Multivariate brain-cognition associations in euthymic bipolar disorder.

BACKGROUND: People with bipolar disorder (BD) tend to show widespread cognitive impairment compared to healthy controls. Impairments in processing speed (PS), attention and executive function (EF) may represent 'core' impairments that have a role in wider cognitive dysfunction. Cognitive impairments appear to relate to structural brain abnormalities in BD, but whether core deficits are related to particular brain regions is unclear and much of the research on brain-cognition associations is limited by univariate analysis and small samples. METHODS: Euthymic BD patients (n = 56) and matched healthy controls (n = 26) underwent T1-weighted MRI scans and completed neuropsychological tests of PS, attention and EF. We utilised public datasets to develop normative models of cortical thickness (n = 5977) to generate robust estimations of cortical abnormalities in patients. Canonical correlation analysis was used to assess multivariate brain-cognition associations in BD, controlling for age, sex and premorbid IQ. RESULTS: BD showed impairments on tests of PS, attention and EF, and abnormal cortical thickness in several brain regions compared to healthy controls. Impairments in tests of PS and EF were most strongly associated with cortical thickness in the left inferior temporal, right entorhinal and right temporal pole areas. CONCLUSION: Impairments in PS, attention and EF can be observed in euthymic BD and may be related to abnormal cortical thickness in temporal regions. Future research should continue to leverage normative modelling and multivariate methods to examine complex brain-cognition associations in BD. Future research may benefit from exploring covariance between traditional brain structural morphological metrics such as cortical thickness, cortical volume and surface area.

The contribution of short-term memory for sound features to speech-in-noise perception and cognition.

Speech-in-noise (SIN) perception is a fundamental ability that declines with aging, as does general cognition. We assess whether auditory cognitive ability, in particular short-term memory for sound features, contributes to both. We examined how auditory memory for fundamental sound features, the carrier frequency and amplitude modulation rate of modulated white noise, contributes to SIN perception. We assessed SIN in 153 healthy participants with varying degrees of hearing loss using measures that require single-digit perception (the Digits-in-Noise, DIN) and sentence perception (Speech-in-Babble, SIB). Independent variables were auditory memory and a range of other factors including the Pure Tone Audiogram (PTA), a measure of dichotic pitch-in-noise perception (Huggins pitch), and demographic variables including age and sex. Multiple linear regression models were compared using Bayesian Model Comparison. The best predictor model for DIN included PTA and Huggins pitch (r2 = 0.32, p < 0.001), whereas the model for SIB included the addition of auditory memory for sound features (r2 = 0.24, p < 0.001). Further analysis demonstrated that auditory memory also explained a significant portion of the variance (28 %) in scores for a screening cognitive test for dementia. Auditory memory for non-speech sounds may therefore provide an important predictor of both SIN and cognitive ability.

Outcomes of Patients With Mild Cognitive Impairment With Lewy Bodies or Alzheimer Disease at 3 and 5 Years After Diagnosis.

BACKGROUND AND OBJECTIVES: Retrospective studies indicate that dementia with Lewy bodies (DLB) may be preceded by a mild cognitive impairment (MCI) prodrome. Research criteria for the prospective identification of MCI with Lewy bodies (MCI-LB) have been developed. We aimed to assess the prognosis of a prospectively identified MCI-LB cohort at 2 key milestones, 3- and 5 years after diagnosis, to examine classification stability over time and rates of adverse outcomes (dementia or death). METHODS: This was a retrospective examination of data from 2 longitudinal observational cohort studies where participants with MCI were prospectively recruited from North East England and differentially classified as MCI due to Alzheimer disease (MCI-AD), possible MCI-LB, or probable MCI-LB. Adverse outcomes (DLB/other dementia or death) and stability of disease-specific classifications were examined in each group. RESULTS: Of 152 participants with baseline MCI (54 MCI-AD, 29 possible MCI-LB, and 69 probable MCI-LB), 126 were followed for up to 3 years (mean age 75.3 years; 40% female). We found that prospective probable MCI-LB classifications were both sensitive (91%) and specific (94%) to classifications either remaining as probable MCI-LB or progressing to DLB (in some cases autopsy confirmed) for 3 or more years after. Classifications were at least as stable as those in MCI-AD. In this cohort with disease-specific MCI classifications, rates of progression to dementia were high: 55% of MCI-LB had developed DLB within 3 years. Dementia occurred in 47% of MCI-AD over the same duration (odds ratio 1.68, 95% CI 0.66-4.26, p = 0.278). Premature death was a common competing risk, occurring in 9% of MCI-AD and 11% of MCI-LB within 3 years. DISCUSSION: These findings support that prospectively identified probable MCI-LB is a prodromal presentation of DLB and that disease-specific classifications of MCI may reliably identify different prodromal dementias.

Brain Morphology Normative modelling platform for abnormality and Centile estimation: Brain MoNoCle.

Normative models of brain structure estimate the effects of covariates such as age and sex using large samples of healthy controls. These models can then be applied to smaller clinical cohorts to distinguish disease effects from other covariates. However, these advanced statistical modelling approaches can be difficult to access, and processing large healthy cohorts is computationally demanding. Thus, accessible platforms with pre-trained normative models are needed. We present such a platform for brain morphology analysis as an open-source web application https://cnnplab.shinyapps.io/normativemodelshiny/, with six key features: (i) user-friendly web interface, (ii) individual and group outputs, (iii) multi-site analysis, (iv) regional and whole-brain analysis, (v) integration with existing tools, and (vi) featuring multiple morphology metrics. Using a diverse sample of 3,276 healthy controls across 21 sites, we pre-trained normative models on various metrics. We validated the models with a small clinical sample of individuals with bipolar disorder, showing outputs that aligned closely with existing literature only after applying our normative modelling. Further validation with a cohort of temporal lobe epilepsy showed agreement with previous group-level findings and individual-level seizure lateralisation. Finally, with the ability to investigate multiple morphology measures in the same framework, we found that biological covariates are better explained in specific morphology measures, and for clinical applications, only some measures are sensitive to the disease process. Our platform offers a comprehensive framework to analyse brain morphology in clinical and research settings. Validations confirm the superiority of normative models and the advantage of investigating a range of brain morphology metrics together.

Advanced qEEG analyses discriminate between dementia subtypes.

BACKGROUND: Dementia is caused by neurodegenerative conditions and characterized by cognitive decline. Diagnostic accuracy for dementia subtypes, such as Alzheimer's Disease (AD), Dementia with Lewy Bodies (DLB) and Parkinson's Disease with dementia (PDD), remains challenging. METHODS: Here, different methods of quantitative electroencephalography (qEEG) analyses were employed to assess their effectiveness in distinguishing dementia subtypes from healthy controls under eyes closed (EC) and eyes open (EO) conditions. RESULTS: Classic Fast-Fourier Transform (FFT) and autoregressive (AR) power analyses differentiated between all conditions for the 4-8 Hz theta range. Only individuals with dementia with Lewy Bodies (DLB) differed from healthy subjects for the wider 4-15 Hz frequency range, encompassing the actual dominant frequency of all individuals. FFT results for this range yielded wider significant discriminators vs AR, also detecting differences between AD and DLB. Analyses of the inclusive dominant / peak frequency range (4-15 Hz) indicated slowing and reduced variability, also discriminating between synucleinopathies vs controls and AD. Dissociation of periodic oscillations and aperiodic components of AR spectra using Fitting-Oscillations-&-One-Over-F (FOOOF) modelling delivered a reliable and subtype-specific slowing of brain oscillatory peaks during EC and EO for all groups. Distinct and robust differences were particularly strong for aperiodic parameters, suggesting their potential diagnostic power in detecting specific changes resulting from age and cognitive status. CONCLUSION: Our findings indicate that qEEG methods can reliably detect dementia subtypes. Spectral analyses comprising an integrated, multi-parameter EEG approach discriminating between periodic and aperiodic components under EC and EO conditions may enhance diagnostic accuracy in the future.

Subjective hearing loss is not associated with an increased risk of Alzheimer's disease dementia.

Hearing loss is a risk-factor for dementia but the reasons for this are unclear. Subjective hearing loss is related to increased future dementia risk, however, this metric has not been previously examined with cognitive, neuroimaging and biochemical measures that are relevant to Alzheimer's disease. We assessed Cognitively Normal and Mild Cognitively Impaired participants from the Alzheimer's Disease Neuroimaging Initiative with subjective hearing loss to examine if they had faster decline in episodic memory scores, hippocampal volume and greater pTau positivity. The likelihood of a dementia diagnosis in hearing impaired participants over a 5-year period was also assessed. There were no statistically significant differences between the hearing subgroups over a 5-year period nor were there in conversions to a dementia diagnosis. Objective hearing loss metrics may provide a more reliable link between hearing loss and dementia risk.

Associations between multimorbidity and neuropathology in dementia: consideration of functional cognitive disorders, psychiatric illness and dementia mimics.

BACKGROUND: Multimorbidity, the presence of two or more health conditions, has been identified as a possible risk factor for clinical dementia. It is unclear whether this is due to worsening brain health and underlying neuropathology, or other factors. In some cases, conditions may reflect the same disease process as dementia (e.g. Parkinson's disease, vascular disease), in others, conditions may reflect a prodromal stage of dementia (e.g. depression, anxiety and psychosis). AIMS: To assess whether multimorbidity in later life was associated with more severe dementia-related neuropathology at autopsy. METHOD: We examined ante-mortem and autopsy data from 767 brain tissue donors from the UK, identifying physical multimorbidity in later life and specific brain-related conditions. We assessed associations between these purported risk factors and dementia-related neuropathological changes at autopsy (Alzheimer's-disease related neuropathology, Lewy body pathology, cerebrovascular disease and limbic-predominant age-related TDP-43 encephalopathy) with logistic models. RESULTS: Physical multimorbidity was not associated with greater dementia-related neuropathological changes. In the presence of physical multimorbidity, clinical dementia was less likely to be associated with Alzheimer's disease pathology. Conversely, conditions which may be clinical or prodromal manifestations of dementia-related neuropathology (Parkinson's disease, cerebrovascular disease, depression and other psychiatric conditions) were associated with dementia and neuropathological changes. CONCLUSIONS: Physical multimorbidity alone is not associated with greater dementia-related neuropathological change; inappropriate inclusion of brain-related conditions in multimorbidity measures and misdiagnosis of neurodegenerative dementia may better explain increased rates of clinical dementia in multimorbidity.

Delirium is more common and associated with worse outcomes in Parkinson's disease compared to older adult controls: results of two prospective longitudinal cohort studies.

BACKGROUND: Inpatient prevalence of Parkinson's disease (PD) delirium varies widely across the literature. Delirium in general older populations is associated with adverse outcomes, such as increased mortality, dementia, and institutionalisation. However, to date there are no comprehensive prospective studies in PD delirium. This study aimed to determine delirium prevalence in hospitalised PD participants and the association with adverse outcomes, compared to a control group of older adults without PD. METHODS: Participants were hospitalised inpatients from the 'Defining Delirium and its Impact in Parkinson's Disease' and the 'Delirium and Cognitive Impact in Dementia' studies comprising 121 PD participants and 199 older adult controls. Delirium was diagnosed prospectively using the Diagnostic and Statistical Manual of Mental Disorders 5th Edition criteria. Outcomes were determined by medical note reviews and/or home visits 12 months post hospital discharge. RESULTS: Delirium was identified in 66.9% of PD participants compared to 38.7% of controls (p < 0.001). In PD participants only, delirium was associated with a significantly higher risk of mortality (HR = 3.3 (95% confidence interval [CI] = 1.3-8.6), p = 0.014) and institutionalisation (OR = 10.7 (95% CI = 2.1-54.6), p = 0.004) 12 months post-discharge, compared to older adult controls. However, delirium was associated with an increased risk of developing dementia 12 months post-discharge in both PD participants (OR = 6.1 (95% CI = 1.3-29.5), p = 0.024) and in controls (OR = 13.4 (95% CI = 2.5-72.6), p = 0.003). CONCLUSION: Delirium is common in hospitalised PD patients, affecting two thirds of patients, and is associated with increased mortality, institutionalisation, and dementia. Further research is essential to understand how to accurately identify, prevent and manage delirium in people with PD who are in hospital.

Cholinergic changes in Lewy body disease: implications for presentation, progression and subtypes.

Cholinergic degeneration is significant in Lewy body disease, including Parkinson's disease, dementia with Lewy bodies, and isolated REM sleep behaviour disorder. Extensive research has demonstrated cholinergic alterations in the CNS of these disorders. More recently, studies have revealed cholinergic denervation in organs that receive parasympathetic denervation. This enables a comprehensive review of cholinergic changes in Lewy body disease, encompassing both central and peripheral regions, various disease stages and diagnostic categories. Across studies, brain regions affected in Lewy body dementia show equal or greater levels of cholinergic impairment compared to the brain regions affected in Lewy body disease without dementia. This observation suggests a continuum of cholinergic alterations between these disorders. Patients without dementia exhibit relative sparing of limbic regions, whereas occipital and superior temporal regions appear to be affected to a similar extent in patients with and without dementia. This implies that posterior cholinergic cell groups in the basal forebrain are affected in the early stages of Lewy body disorders, while more anterior regions are typically affected later in the disease progression. The topographical changes observed in patients affected by comorbid Alzheimer pathology may reflect a combination of changes seen in pure forms of Lewy body disease and those seen in Alzheimer's disease. This suggests that Alzheimer co-pathology is important to understand cholinergic degeneration in Lewy body disease. Thalamic cholinergic innervation is more affected in Lewy body patients with dementia compared to those without dementia, and this may contribute to the distinct clinical presentations observed in these groups. In patients with Alzheimer's disease, the thalamus is variably affected, suggesting a different sequential involvement of cholinergic cell groups in Alzheimer's disease compared to Lewy body disease. Patients with isolated REM sleep behaviour disorder demonstrate cholinergic denervation in abdominal organs that receive parasympathetic innervation from the dorsal motor nucleus of the vagus, similar to patients who experienced this sleep disorder in their prodrome. This implies that REM sleep behaviour disorder is important for understanding peripheral cholinergic changes in both prodromal and manifest phases of Lewy body disease. In conclusion, cholinergic changes in Lewy body disease carry implications for understanding phenotypes and the influence of Alzheimer co-pathology, delineating subtypes and pathological spreading routes, and for developing tailored treatments targeting the cholinergic system.

Instrumental variables in real-world clinical studies of dementia and neurodegenerative disease: Systematic review of the subject-matter argumentation, falsification test, and study design strategies to justify a valid instrument.

OBJECTIVES: We systematically reviewed how investigators argued for and justified the validity of their instrumental variables (IV) in clinical studies of dementia and neurodegenerative disease. METHODS: We included studies using IV analysis with observational data to investigate causal effects in clinical research studies of dementia and neurodegenerative disease. We reported the subject-matter argumentation, falsification test, and study design strategies used to satisfy the three assumptions of a valid IV: relevance, exclusion restriction, and exchangeability. RESULTS: Justification for the relevance assumption was performed in all 12 included studies, exclusion restriction in seven studies, and exchangeability in nine studies. Two subject-matter argumentation strategies emerged from seven studies on the relevance of their IV. All studies except one provided quantitative evidence for the strength of the association between the IV and exposure variable. Four argumentation strategies emerged for exclusion restriction from six studies. Four falsification tests were performed across three studies. Three argumentation strategies emerged for exchangeability across four studies. Nine falsification tests were performed across nine studies. Two notable study design strategies were reported. CONCLUSION: Our results reinforce IV analysis as a feasible option for clinical researchers in dementia and neurodegenerative disease by clarifying known strategies used to validate an IV.

Identifying parkinsonism in mild cognitive impairment.

INTRODUCTION: Clinical parkinsonism is a core diagnostic feature for mild cognitive impairment with Lewy bodies (MCI-LB) but can be challenging to identify. A five-item scale derived from the Unified Parkinson's Disease Rating Scale (UPDRS) has been recommended for the assessment of parkinsonism in dementia. This study aimed to determine whether the five-item scale is effective to identify parkinsonism in MCI. METHODS: Participants with MCI from two cohorts (n = 146) had a physical examination including the UPDRS and [123I]-FP-CIT SPECT striatal dopaminergic imaging. Participants were classified as having clinical parkinsonism (P+) or no parkinsonism (P-), and with abnormal striatal dopaminergic imaging (D+) or normal imaging (D-). The five-item scale was the sum of UPDRS tremor at rest, bradykinesia, action tremor, facial expression, and rigidity scores. The ability of the scale to differentiate P+D+ and P-D- participants was examined. RESULTS: The five-item scale had an AUROC of 0.92 in Cohort 1, but the 7/8 cut-off defined for dementia had low sensitivity to identify P+D+ participants (sensitivity 25%, specificity 100%). Optimal sensitivity and specificity was obtained at a 3/4 cut-off (sensitivity 83%, specificity 88%). In Cohort 2, the five-item scale had an AUROC of 0.97, and the 3/4 cut-off derived from Cohort 1 showed sensitivity of 100% and a specificity of 82% to differentiate P+D+ from P-D- participants. The five-item scale was not effective in differentiating D+ from D- participants. CONCLUSIONS: The five-item scale is effective to identify parkinsonism in MCI, but a lower threshold must be used in MCI compared with dementia.

Lewy body dementia: Overcoming barriers and identifying solutions.

Despite its high prevalence among dementias, Lewy body dementia (LBD) remains poorly understood with a limited, albeit growing, evidence base. The public-health burden that LBD imposes is worsened by overlapping pathologies, which contribute to misdiagnosis, and lack of treatments. For this report, we gathered and analyzed public-domain information on advocacy, funding, research outputs, and the therapeutic pipeline to identify gaps in each of these key elements. To further understand the current gaps, we also conducted interviews with leading experts in regulatory/governmental agencies, LBD advocacy, academic research, and biopharmaceutical research, as well as with funding sources. We identified wide gaps across the entire landscape, the most critical being in research. Many of the experts participated in a workshop to discuss the prioritization of research areas with a view to accelerating therapeutic development and improving patient care. This white paper outlines the opportunities for bridging the major LBD gaps and creates the framework for collaboration in that endeavor. HIGHLIGHTS: A group representing academia, government, industry, and consulting expertise was convened to discuss current progress in Dementia with Lewy Body care and research. Consideration of expert opinion,natural language processing of the literature as well as publicly available data bases, and Delphi inspired discussion led to a proposed consensus document of priorities for the field.

Functional connectivity in Lewy body disease with visual hallucinations.

BACKGROUND AND PURPOSE: Visual hallucinations are a common, potentially distressing experience of people with Lewy body disease (LBD). The underlying brain changes giving rise to visual hallucinations are not fully understood, although previous models have posited that alterations in the connectivity between brain regions involved in attention and visual processing are critical. METHODS: Data from 41 people with LBD and visual hallucinations, 48 with LBD without visual hallucinations and 60 similarly aged healthy comparator participants were used. Connections were investigated between regions in the visual cortex and ventral attention, dorsal attention and default mode networks. RESULTS: Participants with visual hallucinations had worse cognition and motor function than those without visual hallucinations. In those with visual hallucinations, reduced functional connectivity within the ventral attention network and from the visual to default mode network was found. Connectivity strength between the visual and default mode network correlated with the number of correct responses on a pareidolia task, and connectivity within the ventral attention network with visuospatial performance. CONCLUSIONS: Our results add to evidence of dysfunctional connectivity in the visual and attentional networks in those with LBD and visual hallucinations.

A systematic literature review of fMRI and EEG resting-state functional connectivity in Dementia with Lewy Bodies: Underlying mechanisms, clinical manifestation, and methodological considerations.

Previous studies suggest that there may be important links between functional connectivity, disease mechanisms underpinning the Dementia with Lewy Body (DLB) and the key clinical symptoms, but the exact relationship remains unclear. We performed a systematic literature review to address this gap by summarising the research findings while critically considering the impact of methodological differences on findings. The main methodological choices of fMRI articles included data-driven, seed-based or regions of interest approaches, or their combinations. Most studies focused on examining large-scale resting-state networks, which revealed a consistent decrease in connectivity and some associations with non-cognitive symptoms. Although the inter-network connectivity showed mixed results, the main finding is consistent with theories positing disconnection between visual and attentional areas of the brain implicated in the aetiology of psychotic symptoms in the DLB. The primary methodological choice of EEG studies was implementing the phase lag index and using graph theory. The EEG studies revealed a consistent decrease in connectivity on alpha and beta frequency bands. While the overall trend of findings showed decreased connectivity, more subtle changes in the directionality of connectivity were observed when using a hypothesis-driven approach. Problems with cognition were also linked with greater functional connectivity disturbances. In summary, connectivity measures can capture brain disturbances in the DLB and remain crucial in uncovering the causal relationship between the networks' disorganisation and underlying mechanisms resulting in psychotic, motor, and cognitive symptoms of the DLB.

Sex differences in brain atrophy in dementia with Lewy bodies.

INTRODUCTION: Sex influences neurodegeneration, but it has been poorly investigated in dementia with Lewy bodies (DLB). We investigated sex differences in brain atrophy in DLB using magnetic resonance imaging (MRI). METHODS: We included 436 patients from the European-DLB consortium and the Mayo Clinic. Sex differences and sex-by-age interactions were assessed through visual atrophy rating scales (n = 327; 73 ± 8 years, 62% males) and automated estimations of regional gray matter volume and cortical thickness (n = 165; 69 ± 9 years, 72% males). RESULTS: We found a higher likelihood of frontal atrophy and smaller volumes in six cortical regions in males and thinner olfactory cortices in females. There were significant sex-by-age interactions in volume (six regions) and cortical thickness (seven regions) across the entire cortex. DISCUSSION: We demonstrate that males have more widespread cortical atrophy at younger ages, but differences tend to disappear with increasing age, with males and females converging around the age of 75. HIGHLIGHTS: Male DLB patients had higher odds for frontal atrophy on radiological visual rating scales. Male DLB patients displayed a widespread pattern of cortical gray matter alterations on automated methods. Sex differences in gray matter measures in DLB tended to disappear with increasing age.

Poor reactivity of posterior electroencephalographic alpha rhythms during the eyes open condition in patients with dementia due to Parkinson's disease.

Here, we hypothesized that the reactivity of posterior resting-state electroencephalographic (rsEEG) alpha rhythms during the transition from eyes-closed to -open condition might be lower in patients with Parkinson's disease dementia (PDD) than in patients with Alzheimer's disease dementia (ADD). A Eurasian database provided clinical-demographic-rsEEG datasets in 73 PDD patients, 35 ADD patients, and 25 matched cognitively unimpaired (Healthy) persons. The eLORETA freeware was used to estimate cortical rsEEG sources. Results showed substantial (greater than -10%) reduction (reactivity) in the posterior alpha source activities from the eyes-closed to the eyes-open condition in 88% of the Healthy seniors, 57% of the ADD patients, and only 35% of the PDD patients. In these alpha-reactive participants, there was lower reactivity in the parietal alpha source activities in the PDD group than in the healthy control seniors and the ADD patients. These results suggest that PDD patients show poor reactivity of mechanisms desynchronizing posterior rsEEG alpha rhythms in response to visual inputs. That neurophysiological biomarker may provide an endpoint for (non) pharmacological interventions for improving vigilance regulation in those patients.

Sustained attention in mild cognitive impairment with Lewy bodies and Alzheimer's disease.

OBJECTIVE: Attentional impairments are common in dementia with Lewy bodies and its prodromal stage of mild cognitive impairment (MCI) with Lewy bodies (MCI-LB). People with MCI may be capable of compensating for subtle attentional deficits in most circumstances, and so these may present as occasional lapses of attention. We aimed to assess the utility of a continuous performance task (CPT), which requires sustained attention for several minutes, for measuring attentional performance in MCI-LB in comparison to Alzheimer's disease (MCI-AD), and any performance deficits which emerged with sustained effort. METHOD: We included longitudinal data on a CPT sustained attention task for 89 participants with MCI-LB or MCI-AD and 31 healthy controls, estimating ex-Gaussian response time parameters, omission and commission errors. Performance trajectories were estimated both cross-sectionally (intra-task progress from start to end) and longitudinally (change in performance over years). RESULTS: While response times in successful trials were broadly similar, with slight slowing associated with clinical parkinsonism, those with MCI-LB made considerably more errors. Omission errors were more common throughout the task in MCI-LB than MCI-AD (OR 2.3, 95% CI: 1.1-4.7), while commission errors became more common after several minutes of sustained attention. Within MCI-LB, omission errors were more common in those with clinical parkinsonism (OR 1.9, 95% CI: 1.3-2.9) or cognitive fluctuations (OR 4.3, 95% CI: 2.2-8.8). CONCLUSIONS: Sustained attention deficits in MCI-LB may emerge in the form of attentional lapses leading to omissions, and a breakdown in inhibitory control leading to commission errors.

Differential diagnosis of neurodegenerative dementias with the explainable MRI based machine learning algorithm MUQUBIA.

Biomarker-based differential diagnosis of the most common forms of dementia is becoming increasingly important. Machine learning (ML) may be able to address this challenge. The aim of this study was to develop and interpret a ML algorithm capable of differentiating Alzheimer's dementia, frontotemporal dementia, dementia with Lewy bodies and cognitively normal control subjects based on sociodemographic, clinical, and magnetic resonance imaging (MRI) variables. 506 subjects from 5 databases were included. MRI images were processed with FreeSurfer, LPA, and TRACULA to obtain brain volumes and thicknesses, white matter lesions and diffusion metrics. MRI metrics were used in conjunction with clinical and demographic data to perform differential diagnosis based on a Support Vector Machine model called MUQUBIA (Multimodal Quantification of Brain whIte matter biomArkers). Age, gender, Clinical Dementia Rating (CDR) Dementia Staging Instrument, and 19 imaging features formed the best set of discriminative features. The predictive model performed with an overall Area Under the Curve of 98%, high overall precision (88%), recall (88%), and F1 scores (88%) in the test group, and good Label Ranking Average Precision score (0.95) in a subset of neuropathologically assessed patients. The results of MUQUBIA were explained by the SHapley Additive exPlanations (SHAP) method. The MUQUBIA algorithm successfully classified various dementias with good performance using cost-effective clinical and MRI information, and with independent validation, has the potential to assist physicians in their clinical diagnosis.