Salvatore Parlato

The recording of muscle force can be used to control Human–Machine Interfaces (HMIs). A commonly used estimator of muscle force is the envelope of Electromyography (EMG) signals, which requires proper EMG processing. A potentially more convenient alternative is offered by Forcemyography (FMG), which records muscle mechanical activity and inherently provides a signal that is a good estimator of muscle force, without specific processing. This study aimed to compare the performances of EMG and FMG in muscle force estimation aimed at HMI control. Ten healthy subjects performed 15 gradual and 15 rapid isometric biceps brachii contractions at approximately 90° elbow flexion. Force measured at wrist by a load cell, and FMG and EMG signals were recorded simultaneously. Causal root-mean-square EMG envelopes (EMG-RMS) were computed offline using windows of 100, 250, 500, and 1000 ms. For each participant and contraction type, subject-specific sigmoidal regression models were fitted using normalized signals from the first 10 contractions and evaluated on the remaining five held-out contractions. Performance was assessed using the coefficient of determination (R²), root mean squared error (RMSE), and maximum absolute error (MaAE), with paired Wilcoxon tests and Bonferroni correction. Cross-correlation quantified temporal alignment with the reference force. FMG achieved higher mean R² and lower mean RMSE and MaAE across all tested configurations. Statistical analyses on the errors revealed that FMG achieved performance comparable to that of EMG-RMS in gradual muscle contractions and significantly superior performance in rapid muscle contractions. These findings support FMG-based external force estimation with simpler pre-processing and provide preliminary evidence for future implementation and validation in muscle-controlled HMIs, assistive exoskeletons, and rehabilitation devices.

Atrial fibrillation (AF) is the most common type of heart rhythm disorder worldwide. Early recognition of brief episodes of atrial fibrillation can provide important diagnostic information and lead to prompt treatment. AF is mainly characterized by an irregular heartbeat. Today, many personal devices such as smartphones, smartwatches, smart rings, or small wearable medical devices can detect heart rhythm. Sensors can acquire different types of heart-related signals and extract the sequence of inter-beat intervals, i.e., the instantaneous heart rate. Various algorithms, some of which are very complex and require significant computational resources, are used to recognize AF based on inter-beat intervals (RR). This study aims to verify the possibility of using neural networks algorithms directly on a microcontroller connected to sensors for AF detection. Sequences of 25, 50, and 100 RR were extracted from a public database of electrocardiographic signals with annotated episodes of atrial fibrillation. A custom 1D convolutional neural network (1D-CNN) was designed and then validated via a 5-fold subject-wise split cross-validation scheme. In each fold, the model was tested on a set of 3 randomly selected subjects, which had not previously been used for training, to ensure a subject-independent evaluation of model performance. Across all folds, all models achieved high and stable performance, with test accuracies of 0.963 ± 0.031, 0.976 ± 0.022, and 0.980 ± 0.023, respectively, for models using 25 RR, 50 RR, and 100 RR sequences. Precision, recall, F1-score, and AUC-ROC exhibited similarly high performance, confirming robust generalization across unseen subjects. Performance systematically improved with longer RR windows, indicating that richer temporal context enhances discrimination of AF rhythm irregularities. A complete Edge AI prototype integrating a low-power ECG analog front-end, an ARM Cortex M7 microcontroller and an IoT transmitting module was utilized for realistic tests. Inferencing time, peak RAM usage, flash usage and current absorption were measured. The results obtained show the possibility of using neural network algorithms directly on microcontrollers for real-time AF recognition with very low power consumption. The prototype is also capable of sending the suspicious ECG trace to the cloud for final validation by a physician. The proposed methodology can be used for personal screening not only with ECG signals but with any other signal that reproduces the sequence of heartbeats (e.g., photoplethysmographic, pulse oximetric, pressure, accelerometric, etc.).

Seismocardiography (SCG) uses accelerometers to record cardiac-induced accelerations of the chest wall. Cardiorespiratory interactions cause changes in amplitude and morphology of the SCG signals. Accelerometers can also directly monitor respiration by tracking thoracic inclination. This study thoroughly investigated the influence of accelerometer placement on the monitoring accuracy of respiration and cardiorespiratory interactions from SCG signals. Simultaneous recordings acquired by 16 accelerometers and a respiration belt placed onto 9 subjects’ chests were analyzed. Respiratory signals were estimated considering: (a) chest inclination, (b) amplitude modulation (AM) and (c) morphological changes of SCG signals for each sensor location. For the first time in literature, a continuous description of respiratory-induced changes in SCG morphology was obtained via a morphological similarity index (MSi). The performance of respiratory acts detection and inter-breath intervals (IBIs) estimation was evaluated against the concurrent reference respiration signal. High accuracy was achieved in all three kinds of respiratory signals, with average sensitivity and positive predictive value of 95.8% and 95.5% for chest inclination, 85.9% and 84.4% for AM, 94.3% and 95.7% for MSi. Moreover, IBIs measurements showed non-significant biases and limits of agreement of about ± 0.8 s for chest inclination and MSi, and ± 1 s for AM. Performance achieved by chest inclination and MSi appeared not much influenced by sensor location, while AM showed higher variations. Information on breathing and cardiorespiratory interactions can be accurately obtained via SCG on multiple sites on the chest.

Cardiomechanical monitoring techniques record cardiac vibrations on the chest via lightweight electrodeless sensors that allow long-term patient monitoring. Heartbeat detection in cardiomechanical signals is generally achieved by leveraging a simultaneous electrocardiography (ECG) signal to provide a reliable heartbeats localization, which however strongly limits long-term monitoring. A heartbeats localization method based on template matching has demonstrated very high performance in several cardiomechanical signals, with no need for a concurrent ECG recording. However, the reproducibility of that method was limited by the need for manual selection of a heartbeat template from the cardiomechanical signal by a skilled operator. To overcome that limitation, this study presents a fully automated version of the template matching method for ECG-free heartbeat detection, powered by a novel automatic template selection algorithm. The novel method was validated on 256 Seismocardiography (SCG), Gyrocardiography (GCG), and Forcecardiography (FCG) signals, from 150 healthy and pathological subjects. Comparison with all existing methods for ECG-free heartbeat detection was carried out. The method scored sensitivity and positive predictive value (PPV) of 97.8% and 98.6% for SCG, 96.3% and 94.5% for GCG, 99.2% and 99.3% for FCG, on healthy subjects, and of 85% and 95% for both SCG and GCG on pathological subjects. Statistical analyses on inter-beat intervals reported almost unit slopes (R² > 0.998) and limits of agreement within ± 6 ms for healthy subjects and ± 13 ms for pathological subjects. The proposed automated method surpasses all previous ECG-free approaches in heartbeat localization accuracy and was validated on the largest cohort of pathological subjects and the highest number of heartbeats. The method proposed in this study represents the current state of the art for ECG-free monitoring of cardiac activity via cardiomechanical signals, ensuring accurate, reproducible, operator-independent heartbeats localization. MATLAB^® code is released as an off-the-shelf tool to support a more widespread and practical use of cardiomechanical monitoring in both clinical and non-clinical settings.

Forcecardiography (FCG) uses force sensors to record the mechanical vibrations induced on the chest wall by cardiac and respiratory activities. FCG is usually performed via piezoelectric lead-zirconate titanate (PZT) sensors, which simultaneously record the very slow respiratory movements of the chest, the slow infrasonic vibrations due to emptying and filling of heart chambers, the faster infrasonic vibrations due to movements of heart valves, which are usually recorded via Seismocardiography (SCG), and the audible vibrations corresponding to heart sounds, commonly recorded via Phonocardiography (PCG). However, PZT sensors are not flexible and do not adapt very well to the deformations of soft tissues on the chest. This study presents a flexible FCG sensor based on a piezoelectric polyvinylidene fluoride (PVDF) transducer. The PVDF FCG sensor was compared with a well-assessed PZT FCG sensor, as well as with an electro-resistive respiratory band (ERB), an accelerometric SCG sensor, and an electronic stethoscope for PCG. Simultaneous recordings were acquired with these sensors and an electrocardiography (ECG) monitor from a cohort of 35 healthy subjects (16 males and 19 females). The PVDF sensor signals were compared in terms of morphology with those acquired simultaneously via the PZT sensor, the SCG sensor and the electronic stethoscope. Moreover, the estimation accuracies of PVDF and PZT sensors for inter-beat intervals (IBIs) and inter-breath intervals (IBrIs) were assessed against reference ECG and ERB measurements. The results of statistical analyses confirmed that the PVDF sensor provides FCG signals with very high similarity to those acquired via PZT sensors (median cross-correlation index of 0.96 across all subjects) as well as with SCG and PCG signals (median cross-correlation indices of 0.85 and 0.80, respectively). Moreover, the PVDF sensor provides very accurate estimates of IBIs, with R² > 0.99 and Bland–Altman limits of agreement (LoA) of [−5.30; 5.00] ms, and of IBrIs, with R² > 0.96 and LoA of [−0.510; 0.513] s. The flexibility of the PVDF sensor makes it more comfortable and ideal for wearable applications. Unlike PZT, PVDF is lead-free, which increases safety and biocompatibility for prolonged skin contact.

Seismocardiography (SCG) and Gyrocardiography (GCG) use lightweight, miniaturized accelerometers and gyroscopes to record, respectively, cardiac-induced linear accelerations and angular velocities of the chest wall. These inertial sensors are also sensitive to thoracic movements with respiration, which cause baseline wanderings in SCG and GCG signals. Nowadays, accelerometers and gyroscopes are widely integrated into smartphones, thus increasing the potential of SCG and GCG as cardiorespiratory monitoring tools. This study investigates the accuracy of smartphone inertial sensors in simultaneously measuring instantaneous heart rates and breathing rates. Smartphone-derived SCG and GCG signals were acquired from 10 healthy subjects at rest. The performances of heartbeats and respiratory acts detection, as well as of inter-beat intervals (IBIs) and inter-breath intervals (IBrIs) estimation, were evaluated for both SCG and GCG via the comparison with simultaneous electrocardiography and respiration belt signals. Heartbeats were detected with a sensitivity and positive predictive value (PPV) of 89.3% and 93.3% in SCG signals and of 97.3% and 97.9% in GCG signals. Moreover, IBIs measurements reported strong linear relationships (R² > 0.999), non-significant biases, and Bland–Altman limits of agreement (LoA) of ±7.33 ms for SCG and ±5.22 ms for GCG. On the other hand, respiratory acts detection scored a sensitivity and PPV of 95.6% and 94.7% for SCG and of 95.7% and 92.0% for GCG. Furthermore, high R² values (0.976 and 0.968, respectively), non-significant biases, and an LoA of ±0.558 s for SCG and ±0.749 s for GCG were achieved for IBrIs estimates. The results of this study confirm that smartphone inertial sensors can provide accurate measurements of both instantaneous heart rate and breathing rate without the need for additional devices.

Long-term patient monitoring is required for detection of episodes of atrial fibrillation, one of the most widespread cardiac pathologies. Today, the most used non-invasive technique is Holter electrocardiographic (ECG) monitoring, which can often prove ineffective because of the short duration of recordings (e.g., one day). Other techniques such as photo-plethysmography are adopted by smartwatches for much longer duration monitoring, but this has the disadvantage of offering only intermittent measurements. This study proposes an Internet of Things (IoT) sensor that can provide a very long period of continuous monitoring. The sensor consists of an ECG-integrated Analog Front End (MAX30003), a microcontroller (STM32F401RE), and an IoT narrowband module (STEVAL-STMODLTE). The instantaneous heart rate is extracted from the ECG recording in real time. At intervals of two minutes, the sequence of inter-beat intervals is transmitted to an IoT cloud platform (ThingSpeak). Settled atrial fibrillation event recognition software runs on the cloud and generates alerts when it recognizes such arrhythmia. Performances of the proposed sensor were evaluated by generating analog ECG signals from a public dataset of ECG signals with atrial fibrillation episodes, the MIT-BIH Atrial Fibrillation Database, each recording lasting approximately 10 h. Software implementing the Lorentz algorithm, one of the best detectors of atrial fibrillation, was implemented on the cloud platform. The accuracy, sensitivity, and specificity in recognizing atrial fibrillation episodes of the proposed system was calculated by comparison with a cardiologist’s reference data. Across all patients, the proposed method achieved an accuracy of 0.88, a sensitivity 0.71, and a specificity 0.99. The results obtained suggest that the developed system can continuously record and transmit heart rhythms effectively and efficiently and, in addition, offers considerable performance in recognizing atrial fibrillation episodes in real time.

Cardiac auscultation is an essential part of physical examination and plays a key role in the early diagnosis of many cardiovascular diseases. The analysis of phonocardiography (PCG) recordings is generally based on the recognition of the main heart sounds, i.e., S1 and S2, which is not a trivial task. This study proposes a method for an accurate recognition and localization of heart sounds in Forcecardiography (FCG) recordings. FCG is a novel technique able to measure subsonic vibrations and sounds via small force sensors placed onto a subject’s thorax, allowing continuous cardio-respiratory monitoring. In this study, a template-matching technique based on normalized cross-correlation was used to automatically recognize heart sounds in FCG signals recorded from six healthy subjects at rest. Distinct templates were manually selected from each FCG recording and used to separately localize S1 and S2 sounds, as well as S1–S2 pairs. A simultaneously recorded electrocardiography (ECG) trace was used for performance evaluation. The results show that the template matching approach proved capable of separately classifying S1 and S2 sounds in more than 96% of all heartbeats. Linear regression, correlation, and Bland–Altman analyses showed that inter-beat intervals were estimated with high accuracy. Indeed, the estimation error was confined within 10 ms, with negligible impact on heart rate estimation. Heart rate variability (HRV) indices were also computed and turned out to be almost comparable with those obtained from ECG. The preliminary yet encouraging results of this study suggest that the template matching approach based on normalized cross-correlation allows very accurate heart sounds localization and inter-beat intervals estimation.