Recommender system for ablation lines to treat complex atrial tachycardia.

BACKGROUND AND OBJECTIVE: Planning the optimal ablation strategy for the treatment of complex atrial tachycardia (CAT) is a time consuming task and is error-prone. Recently, directed network mapping, a technology based on graph theory, proved to efficiently identify CAT based solely on data of clinical interventions. Briefly, a directed network was used to model the atrial electrical propagation and reentrant activities were identified by looking for closed-loop paths in the network. In this study, we propose a recommender system, built as an optimization problem, able to suggest the optimal ablation strategy for the treatment of CAT. METHODS: The optimization problem modeled the optimal ablation strategy as that one interrupting all reentrant mechanisms while minimizing the ablated atrial surface. The problem was designed on top of directed network mapping. Considering the exponential complexity of finding the optimal solution of the problem, we introduced a heuristic algorithm with polynomial complexity. The proposed algorithm was applied to the data of i) 6 simulated scenarios including both left and right atrial flutter; and ii) 10 subjects that underwent a clinical routine. RESULTS: The recommender system suggested the optimal strategy in 4 out of 6 simulated scenarios. On clinical data, the recommended ablation lines were found satisfactory on 67% of the cases according to the clinician's opinion, while they were correctly located in 89%. The algorithm made use of only data collected during mapping and was able to process them nearly real-time. CONCLUSIONS: The first recommender system for the identification of the optimal ablation lines for CAT, based solely on the data collected during the intervention, is presented. The study may open up interesting scenarios for the application of graph theory for the treatment of CAT.

Explainable AI Points to White Matter Hyperintensities for Alzheimer's Disease Identification: a Preliminary Study.

Deep Learning approaches are powerful tools in a great variety of classification tasks. However, they are limitedly accepted or trusted in clinical frameworks due to their typical "black box" outline: their architecture is well-known, but processes employed in classification are often inaccessible to humans. With this work, we explored the problem of "Explainable AI" (XAI) in Alzheimer's disease (AD) classification tasks. Data from a neuroimaging cohort (n = 251 from OASIS-3) of early-stage AD dementia and healthy controls (HC) were analysed. The MR scans were initially fed to a pre-trained DL model, which achieved good performance on the test set (AUC: 0.82, TPR: 0.78, TNR: 0.81). Results were then investigated by means of an XAI approach (Occlusion Sensitivity method) that provided measures of relevance (RV) as outcome. We compared RV values obtained within healthy tissues with those underlying white matter hyperintensity (WMH) lesions. The analysis was conducted on 4 different groups of data, obtained by stratifying correct and misclassified images according to the health condition of participants (AD/HC). Results highlighted that the DL model found favourable leveraging lesioned brain areas for AD identification. A statistically significant difference ( ) between WMH and healthy tissue contributions was indeed observed for AD recognition, differently from the HC case ( p=0.27). Clinical Relevance - This study, though preliminary, suggested that DL models might be trained to use known clinical information and reinforced the role of WMHs as neuroimaging biomarker for AD dementia. The outlined findings have a significant clinical relevance as they prepare the ground for a progressive increase in the level of trust laid in DL approaches.

Spatial Correlation Between Myocyte's Repolarization Times and Their Alternans Drives T-Wave Alternans on the ECG.

OBJECTIVE: T-wave alternans (TWA) manifests as beat-to-beat fluctuations of T-wave morphology on the electrocardiogram (ECG), with physiological bases not fully understood. Using a biophysical model of the ECG, we demonstrate and give explicit relations that TWA depends on the i) spatial covariance between myocytes' repolarization time and alternans; and ii) global alternans (common to every myocyte). METHODS: We quantified the spatial covariance and global alternans by means of two new metrics, R index and δ, respectively. They were validated on both synthetic and real signals. Computerized simulations were generated using a biophysical model linking the action potentials with the surface ECG. Then, the metrics were computed in STAFF-III dataset, containing ECGs from patients who underwent coronary angioplasty with prolonged balloon inflations, and the time courses of the metrics were analyzed together with TWA measured on the surface ECG. RESULTS: The metrics properly estimated the spatial covariance and global alternans in the synthetic data. In the STAFF-III dataset, the R index progressively increased from baseline to the fourth minute of inflation (median ∆R=0.81 ms; p 0.05), whereas δ was mostly unaltered during the intervention ( δ=0 ms). CONCLUSION: We reported, for the first time, that TWA is significantly driven by the myocyte's spatial covariance between their repolarization times and alternans, and not by global alternans, when TWA is generated by regional ischemia. SIGNIFICANCE: The metrics may reveal new complementary insights into the mechanisms underlying TWA.

Association between ventricular repolarization parameters and cardiovascular death in patients of the SWISS-AF cohort.

BACKGROUND: The effect of the ventricular repolarization heterogeneity has not been systematically assessed in patients with atrial fibrillation (AF). Aim of this study is to assess ventricular repolarization heterogeneity as predictor of cardiovascular (CV) death and/or other CV events in patients with AF. METHODS: From the multicenter prospective Swiss-AF (Swiss Atrial Fibrillation) Cohort Study, we enrolled 1711 patients who were in sinus rhythm (995) or AF (716). Resting ECG recordings of 5-min duration were obtained at baseline. Parameters assessing ventricular repolarization were computed (QTc, Tpeak-Tend, J-Tpeak and V-index). RESULTS: During AF, the V-index was found repeatable (no differences when computed over the whole recording, on the first 2.5-min and on the last 2.5-min segments). During a mean follow-up time of 2.6 ± 1.0 years, 90 patients died for CV reasons. In bivariate Cox regression analysis (adjusted for age only), the V-index was associated with an increased risk of CV death, both in the subgroup of patients in sinus rhythm (SR) as well as those in AF. In multivariate analysis adjusted for clinical risk factors and medications, both prolonged QTc and V-index were independently associated with an increased risk of CV death (QTc: hazard ratio [HR] 2.78, 95% CI 1.79-4.32, p < 0.001; V-index: HR 1.73, 95% CI 1.12-2.69, p = 0.014). CONCLUSIONS: QTc and V-index, measured in a single 5-min ECG recording, were independent predictors of CV death in a cohort of patients with AF and might be a valuable tool for further risk stratification to guide patient management. Clinical Trial Identifier Swiss-AF study: NCT02105844.

Machine Learning Using a Single-Lead ECG to Identify Patients With Atrial Fibrillation-Induced Heart Failure.

Aims: Atrial fibrillation (AF) and heart failure often co-exist. Early identification of AF patients at risk for AF-induced heart failure (AF-HF) is desirable to reduce both morbidity and mortality as well as health care costs. We aimed to leverage the characteristics of beat-to-beat-patterns in AF to prospectively discriminate AF patients with and without AF-HF. Methods: A dataset of 10,234 5-min length RR-interval time series derived from 26 AF-HF patients and 26 control patients was extracted from single-lead Holter-ECGs. A total of 14 features were extracted, and the most informative features were selected. Then, a decision tree classifier with 5-fold cross-validation was trained, validated, and tested on the dataset randomly split. The derived algorithm was then tested on 2,261 5-min segments from six AF-HF and six control patients and validated for various time segments. Results: The algorithm based on the spectral entropy of the RR-intervals, the mean value of the relative RR-interval, and the root mean square of successive differences of the relative RR-interval yielded an accuracy of 73.5%, specificity of 91.4%, sensitivity of 64.7%, and PPV of 87.0% to correctly stratify segments to AF-HF. Considering the majority vote of the segments of each patient, 10/12 patients (83.33%) were correctly classified. Conclusion: Beat-to-beat-analysis using a machine learning classifier identifies patients with AF-induced heart failure with clinically relevant diagnostic properties. Application of this algorithm in routine care may improve early identification of patients at risk for AF-induced cardiomyopathy and improve the yield of targeted clinical follow-up.

Hybrid machine learning to localize atrial flutter substrates using the surface 12-lead electrocardiogram.

AIMS: Atrial flutter (AFlut) is a common re-entrant atrial tachycardia driven by self-sustainable mechanisms that cause excitations to propagate along pathways different from sinus rhythm. Intra-cardiac electrophysiological mapping and catheter ablation are often performed without detailed prior knowledge of the mechanism perpetuating AFlut, likely prolonging the procedure time of these invasive interventions. We sought to discriminate the AFlut location [cavotricuspid isthmus-dependent (CTI), peri-mitral, and other left atrium (LA) AFlut classes] with a machine learning-based algorithm using only the non-invasive signals from the 12-lead electrocardiogram (ECG). METHODS AND RESULTS: Hybrid 12-lead ECG dataset of 1769 signals was used (1424 in silico ECGs, and 345 clinical ECGs from 115 patients-three different ECG segments over time were extracted from each patient corresponding to single AFlut cycles). Seventy-seven features were extracted. A decision tree classifier with a hold-out classification approach was trained, validated, and tested on the dataset randomly split after selecting the most informative features. The clinical test set comprised 38 patients (114 clinical ECGs). The classifier yielded 76.3% accuracy on the clinical test set with a sensitivity of 89.7%, 75.0%, and 64.1% and a positive predictive value of 71.4%, 75.0%, and 86.2% for CTI, peri-mitral, and other LA class, respectively. Considering majority vote of the three segments taken from each patient, the CTI class was correctly classified at 92%. CONCLUSION: Our results show that a machine learning classifier relying only on non-invasive signals can potentially identify the location of AFlut mechanisms. This method could aid in planning and tailoring patient-specific AFlut treatments.

Relationship Between Deceleration Morphology and Phase Rectified Signal Averaging-Based Parameters During Labor.

During labor, uterine contractions trigger the response of the autonomic nervous system (ANS) of the fetus, producing sawtooth-like decelerations in the fetal heart rate (FHR) series. Under chronic hypoxia, ANS is known to regulate FHR differently with respect to healthy fetuses. In this study, we hypothesized that such different ANS regulation might also lead to a change in the FHR deceleration morphology. The hypothesis was tested in an animal model comprising nine normoxic and five chronically hypoxic fetuses that underwent a protocol of umbilical cord occlusions (UCOs). Deceleration morphologies in the fetal inter-beat time interval (FRR) series were modeled using a trapezoid with four parameters, i.e., baseline b, deceleration depth a, UCO response time τ u and recovery time τ r . Comparing normoxic and hypoxic sheep, we found a clear difference for τ u (24.8±9.4 vs. 39.8±9.7 s; p < 0.05), a (268.1±109.5 vs. 373.0±46.0 ms; p < 0.1) and Δτ = τ u - τ r (13.2±6.9 vs. 23.9±7.5 s; p < 0.05). Therefore, the animal model supported the hypothesis that hypoxic fetuses have a longer response time τ u and larger asymmetry Δτ as a response to UCOs. Assessing these morphological parameters during labor is challenging due to non-stationarity, phase desynchronization and noise. For this reason, in the second part of the study, we quantified whether acceleration capacity (AC), deceleration capacity (DC), and deceleration reserve (DR), computed through Phase-Rectified Signal Averaging (PRSA, known to be robust to noise), were correlated with the morphological parameters. DC, AC and DR were correlated with τ u , τ r and Δτ for a wide range of the PRSA parameter T (Pearson's correlation ρ > 0.8, p < 0.05). In conclusion, deceleration morphologies have been found to differ between normoxic and hypoxic sheep fetuses during UCOs. The same difference can be assessed through PRSA based parameters, further motivating future investigations on the translational potential of this methodology on human data.

Directed Network Mapping Approach to Rotor Localization in Atrial Fibrillation Simulation.

Catheter ablation for atrial fibrillation (AF) is one of the most commonly performed electrophysiology procedures. Despite significant advances in our understanding of AF mechanisms in the last years, ablation outcomes remain suboptimal for many patients, particularly those with persistent or long-standing AF. A possible reason is that ablation techniques mainly focus on anatomic, rather than patient-specific functional targets for ablation. The identification of such ablation targets remains challenging. The purpose of this study is to investigate a novel approach based on directed networks, which allow the automatic detection of important arrhythmia mechanisms, that can be convenient for guiding the ablation strategy. The networks are generated by processing unipolar electrograms (EGMs) collected by the catheters positioned at the different regions of the atria. Network vertices represent the locations of the recordings and edges are determined using cross-covariance time-delay estimation method. The algorithm identifies rotational activity, spreading from vertex to vertex creating a cycle. This work is a simulation study and it uses a highly detailed computational 3D model of human atria in which sustained rotor activation of the atria was achieved. Virtual electrodes were placed on the endocardial surface, and EGMs were calculated at each of these electrodes. The propagation of the electric wave fronts in the atrial myocardium during AF is very complex, so in order to properly capture wave propagation patterns, we split EGMs into multiple short time frames. Then, a specific network for each of these time frames was generated, and the cycles repeating in consecutive networks point us to the stable rotor's location. The respective atrial voltage map served as reference. By detecting a cycle between the same 3 nodes in 19 out of 58 networks, where 10 of these networks were in consecutive time frames, a stable rotor was successfully located.

Opening the black box: interpretability of machine learning algorithms in electrocardiography.

Recent studies have suggested that cardiac abnormalities can be detected from the electrocardiogram (ECG) using deep machine learning (DL) models. However, most DL algorithms lack interpretability, since they do not provide any justification for their decisions. In this study, we designed two new frameworks to interpret the classification results of DL algorithms trained for 12-lead ECG classification. The frameworks allow us to highlight not only the ECG samples that contributed most to the classification, but also which between the P-wave, QRS complex and T-wave, hereafter simply called 'waves', were the most relevant for the diagnosis. The frameworks were designed to be compatible with any DL model, including the ones already trained. The frameworks were tested on a selected Deep Neural Network, trained on a publicly available dataset, to automatically classify 24 cardiac abnormalities from 12-lead ECG signals. Experimental results showed that the frameworks were able to detect the most relevant ECG waves contributing to the classification. Often the network relied on portions of the ECG which are also considered by cardiologists to detect the same cardiac abnormalities, but this was not always the case. In conclusion, the proposed frameworks may unveil whether the network relies on features which are clinically significant for the detection of cardiac abnormalities from 12-lead ECG signals, thus increasing the trust in the DL models. This article is part of the theme issue 'Advanced computation in cardiovascular physiology: new challenges and opportunities'.

A Two-Steps-Ahead Estimator for Bubble Entropy.

Aims: Bubble entropy (bEn) is an entropy metric with a limited dependence on parameters. bEn does not directly quantify the conditional entropy of the series, but it assesses the change in entropy of the ordering of portions of its samples of length m, when adding an extra element. The analytical formulation of bEn for autoregressive (AR) processes shows that, for this class of processes, the relation between the first autocorrelation coefficient and bEn changes for odd and even values of m. While this is not an issue, per se, it triggered ideas for further investigation. Methods: Using theoretical considerations on the expected values for AR processes, we examined a two-steps-ahead estimator of bEn, which considered the cost of ordering two additional samples. We first compared it with the original bEn estimator on a simulated series. Then, we tested it on real heart rate variability (HRV) data. Results: The experiments showed that both examined alternatives showed comparable discriminating power. However, for values of 10

Machine learning enables noninvasive prediction of atrial fibrillation driver location and acute pulmonary vein ablation success using the 12-lead ECG.

BACKGROUND: Atrial fibrillation (AF) is the most common supraventricular arrhythmia, characterized by disorganized atrial electrical activity, maintained by localized arrhythmogenic atrial drivers. Pulmonary vein isolation (PVI) allows to exclude PV-related drivers. However, PVI is less effective in patients with additional extra-PV arrhythmogenic drivers. OBJECTIVES: To discriminate whether AF drivers are located near the PVs vs extra-PV regions using the noninvasive 12-lead electrocardiogram (ECG) in a computational and clinical framework, and to computationally predict the acute success of PVI in these cohorts of data. METHODS: AF drivers were induced in 2 computerized atrial models and combined with 8 torso models, resulting in 1128 12-lead ECGs (80 ECGs with AF drivers located in the PVs and 1048 in extra-PV areas). A total of 103 features were extracted from the signals. Binary decision tree classifier was trained on the simulated data and evaluated using hold-out cross-validation. The PVs were subsequently isolated in the models to assess PVI success. Finally, the classifier was tested on a clinical dataset (46 patients: 23 PV-dependent AF and 23 with additional extra-PV sources). RESULTS: The classifier yielded 82.6% specificity and 73.9% sensitivity for detecting PV drivers on the clinical data. Consistency analysis on the 46 patients resulted in 93.5% results match. Applying PVI on the simulated AF cases terminated AF in 100% of the cases in the PV class. CONCLUSION: Machine learning-based classification of 12-lead-ECG allows discrimination between patients with PV drivers vs those with extra-PV drivers of AF. The novel algorithm may aid to identify patients with high acute success rates to PVI.

Assessment of spatial heterogeneity of ventricular repolarization after multi-channel blocker drugs in healthy subjects.

BACKGROUND AND OBJECTIVES: In contrast to potassium channel blockers, drugs affecting multiple channels seem to reduce torsadogenic risks. However, their effect on spatial heterogeneity of ventricular repolarization (SHVR) is still matter of investigation. Aim of this work is to assess the effect of four drugs blocking the human ether-à-go-go-related gene (hERG) potassium channel, alone or in combination with other ionic channel blocks, on SHVR, as estimated by the V-index on short triplicate 10 s ECG. METHODS: The V-index is an estimate of the standard deviation of the repolarization times of the myocytes across the entire myocardium, obtained from multi-lead surface electrocardiograms. Twenty-two healthy subjects received a pure hERG potassium channel blocker (dofetilide) and 3 other drugs with additional varying degrees of sodium and calcium (L-type) channel block (quinidine, ranolazine, and verapamil), as well as placebo. A one-way repeated-measures Friedman test was performed to compare the V-index over time. RESULTS: Computer simulations and Bland-Altman analysis supported the reliability of the estimates of V-index on triplicate 10 s ECG. Ranolazine, verapamil and placebo did not affect the V-index. On the contrary, after quinidine and dofetilide administration, an increase of V-index from predose to its peak value was observed (ΔΔV-index values were 19 ms and 27 ms, respectively, p < 0.05). CONCLUSIONS: High torsadogenic drugs (dofetilide and quinidine) affected significantly the SHVR, as quantified by the V-index. The metric has therefore a potential in assessing drug arrhythmogenicity.

Refined Ventricular Activity Cancellation in Electrograms During Atrial Fibrillation by Combining Average Beat Subtraction and Interpolation.

Many techniques have been developed to cancel the ventricular interference in atrial electrograms (AEG) during atrial fibrillation. In particular, average beat subtraction (ABS) and interpolation are among those mostly adopted. However, ABS usually leaves high power residues and discontinuity at the borders, whereas interpolation totally substitutes the residual activity with a forecasting that might fail at the center of the cancellation segment. In this study, we proposed a new algorithm to refine the ventricular estimate provided by ABS, in such a way that the residual activity should likely be distributed as the local atrial activity. Briefly, the local atrial activity is first modeled with an autoregressive (AR) process, then the estimate is refined by maximizing the log likelihood of the atrial residual activity according to the fitted AR model. We tested the new algorithm on both synthetic and real AEGs, and compared the performance with other four algorithms (two variants of ABS, interpolation and zero substitution). On synthetic data, our algorithm outperformed all the others in terms of average root mean square error (0.043 vs 0.046 for interpolation; p <; 0.05). On real data, our methodology outperformed two variants of ABS (p <; 0.05) and performed similarly to interpolation when considering the high power residues left (both <; 5%), and the log likelihood with the fitted AR model.

Quantification of Spatial Heterogeneity of Ventricular Repolarization During Early-Stage Cardiac Ischemia Induced by Coronary Angioplasty.

Coronary angioplasty (CA) is a surgical procedure meant to break the plaque and restore the blood flow in obstructed coronary arteries. It is based on inserting an inflatable balloon with a catheter in the clogged artery. When the balloon inflation is prolonged, it also provides an excellent model to investigate the electrophysiological changes due to early ischemia. In this work, we tested whether early cardiac ischemia induced by prolonged balloon inflations might lead to changes in spatial heterogeneity of ventricular repolarization (SHVR), as measured by the V-index on the 12-lead ECG. The metric was recently shown to significantly improve the ECG sensitivity for the diagnosis of non-ST elevation myocardial infarction, in patients presenting to the emergency department. The analysis was retrospectively performed on the data of 104 patients who underwent prolonged CA (STAFF III dataset). The V-index was estimated before, during and post-occlusion (limiting the analysis to the first inflation). Successively, it was quantified on short 90 s overlapping windows, during occlusion, to assess the time evolution of SHVR. V-index values estimated during occlusion were significantly larger (median: 6.2 ms, p <; 0.05) than baseline room values. Also, pre- and post-occlusion values did not differ (p > 0.05), suggesting a complete recovery after CA. SHVR progressively increased during the occlusion with respect to baseline (median reaching 55.6 ms vs 34.2 ms). In conclusion, the V-index detected changes in SHVR due to early-stage cardiac ischemia.

Evaluation of the Tinetti score and fall risk assessment via accelerometry-based movement analysis.

Gait and balance disorders are among the main predisposing factors of falls in elderly. Clinical scales are widely employed to assess the risk of falling, but they require trained personnel. We investigate the use of objective measures obtained from a wearable accelerometer to evaluate the fall risk, determined by the Tinetti clinical scale. Seventy-nine patients and eleven volunteers were enrolled in two rehabilitation centers and underwent a full Tinetti test, while wearing a triaxial accelerometer at the chest. Tinetti scores were assessed by expert physicians and those subjects with a score ≤18 were considered at high risk. First, we analyzed 21 accelerometer features by means of statistical tests and correlation analysis. Second, one regression and one classification problem were designed and solved using a linear model (LM) and an artificial neural network (ANN) to predict the Tinetti outcome. Pearson's correlation between the Tinetti score and a subset of 9 features (mainly related with standing and walking) was 0.71. The misclassification error of high risk patient was 0.21 and 0.11, for LM and ANN, respectively. The work might foster the development of a new generation of applications meant to monitor the time evolution of the fall risk using low cost devices at home.

Linear-Sigmoidal modelling of accelerometer features and Tinetti score for automatic fall risk assessment.

Falling in elderly is a worldwide major problem and it can lead to severe injuries or death. Despite the effort made to ensure home environments safe and foster healthy lifestyles, it is still necessary to provide methodologies that can be used at home for detect risk factors associated with falls. In this study, we proposed a new simple non-linear model, i.e., Linear-Sigmoidal model (LS), easy to fit and simple to interpret, used to model accelerometer features and outcome of the clinical scale Tinetti (clinical scale for fall risk prediction). Also, subjects with a score ≤ 18 were considered as high risk of falling. One-hundred-twelve subjects underwent to a Tinetti test while wearing a 3D axis accelerometer at the chest, and the Tinetti score used as gold standard. Ninety subjects were used as training set and twenty-two ones were employed to test the model. The same sets were used to assess the performance of the standard linear regression (LR). Seven accelerometer features and the body mass index were used in the model regression. LS resulted better than LR in terms of model agreement (R2: 0.76 vs 0.72) and classification accuracy (0.91 vs 0.86) on the test set.

Diagnostic and prognostic values of the V-index, a novel ECG marker quantifying spatial heterogeneity of ventricular repolarization, in patients with symptoms suggestive of non-ST-elevation myocardial infarction.

BACKGROUND: The V-index is an ECG marker quantifying spatial heterogeneity of ventricular repolarization. We prospectively assessed the diagnostic and prognostic values of the V-index in patients with suspected non-ST-elevation myocardial infarction (NSTEMI). METHODS: We prospectively enrolled 497 patients presenting with suspected NSTEMI to the emergency department (ED). Digital 12-lead ECGs of five-minute duration were recorded at presentation. The V-index was automatically calculated in a blinded fashion. Patients with a QRS duration >120ms were ruled out from analysis. The final diagnosis was adjudicated by two independent cardiologists. The prognostic endpoint was all-cause mortality during 24months of follow-up. RESULTS: NSTEMI was the final diagnosis in 14% of patients. V-index levels were higher in patients with AMI compared to other causes of chest pain (median 23ms vs. 18ms, p<0.001). The use of the V-index in addition to conventional ECG-criteria improved the diagnostic accuracy for the diagnosis of NSTEMI as quantified by area under the ROC curve from 0.66 to 0.73 (p=0.001) and the sensitivity of the ECG for AMI from 41% to 86% (p<0.001). Cumulative 24-month mortality rates were 99.4%, 98.4% and 88.3% according to tertiles of the V-index (p<0.001). After adjustment for age and important ECG and clinical parameters, the V-index remained an independent predictor of death. CONCLUSIONS: The V-index, an ECG marker quantifying spatial heterogeneity of ventricular repolarization, significantly improves the accuracy and sensitivity of the ECG for the diagnosis of NSTEMI and independently predicts mortality during follow-up.

Pilot Test of a New Personal Health System Integrating Environmental and Wearable Sensors for Telemonitoring and Care of Elderly People at Home (SMARTA Project).

BACKGROUND: The increase in life expectancy is accompanied by a growing number of elderly subjects affected by chronic comorbidities, a health issue which also implies important socioeconomic consequences. Shifting from hospital or community dwelling care towards a home personalized healthcare paradigm would promote active aging with a better quality of life, along with a reduction in healthcare-related costs. OBJECTIVE: The aim of the SMARTA project was to develop and test an innovative personal health system integrating standard sensors as well as innovative wearable and environmental sensors to allow home telemonitoring of vital parameters and detection of anomalies in daily activities, thus supporting active aging through remote healthcare. METHODS: A first phase of the project consisted in the definition of the health and environmental parameters to be monitored (electrocardiography and actigraphy, blood pressure and oxygen saturation, weight, ear temperature, glycemia, home interaction monitoring - water tap, refrigerator, and dishwasher), the feedbacks for the clinicians, and the reminders for the patients. It was followed by a technical feasibility analysis leading to an iterative process of prototype development, sensor integration, and testing. Once the prototype had reached an advanced stage of development, a group of 32 volunteers - including 15 healthy adult subjects, 13 elderly people with cardiac diseases, and 4 clinical operators - was recruited to test the system in a real home setting, in order to evaluate both technical reliability and user perception of the system in terms of effectiveness, usability, acceptance, and attractiveness. RESULTS: The testing in a real home setting showed a good perception of the SMARTA system and its functionalities both by the patients and by the clinicians, who appreciated the user interface and the clinical governance system. The moderate system reliability of 65-70% evidenced some technical issues, mainly related to sensor integration, while the patient's user interface showed excellent reliability (100%). CONCLUSIONS: Both elderly people and clinical operators considered the SMARTA system a promising and attractive tool for improving patients' healthcare while reducing related costs and preserving quality of life. However, the moderate reliability of the system should prompt further technical developments in terms of sensor integration and usability of the clinical operator's user interface.

Parameters influence on acceleration and deceleration capacity based on trans-abdominal ECG in early fetal growth restriction at different gestational age epochs.

OBJECTIVE: Intrauterine growth restriction (IUGR) is characterized by chronic nutrient deprivation and hypoxemia that alters the autonomous nervous system regulation of fetal heart rate variability (fHRV). Phase-rectified signal averaging (PRSA) is a new algorithm capable to identify periodic and quasi-periodic patterns of HR, and which is used to quantify the average acceleration and deceleration capacity (AC/DC) of the heart. The computation of AC/DC depends on the parameters T and s, which we set so that s=T. T and s determine the periodicities that can be detected (the larger T the smaller the frequency of oscillations for which the method is most sensitive). The aim of the study was to evaluate the influence of the parameter T on PRSA computation, based on trans-abdominally acquired fetal ECG (ta-fECG), in early IUGR (<34 weeks of gestation) at two different gestational age epochs. STUDY DESIGN: AC/DC were calculated for different T values (1÷45) on fetal RR intervals derived from ta-fECG in 22 IUGR and in 37 appropriate for gestational age (AGA) fetuses matched for gestational age, in two gestational age epochs: very preterm group (≥26÷<30 weeks), and preterm group (≥30÷<34 weeks), respectively. RESULTS: AC/DC were significantly lower in IUGR than in AGA fetuses for all T≥5 values (p<0.05). The best area under the receiver operating characteristic curve (AUC) in identifying IUGR at time of recording was observed for T9 [AUC AC-T9 0.87, 95% confidence interval (CI) 0.77-0.96; and AUC DC-T9 0.89, 95% CI 0.81-0.98), and in range of T 7÷15. In the same T interval, AC/DC were significantly lower in very preterm than in preterm IUGR group (p<0.05), while there were no differences in AGA fetuses at two gestational age epochs (p>0.05), respectively. The AUCs of AC-T9 and DC-T9 significantly outperformed that obtained by short-term variation (AUC 0.77, 95% CI 0.65-0.90; p=0.009 and p=0.003, respectively). CONCLUSIONS: Our study shows that within the range of T parameter 1÷45, T=9 proved to be the best value to discriminate the AC and DC of the fetal heart rate of IUGR from AGA fetuses prior to 34 weeks of gestation. These significant differences are emphasized in very preterm gestational age epochs.

Automatic vs. clinical assessment of fall risk in older individuals: A proof of concept.

Falling in elderly is a worldwide major problem because it can lead to severe injuries, and even sudden death. Fall risk prediction would provide rapid intervention, as well as reducing the over burden of healthcare systems. Such prediction is currently performed by means of clinical scales. Among them, the Tinetti Scale is one of the better established and mostly used in clinical practice. In this work, we proposed an automatic method to assess the Tinetti scores using a wearable accelerometer. The balance and gait characteristics of 13 elderly subjects have been scored by an expert clinician while performing 8 different motor tasks according to the Tinetti Scale protocol. Two statistical analysis were selected. First, a linear regression study was performed between the Tinetti scores and 8 features (one feature for each task). Second, the generalization quality of the regression model was assessed using a Leave-One SubjectOut approach. The multiple linear regression provided a high correlation between the Tinetti scores and the features proposed (adj. R(2) = 0.948; p = 0.003). Moreover, six of the eight features added statistically significantly to the prediction of the scores (p <; 0.05). When testing the generalization capability of the model, a moderate linear correlation was obtained (R(2) = 0.67; p <; 0.05). The results suggested that the automatic method might be a promising tool to assess the falling risk of older individuals.