Interpretable machine learning for hikikomori screening: The adaptive HRI-15
PLOS One · 20.08.2026 · 21 (8) · e0355595
DOI: 10.1371/journal.pone.0355595 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 20.08.2026. Verfasst von Daiana Colledani und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Psychology, Faculty of Medicine and Psychology, Sapienza University of Rome, Rome, Italy. Hauptthemen laut MEDLINE: Machine Learning, Social Isolation, Mass Screening. Die Arbeit nennt 112 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Hikikomori, or prolonged social withdrawal, is an issue of global relevance. The HRI-15 is a brief tool for its assessment. This study enhances its utility by adding clinical thresholds to identify risk and person-centered clinical profiles, and by developing a machine-learning(ML)–based computerized adaptive test (CAT) to enable rapid screening. Data from a national survey of Italian adolescents ( N = 8,755) were used to conduct ROC analysis and latent profile analysis (LPA). The findings indicated that a score of ≥ 42 achieved optimal classification performance, and four profiles with distinct meanings and systematic differences in anxiety, depression, impulsivity, and risk behaviors were identified. A multivariate conditional inference tree was estimated to develop an ML-based adaptive version of the instrument. The CAT reduced administered items by 53% (7.03/15), accurately reproducing full-length scores ( r = .77–.997) and the corresponding classification; alignment was assessed with latent transition analysis (entropy = .96). The procedure was integrated into an application supporting administration, scoring, and reporting (score, risk, profiles, graphs). Combining a cross-validated cutoff and clinically useful profiles with CAT and its automated administration and reporting application strengthens triage and personalization, enabling large-scale, multidomain screening and earlier intervention for hikikomori risk.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Psychology, Faculty of Medicine and Psychology, Sapienza University of Rome, Rome, Italy.
- Department of Philosophy, Sociology, Education and Applied Psychology (FISPPA), University of Padova, Padua, Italy.
- Department of Humanities, University of Foggia, Foggia, Italy.
- Explora Research and Statistical Analysis, Padua, Italy.
- Novella Fronda Foundation, Padua, Italy.
- National Centre on Addiction and Doping, Italian National Institute of Health, Rome, Italy.
ORCID-Profile: Pasquale Anselmi, Lucia Monacis, Adele Minutillo
Zitieren
APA
Colledani, D., Anselmi, P., Monacis, L., Genetti, B., Fassinato, D., Gomez Perez, L. J., Minutillo, A., Mastrobattista, L., & Mortali, C. (2026). Interpretable machine learning for hikikomori screening: The adaptive HRI-15. PLOS One, 21(8), e0355595. https://doi.org/10.1371/journal.pone.0355595
Vancouver
Colledani D, Anselmi P, Monacis L, Genetti B, Fassinato D, Gomez Perez LJ, et al. Interpretable machine learning for hikikomori screening: The adaptive HRI-15. PLOS One. 2026;21(8):e0355595. doi:10.1371/journal.pone.0355595
BibTeX
@article{Colledani2026,
author = {Colledani, Daiana and Anselmi, Pasquale and Monacis, Lucia and Genetti, Bruno and Fassinato, Daniele and Gomez Perez, Luis J and Minutillo, Adele and Mastrobattista, Luisa and Mortali, Claudia},
title = {Interpretable machine learning for hikikomori screening: The adaptive HRI-15},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {8},
pages = {e0355595},
doi = {10.1371/journal.pone.0355595}
}
EUVIMED