s diagnostic performance in a Korean clinical cohort.Methods: We conducted a retrospective observational study using 318 trichoscopic scalp images labeled by board-certified dermatologists according to the Basic and Specific (BASP) system, collected at Ewha Womans University Medical Center between July 2018 and January 2024. The images were categorized as BASP 0 (no hair loss) or BASP 1\u20133 (early-stage hair loss). A ResNet-18 convolutional neural network, pretrained on ImageNet, was fine-tuned for binary classification. Internal validation was performed using stratified 5-fold cross-validation, and external validation was conducted through ensemble soft voting on a separate hold-out test set of 20 images. Model performance was measured by accuracy, precision, recall, F1-score, and area under the curve (AUC), with 95% confidence intervals (CIs) calculated for hold-out accuracy.Results: Internal validation revealed robust model performance, with 4 out of 5 folds achieving an accuracy above 0.90 and an AUC above 0.93. In external validation on the hold-out test set, the ensemble model achieved an accuracy of 0.90 (95% CI, 0.77\u20131.03) and an AUC of 0.97, with perfect recall for early-stage hair loss. No missing data were present, and the model demonstrated stable convergence without requiring data augmentation.Conclusion: This model demonstrated high accuracy and generalizability for detecting early-stage AGA from trichoscopic images, supporting its potential utility as a screening tool in clinical and teledermatology settings.<\/jats:p>","DOI":"10.12771\/emj.2025.00486","type":"journal-article","created":{"date-parts":[[2025,7,22]],"date-time":"2025-07-22T08:42:28Z","timestamp":1753173748000},"page":"e44","update-policy":"https:\/\/doi.org\/10.12771\/crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Automated early detection of androgenetic alopecia using deep learning on trichoscopic images from a Korean cohort: a retrospective model development and validation study"],"prefix":"10.12771","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-6087-7823","authenticated-orcid":true,"given":"Min Jung","family":"Suh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0116-3325","authenticated-orcid":true,"given":"Sohyun","family":"Ahn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4519-9474","authenticated-orcid":true,"given":"Ji Yeon","family":"Byun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4998","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s40257-019-00479-x"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.5021\/ad.21.085"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1001\/jamadermatol.2020.2188"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"ref5","volume-title":"","author":"Kuhn","year":"2013"},{"key":"ref6","volume-title":"","author":"Goodfellow","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-019-00619-1"}],"container-title":["Ewha Medical Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/e-emj.org\/upload\/pdf\/emj-2025-00486.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/e-emj.org\/journal\/view.php?doi=10.12771\/emj.2025.00486","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/e-emj.org\/upload\/pdf\/emj-2025-00486.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,31]],"date-time":"2025-07-31T07:11:23Z","timestamp":1753945883000},"score":1,"resource":{"primary":{"URL":"http:\/\/e-emj.org\/journal\/view.php?doi=10.12771\/emj.2025.00486"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,31]]},"references-count":7,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,7]]}},"URL":"https:\/\/doi.org\/10.12771\/emj.2025.00486","relation":{},"ISSN":["2234-3180","2234-2591"],"issn-type":[{"value":"2234-3180","type":"print"},{"value":"2234-2591","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,31]]},"assertion":[{"value":"2025-06-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-16","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-22","order":2,"name":"published","label":"Published online","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-31","order":3,"name":"published","label":"Print publication","group":{"name":"publication_history","label":"Publication History"}}]}}