Beyond group classification: probabilistic differential diagnosis of frontotemporal dementia and Alzheimer’s disease with MRI and CSF biomarkers
Open accessAbstract
Abstract Background Neuroimaging and fluid biomarkers are used in clinics to differentiate frontotemporal dementia (FTD) from Alzheimer’s disease (AD) and other neurodegenerative and non-neurodegenerative disorders. We implemented a machine learning (ML) algorithm that provides individual probabilistic scores for these patients based on magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) data. Methods We used a calibrated classifier with a Support Vector Machine with MRI data. We obtained group classifications and individual probabilities associated with group correspondence. We used the individual probabilities to address the clinical problem of confidence in the diagnosis. We investigated whether combining MRI and CSF levels of Neurofilament light (NfL) and 14-3-3 could improve the diagnosis confidence. Results 215 AD patients (65 ± 10 years, 137 women), 103 FTD patients (64 ± 8 years, 49 women), and 173 healthy controls (CTR) (59 ± 15 years, 106 women) were studied. With MRI data only, we obtained accuracies of 88% in the AD vs. healthy controls (CTR) classification, 87% for FTD vs. CTR, 82% for AD vs. FTD, and 80% when differentiating the three groups. A total of 74% of FTD and 73% of AD participants have a high (≥ 0.8) probability of accurate diagnosis in the FTD vs. AD comparison. Adding CSF-NfL and 14-3-3 levels slightly improved the accuracy and the number of patients in the high diagnosis confidence group. Conclusion We propose a ML algorithm that provides individual diagnostic probabilities, and we validate it using MRI and/or CSF data. Our solution holds promise towards clinical applications as support to clinical findings or in settings with limited access to expert diagnoses.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
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?
Supervised ML models, particularly SVMs, achieved 84.5-92.6% accuracy in distinguishing FTD from AD and healthy controls by leveraging combinations of neuropsychological assessments, PET imaging, and demographic data.
“Supervised ML models, particularly SVMs, have achieved high accuracy (84.5–92.6%) in distinguishing FTD from AD and healthy controls by leveraging combinations of neuropsychological assessments, PET imaging, and demographic data”
From Multimodal neuroimaging and AI integration in cognitive disorders: advances, challenges, and future directions for precision medicine (2026) · cites this paper as Pérez-Millan et al., 2024
Cites
Rates of hippocampal atrophy correlate with change in clinical status in aging and AD
Jack, C. R., Petersen, R. C., Xu, Y., O’Brien, P. C., Smith, G. E., Ivnik, R. J., Boeve, B. F., Tangalos, E. G., & Kokmen, E. (2000) · Neurology · doi:10.1212/wnl.55.4.484 · Cited by 937 · see citing works
Clinical, genetic and pathological heterogeneity of frontotemporal dementia: A review
Seelaar, H., Rohrer, J. D., Pijnenburg, Y. A. L., Fox, N. C., & van Swieten, J. C. (2011) · Journal of Neurology, Neurosurgery & Psychiatry · doi:10.1136/jnnp.2010.212225 · Cited by 609 · see citing works
Möller, C., Pijnenburg, Y. A. L., van der Flier, W. M., Versteeg, A., Tijms, B., de Munck, J. C., Hafkemeijer, A., Rombouts, S. A. R. B., van der Grond, J., van Swieten, J., et al. (2016) · Radiology · doi:10.1148/radiol.2015150220 · Cited by 103 · see citing works
Kim, J. P., Kim, J., Park, Y. H., Park, S. B., Lee, J. S., Yoo, S., Kim, E.-J., Kim, H. J., Na, D. L., Brown, J. A., et al. (2019) · NeuroImage: Clinical · doi:10.1016/j.nicl.2019.101811 · Cited by 100 · see citing works
Clinicopathologic differences among patients with behavioral variant frontotemporal dementia
Mendez, M. F., Joshi, A., Tassniyom, K., Teng, E., & Shapira, J. S. (2013) · Neurology · doi:10.1212/wnl.0b013e3182815547 · Cited by 96 · see citing works
Meyer, S., Mueller, K., Stuke, K., Bisenius, S., Diehl-Schmid, J., Jessen, F., Kassubek, J., Kornhuber, J., Ludolph, A. C., Prudlo, J., et al. (2017) · NeuroImage: Clinical · doi:10.1016/j.nicl.2017.02.001 · Cited by 83 · see citing works
Garcia‐Gutierrez, F., Delgado‐Alvarez, A., Delgado‐Alonso, C., Díaz‐Álvarez, J., Pytel, V., Valles‐Salgado, M., Gil, M. J., Hernández‐Lorenzo, L., Matías‐Guiu, J., Ayala, J. L., et al. (2022) · International Journal of Geriatric Psychiatry · doi:10.1002/gps.5667 · Cited by 56 · see citing works
McCarthy, J., Collins, D. L., & Ducharme, S. (2018) · NeuroImage: Clinical · doi:10.1016/j.nicl.2018.08.028 · Cited by 47 · see citing works
Deep grading for MRI-based differential diagnosis of Alzheimer’s disease and frontotemporal dementia
Nguyen, H.-D., Clément, M., Planche, V., Mansencal, B., & Coupé, P. (2023) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2023.102636 · Cited by 35 · see citing works
Wang, J., Redmond, S. J., Bertoux, M., Hodges, J. R., & Hornberger, M. (2016) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2016.00119 · Cited by 35 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Dattola, S., Ielo, A., Varone, G., Cacciola, A., Quartarone, A., & Bonanno, L. (2025) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2025.1547727 · Cited by 14 · see citing works
Dang, M., Liu, B., Chen, Y., & Zhang, Z. (2026) · Psychoradiology · doi:10.1093/psyrad/kkag007 · Cited by 7 · see citing works
Microfluidic platform for understanding Parkinson’s disease and α-synuclein conformation
Tregub, P. P., Zembatov, G. M., Namiot, E., Natalia, K., Stanislav, Y., Sergey, I., & Salmina, A. B. (2025) · Translational Neurodegeneration · doi:10.1186/s40035-025-00526-0 · Cited by 3 · see citing works
“At the same time, it is known that signs of synucleopathy can be observed many years before the clinical manifestation of the disease and morphological manifestations [12].”
Clinical pathways matter for multimodal deep learning in early Alzheimer’s disease detection
Lu, Y., Hammonds, S. K., & Fernandez-Quilez, A. (2026) · Scientific Reports · doi:10.1038/s41598-026-57861-z · Cited by 1
Zhang, P.-F., Juan, Z., Han, J.-L., Wang, Y., Zhu, T.-S., Pang, D.-Y., Zheng, X., & Lu, Z.-M. (2026) · European Archives of Psychiatry and Clinical Neuroscience · doi:10.1007/s00406-026-02338-3
Kang, H., Kang, J., Zeki, M., & Seo, J. (2026) · Frontiers in Neuroscience · doi:10.3389/fnins.2026.1871265
Misra, R., Khokhar, S. K., Kumar, M., Arshad, F., Thanissery, N., Kumar, S., Manae, T. S., Ramakrishnan, S., Haris, M., Mangalore, S., et al. (2026) · Translational Insights · doi:10.53941/ti.2026.100011
“Neuroimaging techniques such as magnetic resonance imaging (MRI) and [18-”
A Comprehensive Study of Deep Learning Techniques for Early Detection of Frontotemporal Dementia
M, A., S, R., & Kumar, G. K. (2026) · 2026 6th International Conference on Pervasive Computing and Social Networking (ICPCSN) · doi:10.1109/icpcsn68523.2026.11543797
“Frontotemporal Dementia and Alzheimer disease are neurodegenerative diseases [1], whose pathological processes differ, and thus clinical manifestations overlap, which creates problems with their differentiation.”
InfluentialInnover pour mieux vieillir : place des gérontechnologies dans les parcours de soins
Hanon, O., Dufour, I., & Rmadi, H. (2026) · Bulletin de l'Académie Nationale de Médecine · doi:10.1016/j.banm.2026.01.024
Shakenova, A. M., & Медетова, Г. Л. (2026) · Ġylym men densaulyķ saķtau. · doi:10.34689/sh.2026.28.2.028
Intel·ligència artificial en biomedicina
Sala‐Llonch, R. (2026) · Compàs d amalgama · doi:10.1344/compas2026.13.7
Self-citation
- Authors
- Pérez-Millan, A., Thirion, B., Falgàs, N., Borrego-Écija, S., Bosch, B., Juncà-Parella, J., Tort-Merino, A., Sarto, J., Augé, J. M., Antonell, A., Bargalló, N., Balasa, M., Lladó, A., Sánchez-Valle, R., & Sala-Llonch, R.
- Affiliations
- Institut national de recherche en sciences et technologies du numérique (FR)
- Hospital Clínic de Barcelona (ES)
- Venue
- Neurobiology of Aging
- Publisher
- Elsevier BV
- Published
- 2024-12
- Volume
- 144
- Pages
- 1-11
- ISSN
- 0197-4580 (ISSN-L)
- OpenAlex
- W4402041968
- Cited by
- 10
- References
- 91
- Citations by year
- 2026: 7 · 2025: 3
- FWCI
- 2.95
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Neurobiology of Aging (publishedVersion, cc-by-nc)
- Research Square (acceptedVersion, cc-by)
- PubMed (publishedVersion)
- HAL (submittedVersion, cc-by)
- Dipòsit Digital de la Universitat de Barcelona (Universitat de Barcelona) (submittedVersion, cc-by-nc)
- Funders
- Instituto de Salud Carlos III (PI19/00198, PI20/0448, PI19/00449)
- H2020 (101058516)
- Generalitat de Catalunya (SGR 2021- 01126)
- European Commission
- H2020 Research Infrastructures
- French National Research Agency (ANR-20-CHIA-0025-01)
- Fundación BBVA
- Ministerio de Ciencia e Innovación
- Universitat de Barcelona (MDM-2017-0729)
- Generalitat de Catalunya Agència de Gestió d'Ajuts Universitaris i de Recerca (2021 SGR 00523)
- Gobierno de España Agencia Estatal de Investigación (CEX2021-001159-M, PID2020-118386RA-I00/ AEI/10.13039/501100011033)
- Topics
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Health Sciences › Medicine › Physiology › Alzheimer's disease research and treatments
- Health Sciences › Medicine › Neurology › Amyotrophic Lateral Sclerosis Research
- Keywords
- frontotemporal dementia, Alzheimer's disease, differential diagnosis, probabilistic diagnosis, machine learning, MRI biomarkers, cerebrospinal fluid biomarkers, neurofilament light chain, diagnostic confidence, neurodegenerative dementia
- MeSH terms
- Machine Learning, Aged, Algorithms, Alzheimer Disease, Diagnosis, Differential, Female, Humans, Magnetic Resonance Imaging, Male, Middle Aged, Probability, Biomarkers, Frontotemporal Dementia, Neuroimaging
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
