Beyond group classification: Probabilistic differential diagnosis of frontotemporal dementia and Alzheimer’s disease with MRI and CSF biomarkers

• Published in: Neurobiology of aging 2024-12, Vol.144, p.1-11
• Main Authors: Pérez-Millan, Agnès, Thirion, Bertrand, Falgàs, Neus, Borrego-Écija, Sergi, Bosch, Beatriz, Juncà-Parella, Jordi, Tort-Merino, Adrià, Sarto, Jordi, Augé, Josep Maria, Antonell, Anna, Bargalló, Nuria, Balasa, Mircea, Lladó, Albert, Sánchez-Valle, Raquel, Sala-Llonch, Roser
• Format: Article
• Language: English
• Subjects: Aged; Algorithms; Alzheimer Disease - cerebrospinal fluid; Alzheimer Disease - diagnosis; Alzheimer Disease - diagnostic imaging; Alzheimer's disease; Biomarkers - cerebrospinal fluid; Cognitive science; CSF biomarkers; Diagnosis, Differential; Female; frontotemporal dementia; Frontotemporal Dementia - cerebrospinal fluid; Frontotemporal Dementia - diagnosis; Frontotemporal Dementia - diagnostic imaging; Humans; individual probability; Machine Learning; magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Middle Aged; Neuroimaging - methods; Neuroscience; Probability
• ISSN: 0197-4580; 1558-1497; 1558-1497
• DOI: 10.1016/j.neurobiolaging.2024.08.008

Neuroimaging and fluid biomarkers are used to differentiate frontotemporal dementia (FTD) from Alzheimer’s disease (AD). We implemented a machine learning algorithm that provides individual probabilistic scores based on magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) data. We investigated whether combining MRI and CSF levels could improve the diagnosis confidence. 215 AD patients, 103 FTD patients, and 173 healthy controls (CTR) were studied. With MRI data, we obtained an accuracy of 82 % for AD vs. FTD. A total of 74 % of FTD and 73 % of AD participants have a high probability of accurate diagnosis. Adding CSF-NfL and 14–3–3 levels improved the accuracy and the number of patients in the confidence group for differentiating FTD from AD. We obtain individual diagnostic probabilities with high precision to address the problem of confidence in the diagnosis. We suggest when MRI, CSF, or the combination are necessary to improve the FTD and AD diagnosis. This algorithm holds promise towards clinical applications as support to clinical findings or in settings with limited access to expert diagnoses. •Machine Learning applied to structural MRI features differentiates FTD from AD.•Probabilistic ML allows the distribution of cases along a spectrum between groups.•Combining MRI and CSF improves accuracy and confidence in diagnosing FTD from AD.