Dante Trabassi

@uniroma1.it

Dante Trabassi


         Download Compact PDF  
https://researchid.co/dante.trabassi
15

Scopus Publications

Scopus Publications

  • Identifying key gait features in stroke patients using wearable inertial sensors and supervised and unsupervised machine learning
    Paolo Brasiliano, Amaranta Soledad Orejel-Bustos, Valeria Belluscio, Andrea Cereatti, Ugo Della Croce, Dante Trabassi, Francesca Salis, Marco Tramontano, Maria Gabriella Buzzi, Giuseppe Vannozzi, Elena Bergamini
    Scientific Reports, 2026
    Stroke is a major cause of motor disability, degrading walking and quality of life. Wearable gait analysis with magneto-inertial measurement units (MIMUs) can quantify post-stroke impairments. We used machine learning to identify discriminative gait features in stroke, coupling supervised feature selection with unsupervised clustering to improve interpretability and generalizability. Eighty-five stroke patients and 97 healthy controls completed 10-Meter Walk Tests while wearing five MIMUs. Feature selection spanned spatiotemporal, symmetry, stability, and smoothness metrics. K-nearest neighbors (KNN), support vector machines (SVM), and decision trees (TREE) were trained, validated, and tested iteratively across data splits; clustering then verified discriminative ability. Sequential backward feature selection retained nine features, yielding accuracies (healthy vs. patient) of 94.1% (KNN), 96.7% (SVM), and 89.1% (TREE). SVM generalized best. Unsupervised k-medoids with cosine distance confirmed discrimination, reaching 90% accuracy with only three features: stride speed, stance-phase coefficient of variation, and medio-lateral harmonic ratio. Results indicate that gait variability, trunk smoothness, and upper-body stability robustly characterize post-stroke dysfunctions. Notably, head-movement smoothness emerged as a novel, discriminative feature. This integrated framework shows how wearable sensors plus machine learning can support clinical gait analysis and rehabilitation planning. Future work should enable real-time deployment and broaden datasets to cover more clinical scenarios.
  • Pilot biomechanical study of complex upper-limb movements in patients with RSA using inertial sensors: Feasibility of sport-specific gestures
    Giorgio Ippolito, Marco Damo, Sergio Ferraro, Dante Trabassi, Mariano Serrao, Riccardo Maria Lanzetti, Michele Francesco Surace, Daniele Mazza
    Shoulder and Elbow, 2026
    Background This study aimed to evaluate recovery of complex upper-limb movements from a kinematic and biomechanical perspective in patients undergoing Reverse Total Shoulder Arthroplasty (RSA), comparing movement quality during athletic gestures with healthy controls. Methods Two groups were analyzed: patients with RSA and healthy individuals without shoulder pathology. Participants performed basic shoulder tasks (flexion–extension and abduction–adduction) and three athletic gestures of increasing complexity: boccia throw, golf swing, and padel víbora stroke. Kinematic data (joint angles, angular velocities, and accelerations) were collected using a wearable inertial motion analysis system (Movit System G1). Results Controls demonstrated a greater range of motion (maximum joint angle: 184.0° vs. 144.03°), though differences were not statistically significant. Angular velocities and accelerations were largely comparable between groups, indicating that patients with RSA adopt conservative yet functional movement strategies. No significant differences were observed during the boccia throw or golf swing. The víbora stroke showed the highest variability but remained within functional limits in both groups. Conclusions This pilot feasibility study suggests that patients with RSA can perform complex upper-limb and sport-specific movements with biomechanical patterns comparable to healthy individuals. Although limited by small sample size, large effect sizes indicate clinically relevant differences, supporting the need for larger, confirmatory studies.
  • Clinical and instrumental gait phenotyping in people with GLUT-1 deficiency syndrome
    Michele Corrado, Valeria Vacchini, Massimiliano Celario, Costanza Varesio, Carla Brancaccio, Valentina Grillo, Francescantonio Cammarota, Federico Bighiani, Alessandro Antoniazzi, Beatrice Agostini, Gloria Vaghi, Luca Martinis, Ilaria Campese, Carlo Alberto Quaranta, Ludovica Pasca, Monica Guglielmetti, Francesca Valentino, Dante Trabassi, Stefano Filippo Castiglia, Mariano Serrao, Cristina Tassorelli, Renato Borgatti, Valentina De Giorgis, Roberto De Icco
    Gait and Posture, 2025
    OBJECTIVES: Glucose transporter type 1 deficiency syndrome (GLUT1-DS) is a rare neurometabolic disorder caused by mutations in the SLC2A1 gene. GLUT1-DS is characterized by epilepsy, cognitive impairment, movement disorders, and gait abnormalities. In the present study we aimed to characterize gait features of GLUT1-DS by means of gait analysis based on a single inertial measurement unit. METHODS: We conducted a case-control study with 32 GLUT1-DS patients (22.4 ± 13.2 years; 13 males) and 32 matched healthy participants (HS). Participants underwent inertial gait analysis, providing spatio-temporal and trunk acceleration-derived gait indexes, including harmonic ratio (HR), largest Lyapunov exponent (sLLE), log-dimensionless jerk score of accelerations (LDLJa), and step length variability (CV). RESULTS: Compared to HS, GLUT1-DS patients showed decreased HR (P < 0.005) across all directions, reflecting reduced symmetry and smoothness of trunk acceleration during gait. sLLE was higher in GLUT1-DS, indicating gait instability (P < 0.005), and LDLJa was elevated (P = 0.001), corroborating lower smoothness of trunk accelerations. Step length variability was also higher in GLUT1-DS patients (P = 0.001). INTERPRETATION: The gait pattern of GLUT1-DS patients is marked by reduced fluidity, stability, and smoothness. Inertial gait analysis could be a valuable tool for monitoring GLUT1-DS progression and tailoring rehabilitative strategies.
  • Discriminative ability, responsiveness, and interpretability of smoothness index of gait in people with multiple sclerosis
    Stefano Filippo Castiglia, Fulvio Dal Farra, Dante Trabassi, Andrea Turolla, Mariano Serrao, Ugo Nocentini, Paolo Brasiliano, Elena Bergamini, Marco Tramontano
    Archives of Physiotherapy, 2025
    Introduction: Gait impairments are common in People with Multiple Sclerosis (PwMS). Several studies have examined the clinometric properties of Inertial Measurement Units (IMUs), with LDLJa identified as a robust metric for gait smoothness. However, its responsiveness and interpretability have not been explored. Methods: This cross-sectional study at IRCCS Santa Lucia Hospital enrolled 44 PwMS (age: 28-71; EDSS: 0-6) and 43 age- and gait-speed-matched healthy participants (HP). Two physiotherapists conducted assessments with five synchronized IMUs during a 10-meter walk at participants’ preferred speed. Data were collected at baseline (T0) and after 4 weeks of training (T1). Results: Significant differences in log dimensionless jerk (LDLJa) were found between PwMS and HP in the AP (p &lt; 0.001, d = 0.63), ML (p &lt; 0.001, d = 1.08), and CC (p = 0.03, d = 0.68) directions. PwMS had lower LDLJaAP values (&lt; -4.88) and LDLJaML values (&lt; -5.40) with probabilities of 63% and 76%, respectively. ΔLDLJaML demonstrated good responsiveness to rehabilitation (AUC ~0.80), with improvements &gt;4.02% representing the optimal MCID for clinical improvement in MiniBesTest. Conclusion: Lower LDLJa values in the AP and ML directions characterize gait smoothness impairment in PwMS. LDLJa in the ML direction is responsive to balance-focused rehabilitation, highlighting its potential for tracking gait disorders and rehabilitation progress.
  • Local Dynamic Stability of Trunk During Gait Can Detect Dynamic Imbalance in Subjects with Episodic Migraine
    Stefano Filippo Castiglia, Gabriele Sebastianelli, Chiara Abagnale, Francesco Casillo, Dante Trabassi, Cherubino Di Lorenzo, Lucia Ziccardi, Vincenzo Parisi, Antonio Di Renzo, Roberto De Icco, Cristina Tassorelli, Mariano Serrao, Gianluca Coppola
    Sensors, 2024
    Background/Hypothesis: Motion sensitivity symptoms, such as dizziness or unsteadiness, are frequently reported as non-headache symptoms of migraine. Postural imbalance has been observed in subjects with vestibular migraine, chronic migraine, and aura. We aimed to assess the ability of largest Lyapunov’s exponent for a short time series (sLLE), which reflects the ability to cope with internal perturbations during gait, to detect differences in local dynamic stability between individuals with migraine without aura (MO) with an episodic pattern between attacks and healthy subjects (HS). Methods: Trunk accelerations of 47 MO and 38 HS were recorded during gait using an inertial measurement unit. The discriminative ability of sLLE was assessed through receiver-operating characteristics curves and cutoff analysis. Partial correlation analysis was conducted between the clinical and gait variables, excluding the effects of gait speed. Results: MO showed higher sLLE values, and reduced pelvic rotation, pelvic tilt, and stride length values. sLLEML and pelvic rotation showed good ability to discriminate between MO and HS and were correlated with the perceived pain, migraine disability assessment score, and each other. Conclusions: these findings may provide new insights into the postural balance control mechanism in subjects with MO and introduce the sLLEML as a potential measure of dynamic instability in MO.
  • The role of stroke-induced immunosuppression as a predictor of functional outcome in the neurorehabilitation setting
    Gloria Vaghi, Andrea Morotti, Elisa Maria Piella, Micol Avenali, Daniele Martinelli, Silvano Cristina, Marta Allena, Valentina Grillo, Michele Corrado, Federico Bighiani, Francescantonio Cammarota, Alessandro Antoniazzi, Federica Ferrari, Federico Mazzacane, Anna Cavallini, Anna Pichiecchio, Elisa Rognone, Luca Martinis, Luca Correale, Stefano Filippo Castiglia, Dante Trabassi, Mariano Serrao, Cristina Tassorelli, Roberto De Icco
    Scientific Reports, 2024
    Stroke affects the interconnection between the nervous and immune systems, leading to a down-regulation of immunity called stroke-induced immunosuppression (SII). The primary aim of this study is to investigate SII role as a predictor of functional, neurological, and motor outcomes in the neurorehabilitation setting (NRB). We conducted a prospective observational study enrolling post-acute stroke patients hospitalized for neurorehabilitation. At NRB admission (T0) and discharge (T1), we assessed presence of SII (defined by a neutrophil-to-lymphocyte ratio ≥ 5) and we evaluated functional independence (Functional Independence Measure-FIM, Barthel Index-BI), motor performances (Tinetti Score, Hauser Ambulation Index) and neurological impairment (NIHSS). We enrolled 96 patients (45.8% females, 70.6 ± 13.9 years, 88.5% ischemic stroke). At T0, 15.6% of patients (15/96) had SII. When compared to immunocompetent patients (IC), the SII group was characterized by worse baseline functional independence, motor performances and neurological disability. The same was confirmed at T1 (FIM p = 0.012, BI p = 0.007, Tinetti p = 0.034, NIHSS p = 0.001). Neurological disability demonstrated a less pronounced improvement in SII (ΔNIHSS: SII: − 2.1 ± 2.3 vs. IC: − 3.1 ± 2.5, p = 0.035). SII group presented a higher percentage of infectious complications during the neurorehabilitation period (SII 80% vs. IC 25.9%; p = 0.001). SII may represent a negative prognostic factor in the neurorehabilitation setting. SII patients were characterized by poorer functional, motor, neurological performances and higher risk of infectious complications. ClinicaTrial registration: NCT05889169.
  • Mixed Reality-Based Smart Occupational Therapy Personalized Protocol for Cerebellar Ataxic Patients
    Michela Franzò, Franco Marinozzi, Alessia Finti, Marco Lattao, Dante Trabassi, Stefano Filippo Castiglia, Mariano Serrao, Fabiano Bini
    Brain Sciences, 2024
    Background: Occupational therapy (OT) is an essential component of patient care, and it is especially beneficial if focused on meaningful activities. For ataxic patients, traditional procedures are currently the most efficient, although without specific guidelines and suggestions for virtual reality integration. In this context, this study proposes Hybrid Smart Rehabilitation (HSR) based on mixed reality (MR) as an aid in overcoming limitations of the traditional OT procedures. Methods: MR-HSR is designed specifically for ataxic patients and developed in Unity with the Holographic Remoting setting for run-time intervention on the scene. The subject reaches a book and grabs it with their hand inside a holographic guide with audio-visive feedback. Hand trajectories acquired from eight ataxic patients and eight healthy subjects were compared and new variables were analyzed to evaluate the performance. The Trust in Automation questionnaire was submitted to assess the opinion of the patients. Results: Patients confirmed their trust in the developer and in the improvement that this system can bring to their rehabilitation. The “total time” and “sway area” of the trajectory were statistically significant and, together with the deviation of the trajectory from the main axis of the guide, although not statistically significant, made it possible to build a classifier. Conclusions: The patient-specific MR-HSR can be considered as an integrative tool for assessing the subject’s condition by analyzing new quantitative variables which, if matched to the Scale for the Assessment and Rating of Ataxia (SARA), could be the basis of a new index to assess the progressiveness of ataxia.
  • Differences in Trunk Acceleration-Derived Gait Indexes in Stroke Subjects with and without Stroke-Induced Immunosuppression
    Luca Martinis, Stefano Filippo Castiglia, Gloria Vaghi, Andrea Morotti, Valentina Grillo, Michele Corrado, Federico Bighiani, Francescantonio Cammarota, Alessandro Antoniazzi, Luca Correale, Giulia Liberali, Elisa Maria Piella, Dante Trabassi, Mariano Serrao, Cristina Tassorelli, Roberto De Icco
    Sensors, 2024
    Background: Stroke-induced immunosuppression (SII) represents a negative rehabilitative prognostic factor associated with poor motor performance at discharge from a neurorehabilitation unit (NRB). This study aims to evaluate the association between SII and gait impairment at NRB admission. Methods: Forty-six stroke patients (65.4 ± 15.8 years, 28 males) and 42 healthy subjects (HS), matched for age, sex, and gait speed, underwent gait analysis using an inertial measurement unit at the lumbar level. Stroke patients were divided into two groups: (i) the SII group was defined using a neutrophil-to-lymphocyte ratio ≥ 5, and (ii) the immunocompetent (IC) group. Harmonic ratio (HR) and short-term largest Lyapunov’s exponent (sLLE) were calculated as measures of gait symmetry and stability, respectively. Results: Out of 46 patients, 14 (30.4%) had SII. HR was higher in HS when compared to SII and IC groups (p &lt; 0.01). HR values were lower in SII when compared to IC subjects (p &lt; 0.01). sLLE was lower in HS when compared to SII and IC groups in the vertical and medio-lateral planes (p ≤ 0.01 for all comparisons). sLLE in the medio-lateral plane was higher in SII when compared to IC subjects (p = 0.04). Conclusions: SII individuals are characterized by a pronounced asymmetric gait and a more impaired dynamic gait stability. Our findings underline the importance of devising tailored rehabilitation programs in patients with SII. Further studies are needed to assess the long-term outcomes and the role of other clinical features on gait pattern.
  • Local Dynamic Stability of Trunk During Gait is Responsive to Rehabilitation in Subjects with Primary Degenerative Cerebellar Ataxia
    Stefano Filippo Castiglia, Dante Trabassi, Carmela Conte, Valeria Gioiosa, Gabriele Sebastianelli, Chiara Abagnale, Alberto Ranavolo, Cherubino Di Lorenzo, Gianluca Coppola, Carlo Casali, Mariano Serrao
    Cerebellum, 2024
    This study aimed to assess the responsiveness to the rehabilitation of three trunk acceleration-derived gait indexes, namely the harmonic ratio (HR), the short-term longest Lyapunov’s exponent (sLLE), and the step-to-step coefficient of variation (CV), in a sample of subjects with primary degenerative cerebellar ataxia (swCA), and investigate the correlations between their improvements (∆), clinical characteristics, and spatio-temporal and kinematic gait features. The trunk acceleration patterns in the antero-posterior (AP), medio-lateral (ML), and vertical (V) directions during gait of 21 swCA were recorded using a magneto-inertial measurement unit placed at the lower back before (T0) and after (T1) a period of inpatient rehabilitation. For comparison, a sample of 21 age- and gait speed-matched healthy subjects (HSmatched) was also included. At T1, sLLE in the AP (sLLEAP) and ML (sLLEML) directions significantly improved with moderate to large effect sizes, as well as SARA scores, stride length, and pelvic rotation. sLLEML and pelvic rotation also approached the HSmatched values at T1, suggesting a normalization of the parameter. HRs and CV did not significantly modify after rehabilitation. ∆sLLEML correlated with ∆ of the gait subscore of the SARA scale (SARAGAIT) and ∆stride length and ∆sLLEAP correlated with ∆pelvic rotation and ∆SARAGAIT. The minimal clinically important differences for sLLEML and sLLEAP were ≥ 36.16% and ≥ 28.19%, respectively, as the minimal score reflects a clinical improvement in SARA scores. When using inertial measurement units, sLLEAP and sLLEML can be considered responsive outcome measures for assessing the effectiveness of rehabilitation on trunk stability during walking in swCA.
  • Optimizing Rare Disease Gait Classification through Data Balancing and Generative AI: Insights from Hereditary Cerebellar Ataxia
    Dante Trabassi, Stefano Filippo Castiglia, Fabiano Bini, Franco Marinozzi, Arash Ajoudani, Marta Lorenzini, Giorgia Chini, Tiwana Varrecchia, Alberto Ranavolo, Roberto De Icco, Carlo Casali, Mariano Serrao
    Sensors, 2024
    The interpretability of gait analysis studies in people with rare diseases, such as those with primary hereditary cerebellar ataxia (pwCA), is frequently limited by the small sample sizes and unbalanced datasets. The purpose of this study was to assess the effectiveness of data balancing and generative artificial intelligence (AI) algorithms in generating synthetic data reflecting the actual gait abnormalities of pwCA. Gait data of 30 pwCA (age: 51.6 ± 12.2 years; 13 females, 17 males) and 100 healthy subjects (age: 57.1 ± 10.4; 60 females, 40 males) were collected at the lumbar level with an inertial measurement unit. Subsampling, oversampling, synthetic minority oversampling, generative adversarial networks, and conditional tabular generative adversarial networks (ctGAN) were applied to generate datasets to be input to a random forest classifier. Consistency and explainability metrics were also calculated to assess the coherence of the generated dataset with known gait abnormalities of pwCA. ctGAN significantly improved the classification performance compared with the original dataset and traditional data augmentation methods. ctGAN are effective methods for balancing tabular datasets from populations with rare diseases, owing to their ability to improve diagnostic models with consistent explainability.
  • Multiscale Entropy Algorithms to Analyze Complexity and Variability of Trunk Accelerations Time Series in Subjects with Parkinson’s Disease
    Stefano Filippo Castiglia, Dante Trabassi, Carmela Conte, Alberto Ranavolo, Gianluca Coppola, Gabriele Sebastianelli, Chiara Abagnale, Francesca Barone, Federico Bighiani, Roberto De Icco, Cristina Tassorelli, Mariano Serrao
    Sensors, 2023
  • Identification of Gait Unbalance and Fallers Among Subjects with Cerebellar Ataxia by a Set of Trunk Acceleration-Derived Indices of Gait
    Stefano Filippo Castiglia, Dante Trabassi, Antonella Tatarelli, Alberto Ranavolo, Tiwana Varrecchia, Lorenzo Fiori, Davide Di Lenola, Ettore Cioffi, Manikandan Raju, Gianluca Coppola, Pietro Caliandro, Carlo Casali, Mariano Serrao
    Cerebellum, 2023
  • Harmonic ratio is the most responsive trunk-acceleration derived gait index to rehabilitation in people with Parkinson's disease at moderate disease stages
    Stefano Filippo Castiglia, Dante Trabassi, Roberto De Icco, Antonella Tatarelli, Micol Avenali, Michele Corrado, Valentina Grillo, Gianluca Coppola, Alessandro Denaro, Cristina Tassorelli, Mariano Serrao
    Gait and Posture, 2022
  • Machine Learning Approach to Support the Detection of Parkinson’s Disease in IMU-Based Gait Analysis
    Dante Trabassi, Mariano Serrao, Tiwana Varrecchia, Alberto Ranavolo, Gianluca Coppola, Roberto De Icco, Cristina Tassorelli, Stefano Filippo Castiglia
    Sensors, 2022
  • Ability of a set of trunk inertial indexes of gait to identify gait instability and recurrent fallers in parkinson’s disease
    Stefano Filippo Castiglia, Antonella Tatarelli, Dante Trabassi, Roberto De Icco, Valentina Grillo, Alberto Ranavolo, Tiwana Varrecchia, Fabrizio Magnifica, Davide Di Lenola, Gianluca Coppola, Donatella Ferrari, Alessandro Denaro, Cristina Tassorelli, Mariano Serrao
    Sensors, 2021