Linking ADHD and Behavioral Assessment Through Identification of Shared Diagnostic Task-Based Functional Connections

Individualized prediction models in ADHD: a systematic review and meta-regression

There have been increasing efforts to develop prediction models supporting personalised detection, prediction, or treatment of ADHD. We overviewed the current status of prediction science in ADHD by: (1) systematically reviewing and appraising available prediction models; (2) quantitatively assessing factors impacting the performance of published models. We did a PRISMA/CHARMS/TRIPOD-compliant systematic review (PROSPERO: CRD42023387502), searching, until 20/12/2023, studies reporting internally and/or externally validated diagnostic/prognostic/treatment-response prediction models in ADHD. Using meta-regressions, we explored the impact of factors affecting the area under the curve (AUC) of the models. We assessed the study risk of bias with the Prediction Model Risk of Bias Assessment Tool (PROBAST). From 7764 identified records, 100 prediction models were included (88% diagnostic, 5% prognostic, and 7% treatment-response). Of these, 96% and 7% were internally and externally validated, respectively. None was implemented in clinical practice. Only 8% of the models were deemed at low risk of bias; 67% were considered at high risk of bias. Clinical, neuroimaging, and cognitive predictors were used in 35%, 31%, and 27% of the studies, respectively. The performance of ADHD prediction models was increased in those models including, compared to those models not including, clinical predictors (β = 6.54, p = 0.007). Type of validation, age range, type of model, number of predictors, study quality, and other type of predictors did not alter the AUC. Several prediction models have been developed to support the diagnosis of ADHD. However, efforts to predict outcomes or treatment response have been limited, and none of the available models is ready for implementation into clinical practice. The use of clinical predictors, which may be combined with other type of predictors, seems to improve the performance of the models. A new generation of research should address these gaps by conducting high quality, replicable, and externally validated models, followed by implementation research.

Impact of prenatal marijuana exposure on adolescent brain structural and functional connectivity and behavioural outcomes

There has been an increase in the number of women using marijuana whilst pregnant. Previous studies have shown that children with prenatal marijuana exposure have developmental deficits in memory and decreased attentiveness. In this study, we assess whether prenatal marijuana exposure is associated with alterations in brain regional morphometry and functional and structural connectivity in adolescents. We downloaded behavioural scores and subject image files from the Adolescent Brain Cognitive DevelopmentSM Study. A total of 178 anatomical and diffusion magnetic resonance imaging files (88 prenatal marijuana exposure and 90 age- and gender-matched controls) and 152 resting-state functional magnetic resonance imaging files (76 prenatal marijuana exposure and 76 controls) were obtained. Behavioural metrics based on the parent-reported child behavioural checklist were also obtained for each subject. The associations of prenatal marijuana exposure with 17 subscales of the child behavioural checklist were calculated. We assessed differences in brain morphometry based on voxel-based and surface-based morphometry in adolescents with prenatal marijuana exposure versus controls. We also evaluated group differences in structural and functional connectivity in adolescents for region-to-region connectivity and graph theoretical metrics. Interactions of prenatal marijuana exposure and graph networks were assessed for impact on behavioural scores. Multiple comparison correction was performed as appropriate. Adolescents with prenatal marijuana exposure had greater abnormal or borderline child behavioural checklist scores in 9 out of 17 subscales. There were no significant differences in voxel- or surface-based morphometry, structural connectivity or functional connectivity between prenatal marijuana exposure and controls. However, there were significant differences in prenatal marijuana exposure-graph network interactions with respect to behavioural scores. There were three structural prenatal marijuana exposure-graph network interactions and seven functional prenatal marijuana exposure-graph network interactions that were significantly associated with behavioural scores. Whilst this study was not able to confirm anatomical or functional differences between prenatal marijuana exposure and unexposed pre-adolescent children, there were prenatal marijuana exposure-brain structural and functional graph network interactions that were significantly associated with behavioural scores. This suggests that altered brain networks may underlie behavioural outcomes in adolescents with prenatal marijuana exposure. More work needs to be conducted to better understand the prognostic value of brain structural and functional network measures in prenatal marijuana exposure.

Sampling inequalities affect generalization of neuroimaging-based diagnostic classifiers in psychiatry

BACKGROUND

The development of machine learning models for aiding in the diagnosis of mental disorder is recognized as a significant breakthrough in the field of psychiatry. However, clinical practice of such models remains a challenge, with poor generalizability being a major limitation.

METHODS

Here, we conducted a pre-registered meta-research assessment on neuroimaging-based models in the psychiatric literature, quantitatively examining global and regional sampling issues over recent decades, from a view that has been relatively underexplored. A total of 476 studies (n = 118,137) were included in the current assessment. Based on these findings, we built a comprehensive 5-star rating system to quantitatively evaluate the quality of existing machine learning models for psychiatric diagnoses.

RESULTS

A global sampling inequality in these models was revealed quantitatively (sampling Gini coefficient (G) = 0.81, p < .01), varying across different countries (regions) (e.g., China, G = 0.47; the USA, G = 0.58; Germany, G = 0.78; the UK, G = 0.87). Furthermore, the severity of this sampling inequality was significantly predicted by national economic levels (β =  - 2.75, p < .001, R²_adj = 0.40; r =  - .84, 95% CI: - .41 to - .97), and was plausibly predictable for model performance, with higher sampling inequality for reporting higher classification accuracy. Further analyses showed that lack of independent testing (84.24% of models, 95% CI: 81.0-87.5%), improper cross-validation (51.68% of models, 95% CI: 47.2-56.2%), and poor technical transparency (87.8% of models, 95% CI: 84.9-90.8%)/availability (80.88% of models, 95% CI: 77.3-84.4%) are prevailing in current diagnostic classifiers despite improvements over time. Relating to these observations, model performances were found decreased in studies with independent cross-country sampling validations (all p < .001, BF₁₀ > 15). In light of this, we proposed a purpose-built quantitative assessment checklist, which demonstrated that the overall ratings of these models increased by publication year but were negatively associated with model performance.

CONCLUSIONS

Together, improving sampling economic equality and hence the quality of machine learning models may be a crucial facet to plausibly translating neuroimaging-based diagnostic classifiers into clinical practice.

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Machine Learning and MRI-based Diagnostic Models for ADHD: Are We There Yet?

OBJECTIVE

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.

METHODS

A comprehensive literature search on MRI-based diagnostic classifiers for ADHD was performed and data regarding the utilized models and samples were gathered.

RESULTS

We found that, although most 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.

CONCLUSION

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.

ADHD and its neurocognitive substrates: A two sample Mendelian randomization study

Attention-deficit/hyperactivity disorder (ADHD) is associated with a wide array of neural and cognitive features, and other psychiatric disorders, identified mainly through cross-sectional associations studies. However, it is unclear if the disorder is causally associated with these neurocognitive features. Here, we applied a two-sample bidirectional Mendelian randomization (MR) study to summary GWAS data to explore the presence and direction of a causal effect between ADHD and a range of neurocognitive features and other psychiatric disorders. The inverse variance weighted method was used in the main analysis, and two MR methods (MR-Egger, weighted median) were used for robustness checks. We found that genetic risk for ADHD was causally associated with a decreased area of lateral orbitofrontal cortex. Conversely, we found that brain volume and some features of intrinsic functional connectivity had causal effects on ADHD risk. Bidirectional causal links were found between ADHD and adult general intelligence, as well as depression and autistic spectrum disorders. Such work highlights the important ties between ADHD and general cognitive ability, and suggest some neural features, previously merely associated with the disorder, may play a causal role in its pathogenesis.

The Connectivity Fingerprints of Highly-Skilled and Disordered Reading Persist Across Cognitive Domains

The capacity to produce and understand written language is a uniquely human skill that exists on a continuum, and foundational to other facets of human cognition. Multivariate classifiers based on support vector machines (SVM) have provided much insight into the networks underlying reading skill beyond what traditional univariate methods can tell us. Shallow models like SVM require large amounts of data, and this problem is compounded when functional connections, which increase exponentially with network size, are predictors of interest. Data reduction using independent component analyses (ICA) mitigates this problem, but conventionally assumes linear relationships. Multilayer feedforward networks, in contrast, readily find optimal low-dimensional encodings of complex patterns that include complex nonlinear or conditional relationships. Samples of poor and highly-skilled young readers were selected from two open access data sets using rhyming and mental multiplication tasks, respectively. Functional connectivity was computed for the rhyming task within a functionally-defined reading network and used to train multilayer feedforward classifier models to simultaneously associate functional connectivity patterns with lexicality (word vs. pseudoword) and reading skill (poor vs. highly-skilled). Classifiers identified validation set lexicality with significantly better than chance accuracy, and reading skill with near-ceiling accuracy. Critically, a series of replications used pre-trained rhyming-task models to classify reading skill from mental multiplication task participants' connectivity with near-ceiling accuracy. The novel deep learning approach presented here provides the clearest demonstration to date that reading-skill dependent functional connectivity within the reading network influences brain processing dynamics across cognitive domains.