Heart rate variability (HRV) reflects the complex interplay of physiological systems, like the autonomic nervous system, which modulates HRV through parasympathetic and sympathetic branches. This study investigates the multiscale multifractal properties of HRV and the influence of autonomic control using an optimized Detrended Fluctuation Analysis (DFA) framework. Building on prior work, we applied a multifractal multiscale DFA to series of cardiac intervals recorded in 9 healthy volunteers before and during selective autonomic blocks (parasympathetic, sympathetic, combined, and central sympathetic). We quantified fractal components over the scales between 9 and 120 s, using moment orders from – 5 to +5 to differentiate between low- and high-amplitude fluctuations. Results reveal that HRV exhibits intrinsic multiscale multifractality, with distinct scale-dependent patterns for different amplitude components. Autonomic blocks alter these patterns: parasympathetic blockade significantly increases the coefficients at scales shorter than 30 s for high-amplitude components and between 20 and 50 s for low-amplitude components, and sympathetic blockade decreases the coefficients at scales around 50 s for the high-amplitude components. Furthermore, unlike sympathetic blockade, parasympathetic blockade increases the degree of multiscale multifractality. This suggests that the multifractal dynamics of high-amplitude components arise from the superposition of autonomic influences with distinct transfer functions—flat for vagal and low-pass for sympathetic modulation; and that the parasympathetic outflow may also contribute to the multifractality of low-amplitude components. In conclusion, this study underscores the potential of multiscale multifractal analysis in characterizing cardiovascular control and the valuable insights it may offer for diagnosing dysautonomia and monitoring therapeutic interventions.

Cuffless blood pressure (BP) monitoring devices represent a promising innovation in hypertension management. This scientific statement provides a comprehensive update on these emerging technologies, their specific validation requirements, their potential clinical applications, and their present and future challenges. These devices generate considerable interest by enabling non-invasive BP measurement without arterial occlusion, thereby eliminating the discomfort associated with traditional cuff-based monitoring, particularly during sleep. The technologies on which these devices are based comprise a heterogeneous group, primarily utilizing pulse wave propagation time or waveform analysis through contact or non-contact sensors. They can be categorized as continuous or intermittent, automated or manual, calibration-free or requiring cuff/demographic calibration, and wearable or stationary. This technological diversity necessitates validation protocols distinct from those used for conventional cuff-based monitors, with specific requirements for each device category. Potential clinical applications include widespread out-of-office BP monitoring, unbiased assessment of circadian BP patterns and BP variability, improved detection of nocturnal hypertension, enhanced treatment adherence and long-term BP control, and continuous monitoring in hospital settings. Additionally, their lower cost compared with conventional technologies could enhance the early detection of hypertension in resource-limited settings. However, due to insufficient accuracy validation, this scientific statement does not recommend their use in clinical decisions in spite of their potential interest, in line with international guidelines not recommending their use in hypertension management. Key challenges ahead include developing standardized validation protocols, establishing normative BP data, managing the resulting burden on clinicians in handling huge volumes of data, exploring additional haemodynamic parameters, and advancing sensor technology, mathematical models, and algorithms.

Cuffless blood pressure (BP) monitoring devices represent a promising innovation in hypertension management. This scientific statement provides a comprehensive update on these emerging technologies, their specific validation requirements, their potential clinical applications, and their present and future challenges. These devices generate considerable interest by enabling noninvasive BP measurement without arterial occlusion, thereby eliminating the discomfort associated with traditional cuff-based monitoring, particularly during sleep. The technologies on which these devices are based comprise a heterogeneous group, primarily utilizing pulse wave propagation time or waveform analysis through contact or noncontact sensors. They can be categorized as continuous or intermittent, automated or manual, calibration-free or requiring cuff/demographic calibration, and wearable or stationary. This technological diversity necessitates validation protocols distinct from those used for conventional cuff-based monitors, with specific requirements for each device category. Potential clinical applications include widespread out-of-office BP monitoring, unbiased assessment of circadian BP patterns and BP variability, improved detection of nocturnal hypertension, enhanced treatment adherence and long-term BP control, and continuous monitoring in hospital settings. Additionally, their lower cost compared with conventional technologies could enhance the early detection of hypertension in resource-limited settings. However, due to insufficient accuracy validation, this scientific statement does not still recommend their use in clinical decisions, in line with international guidelines not recommending their use in hypertension management. Key challenges ahead include developing standardized validation protocols, establishing normative BP data, manage the resulting burden on clinicians in handling huge volumes of data, exploring additional hemodynamic parameters, and advancing sensor technology, mathematical models, and algorithms.

Symbolic analysis (SA) infers cardiac control from spontaneous stationary sequences of heart period (HP) by estimating the probability of symbolic pattern classes. Unfortunately, SA does not assess the fraction of HP variability associated with symbolic pattern families. This study proposes amplitude SA (ASA) accounting for absolute changes between consecutive HPs. ASA leverages uniform 6-bin quantization to symbolize HP, the delay embedding procedure to form length-3 symbolic patterns and a traditional strategy to group symbolic patterns into four classes families according to number and sign of variations between adjacent symbols. ASA computes the fraction of variance associated with symbolic pattern classes. ASA was applied to HP variability derived from: 1) healthy subjects during pharmacological challenges (n = 9; age: 25-46 yrs, 9 males); 2) healthy subjects during graded postural stimuli (n = 19; age: 21-48 yrs, 8 males); 3) Parkinson disease (PD) patients (n = 12; age: 55-79 yrs, 8 males) and matched healthy controls (n = 12; age: 58-72 yrs, 7 males). We computed both global and local ASA markers and we compared them with SA indexes. Over stationary HP series we found that: i) ASA provides a general method to decompose HP variance according to symbolic pattern classes; ii) ASA is useful to describe cardiac control; iii) ASA indexes are complementary to SA markers; iv) ASA emphasizes the link of HP variability markers expressed in absolute units with vagal control; v) global and local ASA approaches provide similar information. SA and ASA should be utilized concomitantly for a deeper characterization of cardiac control from spontaneous HP fluctuations.

Optimizing neuromuscular strength and balance is essential for performance and injury prevention in elite Paralympic sport. However, limited evidence describes how these parameters change over time during specific phases of the training season in athletes with lower limb deficiencies. This retrospective case series aimed to describe longitudinal changes in neuromuscular and balance performance during the fundamental preparation period in elite athletes using prosthetic devices. Routinely collected performance data from five international-level Paralympic athletes (Para-swimming and Para-athletics) were retrospectively analyzed across two preparatory observation windows conducted in consecutive competitive seasons. Neuromuscular performance was assessed using countermovement jump variables, while static balance was evaluated through Inertial Measurement Unit-derived sway metrics. Within-athlete changes were examined using descriptive and exploratory analyses. At the group level, changes were observed in selected neuromuscular and balance outcomes over time, including jump height and path length. Individual analyses revealed substantial inter-athlete variability in the magnitude and direction of changes across all outcomes. Overall, the findings indicate that neuromuscular and postural performance may fluctuate meaningfully during preparatory phases in elite athletes with lower limb deficiencies. This study provides exploratory insights derived from real-world training settings and highlights the value of longitudinal monitoring to support individualized performance management in Paralympic sport.

Promising methods for monitoring blood pressure (BP) are based on the pulse arrival time (PAT) from finger photoplethysmography (PPG). This study aims to investigate the impact of PPG fiducial points, wavelengths, and PAT calibration models on short-term BP estimations. A multi wavelength multisensor PPG device was developed to measure PAT beat-by-beat in ten volunteers during an exercise protocol. Four calibration models (two-coefficient inverse, squared inverse, and logarithmic; and three-coefficient inverse), four fiducial points (wave onset, peak, maximum derivative, and tangents' intersection), and three wavelengths (red, infrared (IR), and green) were compared to estimate BP on 5-min segments and single beats. Finger systolic and diastolic BP (DBP) served as reference. Estimation errors were higher for systolic than DBP. Acceptable (<5 mmHg) median absolute errors (MAEs) for 5-min average systolic BP (SBP) were achieved by combining red or IR wavelengths with inverse or squared-inverse calibrations. For single-beat estimates, MAEs were higher but remained <8 mmHg with red or IR wavelengths, maximum derivative or tangents' intersection fiducial points, and two-coefficient calibrations. Short-term BP estimation from finger PAT is feasible by properly combining calibration models, wavelengths, and fiducial points. Identifying the optimal parameters for estimating BP from finger PAT by PPG, this study contributes to the development of noninvasive devices for accurate and continuous BP monitoring both in clinical settings and in the general population.

The study aimed to investigate and confirm from a physiological and psychological perspective whether preferred music would influence anaerobic performance during the Running-Based Anaerobic Sprint Test (RAST). A total of 18 (men, n = 12, women, n = 6) sub-élite track-and-field and football athletes (mean age 22.2 ± 2.1 years, mean height 175.3 ± 8.0 cm, mean weight 66.4 ± 10.6 kg, mean BMI 21.5 ± 2.2 kg/m2) were voluntarily recruited. The RAST procedure was performed by recording maximum power (Pmax), average power (Pmean), minimum power (Pmin), rating of perceived exertion (RPE), and motivational level (visual analog scale) while listening to preferred or no music through headphones. Listening to music significantly increased motivation (p < 0.001, effect size = 1.31, very large) compared to no music. However, no significant differences were observed in other performance variables between the "with music" and "without music" conditions. Overall, listening to preferred music during an anaerobic exercise improves motivation as confirmed by previous evidence. This could be helpful for athletes to strive for even higher goals by improving their current performance level.

We test the hypothesis that amplitude permutation conditional entropy (APCE) is more powerful than permutation conditional entropy (PCE) when complexity of heart period (HP) dynamics is decreased by vagal blockade or withdrawal. We acquired HP variability in 9 healthy male physicians (age: 25-46 yrs) at baseline (B) and during administration of a high dose of atropine (AT) and in 15 healthy nonsmoking volunteers (age: 24-54 yrs, 9 males and 6 females) at rest in horizontal position (T0) and during 90° head-up tilt (T90). In addition to coarse-graining-free methods, like PCE and APCE, we computed coarse-graining-based k-nearest-neighbor conditional entropy (KNNCE) for comparison. Markers were computed over 256 consecutive HP values, thus targeting the complexity of short-term cardiac control. PCE was unable to detect the decrease of HP variability complexity during AT compared to B, while APCE and KNNCE could. All the conditional entropy markers found a decrease in HP variability complexity during T90 compared to T0. Only APCE was correlated with KNNCE in both protocols. We conclude that APCE is more reliable than PCE in assessing cardiac control complexity, likely due to the better ability of APCE in the presence of the low signal-to-noise ratio of HP dynamics observed during AT.

Heart Rate Variability (HRV) analysis allows for assessing autonomic control from the beat-by-beat dynamics of the time series of cardiac intervals. However, some HRV indices may strongly correlate with the mean heart rate, possibly flawed by the interpretation of HRV changes in terms of autonomic control. Therefore, this study aims to (1) investigate how HRV indices of fluctuation amplitude and multiscale complex dynamics of cardiac time series faithfully describe the autonomic control at different heart rates through a mathematical model of the generation of cardiac action potentials driven by realistically synthesized autonomic modulations; and (2) propose an alternative procedure of HRV analysis less sensitive to the mean heart rate. Results on the synthesized series confirm a strong dependency of amplitude indices of HRV on the mean heart rate due to a nonlinearity in the model, which can be removed by our procedure. Application of our procedure to real cardiac intervals recorded in different postures suggests that the dependency of these indices on the heart rate may importantly affect the physiological interpretation of HRV. By contrast, multiscale complexity indices do not substantially depend on the heart rate provided that multiscale analyses are defined on a time- rather than a beat-basis.

Physical systems are widely characterized in terms of their complex dynamics in physiology and medicine to understand the ability of a living system to adapt to external perturbations [...]

Multisystem Inflammatory Syndrome in Children (MIS-C) is a rare paediatric condition associated with SARS-CoV-2 infection. Its pathophysiology involves an abnormal immune response leading to multi-organ involvement, with symptoms necessitating hospitalization and high-dose immunotherapy. Although patients usually recover with treatment, the long-term impact on cardiopulmonary function remains unclear, particularly regarding the resumption of competitive or recreational sports activities. This study aimed to investigate the potential long-term effects of MIS-C on cardiopulmonary performance through a 9-month follow-up, assessing recovery and readiness for physical activities in affected children aged 8–18 years. Eighteen children with prior MIS-C (diagnosed ≥6 months earlier) and 17 age-matched healthy controls (CNT) were evaluated. Participants underwent baseline testing, including spirometry and ECG, as well as cardiopulmonary exercise testing (CPET). Physical activity levels were assessed using the International Physical Activity Questionnaire (IPAQ). No significant differences were observed between MIS-C patients and controls in terms of anthropometric data or spirometry parameters, including FVC (MIS-C: 3.14 ± 1.06; CNT: 3.07 ± 0.90 L; mean ± SD, P = ns) and FEV1 (MIS-C: 2.69 ± 0.84; CNT: 2.61 ± 0.82 L). CPET peak parameters also showed no differences between groups, with similar oxygen consumption (MIS-C: 31.8 ± 8.3; CNT: 31.6 ± 7.3 mL/min/kg), O2 pulse (MIS-C: 11.7 ± 4.5; CNT: 11.0 ± 2.7 mL/beat), ventilation (MIS-C: 49.1 ± 13.9; CNT: 48.5 ± 15.4 L/min), and heart rate recovery at 1 minute (MIS-C: 135 ± 16 bpm; CNT: 130 ± 20 bpm). Habitual physical activity levels, measured in weekly hours, were also similar between groups. However, one MIS-C patient developed peri-myocarditis following SARS-CoV-2 reinfection during the follow-up period, failing to meet the "Return to Play" criteria. This case underscores the potential vulnerability of certain individuals to SARS-CoV-2 and its variants. Most children with prior MIS-C demonstrated complete recovery of cardiopulmonary function within 9 months of the acute phase, supporting their safe return to physical and sports activities. However, rare cases of persistent cardiac involvement highlight the need for further investigation into the long-term cardiovascular impact of the virus. Future studies are essential to confirm these findings and address remaining uncertainties regarding MIS-C's medium- and long-term effects.

Outdoor physical activity is known to improve cardiovascular health and stress regulation. The practice of Shinrin-Yoku (Forest Bathing) emphasizes the role of natural environments in enhancing well-being. However, how nature versus urban walking impacts physiological and biochemical responses need to be further explored. We aimed to analyse the effects of walking exercise in different outdoor environments (nature vs. urban) on cardiovascular, autonomic, hormonal, and inflammatory parameters measured immediately before and after exercise. Ten participants completed questionnaires on personal data, habitual physical activity, and dietary habits. Physiological and biochemical measurements included systolic and diastolic blood pressure, heart rate, parasympathetic heart rate variability indices (SDNN and pNN50%), oxygen saturation, salivary cortisol levels, inflammatory markers (IL-6 and IL-10), serotonin, β-endorphins, and irisin. These parameters were assessed pre- and post-exercise following Nature walking, performed in a forest and Urban walking, conducted in a city. Both walking sessions occurred on flat paths, at 4 km/h, and at the same time of day. Participants had an age of 50.3±14.6 (m±SD) years, height of 171±19 cm, and weight of 70.4±12.7 kg. Regarding physical activity, 40% engaged in intense activity, while 20% did not perform moderate or intense activity but were sufficiently active based on their weekly METs (IPAQ Questionnaire). Dietary habits, assessed using the MEDAS-14 questionnaire, indicated medium-to-good adherence to the Mediterranean diet. From pre-exercise condition, systolic blood pressure decreased (from pre to post exercise) after nature walking (-6±7 mmHg, p<0.05) but not after urban walking (-8±12 mmHg). Diastolic blood pressure decreased only after urban walking (p<0.05). Oxygen saturation dropped after nature walking (-1.2±1.2%, p<0.05). Heart rate increased after both walks, with no significant differences between the two environments. SDNN and pNN50% were higher (p<0.05) during the immediate recovery after nature walking compared to urban walking. Surprisingly, salivary cortisol decreased after urban walking (-2.1±2.2 ng/ml, p<0.05) but only slightly after nature walking (-0.5±1.5 ng/ml, not significant), serotonin increased only after urban walking (p<0.05), and irisin increased after urban walking (p<0.05) but decreased after nature walking (p<0.05). Nature walking improved HRV parameters, suggesting enhanced immediate parasympathetic activity. However, urban walking showed greater reductions in cortisol levels and increases in serotonin and irisin, indicating mid-term potential benefits associated with physical activity in more familiar and controlled environments. These findings suggest different effects of outdoor environmental contexts on many physiological parameters, underscoring the potential for customized exercise interventions in preventive cardiology.

Continuous adaptations of the movement system to changing environments or task demands rely on superposed fractal processes exhibiting power laws, that is, multifractality. The estimators of the multifractal spectrum potentially reflect the adaptive use of perception, cognition, and action. To observe time-specific behavior in multifractal dynamics, a multiscale multifractal analysis based on DFA (MFMS-DFA) has been recently proposed and applied to cardiovascular dynamics. Here we aimed at evaluating whether MFMS-DFA allows identifying multiscale structures in the dynamics of human movements. Thirty-six (12 females) participants pedaled freely, after a metronomic initiation of the cadence at 60 rpm, against a light workload for 10 min: in reference to cycling (C), cycling while playing “Tetris” on a computer, alone (CT) or collaboratively (CTC) with another pedaling participant. Pedal revolution periods (PRP) series were examined with MFMS-DFA and compared to linearized surrogates, which attested to a presence of multifractality at almost all scales. A marked alteration in multifractality when playing Tetris was evidenced at two scales, τ ≈ 16 and τ ≈ 64 s, yet less marked at τ ≈ 16 s when playing collaboratively. Playing Tetris in collaboration attenuated these alterations, especially in the best Tetris players. This observation suggests the high sensitivity to cognitive demand of MFMS-DFA estimators, extending to the assessment of skill/demand interplay from individual behavior. So, by identifying scale-dependent multifractal structures in movement dynamics, MFMS-DFA has obvious potential for examining brain-movement coordinative structures, likely with sufficient sensitivity to find echo in diagnosing disorders and monitoring the progress of diseases that affect cognition and movement control.

Little is known about the effect of using an attentional focus instruction on motor performance in people with intellectual disabilities. Therefore, this study explored the effects of different attentional focus instructions on gross motor skill performances in individuals with Down syndrome. Seven community-dwelling participants (age 25.2±3.2 yrs, height 1.70±0.04 m, body mass 72.0±6.3 kg) voluntarily participated in the study. Motor performance on 5-meter running (5m sprint), vertical jump (countermovement jump with arm swing, CMJ), broad jump (standing broad jump, SBJ), forward medball throw (FMBT) or overhead medball backward throw (OMBT) and rising-up from a chair (five repetition sit-to-stand, 5STS) were recorded while performing internal-focus (IF) or external-focus (EF) instructions. EF induced significantly (p<0.05) better performance than IF in CMJ (EF: 15±9 cm; IF: 11±8 cm, median ±interquartile range), SBJ (EF: 0.8±1.05 m; IF: 0.5±1.0 m), FMBT (EF: 1.5±1.4 m; IF: 1.4±1.1 m), OMBT (EF: 4.0±1.5 m; IF: 3.6±1.1 m) and 5STS (EF: 14.2±5.4; IF:15.3±7.7 s). The time over the 5m sprint tended to be shorter with EF (4.0±2.0 s) than IF (5.05±3.3 s) but the difference did not reach the statistical significance (p = 0.29). Physical trainers and school teachers should be encouraged to manage different types of attentional focus instructions to improve cognitive and gross motor performances in persons with Down syndrome.

Background: Multisystem Inflammatory Syndrome in Children (MIS-C) has emerged as a severe pediatric complication during the SARS-CoV-2 pandemic, with potential long-term cardiovascular repercussions. We hypothesized that heart rate and blood pressure control at rest and during postural maneuvers in MIS-C patients, months after the remission of the inflammatory syndrome, may reveal long-term autonomic dysfunctions. Methods: We assessed 17 MIS-C patients (13 males; 11.9 ± 2.6 years, m ± SD) 9 months after acute infection and 18 age- (12.5 ± 2.1 years) and sex- (13 males) matched controls. Heart rate and blood pressure variability, baroreflex function, and hemodynamic parameters were analyzed in supine and standing postures. Results: MIS-C patients exhibited reduced heart rate variability, particularly in parasympathetic parameters during standing (pNN50+: 6.1 ± 6.4% in controls, 2.5 ± 3.9% in MIS-C; RMSSD: 34 ± 19 ms in controls, 21 ± 14 ms in MIS-C, p < 0.05), with no interaction between case and posture. Blood pressure variability and baroreflex sensitivity did not differ between groups except for the high-frequency power in systolic blood pressure (3.3 ± 1.2 mmHg2 in controls, 1.8 ± 1.2 mmHg2 in MIS-C, p < 0.05). The MIS-C group also showed lower diastolic pressure–time indices (DPTI) and systolic pressure–time indices (SPTI), particularly in standing (DPTI: 36.2 ± 9.4 mmHg·s in controls, 29.4 ± 6.2 mmHg·s in MIS-C; SPTI: 26.5 ± 4.3 mmHg·s in controls, 23.9 ± 2.4 mmHg·s in MIS-C, p < 0.05). Conclusions: Altered cardiovascular autonomic control may persist in MIS-C patients with, however, compensatory mechanisms that may help maintain cardiovascular homeostasis during light autonomic challenges, such as postural maneuvers. These results highlight the importance of assessing long-term cardiovascular autonomic control in children with MIS-C to possibly identify residual cardiovascular risks and inform targeted interventions and rehabilitation protocols.

Individuals with Down Syndrome exhibit deficits in muscle strength and cardiovascular adaptation, which limit athletic performance. We compared a maximum-intensity 50 m front crawl test between competitive male swimmers with Down Syndrome (SDS; n = 11; 26.5 ± 5.6 years; m ± SD) and a control group of swimmers (CNT; n = 11; 27.1 ± 4.0 years) with similar training routines (about 5 h/week). Wearable sternal sensors measured their heart rate and 3D accelerometry. The regularity index Sample Entropy (SampEn) was calculated using the X component of acceleration. The total times (SDS: 58.91 ± 13.68 s; CNT: 32.55 ± 3.70 s) and stroke counts (SDS: 66.1 ± 9.6; CNT: 51.4 ± 7.4) were significantly higher in the SDS group (p < 0.01). The heart rate was lower in the SDS group during immediate (SDS: 129 ± 15 bpm; CNT: 172 ± 11 bpm) and delayed recovery (30 s, SDS: 104 ± 23 bpm; CNT: 145 ± 21 bpm; 60 s, SDS: 79 ± 27 bpm; CNT: 114 ± 27 bpm) (p < 0.01 for all the comparisons). The SampEn of sternal acceleration showed no differences between the groups and between 0–25 m and 25–50 m. Body pitch correlated strongly with performance in the SDSs (R2 = 0.632, p < 0.01), but during the first 25 m only. The high-intensity front crawl performances differed between the SDS and CNT athletes in terms of time, biomechanics, and training adaptation, suggesting the need for tailored training to improve swimming efficiency in SDSs.

Brain injuries may compromise the heart-brain axis resulting in altered heart rate variability (HRV). Thus, we aim to identify the HRV indices better reflecting the improvements in the heart-brain connections expected to occur in brain-injured patients undergoing rehabilitation. We enrolled 21 patients with Disorder of Consciousness (DoC) admitted to our rehabilitation center after a brain lesion. HRV was assessed at rest and during a reactivity test. The assessments were performed twice: 1) at admission and 2) at discharge from a rehabilitation program. Overall, the patients’ clinical conditions were improved at discharge. Spectral powers with frequency $\gt0.05 \mathrm{~Hz}$ increased with medium effect size after rehabilitation. The self-similarity coefficients at scales around 18 s decreased after rehabilitation, with an almost large effect size during the reactivity test. Thus, some HRV measures change at the end of a rehabilitation program in parallel with a general clinical improvement in DoC patients.

A stroke represents a significant medical condition characterized by the sudden interruption of blood flow to the brain, leading to cellular damage or death. The impact of stroke on individuals can vary from mild impairments to severe disability. Treatment for stroke often focuses on gait rehabilitation. Notably, assessing muscle activation and kinematics patterns using electromyography (EMG) and stereophotogrammetry, respectively, during walking can provide information regarding pathological gait conditions. The concurrent measurement of EMG and kinematics can help in understanding disfunction in the contribution of specific muscles to different phases of gait. To this aim, complexity metrics (e.g., sample entropy; approximate entropy; spectral entropy) applied to EMG and kinematics have been demonstrated to be effective in identifying abnormal conditions. Moreover, the conditional entropy between EMG and kinematics can identify the relationship between gait data and muscle activation patterns. This study aims to utilize several machine learning classifiers to distinguish individuals with stroke from healthy controls based on kinematics and EMG complexity measures. The cubic support vector machine applied to EMG metrics delivered the best classification results reaching 99.85% of accuracy. This method could assist clinicians in monitoring the recovery of motor impairments for stroke patients.