A Deep Learning Approach for Missing Data Imputation of Rating Scales Assessing Attention-Deficit Hyperactivity Disorder

Predicting Adolescent Mental Health Outcomes Across Cultures: A Machine Learning Approach

Adolescent mental health problems are rising rapidly around the world. To combat this rise, clinicians and policymakers need to know which risk factors matter most in predicting poor adolescent mental health. Theory-driven research has identified numerous risk factors that predict adolescent mental health problems but has difficulty distilling and replicating these findings. Data-driven machine learning methods can distill risk factors and replicate findings but have difficulty interpreting findings because these methods are atheoretical. This study demonstrates how data- and theory-driven methods can be integrated to identify the most important preadolescent risk factors in predicting adolescent mental health. Machine learning models examined which of 79 variables assessed at age 10 were the most important predictors of adolescent mental health at ages 13 and 17. These models were examined in a sample of 1176 families with adolescents from nine nations. Machine learning models accurately classified 78% of adolescents who were above-median in age 13 internalizing behavior, 77.3% who were above-median in age 13 externalizing behavior, 73.2% who were above-median in age 17 externalizing behavior, and 60.6% who were above-median in age 17 internalizing behavior. Age 10 measures of youth externalizing and internalizing behavior were the most important predictors of age 13 and 17 externalizing/internalizing behavior, followed by family context variables, parenting behaviors, individual child characteristics, and finally neighborhood and cultural variables. The combination of theoretical and machine-learning models strengthens both approaches and accurately predicts which adolescents demonstrate above average mental health difficulties in approximately 7 of 10 adolescents 3-7 years after the data used in machine learning models were collected.

Interpretable deep learning for improving cancer patient survival based on personal transcriptomes

Precision medicine chooses the optimal drug for a patient by considering individual differences. With the tremendous amount of data accumulated for cancers, we develop an interpretable neural network to predict cancer patient survival based on drug prescriptions and personal transcriptomes (CancerIDP). The deep learning model achieves 96% classification accuracy in distinguishing short-lived from long-lived patients. The Pearson correlation between predicted and actual months-to-death values is as high as 0.937. About 27.4% of patients may survive longer with an alternative medicine chosen by our deep learning model. The median survival time of all patients can increase by 3.9 months. Our interpretable neural network model reveals the most discriminating pathways in the decision-making process, which will further facilitate mechanistic studies of drug development for cancers.

Machine learning in attention-deficit/hyperactivity disorder: new approaches toward understanding the neural mechanisms

Attention-deficit/hyperactivity disorder (ADHD) is a highly prevalent and heterogeneous neurodevelopmental disorder in children and has a high chance of persisting in adulthood. The development of individualized, efficient, and reliable treatment strategies is limited by the lack of understanding of the underlying neural mechanisms. Diverging and inconsistent findings from existing studies suggest that ADHD may be simultaneously associated with multivariate factors across cognitive, genetic, and biological domains. Machine learning algorithms are more capable of detecting complex interactions between multiple variables than conventional statistical methods. Here we present a narrative review of the existing machine learning studies that have contributed to understanding mechanisms underlying ADHD with a focus on behavioral and neurocognitive problems, neurobiological measures including genetic data, structural magnetic resonance imaging (MRI), task-based and resting-state functional MRI (fMRI), electroencephalogram, and functional near-infrared spectroscopy, and prevention and treatment strategies. Implications of machine learning models in ADHD research are discussed. Although increasing evidence suggests that machine learning has potential in studying ADHD, extra precautions are still required when designing machine learning strategies considering the limitations of interpretability and generalization.

Distinguishing different types of attention deficit hyperactivity disorder in children using artificial neural network with clinical intelligent test

Background

Attention deficit hyperactivity disorder (ADHD) is a well-studied topic in child and adolescent psychiatry. ADHD diagnosis relies on information from an assessment scale used by teachers and parents and psychological assessment by physicians; however, the assessment results can be inconsistent.

Purpose

To construct models that automatically distinguish between children with predominantly inattentive-type ADHD (ADHD-I), with combined-type ADHD (ADHD-C), and without ADHD.

Methods

Clinical records with age 6-17 years-old, for January 2011-September 2020 were collected from local general hospitals in northern Taiwan; the data were based on the SNAP-IV scale, the second and third editions of Conners' Continuous Performance Test (CPT), and various intelligence tests. This study used an artificial neural network to construct the models. In addition, k-fold cross-validation was applied to ensure the consistency of the machine learning results.

Results

We collected 328 records using CPT-3 and 239 records using CPT-2. With regard to distinguishing between ADHD-I and ADHD-C, a combination of demographic information, SNAP-IV scale results, and CPT-2 results yielded overall accuracies of 88.75 and 85.56% in the training and testing sets, respectively. The replacement of CPT-2 with CPT-3 results in this model yielded an overall accuracy of 90.46% in the training set and 89.44% in the testing set. With regard to distinguishing between ADHD-I, ADHD-C, and the absence of ADHD, a combination of demographic information, SNAP-IV scale results, and CPT-2 results yielded overall accuracies of 86.74 and 77.43% in the training and testing sets, respectively.

Conclusion

This proposed model distinguished between the ADHD-I and ADHD-C groups with 85-90% accuracy, and it distinguished between the ADHD-I, ADHD-C, and control groups with 77-86% accuracy. The machine learning model helps clinicians identify patients with ADHD in a timely manner.

A Counting Stroop Functional Magnetic Resonance Imaging Study on the Effects of ORADUR-Methylphenidate in Drug-Naive Children with Attention-Deficit/Hyperactivity Disorder

Objective: Methylphenidate is effective in reducing the clinical symptoms of patients with attention-deficit/hyperactivity disorder (ADHD). ORADUR^®-methylphenidate is a new extended-release preparation of methylphenidate. This study aimed at identifying brain regions with activation changes and their correlations with neuropsychological functions after treatment with ORADUR-methylphenidate in children with ADHD. Methods: We recruited drug-naive children with ADHD and age- and sex-matched typically developing (TD) children. They were all scanned with the functional magnetic resonance imaging (fMRI) during the counting Stroop task at baseline, and those with ADHD had the second fMRI assessment after 8-week treatment with ORADUR-methylphenidate. The Rapid Visual Information Processing (RVP) and Conners' Continuous Performance Test (CCPT) were used to assess the attention performance of the ADHD (before and after treatment) and TD groups. Results: ORADUR-methylphenidate significantly decreased inattention (Cohen d = 2.17) and hyperactivity-impulsivity (Cohen d = 0.98) symptoms. We found less activation in the right inferior frontal gyrus (rIFG) in the pre-treatment ADHD children than TD children and greater treatment-induced activation in the dorsal anterior cingulate cortex (dACC) and the right dorsolateral prefrontal cortex (rDLPFC). There was no significant difference between the post-treatment ADHD and TD groups. However, the treatment-related activations in the dACC, rDLPFC, and rIFG were significantly correlated with CCPT and RVP measures. Conclusions: Our findings indicated that ORADUR-methylphenidate increased brain activations in the dACC, rDLPFC, and rIFG in children with ADHD, associated with improved focused attention, reduced impulsivity, and enhanced inhibition control. Activities of these brain regions might be biomarkers for the treatment effectiveness of methylphenidate for ADHD. Clinical Trials Registration: ClinicalTrials.gov number, NCT02450890.

Discrete Missing Data Imputation Using Multilayer Perceptron and Momentum Gradient Descent

Data are a strategic resource for industrial production, and an efficient data-mining process will increase productivity. However, there exist many missing values in data collected in real life due to various problems. Because the missing data may reduce productivity, missing value imputation is an important research topic in data mining. At present, most studies mainly focus on imputation methods for continuous missing data, while a few concentrate on discrete missing data. In this paper, a discrete missing value imputation method based on a multilayer perceptron (MLP) is proposed, which employs a momentum gradient descent algorithm, and some prefilling strategies are utilized to improve the convergence speed of the MLP. To verify the effectiveness of the method, experiments are conducted to compare the classification accuracy with eight common imputation methods, such as the mode, random, hot-deck, KNN, autoencoder, and MLP, under different missing mechanisms and missing proportions. Experimental results verify that the improved MLP model (IMLP) can effectively impute discrete missing values in most situations under three missing patterns.

Handling high-dimensional data with missing values by modern machine learning techniques

High-dimensional data have been regarded as one of the most important types of big data in practice. It happens frequently in practice including genetic study, financial study, and geographical study. Missing data in high dimensional data analysis should be handled properly to reduce nonresponse bias. We discuss some modern machine learning techniques including penalized regression approaches, tree-based approaches, and deep learning (DL) for handling missing data with high dimensionality. Specifically, our proposed methods can be used for estimating general parameters of interest including population means and percentiles with imputation-based estimators, propensity score estimators, and doubly robust estimators. We compare those methods through some limited simulation studies and a real application. Both simulation studies and real application show the benefits of DL and XGboost approaches compared with other methods in terms of balancing bias and variance.

A roadmap for multi-omics data integration using deep learning

High-throughput next-generation sequencing now makes it possible to generate a vast amount of multi-omics data for various applications. These data have revolutionized biomedical research by providing a more comprehensive understanding of the biological systems and molecular mechanisms of disease development. Recently, deep learning (DL) algorithms have become one of the most promising methods in multi-omics data analysis, due to their predictive performance and capability of capturing nonlinear and hierarchical features. While integrating and translating multi-omics data into useful functional insights remain the biggest bottleneck, there is a clear trend towards incorporating multi-omics analysis in biomedical research to help explain the complex relationships between molecular layers. Multi-omics data have a role to improve prevention, early detection and prediction; monitor progression; interpret patterns and endotyping; and design personalized treatments. In this review, we outline a roadmap of multi-omics integration using DL and offer a practical perspective into the advantages, challenges and barriers to the implementation of DL in multi-omics data.

Prediction of antischistosomal small molecules using machine learning in the era of big data

Schistosomiasis is a neglected tropical disease caused by helminths of the Schistosoma genus. Despite its high morbidity and socio-economic burden, therapeutics are just a handful with praziquantel being the main drug. Praziquantel is an old drug registered for human use in 1982 and has since been administered en masse for chemotherapy, risking the development of resistance, thus the need for new drugs with different mechanisms of action. This review examines the use of machine learning (ML) in this era of big data to aid in the prediction of novel antischistosomal molecules. It first discusses the challenges of drug discovery in schistosomiasis. Explanations are then offered for big data, its characteristics and then, some open databases where large biochemical data on schistosomiasis can be obtained for ML model development are examined. The concepts of artificial intelligence, ML, and deep learning and their drug applications are explored in schistosomiasis. The use of binary classification in predicting antischistosomal compounds and some algorithms that have been applied including random forest and naive Bayesian are discussed. For this review, some deep learning algorithms (deep neural networks) are proposed as novel algorithms for predicting antischistosomal molecules via binary classification. Databases specifically designed for housing bioactivity data on antischistosomal molecules enriched with functional genomic datasets and ontologies are thus urgently needed for developing predictive ML models. This shows the application of machine learning techniques for the discovery of novel antischistosomal small molecules via binary classification in the era of big data.