Fig 1.
Leprosy care thematic areas.
Fig 2.
PRISMA flow diagram.
Table 1.
Overview of the data extracted from the selected articles in the SLR.
Fig 3.
Number of works in each thematic area of the leprosy care in the SLR sample.
The vertical axis lists the thematic categories identified: Signs and symptoms, Diagnosis, Surveillance strategy, Epidemiology, and Treatment. The horizontal axis represents the number of studies included in each category.
Fig 4.
Type and source of datasets used in the SLR sample.
The 30 studies were divided firstly in relation to the type of data: Images, Tabular and Hybrid. Within each type they were separated into data characteristics and data availability (public or private). Finally, the name of the data set used is presented in the last column.
Table 2.
Overview of the public dataset sources.
Table 3.
Distribution of sample per classes
Fig 5.
This Figure presents the AI models categorized into different levels, starting with the type of learning: Supervised and unsupervised, where the vertical categories mean that there is still subdivision, and the horizontal categories represent the last category of models.
Fig 6.
Number of AI models per leprosy thematic area.
The vertical axis represents the thematic categories analyzed, while the horizontal axis represents the number of AI models included in each category. Each category is formed by several colors, where each color represents a specific model, detailed in the Figure legend. *Consider that Linear Classifiers correspond to Multinomial and Complement, Naïve Bayes, Bayesian Networks, Gaussian and Stochastic Gradient Descent models. **Consider that Regression correspond to the Logistic Regression, Regression Splines and Elastic-Net Logistic Regression models.
Fig 7.
Number of AI models per data type.
The vertical axis represents the types of data found (image, tabular and hybrid), while the horizontal axis represents the number of AI models included in each type. Each type is formed by several colors, where each color represents a specific model, detailed in the Figure legend. *Consider that Linear Classifiers correspond to Multinomial and Complement, Naïve Bayes, Bayesian Networks, Gaussian and Stochastic Gradient Descent models. **Consider that Regression correspond to the Logistic Regression, Regression Splines and Elastic-Net Logistic Regression models.
Fig 8.
Metrics used to evaluate the models by the type of problems addressed in the SLR sample.
The vertical axis presents the different metrics found in the study, while the horizontal axis represents the number of studies. The studies are further divided into colors representing the type of problem (Binary, Multiclass, Clustering and Feature selection).
Table 4.
Overview of reported results and limitations.