Explainable artificial intelligence based on feature optimization for age at onset prediction of spinocerebellar ataxia type 3

Abstract

Existing treatments can only delay the progression of spinocerebellar ataxia type 3/Machado-Joseph disease (SCA3/MJD) after onset, so the prediction of the age at onset (AAO) can facilitate early intervention and follow-up to improve treatment efficacy. The objective of this study was to develop an explainable artificial intelligence (XAI) based on feature optimization to provide an interpretable and more accurate AAO prediction. A total of 1,008 affected SCA3/MJD subjects from mainland China were analyzed. The expanded cytosine-adenine-guanine (CAG) trinucleotide repeats of 10 polyQ-related genes were genotyped and included in related models as potential AAO modifiers. The performance of 4 feature optimization methods and 10 machine learning (ML) algorithms were compared, followed by building the XAI based on the SHapley Additive exPlanations (SHAP). The model constructed with an artificial neural network (ANN) and feature optimization of Crossing-Correlation-StepSVM performed best and achieved a coefficient of determination (R2) of 0.653 and mean absolute error (MAE), root mean square error (RMSE), and median absolute error (MedianAE) of 4.544, 6.090, and 3.236 years, respectively. The XAI explained the predicted results, which suggests that the factors affecting the AAO were complex and associated with gene interactions. An XAI based on feature optimization can improve the accuracy of AAO prediction and provide interpretable and personalized prediction.

Novel genotype–phenotype correlations, differential cerebellar allele-specific methylation, and a common origin of the (ATTTC)n insertion in spinocerebellar ataxia type 37

“…We generate for the first time a predictive mathematical model for the age of onset and diseases evolution in SCA37 considering the importance of genetic variables such as the size and configuration of the complex 5ʹ(ATTTT)n–(ATTTC)n–3ʹ(ATTTT)n repeat tract. To the best of our knowledge there are only a few studies using mathematical models and machine learning algorithms to predict clinical outcomes in other spinocerebellar ataxias including SCA1, SCA2, SCA3 and SCA6 (Tezenas du Montcel et al 2014 ; Peng et al 2021 ; Ru et al 2022 ; Hatano et al 2023 ). Predictive outcome models are becoming very useful tools for genetic counselling, clinical prognosis, and response follow-up of therapeutic treatments.…”

Neural network system for analyzing statistical factors of patients for predicting the survival of dental implants

“…The main properties of a neural network are set by the choice of its topology ( Muh Ibnu Choldun et al, 2019 ). The organization of neurons and their connections into a certain structure has a significant impact on the computational capabilities of a neural network ( Ru et al, 2022 ). The most common type of artificial neural networks is the feedforward multilayer perceptron, in which the connections between neurons do not form a loop ( Lyu et al, 2022 ).…”