From models to tools: clinical translation of machine learning studies in psychosis
Open accessAbstract
The past decade has seen a proliferation of neuroimaging-based machine learning studies in psychosis. 1 Furthermore, within the span of ten years, small local studies with few dozen participants have evolved into large multi-centre studies with several hundreds of participants. 2 , 3 , 4 , 5 In the midst of the search for accurate models, much attention has been given to methodological challenges including the impact of sample size, 6 , 7 the limitations of traditional case–control designs, 8 , 9 how to best deal with confounding variables 10 and the effects of heterogeneity 11 , 12 and inter-scanner variability, 13 just to mention a few. Although there are still important methodological challenges to overcome, substantial progress is being made, and a solution to these challenges is now considered to be a matter of when rather than if. 14 , 15 Wider discussions in the medical community about the ethical and legal implications of integrating machine learning models within diagnostic and prognostic assessment of patients are also underway. 16 , 17 , 18 , 19 , 20 Taken collectively, the progress being made towards the development and validation of neuroimaging-based machine learning models is encouraging, as if the different pieces of a very complex puzzle were slowly coming together. Less discussed however, are the challenges related to the development and validation of machine learning-based clinical tools. Here the critical distinction is between “models”, which tend to be developed and validated using a limited number of well characterised datasets with the aim of maximising accuracy, sensitivity and specificity, and “tools”, which must be feasible, acceptable and safe, and provide information that will guide clinical decision-making in real-world settings. This is a timely discussion, as a new generation of multi-centre studies aiming to develop machine learning tools to manage patients with psychosis is emerging (e.g., PSYSCAN, 21 PRONIA— www.pronia.eu ).
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Mobile sensing accuracy during weekdays was considerably lower than during the weekends, likely due to a large difference in travel time.
“Mobile sensing accuracy during weekdays was considerably lower than during the weekends, likely a large difference in travel time (between one and two minutes during weekdays compared to seven minutes during weekends) results.”
From A Review of Passenger Counting in Public Transport Concepts with Solution Proposal Based on Image Processing and Machine Learning (2024) · cites this paper as [42]
The Introduction’s “Real-world validation” section discusses lower accuracy when neuroimaging models are tested in naturalistic clinical samples, not mobile sensing or weekday–weekend differences. Searches for mobile sensing, travel time, and weekday–weekend accuracy found no passage addressing the claim; no page numbers were supplied for the indexed passages. (LLM, conf=0.77)
Experimental — accuracy not yet measuredThe approach with the sensor map resulted in generally strong results on the rear door, but this was because of an installation error of the sensor map on the front door.
“The approach with the sensor map resulted in generally strong results on the rear door, but this was because of an installation error of the sensor map on the front door.”
From A Review of Passenger Counting in Public Transport Concepts with Solution Proposal Based on Image Processing and Machine Learning (2024) · cites this paper as [42]
The Introduction’s Feasibility and Safety sections discuss neuroimaging-based clinical tools, not sensor maps or doors. Searches for a rear-door sensor map and a front-door installation error found no passage addressing the claimed results or their explanation. (LLM, conf=0.78)
Experimental — accuracy not yet measuredThe greatest impediment to counting accuracy with the sensor map was people standing on the mat while the bus was in motion.
“The greatest impediment to counting accuracy with the sensor map was people standing on the mat while the bus was in motion.”
From A Review of Passenger Counting in Public Transport Concepts with Solution Proposal Based on Image Processing and Machine Learning (2024) · cites this paper as [42]
The Introduction sections on Safety and Feasibility discuss MRI-based tools for psychosis, not passenger counting. Searches for the sensor map, people standing on a mat, and bus motion found no passage addressing the claimed impediment. (LLM, conf=0.78)
Experimental — accuracy not yet measuredThree-dimensional infrared sensing achieved similar results to video-based overall.
“Three-dimensional infrared sensing achieved similar results to video-based overall.”
From A Review of Passenger Counting in Public Transport Concepts with Solution Proposal Based on Image Processing and Machine Learning (2024) · cites this paper as [42]
The Introduction’s Feasibility section discusses neuroimaging and scanning facilities, but does not compare sensing methods. Searches for three-dimensional infrared sensing and video-based results found no passage in our copy addressing the claimed comparison. (LLM, conf=0.74)
Experimental — accuracy not yet measuredWith the video-based APC solution, the achieved results were more accurate on the front door but had a clear decline in accuracy for the rear door.
“With the video-based APC solution, the achieved results were more accurate on the front door but had a clear decline in accuracy for the rear door.”
From A Review of Passenger Counting in Public Transport Concepts with Solution Proposal Based on Image Processing and Machine Learning (2024) · cites this paper as [42]
The Real-world validation and Clinical utility sections discuss the accuracy of neuroimaging-based tools for psychosis, not video-based automatic passenger counting. Searches for the APC solution and front- versus rear-door accuracy found no passage addressing the claim. (LLM, conf=0.78)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Implementing Machine Learning in Health Care — Addressing Ethical Challenges
Char, D. S., Shah, N. H., & Magnus, D. (2018) · New England Journal of Medicine · doi:10.1056/nejmp1714229 · Cited by 1,857 · see citing works
Unintended consequences of machine learning in medicine
Cabitza, F., Rasoini, R., & Gensini, G. F. (2017) · JAMA · doi:10.1001/jama.2017.7797 · Cited by 1,066 · see citing works
Machine learning in medicine: Addressing ethical challenges
Vayena, E., Blasimme, A., & Cohen, I. G. (2018) · PLOS Medicine · doi:10.1371/journal.pmed.1002689 · Cited by 912 · see citing works
Fiske, A., Henningsen, P., & Buyx, A. (2019) · Journal of Medical Internet Research · doi:10.2196/13216 · Cited by 857 · see citing works
Understanding heterogeneity in clinical cohorts using normative models: Beyond case-control studies
Marquand, A. F., Rezek, I., Buitelaar, J., & Beckmann, C. F. (2016) · Biological Psychiatry · doi:10.1016/j.biopsych.2015.12.023 · Cited by 683 · see citing works
Four ethical priorities for neurotechnologies and AI
Yuste, R., Goering, S., Arcas, B. A. Y., Bi, G., Carmena, J. M., Carter, A., Fins, J. J., Friesen, P., Gallant, J., Huggins, J. E., et al. (2017) · Nature · doi:10.1038/551159a · Cited by 678 · see citing works
There is a blind spot in AI research
Crawford, K., & Calo, R. (2016) · Nature · doi:10.1038/538311a · Cited by 580 · see citing works
Anxiety-Related Reactions Associated With Magnetic Resonance Imaging Examinations
Meléndez, J. C. (1993) · JAMA · doi:10.1001/jama.1993.03510060091039 · Cited by 242 · see citing works
Detecting Neuroimaging Biomarkers for Psychiatric Disorders: Sample Size Matters
Schnack, H. G., & Kahn, R. S. (2016) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2016.00050 · Cited by 228 · see citing works
Kambeitz, J. P., Kambeitz‐Ilankovic, L., Leucht, S., Wood, S. J., Davatzikos, C. A., Malchow, B., Falkai, P., & Koutsouleris, N. (2015) · Neuropsychopharmacology · doi:10.1038/npp.2015.22 · Cited by 217 · see citing works
The NASSS Framework – A Synthesis of Multiple Theories of Technology Implementation
Greenhalgh, T., & Abímbọ́lá, Ṣ. (2019) · Studies in health technology and informatics · doi:10.3233/shti190123 · Cited by 205 · see citing works
Introduction to machine learning
Vieira, S., Pinaya, W. H. L., & Mechelli, A. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-815739-8.00001-8 · Cited by 203 · see citing works
Self-citationNieuwenhuis, M., van Haren, N. E. M., Pol, H. E. H., Cahn, W., Kahn, R. S., & Schnack, H. G. (2012) · NeuroImage · doi:10.1016/j.neuroimage.2012.03.079 · Cited by 186 · see citing works
Rozycki, M., Satterthwaite, T. D., Koutsouleris, N., Erus, G., Doshi, J. J., Wolf, D. H., Yong Fan, A., Gur, R. E., Gur, R. C., Meisenzahl, E. M., et al. (2017) · Schizophrenia Bulletin · doi:10.1093/schbul/sbx137 · Cited by 138 · see citing works
Predictive modelling using neuroimaging data in the presence of confounds
Rao, A. W., Monteiro, J. M., & Mourão-Miranda, J. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2017.01.066 · Cited by 114 · see citing works
Lei, D., Pinaya, W. H. L., van Amelsvoort, T., Marcelis, M. C., Donohoe, G. J., Mothersill, D., Corvin, A. P., Gill, M., Vieira, S., Huang, X., et al. (2019) · Psychological Medicine · doi:10.1017/s0033291719001934 · Cited by 101 · see citing works
Self-citationVieira, S., Gong, Q., Pinaya, W. H. L., Scarpazza, C., Tognin, S., Crespo‐Facorro, B., Tordesillas‐Gutiérrez, D., de la Foz, V. O., Setién‐Suero, E., Scheepers, F. E., et al. (2018) · Schizophrenia Bulletin · doi:10.1093/schbul/sby189 · Cited by 99 · see citing works
Self-citationTognin, S., van Hell, H. H., Merritt, K., Rossum, I. W.-V., Bossong, M. G., Kempton, M. J., Modinos, G., Fusar‐Poli, P., Mechelli, A., Dazzan, P., et al. (2019) · Schizophrenia Bulletin · doi:10.1093/schbul/sbz067 · Cited by 82 · see citing works
Self-citationSchnack, H. G. (2017) · Schizophrenia Research · doi:10.1016/j.schres.2017.10.023 · Cited by 73 · see citing works
Multi-center machine learning in imaging psychiatry: A meta-model approach
Dluhoš, P., Schwarz, D., Cahn, W., van Haren, N. E. M., Kahn, R. S., Španiel, F., Horáček, J., Kašpárek, T., & Schnack, H. G. (2017) · NeuroImage · doi:10.1016/j.neuroimage.2017.03.027 · Cited by 50 · see citing works
Patel, R., Oduola, S., Callard, F. J., Wykes, T., Broadbent, M. T. M., Stewart, R. J., Craig, T., & McGuire, P. K. (2017) · BMJ Open · doi:10.1136/bmjopen-2016-013113 · Cited by 42 · see citing works
Thomas, R. M., Bruin, W. B., Zhutovsky, P., & van Wingen, G. A. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-815739-8.00014-6 · Cited by 40 · see citing works
Clinical utility of magnetic resonance imaging in first-episode psychosis
Falkenberg, I., Benetti, S., Raffin, M., Wuyts, P., Pettersson‐Yeo, W., Dazzan, P., Morgan, K. D., Murray, R. M., Marques, T. R., David, A. S., et al. (2017) · The British Journal of Psychiatry · doi:10.1192/bjp.bp.116.195834 · Cited by 34 · see citing works
Sato, J. R., Rondina, J. M., & Mourão-Miranda, J. (2012) · Frontiers in Neuroscience · doi:10.3389/fnins.2012.00178 · Cited by 22 · see citing works
Applications of machine learning to brain disorders
Scarpazza, C., Baecker, L., Vieira, S., & Mechelli, A. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-815739-8.00003-1 · Cited by 17 · see citing works
Self-citationPomponio, R., Erus, G., Habes, M., Doshi, J., Srinivasan, D., Mamourian, E., Bashyam, V. M., Fan, Y., Launer, L., Masters, C., et al. (2019) · bioRxiv · doi:10.1101/784363 · Cited by 6 · see citing works
Ethical issues in the application of machine learning to brain disorders
Kellmeyer, P. (2019) · Elsevier eBooks · doi:10.1016/b978-0-12-815739-8.00018-3 · Cited by 5 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Machine learning for brain age prediction: Introduction to methods and clinical applications
Baecker, L., Garcia‐Dias, R., Vieira, S., Scarpazza, C., & Mechelli, A. (2021) · EBioMedicine · doi:10.1016/j.ebiom.2021.103600 · Cited by 272 · see citing works
Self-citationTranslation of AI into oncology clinical practice
Naqa, I. E., Karolak, A. M., Luo, Y., Folio, L. R., Tarhini, A. A., Rollison, D. E. M., & Parodi, K. (2023) · Oncogene · doi:10.1038/s41388-023-02826-z · Cited by 83 · see citing works
Vieira, S., Liang, X., Guiomar, R. N. R. M., & Mechelli, A. (2022) · Clinical Psychology Review · doi:10.1016/j.cpr.2022.102193 · Cited by 75 · see citing works
Self-citationPrediction Models for Obstructive Sleep Apnea in Korean Adults Using Machine Learning Techniques
Kim, Y. J., Jeon, J. S., Cho, S., Kim, K. G., & Kang, S. (2021) · Diagnostics · doi:10.3390/diagnostics11040612 · Cited by 48 · see citing works
Multivariate brain-behaviour associations in psychiatric disorders
Vieira, S., Bolton, T. A. W., Schöttner, M., Baecker, L., Marquand, A. F., Mechelli, A., & Hagmann, P. (2024) · Translational Psychiatry · doi:10.1038/s41398-024-02954-4 · Cited by 42 · see citing works
Self-citationThe potential of precision psychiatry: what is in reach?
Kambeitz-Ilankovic, L., Koutsouleris, N., & Upthegrove, R. (2022) · British Journal of Psychiatry · doi:10.1192/bjp.2022.23 · Cited by 22 · see citing works
The human role to guarantee an ethical AI in healthcare: a five-facts approach
Iniesta, R. (2023) · AI and Ethics · doi:10.1007/s43681-023-00353-x · Cited by 29 · see citing works
Li, X., Zhou, K., Xue, F., Chen, Z., Ge, Z., Chen, X., & Song, K. (2020) · Processes · doi:10.3390/pr8111480 · Cited by 25 · see citing works
Sudjai, N., Siriwanarangsun, P., Lektrakul, N., Saiviroonporn, P., Maungsomboon, S., Phimolsarnti, R., Asavamongkolkul, A., & Chandhanayingyong, C. (2023) · Diagnostics · doi:10.3390/diagnostics13020258 · Cited by 21 · see citing works
Tiwari, K. A., Raišutis, R., Liutkus, J., & Valiukevičienė, S. (2020) · Diagnostics · doi:10.3390/diagnostics10090632 · Cited by 19 · see citing works
Radovan, A., Mršić, L., Đambić, G., & Mihaljević, B. (2024) · Eng · doi:10.3390/eng5040172 · Cited by 24 · see citing works
From machine learning to deep learning: A comprehensive study of alcohol and drug use disorder
Rekabdar, B., Albright, D. L., McDaniel, J. T., Talafha, S., & Jeong, H. (2022) · Healthcare Analytics · doi:10.1016/j.health.2022.100104 · Cited by 18 · see citing works
Jiang, H., Chen, P., Sun, Z., Liang, C., Xue, R., Zhao, L., Wang, Q., Li, X., Deng, W., Gao, Z., et al. (2023) · Neuropsychopharmacology · doi:10.1038/s41386-023-01658-5 · Cited by 18 · see citing works
A multidisciplinary approach to insanity assessment as a way to reduce cognitive biases
Scarpazza, C., Zampieri, I., Miolla, A., Melis, G., Pietrini, P., & Sartori, G. (2020) · Forensic Science International · doi:10.1016/j.forsciint.2020.110652 · Cited by 16 · see citing works
Mari, T., Asgard, O., Henderson, J. R., Hewitt, D., Brown, C. A., Stančák, A., & Fallon, N. B. (2023) · Scientific Reports · doi:10.1038/s41598-022-27298-1 · Cited by 16 · see citing works
Vakitbilir, N., Islam, A., Gomez, A., Stein, K. Y., Froese, L., Bergmann, T. J. G., Sainbhi, A. S., McClarty, D., Raj, R., & Zeiler, F. A. (2024) · Sensors · doi:10.3390/s24248148 · Cited by 15 · see citing works
Computational Psychiatry Research Map (CPSYMAP): A New Database for Visualizing Research Papers
Kato, A., Kunisato, Y., Katahira, K., Okimura, T., & Yamashita, Y. (2020) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2020.578706 · Cited by 15 · see citing works
Radočaj, D., & Jurišić, M. (2025) · Fermentation · doi:10.3390/fermentation11030130 · Cited by 13 · see citing works
Tertiary Review on Explainable Artificial Intelligence: Where Do We Stand?
van Mourik, F., Jutte, A., Berendse, S. E., Bukhsh, F. A., & Ahmed, F. (2024) · Machine Learning and Knowledge Extraction · doi:10.3390/make6030098 · Cited by 13 · see citing works
Assessing Pollution with Heavy Metals and Its Impact on Population Health
Saliba, Y., & Bărbulescu, A. (2025) · Toxics · doi:10.3390/toxics13010052 · Cited by 10 · see citing works
Rail Digital Twin and Deep Learning for Passenger Flow Prediction Using Mobile Data
Ou, Y., Mihăiţă, A., Ellison, A., Mao, T., Lee, S., & Fang, C. (2025) · Electronics · doi:10.3390/electronics14122359 · Cited by 14 · see citing works
Scarpazza, C., Miolla, A., Zampieri, I., Melis, G., Sartori, G., Ferracuti, S., & Pietrini, P. (2021) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2021.597918 · Cited by 10 · see citing works
Farooq, S., Hattle, M., Kingstone, T., Ajnakina, O., Dazzan, P., Demjaha, A., Murray, R. M., Forti, M. D., Jones, P. B., Doody, G. A., et al. (2024) · The British Journal of Psychiatry · doi:10.1192/bjp.2024.101 · Cited by 9 · see citing works
Cheng, S., Yin, X. S., Gao, F., & Pan, Y. (2024) · Mathematics · doi:10.3390/math12233832 · Cited by 8 · see citing works
Mihuleţ, E., Burcea, S., Mihai, A., & Czibula, G. (2023) · Atmosphere · doi:10.3390/atmos14010182 · Cited by 8 · see citing works
Solanes, A., & Raduà, J. (2022) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2022.826111 · Cited by 4 · see citing works
Neurofind: using deep learning to make individualised inferences in brain-based disorders
Vieira, S., Baecker, L., Pinaya, W. H. L., Garcia‐Dias, R., Scarpazza, C., Calhoun, V. D., & Mechelli, A. (2025) · Translational Psychiatry · doi:10.1038/s41398-025-03290-x · Cited by 3 · see citing works
Self-citationHeo, W., Kwak, E. J., Grable, J. E., & Park, H. J. (2024) · Mathematics · doi:10.3390/math12162467 · Cited by 3 · see citing works
Krohne, L. G., Hansen, I. H., & Madsen, K. H. (2024) · Neural Computation · doi:10.1162/neco_a_01689 · Cited by 2 · see citing works
Dharejo, M. N., Kashongwe, O. B., Amon, T., Kabelitz, T., & Doherr, M. G. (2025) · Animals · doi:10.3390/ani15192825 · Cited by 1 · see citing works
Li, R., Ren, X., Jiang, T., Huo, J., Ping, J., Zhu, S., & Luo, A. (2026) · Frontiers in Psychiatry · doi:10.3389/fpsyt.2025.1724238 · Cited by 1 · see citing works
Imaging in Psychiatry: A Reappraisal of Preventative Potential
Valli, I., & Verdolini, N. (2022) · Springer eBooks · doi:10.1007/978-3-030-97906-5_14
Roy, M., Reid, R. R., Senkaiahliyan, S., Doria, A. S., Phillips, J. H., Brudno, M., & Singh, D. A. (2024) · Artificial Intelligence Surgery · doi:10.20517/ais.2024.69
Pandya, J. D., & Prajapati, B. G. (2025) · Wiley eBooks · doi:10.1002/9781394242474.ch6 · Cited by 1 · see citing works
Manshanden, A., Groot, B. C., Alaoui, N. M., Seidell, J. C., & Dijkstra, S. C. (2026) · BMC Pediatrics · doi:10.1186/s12887-026-06572-5
- Authors
- Mechelli, A., & Vieira, S.
- Affiliations
- King's College London (GB)
- Corresponding author
- Mechelli, Andrea
- Venue
- npj Schizophrenia
- Published
- 2020-02-14
- Volume
- 6
- Issue
- 1
- Pages
- 4-4
- ISSN
- 2334-265X (ISSN-L)
- PMC
- PMC7021680
- OpenAlex
- W3005801323
- Cited by
- 35
- References
- 27
- Citations by year
- 2026: 2 · 2025: 6 · 2024: 9 · 2023: 6 · 2022: 5 · 2021: 3 · 2020: 4
- FWCI
- 3.28
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- Schizophrenia (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Research Portal (King's College London) (submittedVersion, cc-by)
- Funders
- Wellcome Trust (208519/Z/17/Z)
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Schizophrenia research and treatment
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Keywords
- psychosis, machine learning, neuroimaging, clinical translation, clinical decision support systems, model validation, clinical feasibility, multicenter study
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
