Background: The presence of frequent macro-square-wave jerks (SWJs) has been recently included in the diagnostic criteria for progressive supranuclear palsy (PSP). The aim of the current video-oculographic study was to systematically assess the presence and features of SWJs during a brief fixation task in PSP, in comparison with Parkinson’s disease (PD) patients and healthy controls (HC). Methods: Thirty-eight PSP patients, 55 PD patients and 40 HC were enrolled in the study. All patients underwent a video-oculographic (VOG) examination including a 5-s fixation task, and the number, duration and amplitude of SWJs were recorded. The diagnostic performance of several SWJs parameters were then compared in distinguishing PSP from PD patients and controls. Results: PSP patients showed a higher number and amplitude of SWJs compared to PD patients and controls. At least two SWJs within the 5-s fixation task were observed in 81.6% of PSP patients, 52.7% of PD patients and 25% of HC. The SWJs amplitude was the parameter showing the highest performances in distinguishing PSP from PD (AUC: 0.78) and HC (AUC: 0.88), outperforming the SWJ number and duration. The SWJ amplitude was larger in PSP-Richardson’s syndrome than in PSP-Parkinsonism patients, while no difference was found between PSP patients with different degrees of vertical ocular motor dysfunction. Conclusions: This video-oculographic study provides robust evidence of larger SWJs number and amplitude in PSP than in PD patients, with some potential for differential diagnosis, supporting the inclusion of this ocular sign in PSP criteria.

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.

Parkinson’s disease (PD) is characterized by alterations in movement dynamics that are difficult to quantify with conventional clinical assessment. This study proposes an integrated approach combining graph-based kinematic analysis with explainable machine learning to identify digital biomarkers of Parkinsonian motor impairment. Kinematic signals were acquired using Xsens inertial sensors from 51 patients with PD and 53 healthy controls. For each participant, subject-specific kinematic networks were constructed by modeling inter-segment similarities through Jensen–Shannon divergence, from which global and local graph-theoretical metrics were extracted. A machine learning pipeline incorporating voting feature selection, and XGBoost classification was evaluated using a nested cross-validation design. The model achieved robust performance (AUC = 0.87), and explainability analyses using SHAP identified a subset of 13 features capturing alterations in velocity, inter-segment connectivity, and network centrality. PD was characterized by increased positional variability, reduced distal limb velocity, and a redistribution of network centrality towards proximal body segments. These features were associated with clinical severity, confirming their physiological relevance. By integrating graph-theoretical modeling, explainable artificial intelligence, and machine learning methodology, this work provides a method of discovering quantitative biomarkers capturing alterations in motor coordination. These findings highlight the potential of ML and kinematic networks to support objective motor assessment in PD.

Parkinson’s disease (PD) is a progressive neurodegenerative disorder characterized by motor and non-motor symptoms and widespread alterations in brain networks. Circulating biomarkers such as neurofilament light chain (NfL) and glial fibrillary acidic protein (GFAP) reflect neuroaxonal damage and astroglial activation, respectively, but their relationship with large-scale brain connectivity remains poorly understood. Seventy-three PD patients and thirty-four healthy controls underwent diffusion magnetic resonance imaging. Whole-brain tractography was used to reconstruct structural connectivity networks, and graph-theoretical measures were derived. Serum NfL and GFAP levels were quantified, and their associations with network metrics and clinical variables were assessed. PD patients showed significant alterations in global and nodal network organization compared to controls. Higher NfL and GFAP levels were associated with reduced global clustering coefficient and efficiency, as well as increased path length and modularity. At the regional level, higher biomarker levels were associated with reduced network measures in the right thalamus and right cerebellar cortex. No significant associations were observed in healthy controls. These findings demonstrate that circulating biomarkers of neurodegeneration are linked to both global and regional disruptions of structural brain connectivity in PD, supporting the integration of blood-based biomarkers and connectomics to better characterize disease-related network alterations.