Abstract
Diagnostic rules are codified in consensus manuals such as DSM-5, yet they remain written in narrative form and cannot be computationally interrogated. Here, a deterministic framework is presented that translates diagnostic criteria into a machine-actionable representation of the full symptom space, which can be charted, navigated, and systematically analyzed. Unlike probabilistic models that infer patterns from large textual corpora, this framework directly interrogates explicit consensus criteria, providing a transparent and reproducible means of assessing conceptual coherence. Its potential is demonstrated by charting schizophrenia-spectrum disorders, which remain conceptually distinct despite substantial symptom overlap, and by evaluating the current National Academies’ definition of Long COVID, which is largely subsumed by depressive and anxiety disorders. By making diagnostic consensus computable, the framework provides a reproducible foundation for evaluating delineation properties of existing and candidate diagnostic constructs and for developing interpretable, regulatory-compliant diagnostic support tools.
Similar content being viewed by others
Data availability
The source data supporting the findings of this study, including the data used inTable 1 and Figure 3 and the associated calculated values, are available in a public GitHub repository at: https://github.com/raoul-k/AIDA-Path/tree/main/data.
Code availability
The code used to generate the results in this paper is available in a public GitHub repository at: https://github.com/raoul-k/AIDA-Path. The code for generating CSSCs is publicly available at https://github.com/raoul-k/AIDA-Path/tree/main/Python/Generators, and the specific generators used in this document can be found at https://github.com/raoul-k/AIDA-Path/tree/main/data/generators. A Jupyter Notebook for testing the generators will also be made available in the same repository.
References
American Psychiatric Association. Diagnostic and statistical manual of mental disorders https://doi.org/10.1176/appi.books.9780890425596 (American Psychiatric Association, Washington, DC, 2013).
Beatty, J. In Landscapes of Collectivity in the Life Sciences. In Gissis, S. B., Lamm, E. & Shavit, A. (eds.) Landscapes of Collectivity in the Life Sciences, 179–198 (MIT Press, Cambridge, MA, 2017).
Wegwarth, O. & Gigerenzer, G. Torture by consensus? on the misuse of evidence-based guidelines in medicine. Med., Health Care Philos. 25, 329–338 (2022).
Singh, H., Schiff, G. D., Graber, M. L., Onakpoya, I. & Thompson, M. J. The global burden of diagnostic errors in primary care. BMJ Qual. Saf. 26, 484–494 (2017).
Ely, J. W., Graber, M. L. & Croskerry, P. Checklists to reduce diagnostic errors. Acad. Med. 86, 307–313 (2011).
Newson, J. J., Pastukh, V. & Thiagarajan, T. C. Poor separation of clinical symptom profiles by dsm-5 disorder criteria. Front Psychiatry 12 (2021).
Christensen, M. K. et al. The cost of mental disorders: a systematic review. Epidemiol. Psychiatr. Sci. 29, e161 (2020).
Singhal, K. et al. Large language models encode clinical knowledge. Nature 620, 172–180 (2023).
Joyce, D. W., Kormilitzin, A., Smith, K. A. & Cipriani, A. Explainable artificial intelligence for mental health through transparency and interpretability for understandability. npj Digit. Med. 6, 6 (2023).
Horwitz, A. V.DSM: A History of Psychiatry’s Bible (Johns Hopkins University Press, Baltimore, 2021).
World Health Organization. International classification of diseases, 11th revision (icd-11). (2019).
Cornet, R. & de Keizer, N. Forty years of SNOMED: a literature review. BMC Medical Informatics and Decision Making 8, 1–6 (2008).
Chang, E. & Mostafa, J. The use of SNOMED CT, 2013-2020: a literature review. J. Am. Med. Inform. Assoc. 28, 2017–2026 (2021).
Brooks, P. International Classification of Diseases, Version 10 - Clinical Modification ∣ NCBO BioPortal (2024).
Organisation, I. H. T. S. D. Decision Support with SNOMED CT. Tech. Rep. (2017).
Schriml, L. M. et al. Disease ontology: a backbone for disease semantic integration. Nucleic Acids Res. 40, D940–D946 (2012).
Schriml, L. M. et al. Human disease ontology 2018 update: classification, content and workflow expansion. Nucleic Acids Res. 47, D955–D962 (2019).
Cuthbert, B. N. Research domain criteria: toward future psychiatric nosologies. Dialogues Clin. Neurosci. 17, 89–97 (2015).
Tandon, R., Nasrallah, H. A. & Keshavan, M. S. Schizophrenia, “just the facts” 4. clinical features and conceptualization. Schizophr. Res. 110, 1–23 (2009).
Perälä, J. et al. Lifetime prevalence of psychotic and bipolar i disorders in a general population. Arch. Gen. Psychiatry 64, 19–28 (2007).
Marneros, A. & Akiskal, H. S. The Overlap of Affective and Schizophrenic Spectra (Cambridge University Press, Cambridge, UK, 2007).
National Academies of Sciences, Engineering, and Medicine. A Long COVID Definition: A Chronic, Systemic Disease State with Profound Consequences (The National Academies Press, Washington, DC, 2024).
Ely, E. W., Brown, L. M. & Fineberg, H. V. Long Covid Defined (2024).
Cook, S. A. The complexity of theorem-proving procedures. In Proceedings of the Third Annual ACM Symposium on Theory of Computing (STOC ’71), 151–158 (ACM, New York, NY, USA, 1971).
Karp, R. M. Reducibility among combinatorial problems. In Miller, R. E. & Thatcher, J. W. (eds.) Complexity of Computer Computations, 85–103 (Springer, Boston, MA, 1972).
Walter, C. et al. Transparency of AI/ML-enabled medical devices. npj Digit. Med. 6, 146 (2023).
Korteling, J. H., van de Boer-Visschedijk, G. C., Blankendaal, R. A., Boonekamp, R. C. & Eikelboom, A. R. Human-versus artificial intelligence. Front. Artif. Intell. 4, 622364 (2021).
Klein, J. G. Five pitfalls in decisions about diagnosis and prescribing. BMJ: Br. Med. J. 330, 781–783 (2005).
Mittelstadt, B. D., Price, W. N. & Wachter, S. Artificial intelligence should genuinely support clinical reasoning in medicine. npj Digit. Med. 8, 12 (2025).
Dong, Y. et al. Real-time explainable ai system for clinical decision support by integrating domain knowledge. npj Digit. Med. 6, 88 (2023).
Salton, G. & McGill, M. J.Introduction to Modern Information Retrieval (McGraw-Hill, New York, 1983).
Sammon, J. A nonlinear mapping for data structure analysis. IEEE Trans. Comput. C-18, 401–409 (1969).
Kutil, R. H., Zimmermann, G., Strasser-Kirchweger, B. & Borgelt, C. Profile generators: A link between the narrative and the binary matrix representation. arXiv preprint arXiv:2511.19506 (2025).
Acknowledgements
All authors gratefully acknowledge the support of the InnovationExpress 2021 project AIDA-PATH (20102-F2101312-FPR). GZ gratefully acknowledges the support of the WISS 2025 projects ’IDA-Lab Salzburg’ (20204-WISS/225/197-2019 and 20102-F1901166-KZP) and ’EXDIGIT’ (Excellence in Digital Sciencesand Interdisciplinary Technologies) (20204-WISS/263/6-6022). Further supportwas provided by the Federal State of Salzburg via the Digital NeuroscienceInitiative (20102-F2101143-FP), which is gratefully acknowledged.
Author information
Authors and Affiliations
Contributions
B.S.-K., F.H., R.H.K., and C.B. conceptualized the study. R.H.K., C.B., and W.T. developed the methodology. R.H.K., C.B., and W.T. conducted the formal analysis. B.S.-K., R.H.K., F.H., and C.B. prepared the original draft of the manuscript. All authors contributed to reviewing and editing the manuscript. F.H. and C.B. supervised the project. W.T., F.H., and G.Z. validated the results. C.B. created the visualizations. B.S.-K. and R.H.K. contributed equally to this work.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/.
About this article
Cite this article
Strasser-Kirchweger, B., Kutil, R.H., Zimmermann, G. et al. Machine-actionable criteria chart the symptom space of mental disorders. npj Digit. Med. (2026). https://doi.org/10.1038/s41746-026-02451-6
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41746-026-02451-6
