LAUSR

BT11 How to train your artificial intelligence (AI) dragon: an analysis of human triage performance of communitycaptured images to inform development of AI solutions Gillian X.M. Chin, Callum Hakimi-Khiabani, Sanaa Butt, Alyson Bryden, Shareen Muthiah, Tamas Suveges, Colin Morton, Andrew Coon and Colin Fleming Ninewells Hospital, Dundee, UK; University of Dundee, Dundee, UK; and Stirling Community Hospital, Stirling, UK Our dermatology department uses low-quality images taken on smartphones or digital cameras by primary care clinicians, and high-quality images taken by medical photography. Lowquality images can be taken anywhere, and have useful triage value. High-quality images afford greater diagnostic power. We have studied human triage performance from this system, in the process of developing artificial intelligence (AI) based on both lowand high-quality images. Two studies were performed. To test triage performance using low-quality images, without clinical data, we reviewed a database from 2017 of previously triaged low-quality images. A clinical fellow (O1) in dermatology and a consultant dermatologist (O2) were shown 150 sequentially selected images and asked to triage as benign or suspicious, and then provide the most likely diagnosis. Validated diagnoses were determined from a dermatology diagnostic database. We then examined how many patients were directly discharged from triage when either lowor high-quality images were available. In total, 350 sequential patients, from 2021, triaged using initial low-quality images, then high-quality images, had records analysed to determine the additional benefit from using high-quality images in this context. In the first part of the study, 99% (O1: 100%; O2: 97%) of cancerous/precancerous lesions were correctly identified as suspicious. Provisional diagnoses made by observers matched validated diagnoses in 60% (O1: 58%; O2: 61%) of cases. In the second part of the study, 28% of patients with high-quality images were directly discharged to primary care. A further 32% of these patients completed telephone consultations, ensuring 60% of these patients did not require face-to-face appointments. In summary, cancerous/precancerous lesions were accurately triaged as either benign or malignant. Low-quality images in triage often yield false-positive suspicious responses. Low-quality images produce lower diagnostic accuracy. Low-quality image referral in our system, even without clinical data, permits two in 10 patients to be managed remotely; with high-quality images this is around six in 10. This study is the first real-world investigation of triage use of lowand high-quality data. It supports previous observations that high-quality images increase the likelihood of accurate diagnoses, even without clinical information. Low-quality data are useful in triage, and therefore may be used to develop AI, to complement highquality data AI. Some patients will struggle to attend for highquality image capture and research should focus on improving capture of both lowand high-quality images, and developing real-world AI based on varying populations, presentations and image quality.