Dataset Information

Multimodal neuroimaging-based prediction of adult outcomes in childhood-onset ADHD using ensemble learning techniques.

ABSTRACT: Attention-deficit/hyperactivity disorder (ADHD) is a highly prevalent and heterogeneous neurodevelopmental disorder, which is diagnosed using subjective symptom reports. Machine learning classifiers have been utilized to assist in the development of neuroimaging-based biomarkers for objective diagnosis of ADHD. However, existing basic model-based studies in ADHD report suboptimal classification performances and inconclusive results, mainly due to the limited flexibility for each type of basic classifier to appropriately handle multi-dimensional source features with varying properties. This study applied ensemble learning techniques (ELTs), a meta-algorithm that combine several basic machine learning models into one predictive model in order to decrease variance, bias, or improve predictions, in multimodal neuroimaging data collected from 72 young adults, including 36 probands (18 remitters and 18 persisters of childhood ADHD) and 36 group-matched controls. All currently available optimization strategies for ELTs (i.e., voting, bagging, boosting and stacking techniques) were tested in a pool of semifinal classification results generated by seven basic classifiers. The high-dimensional neuroimaging features for classification included regional cortical gray matter (GM) thickness and surface area, GM volume of subcortical structures, volume and fractional anisotropy of major white matter fiber tracts, pair-wise regional connectivity and global/nodal topological properties of the functional brain network for cue-evoked attention process. As a result, the bagging-based ELT with the base model of support vector machine achieved the best results, with significant improvement of the area under the receiver of operating characteristic curve (0.89 for ADHD vs. controls and 0.9 for ADHD persisters vs. remitters). Features of nodal efficiency in right inferior frontal gyrus, right middle frontal (MFG)-inferior parietal (IPL) functional connectivity, and right amygdala volume significantly contributed to accurate discrimination between ADHD probands and controls; higher nodal efficiency of right MFG greatly contributed to inattentive and hyperactive/impulsive symptom remission, while higher right MFG-IPL functional connectivity strongly linked to symptom persistence in adults with childhood ADHD. Considering their improved robustness than the commonly implemented basic classifiers, findings suggest that ELTs may have the potential to identify more reliable neurobiological markers for neurodevelopmental disorders.

SUBMITTER: Luo Y

PROVIDER: S-EPMC7076568 | biostudies-literature | 2020

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Multimodal neuroimaging-based prediction of adult outcomes in childhood-onset ADHD using ensemble learning techniques.

Luo Yuyang Y Alvarez Tara L TL Halperin Jeffrey M JM Li Xiaobo X

NeuroImage. Clinical 20200307

Attention-deficit/hyperactivity disorder (ADHD) is a highly prevalent and heterogeneous neurodevelopmental disorder, which is diagnosed using subjective symptom reports. Machine learning classifiers have been utilized to assist in the development of neuroimaging-based biomarkers for objective diagnosis of ADHD. However, existing basic model-based studies in ADHD report suboptimal classification performances and inconclusive results, mainly due to the limited flexibility for each type of basic cl ...[more]

PMID: 32182578

Similar Datasets

Project description:Although self-report pain ratings are the gold standard in clinical pain assessment, they are inherently subjective in nature and significantly influenced by multidimensional contextual variables. Although objective biomarkers for pain could substantially aid pain diagnosis and development of novel therapies, reliable markers for clinical pain have been elusive. In this study, individualized physical maneuvers were used to exacerbate clinical pain in patients with chronic low back pain (N = 53), thereby experimentally producing lower and higher pain states. Multivariate machine-learning models were then built from brain imaging (resting-state blood-oxygenation-level-dependent and arterial spin labeling functional imaging) and autonomic activity (heart rate variability) features to predict within-patient clinical pain intensity states (ie, lower vs higher pain) and were then applied to predict between-patient clinical pain ratings with independent training and testing data sets. Within-patient classification between lower and higher clinical pain intensity states showed best performance (accuracy = 92.45%, area under the curve = 0.97) when all 3 multimodal parameters were combined. Between-patient prediction of clinical pain intensity using independent training and testing data sets also demonstrated significant prediction across pain ratings using the combined model (Pearson's r = 0.63). Classification of increased pain was weighted by elevated cerebral blood flow in the thalamus, and prefrontal and posterior cingulate cortices, and increased primary somatosensory connectivity to frontoinsular cortex. Our machine-learning approach introduces a model with putative biomarkers for clinical pain and multiple clinical applications alongside self-report, from pain assessment in noncommunicative patients to identification of objective pain endophenotypes that can be used in future longitudinal research aimed at discovery of new approaches to combat chronic pain.

Project description:The emission of greenhouse gases and natural-resource depletion caused by the production of ordinary Portland cement (OPC) have a detrimental effect on the environment. Thus, an alternative means is required to produce eco-friendly concrete such as geopolymer concrete (GPC). However, GPC has a complex cementitious matrix and an ambiguous mix design. Aside from that, the composition and proportions of materials utilized may have an impact on the compressive strength. Similarly, the use of robust and efficient machine-learning (ML) approaches is now required to forecast the strength of such a composite cementitious matrix. As a result, this study anticipated the compressive strength of GPC with waste resources using ensemble and non-ensemble ML algorithms. This was accomplished through the use of Anaconda (Python). To build a strong ensemble learner by integrating weak learners, adaptive boosting, random forest (RF), and ensemble learner bagging were employed. Furthermore, ensemble learners were utilized on non-ensemble or weak learners, such as decision trees (DT) and support vector machines (SVM) via regression. The data encompassed 156 statistical samples in which nine variables, namely superplasticizer (kg/m3), fly ash (kg/m3), ground granulated blast-furnace slag (GGBS), temperature (°C), coarse and fine aggregate (kg/m3), sodium silicate (Na2SiO3), and sodium hydroxide (NaOH), were chosen to anticipate the results. Exploring it in depth, twenty sub-models with ensemble boosting and bagging approaches were trained, and tuning was performed to achieve the highest possible coefficient of determination (R2). Moreover, cross K-Fold validation analysis and statistical checks were performed via indicators for the evaluation of the models. The result revealed that ensemble approaches yielded robust performance compared to non-ensemble algorithms. Generally, an ensemble learner with the RF and bagging approach on a DT yielded robust performance by achieving a better R2 as 0.93, and with the lowest statistical errors. The communal model in artificial-intelligence analysis, on average, improved the accuracy of the model.

Project description:ObjectiveDespite a prevailing assumption that adult ADHD is a childhood-onset neurodevelopmental disorder, no prospective longitudinal study has described the childhoods of the adult ADHD population. The authors report follow-back analyses of ADHD cases diagnosed in adulthood, alongside follow-forward analyses of ADHD cases diagnosed in childhood, in one cohort.MethodParticipants belonged to a representative birth cohort of 1,037 individuals born in Dunedin, New Zealand, in 1972 and 1973 and followed to age 38, with 95% retention. Symptoms of ADHD, associated clinical features, comorbid disorders, neuropsychological deficits, genome-wide association study-derived polygenic risk, and life impairment indicators were assessed. Data sources were participants, parents, teachers, informants, neuropsychological test results, and administrative records. Adult ADHD diagnoses used DSM-5 criteria, apart from onset age and cross-setting corroboration, which were study outcome measures.ResultsAs expected, childhood ADHD had a prevalence of 6% (predominantly male) and was associated with childhood comorbid disorders, neurocognitive deficits, polygenic risk, and residual adult life impairment. Also as expected, adult ADHD had a prevalence of 3% (gender balanced) and was associated with adult substance dependence, adult life impairment, and treatment contact. Unexpectedly, the childhood ADHD and adult ADHD groups comprised virtually nonoverlapping sets; 90% of adult ADHD cases lacked a history of childhood ADHD. Also unexpectedly, the adult ADHD group did not show tested neuropsychological deficits in childhood or adulthood, nor did they show polygenic risk for childhood ADHD.ConclusionsThe findings raise the possibility that adults presenting with the ADHD symptom picture may not have a childhood-onset neurodevelopmental disorder. If this finding is replicated, then the disorder's place in the classification system must be reconsidered, and research must investigate the etiology of adult ADHD.

Dataset Information

Multimodal neuroimaging-based prediction of adult outcomes in childhood-onset ADHD using ensemble learning techniques.

Publications

Multimodal neuroimaging-based prediction of adult outcomes in childhood-onset ADHD using ensemble learning techniques.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets