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

Ruth Pauli*, Gregor Kohls, Peter Tino, Jack C. Rogers, Sarah Baumann, Katharina Ackermann, Anka Bernhard, Anne Martinelli, Lucres Jansen, Helena Oldenhof, Karen Gonzalez-Madruga, Areti Smaragdi, Miguel Angel Gonzalez-Torres, Iñaki Kerexeta-Lizeaga, Cyril Boonmann, Linda Kersten, Aitana Bigorra, Amaia Hervas, Christina Stadler, Aranzazu Fernandez-RivasArne Popma, Kerstin Konrad, Beate Herpertz-Dahlmann, Graeme Fairchild, Christine M. Freitag, Pia Rotshtein, Stephane A. De Brito

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

70 Downloads (Pure)

Abstract

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.

Original languageEnglish
Number of pages12
JournalEuropean Child and Adolescent Psychiatry
Early online date18 Oct 2021
DOIs
Publication statusE-pub ahead of print - 18 Oct 2021

Bibliographical note

Funding Information:
This study was conducted by the FemNAT-CD consortium (Neurobiology and Treatment of Adolescent Female Conduct Disorder: The Central Role of Emotion Processing, coordinator Christine M. Freitag). This collaborative project is funded by the European Commission under the 7th Framework Health Program, Grant Agreement no. 602407. Ruth Pauli was supported by the Biotechnology and Biological Sciences Research Council’s Midlands Integrative Biosciences Training Partnership (BBSRC MIBTP). During the writing of the manuscript, Stephane A. De Brito was supported by a short-term Invitational Fellowship from the Japanese Society for the Promotion of Science (JSPS - S19103) and an International Academic Fellowship from the Leverhulme Trust (IAF-2019-032).

Publisher Copyright:
© 2021, The Author(s).

Keywords

  • Callous-unemotional traits
  • Conduct disorder
  • Conduct problems
  • Emotion recognition
  • Machine learning

ASJC Scopus subject areas

  • Pediatrics, Perinatology, and Child Health
  • Developmental and Educational Psychology
  • Psychiatry and Mental health

Fingerprint

Dive into the research topics of 'Machine learning classification of conduct disorder with high versus low levels of callous-unemotional traits based on facial emotion recognition abilities'. Together they form a unique fingerprint.

Cite this