Tools for Helping Identify Behavior Disorders: From Parsimonious Nomograms to Machine Learning Models
Abstract
Objective: Disruptive behavior problems like Oppositional Defiant Disorder (ODD) and Conduct Disorder (CD) are high burden conditions where accurate diagnosis is crucial for effective treatment. We evaluated probability nomograms and machine learning (ML) algorithms (logistic regression, LASSO, SVM, random forest) on accuracy, calibration, and generalizability for detecting current ODD or CD diagnoses. Method: Youth aged 5–18 receiving outpatient care were recruited from academic (n=622) and community (n=506) clinics. Predictors included demographics, comorbid diagnoses, mood and behavioral indicators. The criterion was K-SADS diagnoses of ODD/CD. Models were trained in the academic sample, using the community sample for external validation. AUC quantified accuracy, Spiegelhalter's z indexed calibration, and cross-site performance measured generalizability. Results: For ODD diagnostic prediction, the nomogram selected CBCL Aggression as the strongest predictor and reached AUC≈.70 in both samples. ML models achieved good discrimination (AUC≈.86) with good-to-moderate calibration in the academic sample, deteriorating to fair accuracy with severe miscalibration in the community setting. For CD diagnostic prediction, the nomogram built on CBCL Rule-Breaking showed good accuracy (AUC≈.82) in both samples. ML models showed near-excellent accuracy (AUC≈.88) in the academic sample but underperformed in the community sample (AUC=.73-.76), though LASSO, SVM, and random forest maintained good calibration. Conclusion: Across both disorders, nomograms demonstrated lower accuracy but strong cross-site stability, while ML using more predictors achieved superior accuracy that did not generalize. The nomogram offers a low-cost and parsimonious tool. Machine learning is best suited for well-resourced clinics where model training data closely resemble the new cases encountered in practice.
Related
- Development and temporal validation of nomograms and machine learning models for predicting overall and cancer-specific survival in primary distal cholangiocarcinoma: a SEER-based study
- Development and internal validation of machine learning models for identifying suicidal behavior in inpatients with mood disorders.
- A Parsimonious Machine Learning Model for Predicting Invasive Coronary Angiography Referral After Coronary Computed Tomography Angiography: Development and Multicentre External Validation
- Using Diffusion Similarity Networks to Identify, Track, and Predict Movement Disorders
- Refining E-detectioN Tools for Emerging mental disoRders (ENTER) to identify young people at clinical high risk for psychosis in the community: model development and internal validation
BibTeX
@misc{liu2026tools,
title = {{Tools for Helping Identify Behavior Disorders: From Parsimonious Nomograms to Machine Learning Models}},
author = {Yinuo Liu and Eric Youngstrom, Ph.D. and Caroline Bodary and Zhuoyu Shi and Jennifer Youngstrom and Ekaterina Stepanova, MD, PhD and Robert L. Findling},
howpublished = {PsyArXiv},
year = {2026},
month = oct,
doi = {10.31234/osf.io/4sfjz_v2},
url = {https://osf.io/preprints/psyarxiv/4sfjz_v2/},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Tools for Helping Identify Behavior Disorders: From Parsimonious Nomograms to Machine Learning Models
AU - Yinuo Liu
AU - Eric Youngstrom, Ph.D.
AU - Caroline Bodary
AU - Zhuoyu Shi
AU - Jennifer Youngstrom
AU - Ekaterina Stepanova, MD, PhD
AU - Robert L. Findling
PY - 2026
DA - 2026/10/14
PB - PsyArXiv
DO - 10.31234/osf.io/4sfjz_v2
UR - https://osf.io/preprints/psyarxiv/4sfjz_v2/
AB - Objective: Disruptive behavior problems like Oppositional Defiant Disorder (ODD) and Conduct Disorder (CD) are high burden conditions where accurate diagnosis is crucial for effective treatment. We evaluated probability nomograms and machine learning (ML) algorithms (logistic regression, LASSO, SVM, random forest) on accuracy, calibration, and generalizability for detecting current ODD or CD diagnoses. Method: Youth aged 5–18 receiving outpatient care were recruited from academic (n=622) and community (n=506) clinics. Predictors included demographics, comorbid diagnoses, mood and behavioral indicators. The criterion was K-SADS diagnoses of ODD/CD. Models were trained in the academic sample, using the community sample for external validation. AUC quantified accuracy, Spiegelhalter's z indexed calibration, and cross-site performance measured generalizability. Results: For ODD diagnostic prediction, the nomogram selected CBCL Aggression as the strongest predictor and reached AUC≈.70 in both samples. ML models achieved good discrimination (AUC≈.86) with good-to-moderate calibration in the academic sample, deteriorating to fair accuracy with severe miscalibration in the community setting. For CD diagnostic prediction, the nomogram built on CBCL Rule-Breaking showed good accuracy (AUC≈.82) in both samples. ML models showed near-excellent accuracy (AUC≈.88) in the academic sample but underperformed in the community sample (AUC=.73-.76), though LASSO, SVM, and random forest maintained good calibration. Conclusion: Across both disorders, nomograms demonstrated lower accuracy but strong cross-site stability, while ML using more predictors achieved superior accuracy that did not generalize. The nomogram offers a low-cost and parsimonious tool. Machine learning is best suited for well-resourced clinics where model training data closely resemble the new cases encountered in practice.
ER -