• Can sodium/hydrogen exchange inhibitors be repositioned for treating attention deficit hyperactivity disorder? An in silico approach

      Faraone, Stephen V.; Zhang-James, Yanli (Wiley, 2013-10-17)
      Medications for attention deficit hyperactivity disorder (ADHD) are only partially effective. Ideally, new treatment targets would derive from a known pathophysiology. Such data are not available for ADHD. We combine evidence for new etiologic pathways with bioinformatics data to assess the possibility that existing drugs might be repositioning for treating ADHD. We use this approach to determine if prior data implicating the sodium/hydrogen exchanger 9 gene (SLC9A9) in ADHD implicate sodium/hydrogen exchange (NHE) inhibitors as potential treatments. We assessed the potential for repositioning by assessing the similarity of drug–protein binding profiles between NHE inhibitors and drugs known to treat ADHD using the Drug Repositioning and Adverse Reaction via Chemical–Protein Interactome server. NHE9 shows a high degree of amino acid similarity between NHE inhibitor sensitive NHEs in the region of the NHE inhibitor recognition site defined for NHE1. We found high correlations in drug–protein binding profiles among most ADHD drugs. The drug–protein binding profiles of some NHE inhibitors were highly correlated with ADHD drugs whereas the profiles for a control set of nonsteroidal anti-inflammatory drugs (NSAIDs) were not. Further experimental work should evaluate if NHE inhibitors are suitable for treating ADHD. © 2013 Wiley Periodicals, Inc.
    • Evidence for Similar Structural Brain Anomalies in Youth and Adult Attention-Deficit/Hyperactivity Disorder: A Machine Learning Analysis

      Zhang-James, Yanli; Helminen, Emily C; Liu, Jinru; Franke, Barbara; Hoogman, Martine; Faraone, Stephen V. (Cold Spring Harbor Laboratory, 2019-02-11)
      Attention-deficit/hyperactivity disorder (ADHD) affects 5% of children world-wide. Of these, two-thirds continue to have impairing symptoms of ADHD into adulthood. Although a large literature implicates structural brain differences of the disorder, it is not clear if adults with ADHD have similar neuroanatomical differences as those seen in children with recent reports from the large ENIGMA-ADHD consortium finding structural differences for children but not for adults. This paper uses deep learning neural network classification models to determine if there are neuroanatomical changes in the brains of children with ADHD that are also observed for adult ADHD, and vice versa. We found that structural MRI data can significantly separate ADHD from control participants for both children and adults. Consistent with the prior reports from ENIGMA-ADHD, prediction performance and effect sizes were better for the child than the adult samples. The model trained on adult samples significantly predicted ADHD in the child sample, suggesting that our model learned anatomical features that are common to ADHD in childhood and adulthood. These results support the continuity of ADHD’s brain differences from childhood to adulthood. In addition, our work demonstrates a novel use of neural network classification models to test hypotheses about developmental continuity.
    • Machine Learning And MRI-Based Diagnostic Models For ADHD: Are We There Yet?

      Zhang-James, Yanli; Hoogman, Martine; Franke, Barbara; Faraone, Stephen V. (Cold Spring Harbor Laboratory, 2020-10-23)
      Machine learning (ML) has been applied to develop magnetic resonance imaging (MRI)-based diagnostic classifiers for attention-deficit/hyperactivity disorder (ADHD). This systematic review examines this literature to clarify its clinical significance and to assess the implications of the various analytic methods applied. We found that, although most of studies reported the classification accuracies, they varied in choice of MRI modalities, ML models, cross-validation and testing methods, and sample sizes. We found that the accuracies of cross-validation methods inflated the performance estimation compared with those of a held-out test, compromising the model generalizability. Test accuracies have increased with publication year but were not associated with training sample sizes. Improved test accuracy over time was likely due to the use of better ML methods along with strategies to deal with data imbalances. Ultimately, large multi-modal imaging datasets, and potentially the combination with other types of data, like cognitive data and/or genetics, will be essential to achieve the goal of developing clinically useful imaging classification tools for ADHD in the future.
    • Machine-Learning Prediction of Comorbid Substance Use Disorders in ADHD Youth Using Swedish Registry Data

      Zhang-James, Yanli; Chen, Qi; Kuja-Halkola, Ralf; Lichtenstein, Paul; Larsson, Henrik; Faraone, Stephen V. (Cold Spring Harbor Laboratory, 2019-06-06)
      Background: Children with attention-deficit/hyperactivity disorder (ADHD) have a high risk for substance use disorders (SUDs). Early identification of at-risk youth would help allocate scarce resources for prevention programs. Methods: Psychiatric and somatic diagnoses, family history of these disorders, measures of socioeconomic distress, and information about birth complications were obtained from the national registers in Sweden for 19,787 children with ADHD born between 1989 and 1993. We trained (a) a cross-sectional random forest (RF) model using data available by age 17 to predict SUD diagnosis between ages 18 and 19; and (b) a longitudinal recurrent neural network (RNN) model with the Long Short-Term Memory (LSTM) architecture to predict new diagnoses at each age. Results: The area under the receiver operating characteristic curve (AUC) was 0.73(95%CI 0.70–0.76) for the random forest model (RF). Removing prior diagnosis from the predictors, the RF model was still able to achieve significant AUCs when predicting all SUD diagnoses (0.69, 95%CI 0.66–0.72) or new diagnoses (0.67, 95%CI: 0.64, 0.71) during age 18–19. For the model predicting new diagnoses, model calibration was good with a low Brier score of 0.086. Longitudinal LSTM model was able to predict later SUD risks at as early as 2 years age, 10 years before the earliest diagnosis. The average AUC from longitudinal models predicting new diagnoses 1, 2, 5 and 10 years in the future was 0.63. Conclusions: Population registry data can be used to predict at-risk comorbid SUDs in individuals with ADHD. Such predictions can be made many years prior to age of the onset, and their SUD risks can be monitored using longitudinal models over years during child development. Nevertheless, more work is needed to create prediction models based on electronic health records or linked population registers that are sufficiently accurate for use in the clinic.
    • A seq2seq model to forecast the COVID-19 cases, deaths and reproductive R numbers in US counties

      Zhang-James, Yanli; Hess, Jonathan; Salekin, Asif; Wang, Dongliang; Chen, Samuel; Winkelstein, Peter; Morley, Christopher P; Faraone, Stephen V. (Cold Spring Harbor Laboratory, 2021-04-20)
      The global pandemic of coronavirus disease 2019 (COVID-19) has killed almost two million people worldwide and over 400 thousand in the United States (US). As the pandemic evolves, informed policy-making and strategic resource allocation relies on accurate forecasts. To predict the spread of the virus within US counties, we curated an array of county-level demographic and COVID-19-relevant health risk factors. In combination with the county-level case and death numbers curated by John Hopkins university, we developed a forecasting model using deep learning (DL). We implemented an autoencoder-based Seq2Seq model with gated recurrent units (GRUs) in the deep recurrent layers. We trained the model to predict future incident cases, deaths and the reproductive number, R. For most counties, it makes accurate predictions of new incident cases, deaths and R values, up to 30 days in the future. Our framework can also be used to predict other targets that are useful indices for policymaking, for example hospitalization or the occupancy of intensive care units. Our DL framework is publicly available on GitHub and can be adapted for other indices of the COVID-19 spread. We hope that our forecasts and model can help local governments in the continued fight against COVID-19.