Performance of machine-learning algorithms to pattern recognition and classification of hearing impairment in Brazilian farmers exposed to pesticide and/or cigarette smoke.

The use of pesticides has been increasing in agriculture, leading to a public health problem. The aim of this study was to evaluate ototoxic effects in farmers who were exposed to cigarette smoke and/or pesticides and to identify possible classification patterns in the exposure groups. The sample included 127 participants of both sexes aged between 18 and 39, who were divided into the following four groups: control group (CG), smoking group (SG), pesticide group (PG), and smoking + pesticide group (SPG). Meatoscopy, pure tone audiometry, logoaudiometry, high-frequency thresholds, and immittance testing were performed. Data were evaluated by artificial neural network (ANN), K-nearest neighbors (K-NN), and support vector machine (SVM). There was symmetry between the right and left ears, an increase in the incidence of hearing loss at high frequency and of downward sloping audiometric curve configuration, and alteration of stapedial reflex in the three exposed groups. The machine-learning classifiers achieved good classification performance (control and exposed). The best classification results occur in high type (I and II) datasets (about 90% accuracy) in k-NN test. It is concluded that both xenobiotic substances have ototoxic potential; however, their combined use does not present additive or potentiating effects recognizable by the algorithms.

Evaluation of genotoxic effects in Brazilian agricultural workers exposed to pesticides and cigarette smoke using machine-learning algorithms.

Monitoring exposure to xenobiotics by biomarker analyses, such as a micronucleus assay, is extremely important for the precocious detection and prevention of diseases, such as oral cancer. The aim of this study was to evaluate genotoxic effects in rural workers who were exposed to cigarette smoke and/or pesticides and to identify possible classification patterns in the exposure groups. The sample included 120 participants of both sexes aged between 18 and 39, who were divided into the following four groups: control group (CG), smoking group (SG), pesticide group (PG), and smoking + pesticide group (SPG). Their oral mucosa cells were stained with Giemsa for cytogenetic analysis. The total numbers of nuclear abnormalities (CG = 27.16 ± 14.32, SG = 118.23 ± 74.78, PG = 184.23 ± 52.31, and SPG = 191.53 ± 66.94) and micronuclei (CG = 1.46 ± 1.40, SG = 12.20 ± 10.79, PG = 21.60 ± 8.24, and SPG = 20.26 ± 12.76) were higher (p < 0.05) in the three exposed groups compared to the GC. In this study, we considered several different classification algorithms (the artificial neural network, K-nearest neighbors, support vector machine, and optimum path forest). All of the algorithms displayed good classification (accuracy > 80%) when using dataset2 (without the redundant exposure type SPG). It is clear that the data form a robust pattern and that classifiers could be successfully trained on small datasets from the exposure groups. In conclusion, exposing agricultural workers to pesticides and/or tobacco had genotoxic potential, but concomitant exposure to xenobiotics did not lead to additive or potentiating effects.