Crowdsourcing Dermatology Images with Google Search Ads: Creating a Real-World Skin Condition Dataset
Authors:
Preprint
Abstract
Background: Health datasets from clinical sources do not reflect the breadth and diversity of disease in the real world, impacting research, medical education, and artificial intelligence (AI) tool development. Dermatology is a suitable area to develop and test a new and scalable method to create representative health datasets. Methods: We used Google Search advertisements to invite contributions to an open access dataset of images of dermatology conditions, demographic and symptom information. With informed contributor consent, we describe and release this dataset containing 10,408 images from 5,033 contributions from internet users in the United States over 8 months starting March 2023. The dataset includes dermatologist condition labels as well as estimated Fitzpatrick Skin Type (eFST) and Monk Skin Tone (eMST) labels for the images. Results: We received a median of 22 submissions/day (IQR 14-30). Female (66.72%) and younger (52% < age 40) contributors had a higher representation in the dataset compared to the US population, and 32.6% of contributors reported a non-White racial or ethnic identity. Over 97.5% of contributions were genuine images of skin conditions. Dermatologist confidence in assigning a differential diagnosis increased with the number of available variables, and showed a weaker correlation with image sharpness (Spearman's P values <0.001 and 0.01 respectively). Most contributions were short-duration (54% with onset < 7 days ago ) and 89% were allergic, infectious, or inflammatory conditions. eFST and eMST distributions reflected the geographical origin of the dataset. The dataset is available at github.com/google-research-datasets/scin . Conclusion: Search ads are effective at crowdsourcing images of health conditions. The SCIN dataset bridges important gaps in the availability of representative images of common skin conditions.Keywords
All Related Versions
This publication has 30 references indexed in Scilit:
- Development and Clinical Evaluation of an Artificial Intelligence Support Tool for Improving Telemedicine Photo QualityJAMA Dermatology, 2023
- Bias in, bias out: Underreporting and underrepresentation of diverse skin types in machine learning research for skin cancer detection—A scoping reviewJournal of the American Academy of Dermatology, 2022
- Characteristics of publicly available skin cancer image datasets: a systematic reviewThe Lancet Digital Health, 2022
- Lack of Transparency and Potential Bias in Artificial Intelligence Data Sets and AlgorithmsJAMA Dermatology, 2021
- Development and Assessment of an Artificial Intelligence–Based Tool for Skin Condition Diagnosis by Primary Care Physicians and Nurse Practitioners in Teledermatology PracticesJAMA Network Open, 2021
- Use of Google Trends to investigate loss‐of‐smell‒related searches during the COVID‐19 outbreakInternational Forum of Allergy & Rhinology, 2020
- Impact of store-and-forward (SAF) teledermatology on outpatient dermatologic care: A prospective study in an underserved urban primary care settingJournal of the American Academy of Dermatology, 2016
- Detecting influenza epidemics using search engine query dataNature, 2009
- The first images of atopic dermatitis: An attempt at retrospective diagnosis in dermatologyJournal of the American Academy of Dermatology, 2005
- A retrospective biopsy study of the clinical diagnostic accuracy of common skin diseases by different specialties compared with dermatologyJournal of the American Academy of Dermatology, 2005