Search

A large body of evidence has been provided that cardiac autonomic control is deranged in heart failure. It is also commonly accepted that aging is characterized by several molecular and structural changes in organs and tissues, and per se affects cardiac autonomic control. Hence, as far as we are concerned with heart failure in the elderly, both cardiac diseases and age are likely to contribute to the autonomic dysfunction of these patients. In the first part a brief review to the methods currently used to assess the autonomic control of the cardiovascular function in human subjects is reported. Then, major findings on the relationship between aging and cardiac autonomic indexes in normal subjects are presented. In the third part, main concept and experimental observations on autonomic dysfunction in heart failure are reviewed. Finally, some basic considerations on the relationship between aging, cardiac autonomic function and heart failure are introduced. 1. A brief review to the methods currently used to assess the autonomic control of the cardiovascular function in human subjects is reported. 2. The relationship between aging and cardiac autonomic indexes in normal subjects are presented. 3. Main concept and experimental observations on autonomic dysfunction in heart failure are reviewed.

Although heart rate variability (HRV) decreasing has been usually described in obstructive sleep apnea syndrome (OSAS), some studies have recently questioned the validity of spectral HRV analysis in presence of respiratory and arrhythmic disorders. Fractal analysis of HRV is an emerging nonlinear technique overcoming these limitations and allowing short term HRV assessment during hypo/apnea phases. The aim of this study is to analyse the Fractal features in sleep apnea in order to find as these characteristics could change during abnormal respiration patterns in OSAS. We studied 30 polysomnographic recordings of severe OSAS (AHl30) pts. (age 55±9) and 10 PR of normal subjects (age 46±4). Hypo/apnea phases and related beat-to-beat time series have been detected and classified by automated algorithms and manually verified by expert technicians. Fractal analysis was performed by the Higuchi algorithm (FD). Results showed that while FD does not significantly differ between Normals (l.6J±0.09) and normal breath epochs in OSAS, it significantly (p

Upper limb reaching movements (RM) are the most used motor task in robotic rehabilitation treatments of several disorders of the arm and the shoulder. Robotic rehabilitation allow to record quantitative data about movement patterns that can help clinicians to better address the rehabilitation protocols providing information not captured using clinical measures, but the biomechanical parameters proposed until today, to evaluate the quality of the movement, are related to the specific robot used and to the type of exercise performed and are not yet standardized. In this paper a quantitative kinematic assessment of robot assisted upper arm free reaching movements is proposed. Particularly, the effect of rotator cuff tendinopathy on kinematic patterns during horizontal movements has been evaluated

Human upper limb is involved in many daily human activities. The muscle activities during basic and daily upper-limb motions are an important area of research in rehabilitation field in order to evaluate the recovery of patients affected by congenital or acquired brain injury. Much better results in sensorimotor and cognitive processes are promised by the emerging robot-mediated therapy. Although the shoulder is the most complex joint in the body, both as to freedom range and for the musculartendon structure, not so many research devices have been proposed to study its movements and no study has proposed standardized electromyographic assessment during robot-assisted reaching movements of the upper arm. This study aimed to develop a quantitative assessment of the electromyographic pattern of the arm???s muscles involved in reaching movements robot-assisted by means of indices used to describe effectively the main features of the pattern in five normal subjects to implement rehabilitation strategies patients oriented.

During human walking, the muscle activity of the lower extremities needs to be well coordinated to provide support, dynamic balance, propulsion, and foot clearance. Clinical aspects of patients who are hemiplegic as a result of stroke vary according to the damaged region of brain tissue, its size, and the cause of damage. Functional recovery of limb mobility of patients with spinal or cerebral injuries can take great advantage of the basic role played by sensorial and proprioceptive stimulations. On this base the Institute of Biomedical Problems of the Russian Academy of Sciences have recently developed the ???Regent Suit??? (RS), an experimental medical device derived from a suit worn by astronauts for therapeutical purposes during space flights. Although preliminary studies describe rehabilitation outcome of the RS in stroke, EMG changes induced by the suit are not known. Aim of the paper is to describe the effects of RS on lower limb EMG patterns on hemiparetic subjects

Although symbolic dynamics analysis (SDA) has been proposed for encoding words of different length and symbols, the resulting rapidly growing number of patterns has limited its clinical use. Aim of this study is to propose new SDA indices tested on a clinical data-set. We studied 40 ECG Holter of normal (NR), post-MI (MI), heart failure (HF) and transplanted (TR) subjects. RR differences were encoded into 5 symbols, deriving 3, 5 and 7 length words classified by a dominance's criterion in pattern words with a predominant vagal content (V), decelerating content (D), accelerating content (A), sympathetic content (S) and without variability content (0). Their distributions were then quantified by Kurtosis an Chi-square indexes. Results showed an optimum word-length of 3, where both Kurtosis (2.2±0.6; 2.2±0.9; 3.1±0.9; 4.0±0.4) and Chi-square (7±5; 8±5; 26±17; 106±42, respectively for N, MI, HF and TR) showed very significant p

Among the plethora of indices that can describe the fractal-like behaviour of heart rate variability (HRV), the fractal dimension (FD) and the power-law exponent (β) have gained wide acceptance. Since HRV is generally modelled with fractional Brownian motion (fBm), the linear scaling relationship between β and FD, valid for fBm, is often applied to HRV series to derive one index from the other. In this paper the relationship between β and FD is calculated in normal (NR) and heart failure (HF) HRV series. Results revealed that a linear dependence between β and FD can be found only when the slope of the spectral density is calculated over the whole spectrum instead of considering more widespread very low frequency ranges. Moreover, the relationship is slightly different from that characterizing fBm and is not unique for the two categories of subjects. The common practice of estimating β from FD for HRV applying the theoretical relationship should be reconsidered.

Pathologies which imply motor impairment are most common and very studied. The aim of the study is to explore the repeatability of kinematic parameters related to the Timed Up and Go test in different pathologies: hemiparesis, femur fracture, hip replacement and knee replacement. We performed the study instrumenting the patients with a commercial wearable inertial system for gait analysis: G-WALK System by BTS Bioengineering Inc. A cohort of 40 patients with neurological and orthopedic pathologies was enrolled in the study. Repeatability was assessed through the calculation of the Intraclass Correlation Coefficient. Study results showed that the motion parameters exhibited different repeatability. Moreover their repeatability changed on the basis of the kind of pathology under examination. The study demonstrated the importance of a repeatability study to be a valuable approach to select the kinematic parameters which are be able to better characterize a specific pathology and consequently the rehabilitation outcome of patients. The future investigations on enriched datasets will further confirm these preliminary results.

Despite the growing use of different wearable inertial systems, increasingly diffused in clinical practice, there is still a lack of knowledge about the agreement between systems based also on different sensor configuration. Aim of the study has been the investigation of the agreement between Opal and G-Walk wearable inertial systems in gait analysis on normal and post stroke subjects. Although both systems are able to describe significant gait differences in the two populations, study results suggest that gait analysis evaluations carried out by different inertial systems does not give completely overlapping estimation about the different parameters and that this must be taken in correct account especially comparing results of clinical trials obtained by different systems and sensor’s placements.

To evaluate the relationship between lesion's severity and nonlinear indexes of HRV, 20 first-ever stroke subjects and 10 healthy subjects were studied. All patients, divided in two groups according to presence of single or multiple medium cerebral artery lesion, underwent to a 24-hour Hotter ECG recording. All RR time series were analyzed by Poincare Plot, fractal dimension, power-law behaviour, spectral and time- domain techniques. A direct relationship between increasing lesion's severity and progressive collapsing of PPlots and FD index was observed, while lower significance were found for beta exponent, spectral and time-domain parameters. These results suggest that PPlots and FD analysis contains relevant information related to different HRV dynamics in normal and stroke subjects with different lesion's severity.

The impact of neurodegenerative disorders is twofold; they affect both quality of life and healthcare expenditure. In the case of Parkinson’s disease, several strategies have been attempted to support the pharmacological treatment with rehabilitation protocols aimed at restoring motor function. In this scenario, the study of upper limb control mechanisms is particularly relevant due to the complexity of the joints involved in the movement of the arm. For these reasons, it is difficult to define proper indicators of the rehabilitation outcome. In this work, we propose a methodology to analyze and extract an ensemble of kinematic parameters from signals acquired during a complex upper limb reaching task. The methodology is tested in both healthy subjects and Parkinson’s disease patients (N = 12), and a statistical analysis is carried out to establish the value of the extracted kinematic features in distinguishing between the two groups under study. The parameters with the greatest number of significances across the submovements are duration, mean velocity, maximum velocity, maximum acceleration, and smoothness. Results allowed the identification of a subset of significant kinematic parameters that could serve as a proof-of-concept for a future definition of potential indicators of the rehabilitation outcome in Parkinson’s disease.

Background: After the acute disease, convalescent coronavirus disease 2019 (COVID-19) patients may experience several persistent manifestations that require multidisciplinary pulmonary rehabilitation (PR). By using a machine learning (ML) approach, we aimed to evaluate the clinical characteristics predicting the effectiveness of PR, expressed by an improved performance at the 6-min walking test (6MWT). Methods: Convalescent COVID-19 patients referring to a Pulmonary Rehabilitation Unit were consecutively screened. The 6MWT performance was partitioned into three classes, corresponding to different degrees of improvement (low, medium, and high) following PR. A multiclass supervised classification learning was performed with random forest (RF), adaptive boosting (ADA-B), and gradient boosting (GB), as well as tree-based and k-nearest neighbors (KNN) as instance-based algorithms. Results: To train and validate our model, we included 189 convalescent COVID-19 patients (74.1% males, mean age 59.7 years). RF obtained the best results in terms of accuracy (83.7%), sensitivity (84.0%), and area under the ROC curve (94.5%), while ADA-B reached the highest specificity (92.7%). Conclusions: Our model enables a good performance in predicting the rehabilitation outcome in convalescent COVID-19 patients.

After the acute disease, post-COVID-19 patients may present several and persistent symptoms, known as the new paradigm of "post-acute COVID-19 syndrome". This necessitates a multidisciplinary rehabilitation that has been proposed but whose effectiveness is still to be assessed. In this study, convalescent COVID-19 patients undergoing pulmonary rehabilitation (PR) after reporting long-term symptoms were consecutively enrolled. Then, they were grouped by laboratory parameters at admission through an unsupervised Machine Learning (ML) approach. We aimed to identify potential indicators that could discriminate several phenotypes leading to a different responsiveness to the rehabilitation program. A k-means clustering method was performed; then, statistical analysis was employed to compare clinical and hematochemical parameters of the obtained clusters. The dataset consisted of 78 patients (84.8% males, mean age 60.72 years). The optimal number for clustering was k=2 with a silhouette coefficient of 0.85, and D-Dimer resulted the most discriminating parameter, thus confirming its role as a marker of inflammation. The phenotypes exhibited statistically significant differences in terms of age (p=0.007), packs of cigarettes per year (p=0.003), uricemia (p=0.010), PCR (p=0.026), D-Dimer (p

Heart rate is a nonstationary signal and its variation may contain indicators of current disease or warnings about impending cardiac diseases. Hence, heart rate variation analysis has become a noninvasive tool to further study the activities of the autonomic nervous system. In this scenario, the Poincaré plot analysis has proven to be a valuable tool to support cardiac diseases diagnosis. The study’s aim is a preliminary exploration of the feasibility of machine learning to classify subjects belonging to five cardiac states (healthy, hypertension, myocardial infarction, congestive heart failure and heart transplanted) using ten unconventional quantitative parameters extracted from bidimensional and three-dimensional Poincaré maps. Knime Analytic Platform was used to implement several machine learning algorithms: Gradient Boosting, Adaptive Boosting, k-Nearest Neighbor and Naïve Bayes. Accuracy, sensitivity and specificity were computed to assess the performances of the predictive models using the leave-one-out cross-validation. The Synthetic Minority Oversampling technique was previously performed for data augmentation considering the small size of the dataset and the number of features. A feature importance, ranked on the basis of the Information Gain values, was computed. Preliminarily, a univariate statistical analysis was performed through one-way Kruskal Wallis plus post-hoc for all the features. Machine learning analysis achieved interesting results in terms of evaluation metrics, such as demonstrated by Adaptive Boosting and k-Nearest Neighbor (accuracies greater than 90%). Gradient Boosting and k-Nearest Neighbor reached even 100% score in sensitivity and specificity, respectively. The most important features according to information gain are in line with the results obtained from the statistical analysis confirming their predictive power. The study shows the proposed combination of unconventional features extracted from Poincaré maps and well-known machine learning algorithms represents a valuable approach to automatically classify patients with different cardiac diseases. Future investigations on enriched datasets will further confirm the potential application of this methodology in diagnostic.

Many work-activities can imply a biomechanical overload. Among these activities, lifting loads may determine work-related musculoskeletal disorders. In order to limit injuries, the National Institute for Occupational Safety and Health (NIOSH) proposed a methodology for assessing biomechanical risk in lifting tasks by means of a math formula based on intensity, duration, frequency and other geometrical characteristic of the lifting. In this work, we explored the feasibility of tree-based machine learning algorithms to classify biomechanical risk according to the Revised NIOSH lifting equation. Electromyography signals acquired from the biceps during lifting loads were collected using a wearable sensors for surface electromyography on a study population composed of 5 healthy young subjects. The EMG signals were segmented in order to extract the region of interest related to the lifting actions and for each region of interest several features in time and frequency domains were extracted. High results - greater than 95% - were obtained in terms of evaluation metrics for a binary risk/no-risk classification. In conclusion, this work indicates the proposed combination of features and machine learning algorithms represents a valid approach to automatically classify risk activities according to the Revised NISOH lifting equation. Future investigation on enriched study population could confirm the potentiality of this methodology to automatically classify potential risky activities.

The use of e-textile technologies spread out in the scientific research with several applications in both medical and nonmedical world. In particular, wearable technologies and miniature electronics devices were implemented and tested for medical research purposes. In this paper, a systematic review regarding the use of e-textile for clinical applications was conducted: the Scopus and Pubmed databases were investigate by considering research studies from 2010 to 2020. Overall, 262 papers were found, and 71 of them were included in the systematic review. Of the included studies, 63.4% focused on information and communication technology studies, while the other 36.6% focused on industrial bioengineering applications. Overall, 56.3% of the research was published as an article, while the remainder were conference papers. Papers included in the review were grouped by main aim into cardiological, muscular, physical medicine and orthopaedic, respiratory, and miscellaneous applications. The systematic review showed that there are several types of applications regarding e-textile in medicine and several devices were implemented as well; nevertheless, there is still a lack of validation studies on larger cohorts of subjects since the majority of the research only focuses on developing and testing the new device without considering a further extended validation.

The reduction of healthcare-associated infections (HAIs) is one of the most important issues in the healthcare context for every type of hospital. In three operational units of the Scientific Clinical Institutes Maugeri SpA SB, a rehabilitation hospital in Cassano delle Murge (Italy), some corrective measures were introduced in 2017 to reduce the occurrence of HAIs. Lean Six Sigma was used together with the Define, Measure, Analyze, Improve, Control (DMAIC) roadmap to analyze both the impact of such measures on HAIs and the length of hospital stay (LOS) in the Rehabilitative Cardiology, Rehabilitative Neurology, Functional Recovery and Rehabilitation units in the Medical Center for Intensive Rehabilitation. The data of 2415 patients were analyzed, considering the phases both before and after the introduction of the measures. The hospital experienced a LOS reduction in both patients with and without HAIs; in particular, Cardiology had the greatest reduction for patients with infections (−7 days). The overall decrease in HAIs in the hospital was 3.44%, going from 169 to 121 cases of infections. The noteworthy decrease in LOS implies an increase in admissions and in the turnover indicator of the hospital, which has a positive impact on the hospital management as well as on costs.

Heart-rate variability has proved a valid tool in prognosis definition of patients with congestive heart failure (CHF). Previous research has documented Poincaré plot analysis as a valuable approach to study heart-rate variability performance among different subjects. In this paper, we explored the possibility to feed machine-learning (ML) algorithms using unconventional quantitative parameters extracted from Poincaré plots (generated from 24-h electrocardiogram recordings) to classify patients with CHF belonging to different New York Heart Association (NYHA) classes. We performed in sequence the following investigations: first, a statistical analysis was carried out on 9 morphological parameters, automatically measured from Poincaré plots. Subsequently, a feature selection through a wrapper with a 10-fold cross-validation method was performed to find the best subset of features which maximized the classification accuracy for each considered ML algorithm. Finally, patient classification was assessed through a ML analysis using AdaBoost of Decision Tree, k-Nearest Neighbors and Naive Bayes algorithms. A univariate statistical analysis proved 5 out of 9 parameters presented statistically significant differences among patients of distinct NYHA classes, similarly, a multivariate logistic regression confirmed the importance of the parameter ρy in the separability between low-risk and high-risk classes. The ML analysis achieved promising results in terms of evaluation metrics (especially the Naive Bayes algorithm), with accuracies greater than 80% and Area Under the Receiver Operating Curve indices greater than 0.7 for the overall three algorithms. The study indicates the proposed features have a predictive power to discriminate the NYHA classes, to which the features seem evenly correlated. Despite the NYHA classification being subjective and easily recognized by cardiologists, the potential relevance in the clinical cardiology of the proposed features and the promising ML results implies the methodology could be a valuable approach to automatically classify CHF. Future investigations on enriched datasets may further confirm the presented evidence.

Hereditary Spastic Paraplegia (HSP) is a rare inherited neurological disorder, whose predominant feature is a spastic gait. Gait analysis represents an objective tool to quantify the impairment of gait pattern in patients with HSP, thus supporting diagnosis and monitoring of disease progression. This study contributes to the characterization of HSP pathological gait, providing the assessment of test-retest repeatability of 122 parameters regarding postural sway, anticipatory postural adjustment in step initiation, gait and turn tasks. Data are collected on a cohort of thirty-five HSP patients, performing three consecutive repetitions of the Instrumented Stand and Walk (iSAW) test provided by Mobility Lab gait analysis system by APDM. Intraclass Correlation Coefficient (ICC) is used to assess repeatability. Repeatability Limit (RL) has also been evaluated and compared to the absolute value of difference (DoM) of HSP patients' measurements mean and normative mean of the same variable, in order to understand which variable can better characterize HSP gait with respect to normal gait. Results show that gait and turn measurements are more repeatable than sway and anticipatory postural adjustments variables. Furthermore, this study confirms previous findings in this field, identifying, among other gait parameters, cadence, gait velocity, stride length and RoM of the shanks as the main distinctive parameters of the pathology. Conversely, the RoM of the knees presents excellent repeatability, but low difference between healthy and pathological subjects.

SWEET Sock is a wearable e-textile sock for gait analysis. It is based on the acquisition and digital processing of the angular velocities of the lower limbs. In this paper we focus on the study of test-retest reliability of this system in measuring spatio-temporal gait parameters. The analysis was simultaneously conducted on data acquired by a multicamera system for gait analysis (SMART-DX 700 by BTS), in order to have reference values. A group of healthy subjects, equipped with both systems, performed four repeated walking tests along an 11 m walkway, consecutively and under constant conditions. The four tests were repeated at preferred, slow and fast self-selected walking speed. The Intraclass Correlation Coefficient (ICC) and Minimum Detectable Change (MDC) were evaluated to assess the repeatability of the measures. ICC values range from moderate to excellent for all gait parameters assessed by smart socks. The novel system presents test-retest reliability values comparable to, if not higher than, those shown by the gold standard. Finally, the results of gait reliability as a function of walking speed show excellent ICCs and very low MDCs for all parameters evaluated on trials at fast velocity, supporting the referenced hypothesis that faster movement is more consistent.

Progressive supranuclear palsy (PSP) is a rare and rapidly progressing atypical parkinsonism. Albeit existing clinical criteria for PSP have good specificity and sensitivity, there is a need for biomarkers able to capture early objective disease-specific abnormalities. This study aimed to identify gait patterns specifically associated with early PSP. The study population comprised 104 consecutively enrolled participants (83 PD and 21 PSP patients). Gait was investigated using a gait analysis system during normal gait and a cognitive dual task. Univariate statistical analysis and binary logistic regression were used to compare all PD patients and all PSP patients, as well as newly diagnosed PD and early PSP patients. Gait pattern was poorer in PSP patients than in PD patients, even from early stages. PSP patients exhibited reduced velocity and increased measures of dynamic instability when compared to PD patients. Application of predictive models to gait data revealed that PD gait pattern was typified by increased cadence and longer cycle length, whereas a longer stance phase characterized PSP patients in both mid and early disease stages. The present study demonstrates that quantitative gait evaluation clearly distinguishes PSP patients from PD patients since the earliest stages of disease. First, this might candidate gait analysis as a reliable biomarker in both clinical and research setting. Furthermore, our results may offer speculative clues for conceiving early disease-specific rehabilitation strategies.

Unilateral Spatial Neglect is a cognitive impairment of neuropsychological interest that is a consequence of stroke able to influence negatively the rehabilitation outcome of patients with stroke. The aim of the study is to explore the feasibility of machine learning to classify stroke patients with and without unilateral spatial neglect using clinical features. We performed the study using a machine learning approach by means the following tree-based algorithms: Decision Tree, Random Forest, Rotation Forest, AdaBoost of decision stumps and Gradient Boost tree using six clinical features both numerical and nominal: Montreal Cognitive Assessment, Functional Independence Measure scale, Barthel Index, aetiology, site of brain lesion and presence of hemiparesis at lower limbs. Tree-based Machine learning analysis achieved interesting results in terms of evaluation metrics scores; the best algorithm was Random Forest with an Accuracy, Sensitivity, Specificity, Precision and Area under the Receiver Operating Characteristic curve equal to 0.92, 0.83, 1.00, 1.00, 0.95 respectively. The study demonstrated the proposed combination of clinical features and algorithms represents a valuable approach to automatically classify stroke patients with and without Unilateral Spatial Neglect. The future investigations on enriched datasets will further confirm the potential application of this methodology as prognostic support to be chosen among those already implemented in the clinical field.

The study of posture and gait abnormalities has revealed over years potential information to improve the rehabilitation outcome of several classes of ill patients; nevertheless, this results still an area of research almost completely unexplored in the case of obese patients. Consequently, this study was designed as a preliminary investigation to determine potential statistical correlations between kinematic features and “gold standard” methodologies in the field, e.g., the Western Ontario and Mc Master University scale and the Barthel index. To this aim, physicians prepared bioelectrical impedance analyses and clinical assessments to evaluate patients' clinical scores, while biomedical engineers have organized Instrumented Stand and Walking tests to quantify several kinematic features using a microelectromechanical system equipped by a series of inertial measurement units. Finally, a statistical correlation analysis has allowed to reveal several features – related to patients’ anticipatory postural adjustments movements and gait – demonstrated a mild and moderate correlation with some clinical indices. In conclusion, this paper presents a novel view to address and design innovative rehabilitation strategies for obese patients.

Studies and reviews show that the vast majority of students around the world use heavy and uncomfortable backpacks, which could negatively affect their skeletal-muscle development or at least generate a non-physiological functional overload and a change in the kinematics of gait. The purpose of this study is to investigate the role of the school backpack during the execution of the Walk test trying to identify if and how much it affects walking in terms of space-time parameters considering whether it might be correlated to potential spine disorders during the development age. A population-based sample of 98 students (60% female) aging from 10 to 12 years old was studied; gender, age, weight and lower limb length were recorded. Kinematic data were computed using a wearable inertial device for gait analysis: G-WALK System by BTS Bioengineering and analyzed using t-test and Machine Learning. Overall, concerning t-test between free walk and walk with backpack, it emerges a significant statistical difference on 9 out of 10 kinematic parameters, of which 6 with maximum statistical significance (p-value < 0.0001). Machine Learning analysis was carried out through Linear Discriminant Analysis, Naive Bayes, AdaBoost and Random Forest algorithms considering as different classes: free walk and walk with backpack. Accuracy and ROC Area were considered as evaluation metrics. The best performances were reached with Linear Discriminant Analysis with an accuracy of 85.71% and a ROC Area of 0.92. Study results showed a drastic change on kinematic due to the backpack. These results should be taken in correct account to safeguard children’s health wearing backpack for prolonged periods.

Stroke is among the leading causes of death and disability worldwide. Approximately 20–25% of stroke survivors present severe disability, which is associated with increased mortality risk. Prognostication is inherent in the process of clinical decision-making. Machine learning (ML) methods have gained increasing popularity in the setting of biomedical research. The aim of this study was twofold: assessing the performance of ML tree-based algorithms for predicting three-year mortality model in 1207 stroke patients with severe disability who completed rehabilitation and comparing the performance of ML algorithms to that of a standard logistic regression. The logistic regression model achieved an area under the Receiver Operating Characteristics curve (AUC) of 0.745 and was well calibrated. At the optimal risk threshold, the model had an accuracy of 75.7%, a positive predictive value (PPV) of 33.9%, and a negative predictive value (NPV) of 91.0%. The ML algorithm outperformed the logistic regression model through the implementation of synthetic minority oversampling technique and the Random Forests, achieving an AUC of 0.928 and an accuracy of 86.3%. The PPV was 84.6% and the NPV 87.5%. This study introduced a step forward in the creation of standardisable tools for predicting health outcomes in individuals affected by stroke.

The aim of this work is to design and develop a sensorized sock in Electronic Textile (ET), SWEET-Sock. The device has been realized by three textile sensor placed in a specific points of plantar arch and an accelerometer unit, both embedded and connected by conductive thread. The sensors allows the acquisition of plantar pressure and acceleration signals deriving from the motion of the lower limbs. The detected biosignals have been condictionated by a voltage divider and then were acquired through a LilyPad Arduino microcontroller and transmitted using the Simblee BLE technology to a custom made mobile app. Data were afterwards uploaded through a smartphone on a dropbox cloud where a custom made MATLAB GUI platform has been developed for further digital signal processing of main biomechanical parameters of clinical interest in postural and gait analysis.

Human machine interfaces (HMIs) are employed in a broad range of applications, spanning from assistive devices for disability to remote manipulation and gaming controllers. In this study, a new piezoresistive sensors array armband is proposed for hand gesture recognition. The armband encloses only three sensors targeting specific forearm muscles, with the aim to discriminate eight hand movements. Each sensor is made by a force-sensitive resistor (FSR) with a dedicated mechanical coupler and is designed to sense muscle swelling during contraction. The armband is designed to be easily wearable and adjustable for any user and was tested on 10 volunteers. Hand gestures are classified by means of different machine learning algorithms, and classification performances are assessed applying both, the 10-fold and leave-one-out cross-validations. A linear support vector machine provided 96% mean accuracy across all participants. Ultimately, this classifier was implemented on an Arduino platform and allowed successful control for videogames in real-time. The low power consumption together with the high level of accuracy suggests the potential of this device for exergames commonly employed for neuromotor rehabilitation. The reduced number of sensors makes this HMI also suitable for hand-prosthesis control.

Although a very large number of students in the world use uncomfortable and heavy backpacks, their negative influence on gait in terms of spatiotemporal and kinematic parameters are still not well investigated. The purpose of the paper is to investigate the role of the school backpack during the execution of the Timed Up and Go test trying to identify if and how much it affects walking in terms of spatiotemporal and kinematic parameters considering whether it might be correlated to low back pain in children. A population-based sample of 98 children students ages 10-12 years was studied; gender, age, weight and lower limb length were recorded. Data were computed using a wearable inertial device for gait analysis: G-Walk System by BTS Bioengineering and analyzed through Inferential Statistics and Machine Learning. Overall, concerning Inferential Statistics carried out through ANOVA test for each motion parameter between free walk and walk with backpack, it was found that there is a significant statistical difference on 23 out of 30 motion parameters, of which 20 with maximum statistical significance (p

Parkinson’s Disease (PD) is a common neurodegenerative disorder whose clinical picture is characterized by motor and non-motor symptoms. One of motor symptoms is freezing of gait (FoG) that consists in a few seconds during which patients can't start to walk again. In this paper 41 patients affected by PD, with and without FoG, underwent gait analysis performing three gait tasks: normal gait, a motor dual task and a cognitive task. A statistical analysis was performed on clinical, demographical and on the spatial and temporal parameters in order to find any difference between PD patients with and without FoG; the last one obtained no statistically significant results. Thus, a machine learning analysis was implemented employing tree-based algorithms (decision tree, Random Forests, Gradient Boosted Tree, Ada-Boosting of a decision tree) and using as input the spatial and temporal features of gait. The results were promising since accuracy, specificity and sensitivity overcame 90%, reaching also 100% of sensitivity in some cases. The best algorithms were Gradient Boosted Tree and the Ada-Boosting of a decision tree while Random Forests and decision tree obtained lower results. This study proved that machine learning can help to identify patients affected by mild form of FoG that exposes them to a major risk of developing more severe form of freezing with a consequent increased risk of falling.

As an alternative to the traditional methods of analysis in the time and frequency domains regarding heart rate variability, new interest has been concentrated in using a non-linear analysis technique of the beat-beat time series, known as the Poincare Plot Analysis. The parameters provided by the analysis can be used as input for machine learning algorithms in order to distinguish patients in three classes of congestive heart failure, according to the New York Heart Association. Tree-based algorithms for classification and synthetic minority oversampling technique (SMOTE) for balancing the dataset with artificial data were implemented in Knime analytics platform, reaching an overall accuracy between 75% and 80%, specificity and sensitivity greater than 90% in some classes and F-measures ranging from 68% to 92%. Further investigations could be pursued with bigger datasets and avoiding the use of artificial data to balance the classes.

It is well known that the interpretation of cardiotocographic (CTG) signals is still subjective and prone to misinterpretations; as a consequence, there has been an increase of cesarean sections, often not necessary, and initial expectations of significantly reducing perinatal morbidity and mortality have been unattended. Nevertheless, in developed countries, CTG is still the most widely employed prenatal technique for monitoring fetal health; and in many countries it represents a medical report with legal value. To overcome the drawbacks of the visual interpretation, many computerized systems for automatic or semi-automatic analysis of CTG have been developed in the last years. Recently, in order to support the diagnosis process, and to increase the predictive capability of these systems, also other techniques such as artificial neural network, deep learning and machine learning have been introduced. In previous works of the authors, software for automatic CTG analysis has been developed and described in detail. Now, by employing a dataset of features extracted from CTG signals with that software, to enhance its performances, different algorithms, such as J48, Adaboosting, Random Forests and Gradient Boosted Tree, have been tested to predict whether a birth would be a caesarean section or a vaginal delivery. The RF algorithm showed the best performance, since it reached the highest accuracy (87.6%), precision (87.9%) and AUCROC (93.0%). These preliminary results are very satisfying and encouraging; they confirm that to enrich the CTG analysis software with this methodology can help to significantly improve CTG classification. © 2020, Springer Nature Switzerland AG.