Classification of pure conduct disorder from healthy controls based on indices of brain networks during resting state

Zhang, Jiang; Liu, Yuyan; Luo, Ruisen; Du, Zhengcong; Lu, Fengmei; Yuan, Zhen; Zhou, Jiansong; Li, Shasha

doi:10.1007/s11517-020-02215-8

Cited by 8 publications

(11 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With these few exceptions, there is a virtually exclusive focus on lowlevel, subclinical psychopathic traits in healthy volunteers 99,100,111,113,114 . This contrasts sharply with the data-driven literature 44,[60][61][62][63]65,67,68 and conventional psychopathy research (e.g., [117][118][119], where the focus is largely on diagnosed individuals. While there are good arguments for treating psychopathy as a set of traits rather than a category of disorder 4,[29][30][31] , a focus on purely subclinical phenomena may not generate transdiagnostic markers across different clinical disorders.…”

Section: Theory-driven Approachesmentioning

confidence: 67%

“…Data-driven approaches, with their 'agnostic' approach to distinguishing between different classes of disorder and health, have demonstrated that psychopathy, antisocial personality disorder, and conduct disorder can be reliably distinguished from health using a range of neuroimaging, behavioural, and questionnaire-derived measures 44,[61][62][63][65][66][67][68] . The successful identification of these disorders, based on criteria other than the diagnostic criteria (e.g., neuroimaging data), suggests that they all capture genuine psychopathology to a large extent.…”

Section: Discussionmentioning

confidence: 99%

“…In youths, a series of studies have been conducted with a sample of Chinese adolescent boys (aged 14-15) with 'pure' (non-comorbid) conduct disorder, and healthy controls. Different classifiers have achieved maximum accuracies ranging from 78% to 85% 61-63 using regional grey matter volumes from this sample, while resting state functional MRI data from a similar sample ('non-comorbid' Chinese adolescent boys aged 15-17) yielded accuracies of 75% 64 and 94% 65 . These studies highlight the power of the multivariate machine learning approach.…”

Section: Data-driven Approachesmentioning

confidence: 96%

“…This raises sensitive ethical issues around the clinical use of classifiers, especially regarding ethnic biases 81 . Conversely, many researchers mitigate this issue by using demographically well-matched, numerically balanced groups, sometimes with variance associated with confounding factors already regressed out (e.g., 44,65,68,69 ). This increases interpretability and reduces opportunities for confounding variables to drive classification, but it is less datadriven and often results in samples that do not reflect the real-world incidence of health and disorder.…”

Section: Data-driven Approachesmentioning

confidence: 99%

See 3 more Smart Citations

The computational psychiatry of antisocial behaviour and psychopathy

Pauli

Lockwood

2023

Neuroscience & Biobehavioral Reviews

View full text Add to dashboard Cite

Section: Theory-driven Approachesmentioning

confidence: 67%

Section: Discussionmentioning

confidence: 99%

Section: Data-driven Approachesmentioning

confidence: 96%

Section: Data-driven Approachesmentioning

confidence: 99%

See 2 more Smart Citations

The computational psychiatry of antisocial behaviour and psychopathy

Pauli

Lockwood

2023

Neuroscience & Biobehavioral Reviews

View full text Add to dashboard Cite

“…5 However, CD has been relatively less studied in China compared with ADHD and ASD. Of existing literature concerning CD burden in China, only a limited number of studies have been conducted with a few disease burden figures in a certain region at a certain time point, 6 rather than the long-term trend studies on CD incidence across the country. An essential requirement for advancements in reducing the CD burden and for rational allocation of health care resources is the improved understanding of its epidemiology.…”

mentioning

confidence: 99%

Secular Trend in the Incidence of Conduct Disorder in China from 1990 to 2019: A Joinpoint and Age-Period-Cohort Analysis

Wang

Huang

et al. 2022

J Dev Behav Pediatr

Self Cite

View full text Add to dashboard Cite

The aim of this study was to analyze the secular trends of conduct disorder (CD) incidence in China from 1990 to 2019 under the joinpoint analysis and the age-period-cohort framework. Methods: The sex-specific incidence rates of CD from 1990 to 2019 were extracted from the Global Burden of Disease Study 2019 database according to the age group. The joinpoint regression and the age-period-cohort model were conducted using the average annual percent changes and relative risks as size effects, respectively. Results: From 1990 to 2019, age-standardized rates (ASRs) of CD incidence showed an overall increasing trend in both sexes, and this variation trend was observed in almost all age groups. The annual sex-specific ASRs were lower in China than those worldwide but were rapidly growing. Age effects were the most significant risk factor for CD, with the highest risk in adolescents aged 10 to 14 years, followed by children aged 5 to 9 years, but a relatively lower risk in adolescents aged 15 to 19 years than in other age groups. However, period and cohort effects were not statistically significant. Conclusion: CD incidence rates in China have been increasing in both sexes from 1990 to 2019. Further studies are necessary to explain the etiology of these increases and promote the early identification of individuals at risk for developing CD.

show abstract

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

et al. 2023

View full text Add to dashboard Cite

ImportanceNeuroimaging-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.ObjectiveTo systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.Evidence ReviewPubMed 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.FindingsA 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 RelevanceThis 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.

show abstract

Classification of pure conduct disorder from healthy controls based on indices of brain networks during resting state

Cited by 8 publications

References 51 publications

The computational psychiatry of antisocial behaviour and psychopathy

The computational psychiatry of antisocial behaviour and psychopathy

Secular Trend in the Incidence of Conduct Disorder in China from 1990 to 2019: A Joinpoint and Age-Period-Cohort Analysis

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis

Contact Info

Product

Resources

About