We conducted a prospective, observational clinical validation study to assess the diagnostic accuracy of the AI algorithm (ADAE) in predicting melanoma from dermoscopy skin lesion images. Patients who had consented for a skin biopsy to exclude melanoma were eligible. All lesions underwent biopsy.
{ "acquisition_day": 1, "age_approx": 45, "anatom_site_general": "upper extremity", "benign_malignant": "malignant", "clin_size_long_diam_mm": "7.70", "concomitant_biopsy": true, "dermoscopic_type": "non-contact polarized", "diagnosis": "squamous cell carcinoma", "diagnosis_1": "Malignant", "diagnosis_2": "Malignant epidermal proliferations", "diagnosis_3": "Squamous cell carcinoma in situ", "diagnosis_confirm_type": "histopathology", "family_hx_mm": true, "fitzpatrick_skin_type": "I", "image_type": "dermoscopic", "lesion_id": "IL_6490559", "melanocytic": false, "patient_id": "IP_2891227", "personal_hx_mm": false, "sex": "male" }
{ "acquisition_day": 1, "age_approx": 65, "anatom_site_general": "posterior torso", "benign_malignant": "benign", "clin_size_long_diam_mm": "8.80", "concomitant_biopsy": true, "dermoscopic_type": "contact polarized", "diagnosis": "nevus", "diagnosis_1": "Benign", "diagnosis_2": "Benign melanocytic proliferations", "diagnosis_3": "Nevus", "diagnosis_4": "Nevus, Atypical, Dysplastic, or Clark", "diagnosis_5": "Nevus, Atypical", "diagnosis_confirm_type": "histopathology", "family_hx_mm": false, "fitzpatrick_skin_type": "II", "image_type": "dermoscopic", "lesion_id": "IL_1168971", "melanocytic": true, "patient_id": "IP_6028537", "personal_hx_mm": true, "sex": "male" }
{ "acquisition_day": 1, "age_approx": 45, "anatom_site_general": "upper extremity", "benign_malignant": "benign", "clin_size_long_diam_mm": "1.40", "concomitant_biopsy": true, "diagnosis": "seborrheic keratosis", "diagnosis_1": "Benign", "diagnosis_2": "Collision - Only benign proliferations", "diagnosis_confirm_type": "histopathology", "family_hx_mm": true, "fitzpatrick_skin_type": "II", "image_type": "dermoscopic", "lesion_id": "IL_2663985", "melanocytic": true, "patient_id": "IP_0918668", "personal_hx_mm": false, "sex": "female" }