Use of artificial intelligence as a diagnostic support tool for skin lesions in primary care: feasibility study in clinical practice

Abstract

Background Dermatological conditions are a relevant health problem. Machine learning (ML) models are increasingly being applied to dermatology as a diagnostic decision support tool using image analysis, especially for skin cancer detection and disease classification. Objective The objective of this study was to perform a prospective validation of an image analysis ML model, which is capable of screening 44 skin diseases, comparing its diagnostic accuracy with that of General Practitioners (GPs) and teledermatology (TD) dermatologists in a real-life setting. Methods Prospective, diagnostic accuracy study including 100 consecutive patients with a skin problem who visited a participating GP in central Catalonia, Spain, between June 2021 and October 2021. The skin issue was first assessed by the GPs. Then an anonymised skin disease picture was taken and uploaded to the ML application, which returned a list with the Top-5 possible diagnosis in order of probability. The same image was then sent to a dermatologist via TD for diagnosis, as per clinical practice. The GPs Top-3, ML model’s Top-5 and dermatologist’s Top-3 assessments were compared to calculate the accuracy, sensitivity, specificity and diagnostic accuracy of the ML models. Results The overall Top-1 accuracy of the ML model (39%) was lower than that of GPs (64%) and dermatologists (72%). When the analysis was limited to the diagnoses on which the algorithm had been explicitly trained (n=82), the balanced Top-1 accuracy of the ML model increased (48%) and in the Top-3 (75%) was comparable to the GPs Top-3 accuracy (76%). The Top-5 accuracy of the ML model (89%) was comparable to the dermatologist Top-3 accuracy (90%). For the different diseases, the sensitivity of the model (Top-3 87% and Top-5 84%) is higher than that of the clinicians (Top-3 GPs 76% and Top-3 dermatologists 84%) only in the benign tumour pathology group, being on the other hand the most prevalent category (n=53). About the satisfaction of professionals, 92% of the GPs considered it as a useful diagnostic support tool (DST) for the differential diagnosis and in 60% of the cases as an aid in the final diagnosis of the skin lesion. Conclusions The overall diagnostic accuracy of the model in this study under real conditions is lower than that of both GPs and dermatologists, a fact that is consistent with the few existing prospective studies under real conditions. These results highlight the potential of the ML models to assist GPs as a DST for skin conditions especially in the differential diagnosis. However, external testing in real conditions is essential for data validation and regulating these AI diagnostic models, in order to deploy ML models in a Primary Care setting.

Diabetes Detection Models in Mexican Patients by Combining Machine Learning Algorithms and Feature Selection Techniques for Clinical and Paraclinical Attributes: A Comparative Evaluation

“…One domain that has significantly benefited from these advancements is healthcare, where numerous applications have been proposed and implemented to facilitate medical diagnosis [15,16]. These applications have demonstrated remarkable accuracy in diagnosing a wide range of prevalent diseases, including cancer, eye diseases, heart diseases, skin lesions, gastrointestinal diseases, respiratory diseases, and diabetes [17][18][19][20][21][22][23]. The availability and widespread use of these applications have empowered medical professionals to make critical decisions for their patients with increased confidence, resulting in significant benefits for the medical field and healthcare services as a whole.…”