Machine-actionable criteria chart the symptom space of mental disorders
Strasser-Kirchweger, B.; Kutil, R. H.; Zimmermann, G.; Borgelt, C.; Trutschnig, W.; Hutzler, F.
Show abstract
Diagnostic manuals encode community consensus in prose yet offer no direct means to computationally evaluate the conceptual integrity of disorder definitions. We introduce a machine-actionable framework that translates narrative diagnostic criteria into the full symptom space--the exhaustive set of symptom combinations valid for each disorder. This approach enables charting of how these symptom spaces intersect, diverge, or subsume one another. Applied to representative DSM-5 disorders and to the emerging definition of Long COVID, the framework confirms clear boundaries among established disorders while highlighting substantial conceptual redundancy between Long COVID and mood or anxiety disorders. Whereas probabilistic models infer patterns from broad textual corpora, the proposed framework directly interrogates explicit consensus criteria, providing a transparent and reproducible means of assessing conceptual coherence. By making consensus-based diagnostic knowledge computable, the framework supports the refinement of classification systems and provides a foundation for interpretable clinical decision support.
Matching journals
The top 4 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Continuous-Time and Dynamic Suicide Attempt Risk Prediction with Neural Ordinary Differential Equations 93%
- Clinical Knowledge Extraction via Sparse Embedding Regression (KESER) with Multi-Center Large Scale Electronic Health Record Data 93%
- Few shot learning for phenotype-driven diagnosis of patients with rare genetic diseases 92%
Similar papers in this journal
- Pretrained Patient Trajectories for Adverse Drug Event Prediction Using Common Data Model-based Electronic Health Records 90%
- Clinical trial emulation can identify new opportunities to enhance the regulation of drug safety in pregnancy 90%
- The Interpretable Multimodal Machine Learning (IMML) framework reveals pathological signatures of distal sensorimotor polyneuropathy 89%
Similar papers in this journal
- Simulation of undiagnosed patients with novel genetic conditions 93%
- Bivariate Gaussian Mixture Model of GWAS (BGMG)quantifies polygenic overlap between complex traitsbeyond genetic correlation 93%
- Deep representation learning for clustering longitudinal survival data from electronic health records 92%
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.