Effectiveness of preliminary differential diagnosis of benign and malignant skin neoplasms using the Derma Onko Check artificial intelligence program
A. I. Lamotkin, D. I. Korabelnikov, Olga Yu. Olisova, Igor A. Lamotkin
Abstract
Objective: to evaluate the effectiveness of preliminary differential diagnostics of benign and malignant skin tumors during initial medical consultations in primary health care using the Derma Onko Check artificial intelligence (AI) program for electronic computing devices (smartphone application). Material and methods. The effectiveness of the Derma Onko Check program for visual identification of benign and malignant skin tumors was evaluated in 135 patients aged 22 to 78 years with various skin lesions that appeared visually suspicious for malignancy. The conclusions generated by the program were compared with the results of dermatoscopic and morphological examinations. Results. The diagnostic accuracy of the Derma Onko Check program in determining the likelihood of a patient having a benign or malignant skin tumor was 96%, sensitivity was 98%, specificity was 96%, the proportion of false-positive results was 4.3%, and the propor Conclusion. The use of modern AI-based software for electronic computing devices enables early detection of malignant skin tumors during initial examinations in primary health care. This is particularly relevant for medical institutions and regions with a shortage or absence of dermatologists and oncologists. tion of falsenegative results was 2.4%.