Machine learning (ML) techniques as effective methods for evaluating hair and skin assessments: A systematic review

Machine Learning (ML) techniques provide the ability to effectively evaluate and analyze human skin and hair assessments. The aim of this study is to systematically review the effectiveness of applying Machine Learning (ML) methods and Artificial Intelligence (AI) techniques in order to evaluate hair and skin assessments. PubMed, Web of Science, IEEE Xplore, and Science Direct were searched in order to retrieve research publications between 1 January 2010 and 31 March 2020 using appropriate keywords such as "hair and skin analysis." Following accurate screening, 20 peer-reviewed publications were selected for inclusion in this systematic review. The analysis demonstrated that prevalent Machine Learning (ML) methods comprised of Support Vector Machine (SVM), k-nearest Neighbor, and Artificial Neural Networks (ANN). ANN's were observed to yield the highest accuracy of 95% followed by SVM generating 90%. These techniques were most commonly applied for drafting framework assessments such as that of Melanoma. Values of parameters such as Sensitivity, Specificity, and Area under the Curve (AUC) were extracted from the studies and with the help of comparisons, relevant inferences were also made. ANN's were observed to yield the highest sensitivity of 82.30% as well as a 96.90% specificity. Hence, with this systematic review, a summarization of the studies was drafted that encapsulated how Machine Learning (ML) techniques have been employed for the analysis and evaluation of hair and skin assessments.