https://doi.org/10.55788/f9840392
Dr Kashini Andrew (University Hospitals Birmingham NHS Foundation Trust, UK) and his fellow researchers developed AI technology for the detection of skin cancer [1]. They now presented the 2022–2023 software version’s results in comparison to earlier findings of the first version that was tested in 2020–2021.
Over 2.6 years, a total of 22,356 patients were evaluated by the AI tool. This was triggered by a suspicion of a skin malignancy by the general practitioner. AI categorisation of the lesions was reviewed by a dermatologist outside the hospital in case of a benign result and by a university hospital consultant when cancer was suspected.
Between the first and the latest version of the detection software, further training of the AI with images of confirmed diagnoses took place. Sensitivity for melanoma recognition increased from 86% in 2020–2021 to 100% (59 out of 59 cases) in AI version 3. The latest AI version correctly labelled 99.5% of skin cancers (189 out of 190 cases), while the earliest software version achieved a sensitivity of 83.8%.
"This study has demonstrated how AI is rapidly improving and learning, with the high accuracy directly attributable to improvements in AI training techniques and the quality of data used to train the AI,” Dr Andrew commented on the improvement in detection. For pre-malignant lesions, the current sensitivity was also higher than in AI version 1, with a current rate of 92.5%. The AI demonstrated a specificity of 75.3% in recognising benign lesions. Notably, there was 1 case of basal cell carcinoma misclassified as benign by the AI, and the dermatologist had a benign-to-cancer overturn rate of 0.1%.
"We would like to stress that AI should not be used as a stand-alone tool in skin cancer detection and that AI is not a substitute for consultant dermatologists," study co-author Dr Irshad Zaki (University Hospitals Birmingham NHS Foundation Trust, UK) said. The use of AI version 3 was calculated to have saved 1,000 in-person appointments in secondary care. “Our data shows the great promise of AI in future provision of healthcare,” Dr Andrew concluded.
- Andrew K, et al. Continued Improvement of Artificial Intelligence in Identifying Skin Cancer. P1005, EADV Congress 2023, 11–14 October, Berlin, Germany.
Copyright ©2023 Medicom Medical Publishers
Posted on
Previous Article
« Dermoscopy training combined with AI significantly improves skin cancer detection Next Article
Women with psoriasis face increased adverse effects with systemic therapy »
« Dermoscopy training combined with AI significantly improves skin cancer detection Next Article
Women with psoriasis face increased adverse effects with systemic therapy »
Table of Contents: EADV 2023
Featured articles
Tapinarof on course to become a new topical treatment in AD
AD and Eczema in 2023
Tapinarof on course to become a new topical treatment in AD
Upadacitinib provides sustained skin clearance in adolescents and adults with AD
Sustained deep clinical and itch responses with novel IL-13 inhibitor
IL-13 inhibitor shows potential in atopic dermatitis
Encouraging results for amlitelimab in atopic dermatitis
Chronic hand eczema: patients share similar molecular signatures regardless of AD status
Severe hand eczema: dupilumab could be a future treatment
Psoriasis News
Dual IL-17 blockade yields efficacy on joints and skin
High-dose subcutaneous spesolimab prevents GPP flares up to week 48
Drug survival of guselkumab and risankizumab seems superior to other biologics
IL-23 blockers may lower the risk of developing inflammatory and psoriatic arthritis
First-in-class oral IL-23 inhibitor safe and effective for moderate-to-severe plaque psoriasis
Hidradenitis Suppurativa: End of the Diagnostic and Therapeutic Draught
Skin tape stripping allows a novel precision medicine approach in HS
Nanobodies: A novel way to treat HS
Anti-IL17 blockade leads to maintained pain reduction in patients with HS
Vitiligo: Novel Treatment Options
JAK1 inhibition: a promising forthcoming treatment option in vitiligo
Vitiligo: Continuation of topical ruxolitinib successful in many initial non-responders
Alopecia Areata: Novel Developments
JAK3/TEC inhibition achieves clinically meaningful responses in AA
Alopecia areata: remarkable regrowth rates with deuruxolitinib
Botanical drug solution improves hair regrowth in children and adolescents with AA
What’s New in Other Disease Entities
Nemolizumab shows high success rates in prurigo nodularis
Remibrutinib reduces itch, sleep problems, and activity impairment in patients with CSU
Innovative wound gel reduces frequency of painful dressing changes in epidermolysis bullosa
Best of the Posters
Women with psoriasis face increased adverse effects with systemic therapy
Improved AI tool shows high sensitivity rates in skin cancer detection
Dermoscopy training combined with AI significantly improves skin cancer detection
Related Articles
© 2024 Medicom Medical Publishers. All rights reserved. Terms and Conditions | Privacy Policy