Exploring the potential of artificial intelligence in improving skin lesion diagnosis in primary care.

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. 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. 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. 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 96%) 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. The overall diagnostic accuracy of the model in this study, under real-life conditions, is lower than that of both GPs and dermatologists. This result aligns with the findings of few existing prospective studies conducted under real-life conditions. The outcomes emphasize the significance of involving clinicians in the training of the model and the capability of ML models to assist GPs, particularly in differential diagnosis. Nevertheless, external testing in real-life conditions is crucial for data validation and regulation of these AI diagnostic models before they can be used in primary care.

Using artificial intelligence on dermatology conditions in Uganda: a case for diversity in training data sets for machine learning.

Background: In pursuit of applying universal non-biased Artificial Intelligence (AI) in healthcare, it is essential that data from different geographies are represented. Objective: To assess the diagnostic performance of an AI-powered dermatological algorithm called Skin Image Search on Fitzpatrick 6 skin type (dark skin) dermatological conditions. Methods: 123 dermatological images selected from a total of 173 images were retrospectively extracted from the electronic database of a Ugandan telehealth company, The Medical Concierge Group (TMCG) after getting their consent. Details of age, gender, and dermatological clinical diagnosis were analysed using R on R studio software to assess the diagnostic accuracy of the AI app along with disease diagnosis and body part. Predictability levels of the AI app were graded on a scale of 0 to 5, where 0- no prediction was made and 1-5 demonstrated a reduction incorrect diagnosis prediction rate of the AI. Results: 76 (62%) of the dermatological images were from females and 47 (38%) from males. Overall diagnostic accuracy of the AI app on black dermatological conditions was low at 17% (21 out of 123 predictable images) compared to 69.9% performance on Caucasian skin type as reported from the training results. There were varying predictability levels correctness i.e., 1-8.9%, 2-2.4%, 3-2.4%, 4-1.6%, 5-1.6% with performance along individual diagnosis highest with dermatitis (80%). Conclusion: There is need for diversity of image datasets used to train dermatology algorithms for AI applications to increase accuracy across skin types and geographies.

Using Artificial Intelligence as a Diagnostic Decision Support Tool in Skin Disease: Protocol for an Observational Prospective Cohort Study.

BACKGROUND: Dermatological conditions are a relevant health problem. Each person has an average of 1.6 skin diseases per year, and consultations for skin pathology represent 20% of the total annual visits to primary care and around 35% are referred to a dermatology specialist. Machine learning (ML) models can be a good tool to help primary care professionals, as it can analyze and optimize complex sets of data. In addition, ML models are increasingly being applied to dermatology as a diagnostic decision support tool using image analysis, especially for skin cancer detection and classification. OBJECTIVE: This study aims to perform a prospective validation of an image analysis ML model as a diagnostic decision support tool for the diagnosis of dermatological conditions. METHODS: In this prospective study, 100 consecutive patients who visit a participant general practitioner (GP) with a skin problem in central Catalonia were recruited. Data collection was planned to last 7 months. Anonymized pictures of skin diseases were taken and introduced to the ML model interface (capable of screening for 44 different skin diseases), which returned the top 5 diagnoses by probability. The same image was also sent as a teledermatology consultation following the current stablished workflow. The GP, ML model, and dermatologist's assessments will be compared to calculate the precision, sensitivity, specificity, and accuracy of the ML model. The results will be represented globally and individually for each skin disease class using a confusion matrix and one-versus-all methodology. The time taken to make the diagnosis will also be taken into consideration. RESULTS: Patient recruitment began in June 2021 and lasted for 5 months. Currently, all patients have been recruited and the images have been shown to the GPs and dermatologists. The analysis of the results has already started. CONCLUSIONS: This study will provide information about ML models' effectiveness and limitations. External testing is essential for regulating these diagnostic systems to deploy ML models in a primary care practice setting.

Smartphone teledermoscopy referrals: a novel process for improved triage of skin cancer patients.

In this open, controlled, multicentre and prospective observational study, smartphone teledermoscopy referrals were sent from 20 primary healthcare centres to 2 dermatology departments for triage of skin lesions of concern using a smartphone application and a compatible digital dermoscope. The outcome for 816 patients referred via smartphone teledermoscopy was compared with 746 patients referred via the traditional paper-based system. When surgical treatment was required, the waiting time was significantly shorter using teledermoscopy for patients with melanoma, melanoma in situ, squamous cell carcinoma, squamous cell carcinoma in situ and basal cell carcinoma. Triage decisions were also more reliable with teledermoscopy and over 40% of the teledermoscopy patients could potentially have avoided face-to-face visits. Only 4 teledermoscopy referrals (0.4%) had to be excluded due to poor image quality. Smartphone teledermoscopy referrals allow for faster and more efficient management of patients with skin cancer as compared to traditional paper referrals.

Mobile teledermoscopy-there's an app for that!

BACKGROUND: The introduction of the smartphone with high-quality, built-in digital cameras and easy-to-install software may make it more convenient to perform teledermatology. In this study we looked at the feasibility of using a smartphone (iPhone 4(®)) with an installed application especially developed for teledermatology (iDoc24(®)) and a dermoscope (FotoFinder Handyscope(®)) that is customized to attach to the smartphone to be able to carry out mobile teledermoscopy. OBJECTIVES: To study the diagnostic accuracy of this mobile teledermoscopy solution, to determine the interobserver concordance between teledermoscopists (TDs) and a dermatologist meeting the patient face-to-face (FTF), and to assess the adequacy of the TDs' management decisions and to evaluate the image quality obtained. PATIENTS/METHODS: During a 16-week period, patients with one or more suspicious skin lesions deemed to need a biopsy or excision were included. The smartphone app was used to send a clinical image, a dermoscopy image and relevant clinical information to a secure Internet platform (Tele-Dermis(®)). Two TDs assessed the incoming cases, providing a specific primary diagnosis and a management decision. They also graded the image quality. The histopathological diagnosis was used as the gold standard. RESULTS: Sixty-nine lesions were included. The FTF dermatologist's diagnostic accuracy was 66.7%, which was statistically higher than TD 1 (50.7%, P=0.04) but similar to TD 2 (60.9%, P=0.52). The interobserver concordances between the FTF dermatologist and the two TDs and between the respective TDs showed moderate to substantial agreement. The TDs provided adequate management decisions for 68 (98.6%) and 69 (100%) lesions, respectively. The image quality was rated as excellent or sufficient in 94% and 84% of the cases by the respective TDs. CONCLUSION: This novel mobile teledermoscopy solution may be useful as a triage tool for patients referred to dermatologists for suspicious skin lesions.

Use of the mobile phone multimedia messaging service for teledermatology.

We examined the feasibility of using mobile phone Multimedia Messaging Service (MMS) to send teledermatology referrals from a general practitioner to a dermatologist. Digital photographs of skin conditions in 40 consecutive patients were sent together with relevant clinical information to dermatologists at a university hospital. Two dermatologists separately assessed the MMS referrals. The suspected diagnosis, triage and management decisions were compared to those given after separate face-to-face (FTF) visits, and again after agreeing on a final clinical and/or histopathological diagnosis. Thirty-two patients (80%) were diagnosed with skin tumours and 8 patients (20%) with other skin conditions. Both dermatologists were able to make a correct diagnosis in 31 patients (78%) based solely on the MMS referral. They also provided adequate management recommendations for 98% of the patients. Adequate triage decisions after assessment of the MMS referrals were made for 34 (85%) and 38 (95%) patients by the two dermatologists. There was an inter-observer concordance of 68% for the teledermatology diagnosis, compared to 88% concordance after the separate FTF visits. The diagnostic accuracy and adequacy of the triage and management decisions achieved using MMS referrals were similar to those obtained with other store-and-forward teledermatology methods.