Machine learning algorithms to the early diagnosis of fetal alcohol spectrum disorders

Abstract

Introduction: Fetal alcohol spectrum disorders include a variety of physical and neurocognitive disorders caused by prenatal alcohol exposure. Although their overall prevalence is around 0.77%, FASD remains underdiagnosed and little known, partly due to the complexity of their diagnosis, which shares some symptoms with other pathologies such as autism spectrum, depression or hyperactivity disorders.

Methods: This study included 73 control and 158 patients diagnosed with FASD. Variables selected were based on IOM classification from 2016, including sociodemographic, clinical, and psychological characteristics. Statistical analysis included Kruskal-Wallis test for quantitative factors, Chi-square test for qualitative variables, and Machine Learning (ML) algorithms for predictions.

Results: This study explores the application ML in diagnosing FASD and its subtypes: Fetal Alcohol Syndrome (FAS), partial FAS (pFAS), and Alcohol-Related Neurodevelopmental Disorder (ARND). ML constructed a profile for FASD based on socio-demographic, clinical, and psychological data from children with FASD compared to a control group. Random Forest (RF) model was the most efficient for predicting FASD, achieving the highest metrics in accuracy (0.92), precision (0.96), sensitivity (0.92), F1 Score (0.94), specificity (0.92), and AUC (0.92). For FAS, XGBoost model obtained the highest accuracy (0.94), precision (0.91), sensitivity (0.91), F1 Score (0.91), specificity (0.96), and AUC (0.93). In the case of pFAS, RF model showed its effectiveness, with high levels of accuracy (0.90), precision (0.86), sensitivity (0.96), F1 Score (0.91), specificity (0.83), and AUC (0.90). For ARND, RF model obtained the best levels of accuracy (0.87), precision (0.76), sensitivity (0.93), F1 Score (0.84), specificity (0.83), and AUC (0.88). Our study identified key variables for efficient FASD screening, including traditional clinical characteristics like maternal alcohol consumption, lip-philtrum, microcephaly, height and weight impairment, as well as neuropsychological variables such as the Working Memory Index (WMI), aggressive behavior, IQ, somatic complaints, and depressive problems.

Discussion: Our findings emphasize the importance of ML analyses for early diagnoses of FASD, allowing a better understanding of FASD subtypes to potentially improve clinical practice and avoid misdiagnosis.

Keywords: PAE; Random Forest (RF); eXtreme Gradient Boosting (XGB); early diagnosis; fetal alcohol spectrum disorders; machine learning; neurodevelopment.

Figure 1

Study flowchart. Flowchart of FASD and non-FASD diagnosis and machine learning prediction.

Figure 2

Model performance of machine learning algorithms for FASD prediction. LR, Logistic Regression; SVML, Support Vector Machine Linear Kernel; LDA, Linear Discriminant Analysis; SVMP, Support Vector Machine Polynomial Kernel; KNN, k-Nearest Neighbor; RF, Random Forest; XGB, Gradient-Boosted Trees.

Figure 3

Mean variable-importance of RF model for FASD prediction. Mean variable importance was calculated by using 50 permutations and the root-mean-squared-error-loss-function for the RF model. RF, Random Forest.

Figure 4

Model performance of machine learning algorithms for FAS prediction. LR, Logistic Regression; SVML, Support Vector Machine Linear Kernel; LDA, Linear Discriminant Analysis; SVMP, Support Vector Machine Polynomial Kernel; KNN, k-Nearest Neighbor; RF, Random Forest; XGB, Gradient-Boosted Trees.

Figure 5

Mean variable-importance of XGB model for FAS prediction. Mean variable importance was calculated by using 50 permutations and the root-mean-squared-error-loss-function for the XGB model. XGB, eXtreme Gradient Boosting.

Figure 6

Model performance of machine learning algorithms for pFAS prediction. LR; Logistic Regression; SVML, Support Vector Machine Linear Kernel; LDA, Linear Discriminant Analysis; SVMP, Support Vector Machine Polynomial Kernel; KNN, k-Nearest Neighbor; RF, Random Forest; XGB, Gradient-Boosted Trees.

Figure 7

Mean variable-importance of RF model for pFAS prediction. Mean variable importance was calculated by using 50 permutations and the root-mean-squared-error-loss-function for the RF model. RF, Random Forest.

Figure 8

Model performance of machine learning algorithms for ARND prediction. LR, Logistic Regression; SVML, Support Vector Machine linear kernel; LDA, Linear Discriminant Analysis; SVMP, Support Vector Machine polynomial kernel; KNN, k-nearest neighbor; RF, Random Forest; XGB, gradient-boosted trees.

Figure 9

Mean variable-importance of RF model for ARND prediction. Mean variable importance was calculated by using 50 permutations and the root-mean-squared-error-loss-function for the RF model.