Skinive’s accuracy report “Dynamics of the neural network accuracy in the context of modernization of the algorithms of skin pathology recognition” is officially published at Social Science Research Network.

www.ssrn.com

Skinive neural network uses a machine-learning algorithm to calculate the risk rating of skin pathologies. For this study, we used Skinive’s 2020 and 2021 versions trained on 64,000 and 115,000 images respectively. Three validation datasets were used to assess the sensitivity of the algorithm: precancer + cancer, HPV skin pathology, acne, containing 285 images in each set. The specificity has been calculated on a separate validation set containing 6,000 benign neoplasm cases.

The purpose of this study was to estimate the accuracy of Skinive’s algorithm.

We have improved the algorithm to show a statistically significant decrease in the number of neural network errors in determining the risks of skin pathologies.

The results of sensitivity and specificity of the Skinive neural network indicate that the algorithm is highly accurate in detecting various neoplasms and skin diseases. The sensitivity of the Skinive neural network in detecting malignant neoplasms was 89.1% and 95.4% in 2020 and 2021 respectively. The specificity of Skinive’s neural network in determining benign neoplasms was 95.3% in 2020 and 97.9% in 2021. For all skin neoplasms: in 2020, the sensitivity was 95.3%, for specificity 93.5%; in 2021, it was 97.9% and 97.1% respectively.

Download Full Report (PDF): https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3974784