Machine learning (ML) models for skin cancer recognition may have variable performance across different skin phototypes and skin cancer types. Overall performance metrics alone are insufficient to detect poor subgroup performance. We aimed (1) to assess whether studies of ML models reported results separately for different skin phototypes and rarer skin cancers, and (2) to graphically represent the skin cancer training datasets used by current ML models. In this systematic review, we searched PubMed, Embase and CENTRAL. We included all studies in medical journals assessing an ML technique for skin cancer diagnosis that used clinical or dermoscopic images from 1 January 2012 to 22 September 2021. No language restrictions were applied. We considered rarer skin cancers to be skin cancers other than pigmented melanoma, basal cell carcinoma and squamous cell carcinoma. We identified 114 studies for inclusion. Rarer skin cancers were included by 8/114 studies (7.0%), and results for a rarer skin cancer were reported separately in 1/114 studies (0.9%). Performance was reported across all skin phototypes in 1/114 studies (0.9%), but performance was uncertain in skin phototypes I and VI from minimal representation of the skin phototypes in the test dataset (9/3756 and 1/3756, respectively). For training datasets, although public datasets were most frequently used, with the most widely used being the International Skin Imaging Collaboration (ISIC) archive (65/114 studies, 57.0%), the largest datasets were private. Our review identified that most ML models did not report performance separately for rarer skin cancers and different skin phototypes. A degree of variability in ML model performance across subgroups is expected, but the current lack of transparency is not justifiable and risks models being used inappropriately in populations in whom accuracy is low.
Empowering lay screeners, such as preschool teachers, on vision screening is a cost-effective way to ensure larger populations of children can be screened. Although the validity of lay screeners in conducting vision screening were reported in several studies, none showed data concerning improvement of the level of knowledge among lay screeners after completing vision screening training, which could indicate the effectiveness of the training program. This study aimed to determine the level of knowledge of preschool teachers before and after attending a training program. Sixty preschool teachers from Tabika and Taska KEMAS were randomly selected. The Study Group (n = 30) was given theory and practical training on vision screening, whereas the Control Group (n = 30) was only given brief verbal instructions on how to conduct the screening. A theory test containing 15 questions related to the training modules were administered to both groups, before and after their training/briefing respectively. The findings showed that the level of knowledge among preschool teachers in the Study Group (73.24 ± 11.73%) was significantly higher than the Control Group (56.22 ± 13.11%) (p < 0.01). There was also a significant improvement in the level of knowledge among preschool teachers in the Study Group after the training (p<0.001), whereas no improvement was noted among preschool teachers in the Control Group (p = 0.636). This study shows the importance of conducting training for preschool teachers prior to their involvement in conducting vision screening in order to deliver an effective vision screening program to the preschoolers.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.