Subcortical tau is linked to hypoperfusion in connected cortical regions in 4-repeat tauopathies.

4-repeat (4R) tauopathies are neurodegenerative diseases characterized by cerebral accumulation of 4R tau pathology. The most prominent 4R-tauopathies are progressive-supranuclear-palsy (PSP) and corticobasal-degeneration (CBD) characterized by subcortical tau accumulation and cortical neuronal dysfunction, as shown by PET-assessed hypoperfusion and glucose hypometabolism. Yet, there is a spatial mismatch between subcortical tau deposition patterns and cortical neuronal dysfunction, and it is unclear how these two pathological brain changes are interrelated. Here, we hypothesized that subcortical tau pathology induces remote neuronal dysfunction in functionally connected cortical regions to test a pathophysiological model that mechanistically links subcortical tau accumulation to cortical neuronal dysfunction in 4R tauopathies. We included 51 Aß-negative patients with clinically diagnosed PSP variants (n=26) or Corticobasal Syndrome (CBS; n=25) who underwent structural MRI and 18F-PI-2620 tau-PET. 18F-PI-2620 tau-PET was recorded using a dynamic one-stop-shop acquisition protocol, to determine an early 0.5-2.5 min post-tracer-injection perfusion window for assessing cortical neuronal dysfunction, as well as a 20-40 min post-tracer-injection window to determine 4R-tau load. Perfusion-PET (i.e. early-window) was assessed in 200 cortical regions, and tau-PET was assessed in 32 subcortical regions of established functional brain atlasses. We determined tau epicenters as subcortical regions with highest 18F-PI-2620 tau-PET signal and assessed the connectivity of tau epicenters to cortical ROIs using a resting-state fMRI-based functional connectivity template derived from 69 healthy elderly controls from the ADNI cohort. Using linear regression, we assessed whether i) higher subcortical tau-PET was associated with reduced cortical perfusion and ii) whether cortical perfusion reductions were observed preferentially in regions closely connected to subcortical tau epicenters. As hypothesized, higher subcortical tau-PET was associated with overall lower cortical perfusion, which remained consistent when controlling for cortical tau-PET. Using group-average and subject-level PET data, we found that the seed-based connectivity pattern of subcortical tau epicenters aligned with cortical perfusion patterns, where cortical regions that were more closely connected to the tau epicenter showed lower perfusion. Together, subcortical tau-accumulation is associated with remote perfusion reductions indicative of neuronal dysfunction in functionally connected cortical regions in 4R-tauopathies. This suggests that subcortical tau pathology may induce cortical dysfunction, which may contribute to clinical disease manifestation and clinical heterogeneity.

Multimodal imaging and electrophysiological study in the differential diagnosis of rest tremor.

Introduction: Distinguishing tremor-dominant Parkinson's disease (tPD) from essential tremor with rest tremor (rET) can be challenging and often requires dopamine imaging. This study aimed to differentiate between these two diseases through a machine learning (ML) approach based on rest tremor (RT) electrophysiological features and structural MRI data. Methods: We enrolled 72 patients including 40 tPD patients and 32 rET patients, and 45 control subjects (HC). RT electrophysiological features (frequency, amplitude, and phase) were calculated using surface electromyography (sEMG). Several MRI morphometric variables (cortical thickness, surface area, cortical/subcortical volumes, roughness, and mean curvature) were extracted using Freesurfer. ML models based on a tree-based classification algorithm termed XGBoost using MRI and/or electrophysiological data were tested in distinguishing tPD from rET patients. Results: Both structural MRI and sEMG data showed acceptable performance in distinguishing the two patient groups. Models based on electrophysiological data performed slightly better than those based on MRI data only (mean AUC: 0.92 and 0.87, respectively; p = 0.0071). The top-performing model used a combination of sEMG features (amplitude and phase) and MRI data (cortical volumes, surface area, and mean curvature), reaching AUC: 0.97 ± 0.03 and outperforming models using separately either MRI (p = 0.0001) or EMG data (p = 0.0231). In the best model, the most important feature was the RT phase. Conclusion: Machine learning models combining electrophysiological and MRI data showed great potential in distinguishing between tPD and rET patients and may serve as biomarkers to support clinicians in the differential diagnosis of rest tremor syndromes in the absence of expensive and invasive diagnostic procedures such as dopamine imaging.

Magnetic Resonance Imaging Measures to Track Atrophy Progression in Progressive Supranuclear Palsy in Clinical Trials.

BACKGROUND: Several magnetic resonance imaging (MRI) measures have been suggested as progression biomarkers in progressive supranuclear palsy (PSP), and some PSP staging systems have been recently proposed. OBJECTIVE: Comparing structural MRI measures and staging systems in tracking atrophy progression in PSP and estimating the sample size to use them as endpoints in clinical trials. METHODS: Progressive supranuclear palsy-Richardson's syndrome (PSP-RS) patients with one-year-follow-up longitudinal brain MRI were selected from the placebo arms of international trials (NCT03068468, NCT01110720, NCT01049399) and the DescribePSP cohort. The discovery cohort included patients from the NCT03068468 trial; the validation cohort included patients from other sources. Multisite age-matched healthy controls (HC) were included for comparison. Several MRI measures were compared: automated atlas-based volumetry (44 regions), automated planimetric measures of brainstem regions, and four previously described staging systems, applied to volumetric data. RESULTS: Of 508 participants, 226 PSP patients including discovery (n = 121) and validation (n = 105) cohorts, and 251 HC were included. In PSP patients, the annualized percentage change of brainstem and midbrain volume, and a combined index including midbrain, frontal lobe, and third ventricle volume change, were the progression biomarkers with the highest effect size in both cohorts (discovery: >1.6; validation cohort: >1.3). These measures required the lowest sample sizes (n < 100) to detect 30% atrophy progression, compared with other volumetric/planimetric measures and staging systems. CONCLUSIONS: This evidence may inform the selection of imaging endpoints to assess the treatment efficacy in reducing brain atrophy rate in PSP clinical trials, with automated atlas-based volumetry requiring smaller sample size than staging systems and planimetry to observe significant treatment effects. © 2024 The Author(s). Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.

Measurement invariance across countries of the Test of Memory Strategies (TMS): A contribution to the cross-national validity study.

Previous literature showed a complex interpretation of recall tasks due to the complex relationship between Executive Functions (EF) and Long Term Memory (M). The Test of Memory Strategies (TMS) could be useful for assessing this issue, because it evaluates EF and M simultaneously. This study aims to explore the validity of the TMS structure, comparing the models proposed by Vaccaro et al. (2022) and evaluating the measurement invariance according to three countries (Italy, Spain, and Portugal) through Confirmatory Factor Analysis (CFA). Four hundred thirty-one healthy subjects (Age mean = 54.84, sd = 20.43; Education mean = 8.85, sd =4.05; M = 177, F = 259) were recruited in three countries (Italy, Spain, and Portugal). Measurement invariance across three country groups was evaluated through Structural Equation modeling. Also, convergent and divergent validity were examined through the correlation between TMS and classical neuropsychological tests. CFA outcomes suggested that the best model was the three-dimensional model, in which list 1 and list2 reflect EF, list 3 reflects a mixed factor of EF and M (EFM) and list4 and list5 reflect M. This result is in line with the theory that TMS decreases EF components progressively. TMS was metric invariant to the country, but scalar invariance was not tenable. Finally, the factor scores of TMS showed convergent validity with the classical neuropsychological tests. The overall results support cross-validation of TMS in the three countries considered.

Combined blood Neurofilament light chain and third ventricle width to differentiate Progressive Supranuclear Palsy from Parkinson's Disease: A machine learning study.

INTRODUCTION: Differentiating Progressive Supranuclear Palsy (PSP) from Parkinson's Disease (PD) may be clinically challenging. In this study, we explored the performance of machine learning models based on MR imaging and blood molecular biomarkers in distinguishing between these two neurodegenerative diseases. METHODS: Twenty-eight PSP patients, 46 PD patients and 60 control subjects (HC) were consecutively enrolled in the study. Serum concentration of neurofilament light chain protein (Nf-L) was assessed by single molecule array (SIMOA), while an automatic segmentation algorithm was employed for T1-weighted measurements of third ventricle width/intracranial diameter ratio (3rdV/ID). Machine learning (ML) models with Logistic Regression (LR), Random Forest (RF), and XGBoost algorithms based on 3rdV/ID and serum Nf-L levels were tested in distinguishing among PSP, PD and HC. RESULTS: PSP patients showed higher serum Nf-L levels and larger 3rdV/ID ratio in comparison with both PD and HC groups (p < 0.005). All ML algorithms (LR, RF and XGBoost) showed that the combination of MRI and blood biomarkers had excellent classification performances in differentiating PSP from PD (AUC ≥0.92), outperforming each biomarker used alone (AUC: 0.85-0.90). Among the different algorithms, XGBoost was slightly more powerful than LR and RF in distinguishing PSP from PD patients, reaching AUC of 0.94 ± 0.04. CONCLUSION: Our findings highlight the usefulness of combining blood and simple linear MRI biomarkers to accurately distinguish between PSP and PD patients. This multimodal approach may play a pivotal role in patient management and clinical decision-making, paving the way for more effective and timely interventions in these neurodegenerative diseases.

Combined cortical thickness and blink reflex recovery cycle to differentiate essential tremor with and without resting tremor.

Objective: To investigate the performance of structural MRI cortical and subcortical morphometric data combined with blink-reflex recovery cycle (BRrc) values using machine learning (ML) models in distinguishing between essential tremor (ET) with resting tremor (rET) and classic ET. Methods: We enrolled 47 ET, 43 rET patients and 45 healthy controls (HC). All participants underwent brain 3 T-MRI and BRrc examination at different interstimulus intervals (ISIs, 100-300 msec). MRI data (cortical thickness, volumes, surface area, roughness, mean curvature and subcortical volumes) were extracted using Freesurfer on T1-weighted images. We employed two decision tree-based ML classification algorithms (eXtreme Gradient Boosting [XGBoost] and Random Forest) combining MRI data and BRrc values to differentiate between rET and ET patients. Results: ML models based exclusively on MRI features reached acceptable performance (AUC: 0.85-0.86) in differentiating rET from ET patients and from HC. Similar performances were obtained by ML models based on BRrc data (AUC: 0.81-0.82 in rET vs. ET and AUC: 0.88-0.89 in rET vs. HC). ML models combining imaging data (cortical thickness, surface, roughness, and mean curvature) together with BRrc values showed the highest classification performance in distinguishing between rET and ET patients, reaching AUC of 0.94 ± 0.05. The improvement in classification performances when BRrc data were added to imaging features was confirmed by both ML algorithms. Conclusion: This study highlights the usefulness of adding a simple electrophysiological assessment such as BRrc to MRI cortical morphometric features for accurately distinguishing rET from ET patients, paving the way for a better classification of these ET syndromes.

Sex Differences in Conversion Risk from Mild Cognitive Impairment to Alzheimer's Disease: An Explainable Machine Learning Study with Random Survival Forests and SHAP.

Alzheimer's disease (AD) exhibits sex-linked variations, with women having a higher prevalence, and little is known about the sexual dimorphism in progressing from Mild Cognitive Impairment (MCI) to AD. The main aim of our study was to shed light on the sex-specific conversion-to-AD risk factors using Random Survival Forests (RSF), a Machine Learning survival approach, and Shapley Additive Explanations (SHAP) on dementia biomarkers in stable (sMCI) and progressive (pMCI) patients. With this purpose, we built two separate models for male (M-RSF) and female (F-RSF) cohorts to assess whether global explanations differ between the sexes. Similarly, SHAP local explanations were obtained to investigate changes across sexes in feature contributions to individual risk predictions. The M-RSF achieved higher performance on the test set (0.87) than the F-RSF (0.79), and global explanations of male and female models had limited similarity (<71.1%). Common influential variables across the sexes included brain glucose metabolism and CSF biomarkers. Conversely, the M-RSF had a notable contribution from hippocampus, which had a lower impact on the F-RSF, while verbal memory and executive function were key contributors only in F-RSF. Our findings confirmed that females had a higher risk of progressing to dementia; moreover, we highlighted distinct sex-driven patterns of variable importance, uncovering different feature contribution risks across sexes that decrease/increase the conversion-to-AD risk.

Genotype-phenotype correlation in PRKN-associated Parkinson's disease.

Bi-allelic pathogenic variants in PRKN are the most common cause of autosomal recessive Parkinson's disease (PD). 647 patients with PRKN-PD were included in this international study. The pathogenic variants present were characterised and investigated for their effect on phenotype. Clinical features and progression of PRKN-PD was also assessed. Among 133 variants in index cases (n = 582), there were 58 (43.6%) structural variants, 34 (25.6%) missense, 20 (15%) frameshift, 10 splice site (7.5%%), 9 (6.8%) nonsense and 2 (1.5%) indels. The most frequent variant overall was an exon 3 deletion (n = 145, 12.3%), followed by the p.R275W substitution (n = 117, 10%). Exon3, RING0 protein domain and the ubiquitin-like protein domain were mutational hotspots with 31%, 35.4% and 31.7% of index cases presenting mutations in these regions respectively. The presence of a frameshift or structural variant was associated with a 3.4 ± 1.6 years or a 4.7 ± 1.6 years earlier age at onset of PRKN-PD respectively (p < 0.05). Furthermore, variants located in the N-terminus of the protein, a region enriched with frameshift variants, were associated with an earlier age at onset. The phenotype of PRKN-PD was characterised by slow motor progression, preserved cognition, an excellent motor response to levodopa therapy and later development of motor complications compared to early-onset PD. Non-motor symptoms were however common in PRKN-PD. Our findings on the relationship between the type of variant in PRKN and the phenotype of the disease may have implications for both genetic counselling and the design of precision clinical trials.

Periodic Leg Movements during Sleep Associated with REM Sleep Behavior Disorder: A Machine Learning Study.

Most patients with idiopathic REM sleep behavior disorder (iRBD) present peculiar repetitive leg jerks during sleep in their clinical spectrum, called periodic leg movements (PLMS). The clinical differentiation of iRBD patients with and without PLMS is challenging, without polysomnographic confirmation. The aim of this study is to develop a new Machine Learning (ML) approach to distinguish between iRBD phenotypes. Heart rate variability (HRV) data were acquired from forty-two consecutive iRBD patients (23 with PLMS and 19 without PLMS). All participants underwent video-polysomnography to confirm the clinical diagnosis. ML models based on Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), and eXtreme Gradient Boosting (XGBoost) were trained on HRV data, and classification performances were assessed using Leave-One-Out cross-validation. No significant clinical differences emerged between the two groups. The RF model showed the best performance in differentiating between iRBD phenotypes with excellent accuracy (86%), sensitivity (96%), and specificity (74%); SVM and XGBoost had good accuracy (81% and 78%, respectively), sensitivity (83% for both), and specificity (79% and 72%, respectively). In contrast, LR had low performances (accuracy 71%). Our results demonstrate that ML algorithms accurately differentiate iRBD patients from those without PLMS, encouraging the use of Artificial Intelligence to support the diagnosis of clinically indistinguishable iRBD phenotypes.

Use, tolerability, benefits and side effects of orthotic devices in Charcot-Marie-Tooth disease.

BACKGROUND: Shoe inserts, orthopaedic shoes, ankle-foot orthoses (AFOs) are important devices in Charcot-Marie-Tooth disease (CMT) management, but data about use, benefits and tolerance are scanty. METHODS: We administered to Italian CMT Registry patients an online ad hoc questionnaire investigating use, complications and perceived benefit/tolerability/emotional distress of shoe inserts, orthopaedic shoes, AFOs and other orthoses/aids. Patients were also asked to fill in the Quebec User Evaluation of Satisfaction with assistive Technology questionnaire, rating satisfaction with currently used AFO and related services. RESULTS: We analysed answers from 266 CMT patients. Seventy per cent of subjects were prescribed lower limb orthoses, but 19% did not used them. Overall, 39% of subjects wore shoe inserts, 18% orthopaedic shoes and 23% AFOs. Frequency of abandonment was high: 24% for shoe inserts, 28% for orthopaedic shoes and 31% for AFOs. Complications were reported by 59% of patients and were more frequently related to AFOs (69%). AFO users experienced greater emotional distress and reduced tolerability as compared with shoe inserts (p<0.001) and orthopaedic shoes (p=0.003 and p=0.045, respectively). Disease severity, degree of foot weakness, customisation and timing for customisation were determinant factors in AFOs' tolerability. Quality of professional and follow-up services were perceived issues. CONCLUSIONS: The majority of CMT patients is prescribed shoe inserts, orthopaedic shoes and/or AFOs. Although perceived benefits and tolerability are rather good, there is a high rate of complications, potentially inappropriate prescriptions and considerable emotional distress, which reduce the use of AFOs. A rational, patient-oriented and multidisciplinary approach to orthoses prescription must be encouraged.

Neuroimaging correlates of postural instability in Parkinson's disease.

BACKGROUND: Postural instability (PI) is a common disabling symptom in Parkinson's disease (PD), but little is known on its pathophysiological basis. OBJECTIVE: In this study, we aimed to identify the brain structures associated with PI in PD patients, using different MRI approaches. METHODS: We consecutively enrolled 142 PD patients and 45 control subjects. PI was assessed using the MDS-UPDRS-III pull-test item (PT). A whole-brain regression analysis identified brain areas where grey matter (GM) volume correlated with the PT score in PD patients. Voxel-based morphometry (VBM) and Tract-Based Spatial Statistics (TBSS) were also used to compare unsteady (PT ≥ 1) and steady (PT = 0) PD patients. Associations between GM volume in regions of interest (ROI) and several clinical features were then investigated using LASSO regression analysis. RESULTS: PI was present in 44.4% of PD patients. The whole-brain approach identified the bilateral inferior frontal gyrus (IFG) and superior temporal gyrus (STG) as the only regions associated with the presence of postural instability. VBM analysis showed reduced GM volume in fronto-temporal areas (superior, middle, medial and inferior frontal gyrus, and STG) in unsteady compared with steady PD patients, and the GM volume of these regions was selectively associated with the PT score and not with any other motor or non-motor symptom. CONCLUSIONS: This study demonstrates a significant atrophy of fronto-temporal regions in unsteady PD patients, suggesting that these brain areas may play a role in the pathophysiological mechanisms underlying postural instability in PD. This result paves the way for further studies on postural instability in Parkinsonism.

Explainability of random survival forests in predicting conversion risk from mild cognitive impairment to Alzheimer's disease.

Random Survival Forests (RSF) has recently showed better performance than statistical survival methods as Cox proportional hazard (CPH) in predicting conversion risk from mild cognitive impairment (MCI) to Alzheimer's disease (AD). However, RSF application in real-world clinical setting is still limited due to its black-box nature.For this reason, we aimed at providing a comprehensive study of RSF explainability with SHapley Additive exPlanations (SHAP) on biomarkers of stable and progressive patients (sMCI and pMCI) from Alzheimer's Disease Neuroimaging Initiative. We evaluated three global explanations-RSF feature importance, permutation importance and SHAP importance-and we quantitatively compared them with Rank-Biased Overlap (RBO). Moreover, we assessed whether multicollinearity among variables may perturb SHAP outcome. Lastly, we stratified pMCI test patients in high, medium and low risk grade, to investigate individual SHAP explanation of one pMCI patient per risk group.We confirmed that RSF had higher accuracy (0.890) than CPH (0.819), and its stability and robustness was demonstrated by high overlap (RBO > 90%) between feature rankings within first eight features. SHAP local explanations with and without correlated variables had no substantial difference, showing that multicollinearity did not alter the model. FDG, ABETA42 and HCI were the first important features in global explanations, with the highest contribution also in local explanation. FAQ, mPACCdigit, mPACCtrailsB and RAVLT immediate had the highest influence among all clinical and neuropsychological assessments in increasing progression risk, as particularly evident in pMCI patients' individual explanation. In conclusion, our findings suggest that RSF represents a useful tool to support clinicians in estimating conversion-to-AD risk and that SHAP explainer boosts its clinical utility with intelligible and interpretable individual outcomes that highlights key features associated with AD prognosis.

The effect of the COVID-19 pandemic on the treated incidence of psychotic disorders in South London.

Evidence on the impact of the COVID-19 pandemic on psychotic disorders is so far scarce. We conducted an incidence study to ascertain rates of first-episode psychosis (FEP) before and during the COVID-19 pandemic in South London. We screened clinical records of individuals living in the London boroughs of Southwark and Lambeth who were referred to the early intervention services before (from 1/3/2019 to 28/2/2020) and during (from 1/3/2020 to 28/2/2021) the COVID-19 pandemic. We used the Office for National Statistics to determine the population at risk. We computed crude and sex-age standardised FEP incidence per 100,000 person-years. We used Poisson regression to calculate the incidence rate ratio (IRR) across the COVID-19 pandemic. A total of 321 incident cases of FEP were identified during the COVID-19 pandemic, accounting for a crude rate of 69.8 (95% CI 62.1-77.4) per 100,000 person-years. The crude rate for the year before was 47.5 (95% CI 41.2-53.8). The incidence variation between the two years accounted for an adjusted IRR of 1.45 (95% CI 1.22-1.72). The pandemic was accompanied by a 45% spike in the rates of first-episode psychosis. This finding should inform public health research and demonstrate the need for adequate resources for secondary care.

Development of a New Wearable Device for the Characterization of Hand Tremor.

Rest tremor (RT) is observed in subjects with Parkinson's disease (PD) and Essential Tremor (ET). Electromyography (EMG) studies have shown that PD subjects exhibit alternating contractions of antagonistic muscles involved in tremors, while the contraction pattern of antagonistic muscles is synchronous in ET subjects. Therefore, the RT pattern can be used as a potential biomarker for differentiating PD from ET subjects. In this study, we developed a new wearable device and method for differentiating alternating from a synchronous RT pattern using inertial data. The novelty of our approach relies on the fact that the evaluation of synchronous or alternating tremor patterns using inertial sensors has never been described so far, and current approaches to evaluate the tremor patterns are based on surface EMG, which may be difficult to carry out for non-specialized operators. This new device, named "RT-Ring", is based on a six-axis inertial measurement unit and a Bluetooth Low-Energy microprocessor, and can be worn on a finger of the tremulous hand. A mobile app guides the operator through the whole acquisition process of inertial data from the hand with RT, and the prediction of tremor patterns is performed on a remote server through machine learning (ML) models. We used two decision tree-based algorithms, XGBoost and Random Forest, which were trained on features extracted from inertial data and achieved a classification accuracy of 92% and 89%, respectively, in differentiating alternating from synchronous tremor segments in the validation set. Finally, the classification response (alternating or synchronous RT pattern) is shown to the operator on the mobile app within a few seconds. This study is the first to demonstrate that different electromyographic tremor patterns have their counterparts in terms of rhythmic movement features, thus making inertial data suitable for predicting the muscular contraction pattern of tremors.

A Reflection on Motor Overflow, Mirror Phenomena, Synkinesia and Entrainment.

In patients with movement disorders, voluntary movements can sometimes be accompanied by unintentional muscle contractions in other body regions. In this review, we discuss clinical and pathophysiological aspects of several motor phenomena including mirror movements, dystonic overflow, synkinesia, entrainment and mirror dystonia, focusing on their similarities and differences. These phenomena share some common clinical and pathophysiological features, which often leads to confusion in their definition. However, they differ in several aspects, such as the body part showing the undesired movement, the type of this movement (identical or not to the intentional movement), the underlying neurological condition, and the role of primary motor areas, descending pathways and inhibitory circuits involved, suggesting that these are distinct phenomena. We summarize the main features of these fascinating clinical signs aiming to improve the clinical recognition and standardize the terminology in research studies. We also suggest that the term "mirror dystonia" may be not appropriate to describe this peculiar phenomenon which may be closer to dystonic overflow rather than to the classical mirror movements.

Brain MRI in Progressive Supranuclear Palsy with Richardson's Syndrome and Variant Phenotypes.

BACKGROUND: Brain magnetic resonance imaging (MRI) is used to support the diagnosis of progressive supranuclear palsy (PSP). However, the value of visual descriptive, manual planimetric, automatic volumetric MRI markers and fully automatic categorization is unclear, particularly regarding PSP predominance types other than Richardson's syndrome (RS). OBJECTIVES: To compare different visual reading strategies and automatic classification of T1-weighted MRI for detection of PSP in a typical clinical cohort including PSP-RS and (non-RS) variant PSP (vPSP) patients. METHODS: Forty-one patients (21 RS, 20 vPSP) and 46 healthy controls were included. Three readers using three strategies performed MRI analysis: exclusively visual reading using descriptive signs (hummingbird, morning-glory, Mickey-Mouse), visual reading supported by manual planimetry measures, and visual reading supported by automatic volumetry. Fully automatic classification was performed using a pre-trained support vector machine (SVM) on the results of atlas-based volumetry. RESULTS: All tested methods achieved higher specificity than sensitivity. Limited sensitivity was driven to large extent by false negative vPSP cases. Support by automatic volumetry resulted in the highest accuracy (75.1% ± 3.5%) among the visual strategies, but performed not better than the midbrain area (75.9%), the best single planimetric measure. Automatic classification by SVM clearly outperformed all other methods (accuracy, 87.4%), representing the only method to provide clinically useful sensitivity also in vPSP (70.0%). CONCLUSIONS: Fully automatic classification of volumetric MRI measures using machine learning methods outperforms visual MRI analysis without and with planimetry or volumetry support, particularly regarding diagnosis of vPSP, suggesting the use in settings with a broad phenotypic PSP spectrum. © 2023 The Authors. Movement Disorders published by Wiley Periodicals LLC on behalf of International Parkinson and Movement Disorder Society.