Machine learning classification of conduct disorder with high versus low levels of callous-unemotional traits based on facial emotion recognition abilities

• Published in: European child & adolescent psychiatry Vol. 32; no. 4; pp. 589 - 600
• Main Authors: Pauli, Ruth, Kohls, Gregor, Tino, Peter, Rogers, Jack C., Baumann, Sarah, Ackermann, Katharina, Bernhard, Anka, Martinelli, Anne, Jansen, Lucres, Oldenhof, Helena, Gonzalez-Madruga, Karen, Smaragdi, Areti, Gonzalez-Torres, Miguel Angel, Kerexeta-Lizeaga, Iñaki, Boonmann, Cyril, Kersten, Linda, Bigorra, Aitana, Hervas, Amaia, Stadler, Christina, Fernandez-Rivas, Aranzazu, Popma, Arne, Konrad, Kerstin, Herpertz-Dahlmann, Beate, Fairchild, Graeme, Freitag, Christine M., Rotshtein, Pia, De Brito, Stephane A.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01-04-2023; Springer Nature B.V
• Subjects: Ability; Acknowledgment; Adolescent; Child and Adolescent Psychiatry; Conduct disorder; Conduct Disorder - diagnosis; Conduct Disorder - psychology; Emotion recognition; Emotions; Facial expressions; Facial Recognition; Fear; Fear & phobias; Humans; Individual differences; Learning algorithms; Machine learning; Medicine; Medicine & Public Health; Original Contribution; Pattern recognition; Psychiatry; Psychological distress; Recognition, Psychology; Sadness; Conduct disorder; Emotion recognition; Conduct problems; Callous-unemotional traits; Machine learning
• ISSN: 1018-8827; 1435-165X; 1435-165X
• DOI: 10.1007/s00787-021-01893-5

Conduct disorder (CD) with high levels of callous-unemotional traits (CD/HCU) has been theoretically linked to specific difficulties with fear and sadness recognition, in contrast to CD with low levels of callous-unemotional traits (CD/LCU). However, experimental evidence for this distinction is mixed, and it is unclear whether these difficulties are a reliable marker of CD/HCU compared to CD/LCU. In a large sample (
N
 = 1263, 9–18 years), we combined univariate analyses and machine learning classifiers to investigate whether CD/HCU is associated with disproportionate difficulties with fear and sadness recognition over other emotions, and whether such difficulties are a reliable individual-level marker of CD/HCU. We observed similar emotion recognition abilities in CD/HCU and CD/LCU. The CD/HCU group underperformed relative to typically developing (TD) youths, but difficulties were not specific to fear or sadness. Classifiers did not distinguish between youths with CD/HCU versus CD/LCU (52% accuracy), although youths with CD/HCU and CD/LCU were reliably distinguished from TD youths (64% and 60%, respectively). In the subset of classifiers that performed well for youths with CD/HCU, fear and sadness were the most relevant emotions for distinguishing them from youths with CD/LCU and TD youths, respectively. We conclude that non-specific emotion recognition difficulties are common in CD/HCU, but are not reliable individual-level markers of CD/HCU versus CD/LCU. These findings highlight that a reduced ability to recognise facial expressions of distress should not be assumed to be a core feature of CD/HCU.