RESUMEN
The performance of a pulse oximeter based on photoelectric detection is greatly affected by motion noise (MA) in the photoplethysmographic (PPG) signal. This paper presents an algorithm for detecting motion oxygen saturation, which reconstructs a motion noise reference signal using ensemble of complete adaptive noise and empirical mode decomposition combined with multi-scale permutation entropy, and eliminates MA in the PPG signal using a convex combination least mean square adaptive filters to calculate dynamic oxygen saturation. The test results show that, under simulated walking and jogging conditions, the mean absolute error (MAE) of oxygen saturation estimated by the proposed algorithm and the reference oxygen saturation are 0.05 and 0.07, respectively, with means absolute percentage error (MAPE) of 0.05% and 0.07%, respectively. The overall Pearson correlation coefficient reaches 0.971 2. The proposed scheme effectively reduces motion artifacts in the corrupted PPG signal and is expected to be applied in portable photoelectric pulse oximeters to improve the accuracy of dynamic oxygen saturation measurement.
Asunto(s)
Algoritmos , Artefactos , Oximetría , Saturación de Oxígeno , Fotopletismografía , Procesamiento de Señales Asistido por Computador , Fotopletismografía/métodos , Fotopletismografía/instrumentación , Oximetría/métodos , Oximetría/instrumentación , Humanos , Análisis de los Mínimos Cuadrados , Movimiento (Física) , Oxígeno/sangreRESUMEN
BACKGROUND: To detect preload responsiveness in patients ventilated with a tidal volume (Vt) at 6 mL/kg of predicted body weight (PBW), the Vt-challenge consists in increasing Vt from 6 to 8 mL/kg PBW and measuring the increase in pulse pressure variation (PPV). However, this requires an arterial catheter. The perfusion index (PI), which reflects the amplitude of the photoplethysmographic signal, may reflect stroke volume and its respiratory variation (pleth variability index, PVI) may estimate PPV. We assessed whether Vt-challenge-induced changes in PI or PVI could be as reliable as changes in PPV for detecting preload responsiveness defined by a PLR-induced increase in cardiac index (CI) ≥ 10%. METHODS: In critically ill patients ventilated with Vt = 6 mL/kg PBW and no spontaneous breathing, haemodynamic (PICCO2 system) and photoplethysmographic (Masimo-SET technique, sensor placed on the finger or the forehead) data were recorded during a Vt-challenge and a PLR test. RESULTS: Among 63 screened patients, 21 (33%) were excluded because of an unstable PI signal and/or atrial fibrillation and 42 were included. During the Vt-challenge in the 16 preload responders, CI decreased by 4.8 ± 2.8% (percent change), PPV increased by 4.4 ± 1.9% (absolute change), PIfinger decreased by 14.5 ± 10.7% (percent change), PVIfinger increased by 1.9 ± 2.6% (absolute change), PIforehead decreased by 18.7 ± 10.9 (percent change) and PVIforehead increased by 1.0 ± 2.5 (absolute change). All these changes were larger than in preload non-responders. The area under the ROC curve (AUROC) for detecting preload responsiveness was 0.97 ± 0.02 for the Vt-challenge-induced changes in CI (percent change), 0.95 ± 0.04 for the Vt-challenge-induced changes in PPV (absolute change), 0.98 ± 0.02 for Vt-challenge-induced changes in PIforehead (percent change) and 0.85 ± 0.05 for Vt-challenge-induced changes in PIfinger (percent change) (p = 0.04 vs. PIforehead). The AUROC for the Vt-challenge-induced changes in PVIforehead and PVIfinger was significantly larger than 0.50, but smaller than the AUROC for the Vt-challenge-induced changes in PPV. CONCLUSIONS: In patients under mechanical ventilation with no spontaneous breathing and/or atrial fibrillation, changes in PI detected during Vt-challenge reliably detected preload responsiveness. The reliability was better when PI was measured on the forehead than on the fingertip. Changes in PVI during the Vt-challenge also detected preload responsiveness, but with lower accuracy.
Asunto(s)
Índice de Perfusión , Fotopletismografía , Volumen de Ventilación Pulmonar , Humanos , Fotopletismografía/métodos , Volumen de Ventilación Pulmonar/fisiología , Masculino , Femenino , Persona de Mediana Edad , Anciano , Índice de Perfusión/métodos , Presión Sanguínea/fisiología , Volumen Sistólico/fisiología , Hemodinámica/fisiología , Respiración Artificial/métodosRESUMEN
Objective.We investigated fluctuations of the photoplethysmography (PPG) waveform in patients undergoing surgery. There is an association between the morphologic variation extracted from arterial blood pressure (ABP) signals and short-term surgical outcomes. The underlying physiology could be the numerous regulatory mechanisms on the cardiovascular system. We hypothesized that similar information might exist in PPG waveform. However, due to the principles of light absorption, the noninvasive PPG signals are more susceptible to artifacts and necessitate meticulous signal processing.Approach.Employing the unsupervised manifold learning algorithm, dynamic diffusion map, we quantified multivariate waveform morphological variations from the PPG continuous waveform signal. Additionally, we developed several data analysis techniques to mitigate PPG signal artifacts to enhance performance and subsequently validated them using real-life clinical database.Main results.Our findings show similar associations between PPG waveform during surgery and short-term surgical outcomes, consistent with the observations from ABP waveform analysis.Significance.The variation of morphology information in the PPG waveform signal in major surgery provides clinical meanings, which may offer new opportunity of PPG waveform in a wider range of biomedical applications, due to its non-invasive nature.
Asunto(s)
Fotopletismografía , Procesamiento de Señales Asistido por Computador , Aprendizaje Automático no Supervisado , Fotopletismografía/métodos , Humanos , Femenino , Masculino , Persona de Mediana Edad , Artefactos , Anciano , AdultoRESUMEN
While individuals fail to assess their mental health subjectively in their day-to-day activities, the recent development of consumer-grade wearable devices has enormous potential to monitor daily workload objectively by acquiring physiological signals. Therefore, this work collected consumer-grade physiological signals from twenty-four participants, following a four-hour cognitive load elicitation paradigm with self-chosen tasks in uncontrolled environments and a four-hour mental workload elicitation paradigm in a controlled environment. The recorded dataset of approximately 315 hours consists of electroencephalography, acceleration, electrodermal activity, and photoplethysmogram data balanced across low and high load levels. Participants performed office-like tasks in the controlled environment (mental arithmetic, Stroop, N-Back, and Sudoku) with two defined difficulty levels and in the uncontrolled environments (mainly researching, programming, and writing emails). Each task label was provided by participants using two 5-point Likert scales of mental workload and stress and the pairwise NASA-TLX questionnaire. This data is suitable for developing real-time mental health assessment methods, conducting research on signal processing techniques for challenging environments, and developing personal cognitive load assistants.
Asunto(s)
Cognición , Electroencefalografía , Humanos , Fotopletismografía , Carga de Trabajo , Respuesta Galvánica de la PielRESUMEN
BACKGROUND: Knowledge feature (KF) with clear physiological significance of photoplethysmography are widely used in predicting blood pressure. However, KF primarily focus on local information of photoplethysmography, which may struggle to capture the overall characteristics. METHODS: Firstly, functional data analysis (FDA) was introduced to extract two types of data feature (DF). Furthermore, data-knowledge co-driven feature (DKCF) was proposed by combining FDA and constraints of KF. Finally, random forest, ada boost, gradient boosting, support vector machine and deep neural network were adopted, to compare the abilities of KF, DFs and DKCF in predicting blood pressure with two datasets (A published dataset and a self-collected dataset). RESULTS: Under the premise of extracting only 9 features, the average mean absolute errors (MAE) of systolic blood pressure (SBP) and diastolic blood pressure (DBP) obtained by DKCF are both the smallest in dataset 1. In dataset 2, DKCF acquires the smallest MAE in predicting SBP and obtains the second smallest MAE in predicting DBP. CONCLUSIONS: The results demonstrate that low-dimensional DKCF of photoplethysmography is closely correlated with blood pressure, which may serve as an important indicator for health assessment.
Asunto(s)
Presión Sanguínea , Fotopletismografía , Humanos , Fotopletismografía/métodos , Presión Sanguínea/fisiología , Masculino , Femenino , Determinación de la Presión Sanguínea/métodos , Adulto , Máquina de Vectores de Soporte , Redes Neurales de la Computación , Persona de Mediana EdadRESUMEN
Atrial fibrillation (AF) is the most prevalent arrhythmia characterized by intermittent and asymptomatic episodes. However, traditional detection methods often fail to capture the sporadic and intricate nature of AF, resulting in an increased risk of false-positive diagnoses. To address these challenges, this study proposes an intelligent AF detection and diagnosis method that integrates Complementary Ensemble Empirical Mode Decomposition, Power-Normalized Cepstral Coefficients, Bi-directional Long Short-term Memory (CEPNCC-BiLSTM), and photoelectric volumetric pulse wave technology to enhance accuracy in detecting AF. Compared to other approaches, the proposed method demonstrates faster preprocessing efficiency and higher sensitivity in detecting AF while effectively filtering out false alarms from photoplethysmography (PPG) recordings of non-AF patients. Considering the limitations of conventional AF detection evaluation systems that lack a comprehensive assessment of efficiency and accuracy, this study proposes the ET-score evaluation system based on F-measurement, which incorporates both computational speed and accuracy to provide a holistic assessment of overall performance. Evaluated with the ET-score, the CEPNCC-BiLSTM method outperforms EEMD-based improved Power-Normalized Cepstral Coefficients and Bi-directional Long Short-term Memory (EPNCC-BiLSTM), Support Vector Machine (SVM), EPNCC-SVM, and CEPNCC-SVM methods. Notably, this approach achieves an outstanding accuracy rate of up to 99.2% while processing PPG recordings within 5 s, highlighting its potential for long-term AF monitoring.
Asunto(s)
Algoritmos , Fibrilación Atrial , Fotopletismografía , Procesamiento de Señales Asistido por Computador , Fotopletismografía/métodos , Humanos , Fibrilación Atrial/diagnóstico , Fibrilación Atrial/fisiopatología , Masculino , Femenino , Adulto , Persona de Mediana EdadRESUMEN
Preterm birth (PTB) remains a global health concern, impacting neonatal mortality and lifelong health consequences. Traditional methods for estimating PTB rely on electronic health records or biomedical signals, limited to short-term assessments in clinical settings. Recent studies have leveraged wearable technologies for in-home maternal health monitoring, offering continuous assessment of maternal autonomic nervous system (ANS) activity and facilitating the exploration of PTB risk. In this paper, we conduct a longitudinal study to assess the risk of PTB by examining maternal ANS activity through heart rate (HR) and heart rate variability (HRV). To achieve this, we collect long-term raw photoplethysmogram (PPG) signals from 58 pregnant women (including seven preterm cases) from gestational weeks 12-15 to three months post-delivery using smartwatches in daily life settings. We employ a PPG processing pipeline to accurately extract HR and HRV, and an autoencoder machine learning model with SHAP analysis to generate explainable abnormality scores indicative of PTB risk. Our results reveal distinctive patterns in PTB abnormality scores during the second pregnancy trimester, indicating the potential for early PTB risk estimation. Moreover, we find that HR, average of interbeat intervals (AVNN), SD1SD2 ratio, and standard deviation of interbeat intervals (SDNN) emerge as significant PTB indicators.
Asunto(s)
Frecuencia Cardíaca , Nacimiento Prematuro , Humanos , Femenino , Frecuencia Cardíaca/fisiología , Embarazo , Nacimiento Prematuro/fisiopatología , Estudios Longitudinales , Adulto , Fotopletismografía/métodos , Medición de Riesgo/métodos , Sistema Nervioso Autónomo/fisiopatología , Aprendizaje Automático , Recién Nacido , Monitoreo Fisiológico/métodosRESUMEN
The compensatory reserve index (CRI), derived from machine learning algorithms from peripherally obtained photoplethysmography signals, provides a non-invasive assessment of cardiovascular stability, that may be useful clinically. Briefly, the CRI device provides a value between 0 and 1, with 1 reflecting full compensable capabilities and 0 reflecting little to no compensable capabilities. However, the CRI algorithm was developed in younger to middle aged adults, such that it is unknown if older age modulates CRI responses to cardiovascular challenges. In young and older subjects, we compared CRI responses to normothermic and hyperthermic progressive lower body negative pressure (LBNP), and volume loading with saline infusion. Eleven younger (20-36 years) and 10 older (61-75 years) healthy participants underwent (1) graded normothermic LBNP up to 30 mmHg, (2) graded hyperthermic (1.5°C increase in blood temperature) LBNP up to 30 mmHg, and (3) infusion of 15 mL/kg saline (volume loading) with hyperthermia maintained. CRI was obtained throughout each procedure. CRI at 30 mmHg LBNP was 0.18 and 0.24 units greater in the older group during normothermic and hyperthermic LBNP, respectively. However, CRI was not different between age groups at any other LBNP stage, nor did CRI change with volume loading regardless of age. In response to passive hyperthermia alone, regression analyses showed that heart rate was the strongest predictor of CRI. Blood temperature, rate pressure product, and stroke volume were also predictive of CRI but to a lesser extent. In conclusion, age attenuates the reduction in CRI during progressive normothermic and hyperthermic LBNP, but only at 30 mmHg. Second, the CRI was unchanged during volume loading in all subjects. Future studies should determine whether the age differences in CRI reflect age differences in LBNP tolerance.
Asunto(s)
Hipovolemia , Presión Negativa de la Región Corporal Inferior , Humanos , Adulto , Masculino , Femenino , Hipovolemia/fisiopatología , Persona de Mediana Edad , Proyectos Piloto , Presión Negativa de la Región Corporal Inferior/métodos , Anciano , Hipertermia/fisiopatología , Adulto Joven , Frecuencia Cardíaca/fisiología , Envejecimiento/fisiología , Fotopletismografía/métodos , Volumen SanguíneoRESUMEN
The use of observed wearable sensor data (e.g., photoplethysmograms [PPG]) to infer health measures (e.g., glucose level or blood pressure) is a very active area of research. Such technology can have a significant impact on health screening, chronic disease management and remote monitoring. A common approach is to collect sensor data and corresponding labels from a clinical grade device (e.g., blood pressure cuff) and train deep learning models to map one to the other. Although well intentioned, this approach often ignores a principled analysis of whether the input sensor data have enough information to predict the desired metric. We analyze the task of predicting blood pressure from PPG pulse wave analysis. Our review of the prior work reveals that many papers fall prey to data leakage and unrealistic constraints on the task and preprocessing steps. We propose a set of tools to help determine if the input signal in question (e.g., PPG) is indeed a good predictor of the desired label (e.g., blood pressure). Using our proposed tools, we found that blood pressure prediction using PPG has a high multi-valued mapping factor of 33.2% and low mutual information of 9.8%. In comparison, heart rate prediction using PPG, a well-established task, has a very low multi-valued mapping factor of 0.75% and high mutual information of 87.7%. We argue that these results provide a more realistic representation of the current progress toward the goal of wearable blood pressure measurement via PPG pulse wave analysis. For code, see our project page: https://github.com/lirus7/PPG-BP-Analysis.
Asunto(s)
Presión Sanguínea , Fotopletismografía , Fotopletismografía/métodos , Humanos , Presión Sanguínea/fisiología , Análisis de la Onda del Pulso/métodos , Determinación de la Presión Sanguínea/métodos , Procesamiento de Señales Asistido por Computador , Aprendizaje Profundo , Dispositivos Electrónicos VestiblesRESUMEN
Objective. The widespread adoption of Photoplethysmography (PPG) as a non-invasive method for detecting blood volume variations and deriving vital physiological parameters reflecting health status has surged, primarily due to its accessibility, cost-effectiveness, and non-intrusive nature. This has led to extensive research around this technique in both daily life and clinical applications. Interestingly, despite the existence of contradictory explanations of the underlying mechanism of PPG signals across various applications, a systematic investigation into this crucial matter has not been conducted thus far. This gap in understanding hinders the full exploitation of PPG technology and undermines its accuracy and reliability in numerous applications.Approach. Building upon a comprehensive review of the fundamental principles and technological advancements in PPG, this paper initially attributes the origin of PPG signals to a combination of physical and physiological transmission processes. Furthermore, three distinct models outlining the concerned physiological transmission processes are synthesized, with each model undergoing critical examination based on theoretical underpinnings, empirical evidence, and constraints.Significance. The ultimate objective is to form a fundamental framework for a better understanding of physiological transmission processes in PPG signal generation and to facilitate the development of more reliable technologies for detecting physiological signals.
Asunto(s)
Fotopletismografía , Procesamiento de Señales Asistido por Computador , Fotopletismografía/métodos , Humanos , Volumen Sanguíneo/fisiologíaRESUMEN
Patients with surgical, pulmonary, and cardiac problems, continual monitoring of Oxygen Saturation of a Person (SpO2) and Respiratory Rate (RR) is essential. Similarly, the persons with cardiopulmonary health issues, RR estimation is crucial. The performance of the ventilator assistance and lung medicines are evaluated using SpO2 and RR. For the persons, those who are living alone with respiratory illnesses need a compulsory estimation of RR. In case of serious illness, the RR might face abrupt changes. The immobility of the disturbance and RR makes the RR evaluation from the PhotoPlethysmoGraphic (PPG) signals is a difficult challenge. So, an efficient RR and SpO2 estimation framework from the PPG signal using the deep learning method is developed in this paper. At first, the PPG signal is collected from standard data sources. The collected PPG signals undergo signal pre-processing. The pre-processing procedures include Motion Artifacts (MA) removal and filtering techniques. The pre-processed signals are split into distinct windows. From the split windows of the signals, the spectral features, RR, and Respiratory Peak Variance (RPV) features are extracted. The retrieved features are selected optimally with the help of Advanced Golden Tortoise Beetle Optimizer (AGTBO). The weights are chosen optimally with the same AGTBO. The optimally selected features are fused with the optimal features to get the weighted optimal features. These weighted optimal features are fed into the Ensemble Learning-based RR and SpO2 Estimation Network (ELRR-SpO2EN). The ensemble learning model is developed by combining Multilayer Perceptron (MLP), AdaBoost, and Attention-based Long Short Term Memory (A-LSTM). The performance of the developed RR and SpO2 estimation model is compared with other existing techniques. The experimental analysis results revealed that the proposed AGTBO-ELRR-SpO2EN model attained 96 % accuracy for the second dataset, which is higher than the conventional models such as MLP (90 %), Adaboost (92 %), A-LSTM (92 %), and MLP-ADA-ALSTM (94 %). Thus, it has been confirmed that the designed RR and SpO2 estimation framework from PPG signals is more efficient than the other conventional models.
Asunto(s)
Saturación de Oxígeno , Fotopletismografía , Procesamiento de Señales Asistido por Computador , Fotopletismografía/métodos , Humanos , Saturación de Oxígeno/fisiología , Artefactos , Frecuencia Respiratoria/fisiología , Masculino , Oxígeno/sangre , Oxígeno/metabolismoRESUMEN
STUDY OBJECTIVES: Advanced signal processing of photoplethysmographic data enables novel analyses which may improve the understanding of the pathogenesis of dysglycemia associated with sleep disorders. We aimed to identify sleep-related pulse wave characteristics in diabetic patients compared to normoglycemic individuals, independent of cardiovascular-related comorbidities. METHODS: This cross-sectional evaluation of the population-based Swedish CArdioPulmonary bioImage Study (SCAPIS) included overnight oximetry-derived pulse wave data from 3997 subjects (45 % males, age 50-64 years). Metabolic status was classified as normoglycemic (n = 3220), pre-diabetic (n = 544), or diabetic (n = 233). Nine validated pulse wave features proposed to influence cardiovascular risk were derived and compared between metabolic status groups. Logistic prediction models and genetic matching were applied to capture diabetes-related pulse wave characteristics during sleep. The model was controlled for anthropometrics, lifestyle, sleep apnea, and in the final adjustment even for cardiometabolic factors like dyslipidaemia, hypertension, and coronary artery calcification. RESULTS: Pulse wave-derived parameters differed between normoglycemic and diabetic individuals in eight dimensions in unadjusted as well as in the partially adjusted model (anthropometric factors and sleep apnea, p ≤ 0.001). All covariates confirmed significant differences between normoglycemic and diabetic subjects (all p ≤ 0.001). Reduced cardio-respiratory coupling (respiratory-related pulse oscillations) (ß = -0.010, p = 0.012), as well as increased vascular stiffness (shortened pulse propagation time (ß = -0.015, p = 0.001), were independently associated with diabetes even when controlled for cardiometabolic factors. These results were confirmed through a matched cohort comparative analysis. CONCLUSIONS: Photoplethysmographic pulse wave analysis during sleep can be utilized to capture multiple features of modified autonomic regulation and cardiovascular consequences in diabetic subjects. Dampened heart rate variability and increased vascular stiffness during sleep showed the strongest associations with diabetes.
Asunto(s)
Análisis de la Onda del Pulso , Humanos , Masculino , Femenino , Persona de Mediana Edad , Estudios Transversales , Suecia/epidemiología , Diabetes Mellitus/fisiopatología , Diabetes Mellitus/epidemiología , Sueño/fisiología , Fotopletismografía , Oximetría , Enfermedades Cardiovasculares/fisiopatología , Enfermedades Cardiovasculares/epidemiología , Dedos/irrigación sanguínea , Dedos/fisiopatologíaRESUMEN
A point-of-care non-invasive test for Coronary Artery Disease (CAD) (POC-CAD) has been previously developed and validated. The test requires the simultaneous acquisition of orthogonal voltage gradient (OVG) and photoplethysmogram signals, which is the primary methodology described in this paper. The acquisition of the OVG, a biopotential signal, necessitates the placement of electrodes on the prepared skin of the patient's thorax (arranged similarly to the Frank lead configuration, comprising six bipolar electrodes and a reference electrode) and a hemodynamic sensor on the finger (using a standard transmission modality). The signal is uploaded to a cloud-based system, where engineered features are extracted from the signal and supplied to a machine-learned algorithm to yield the CAD Score. The physician must then interpret the value of the CAD Score in the context of their patient's pre-test probability of CAD, resulting in a post-test probability of CAD. This interpretation can be performed at the level of test positivity and test negativity or at a finer level of granularity; methodologies for each are proposed here based on likelihood ratios. Using the post-test probability, the physician must determine the appropriate next step in the treatment of their patient; several scenarios are used to illustrate this process. Test adoption is only feasible if economically viable; a discussion of the integration of the test into the CAD diagnostic flow and the resultant cost savings to the healthcare system is provided. The economic model demonstrates that cost savings to the healthcare system can be achieved by preventing delayed treatment, which, if left unaddressed, results in disease progression requiring more advanced (and expensive) care.
Asunto(s)
Enfermedad de la Arteria Coronaria , Pruebas en el Punto de Atención , Humanos , Enfermedad de la Arteria Coronaria/diagnóstico , Enfermedad de la Arteria Coronaria/economía , Pruebas en el Punto de Atención/economía , Fotopletismografía/métodos , Fotopletismografía/instrumentación , AlgoritmosRESUMEN
Peripheral Capillary Oxygen Saturation (SpO2) has received increasing attention during the COVID-19 pandemic. Clinical investigations have demonstrated that individuals afflicted with COVID-19 exhibit notably reduced levels of SpO2 before the deterioration of their health status. To cost-effectively enable individuals to monitor their SpO2, this paper proposes a novel neural network model named "ITSCAN" based on Temporal Shift Module. Benefiting from the widespread use of smartphones, this model can assess an individual's SpO2 in real time, utilizing standard facial video footage, with a temporal granularity of seconds. The model is interweaved by two distinct branches: the motion branch, responsible for extracting spatiotemporal data features and the appearance branch, focusing on the correlation between feature channels and the location information of feature map using coordinate attention mechanisms. Accordingly, the SpO2 estimator generates the corresponding SpO2 value. This paper summarizes for the first time 5 loss functions commonly used in the SpO2 estimation model. Subsequently, a novel loss function has been contributed through the examination of various combinations and careful selection of hyperparameters. Comprehensive ablation experiments analyze the independent impact of each module on the overall model performance. Finally, the experimental results based on the public dataset (VIPL-HR) show that our model has obvious advantages in MAE (1.10%) and RMSE (1.19%) compared with related work, which implies more accuracy of the proposed method to contribute to public health.
Asunto(s)
COVID-19 , Saturación de Oxígeno , Fotopletismografía , Humanos , Fotopletismografía/métodos , COVID-19/sangre , COVID-19/diagnóstico , Redes Neurales de la Computación , Oximetría/métodos , Oxígeno/sangre , SARS-CoV-2/aislamiento & purificación , Monitoreo Fisiológico/métodos , Teléfono InteligenteRESUMEN
Integrating continuous monitoring into everyday objects enables the early detection of diseases. This paper presents a novel approach to heartbeat monitoring on eScooters using multi-modal signal fusion. We explore heartbeat monitoring using electrocardiography (ECG) and photoplethysmography (PPG) and evaluate four signal fusion approaches based on convolutional neural network (CNN) and long short-term memory (LSTM) architectures. We perform an evaluation study using skin-attached ECG electrodes for ground truth generation. The CNN+LSTM late fusion accurately measures the heartbeat for 76.17% of the driving time.
Asunto(s)
Electrocardiografía , Frecuencia Cardíaca , Fotopletismografía , Humanos , Fotopletismografía/métodos , Frecuencia Cardíaca/fisiología , Redes Neurales de la Computación , Procesamiento de Señales Asistido por Computador , Monitoreo Fisiológico/métodosRESUMEN
Continuous monitoring of physiological signals such as electrocardiogram (ECG) in driving environments has the potential to reduce the need for frequent health check-ups by providing real-time information on cardiovascular health. However, capturing ECG from sensors mounted on steering wheels creates difficulties due to motion artifacts, noise, and dropouts. To address this, we propose a novel method for reliable and accurate detection of heartbeats using sensor fusion with a bidirectional long short-term memory (BiLSTM) model. Our dataset contains reference ECG, steering wheel ECG, photoplethysmogram (PPG), and imaging PPG (iPPG) signals, which are more feasible to capture in driving scenarios. We combine these signals for R-wave detection. We conduct experiments with individual signals and signal fusion techniques to evaluate the performance of detected heartbeat positions. The BiLSTMs model achieves a performance of 62.69% in the driving scenario city. The model can be integrated into the system to detect heartbeat positions for further analysis.
Asunto(s)
Electrocardiografía , Fotopletismografía , Procesamiento de Señales Asistido por Computador , Humanos , Fotopletismografía/métodos , Frecuencia Cardíaca/fisiología , Conducción de Automóvil , AlgoritmosRESUMEN
Objective: Photoelectric volumetric tracing (PPG) exhibits high sensitivity and specificity in flap monitoring. Deep learning (DL) is capable of automatically and robustly extracting features from raw data. In this study, we propose combining PPG with 1D convolutional neural networks (1D-CNN) to preliminarily explore the method's ability to distinguish the degree of embolism and to localize the embolic site in skin flap arteries. Methods: Data were collected under normal conditions and various embolic scenarios by creating vascular emboli in a dermatome artery model and a rabbit dermatome model. These datasets were then trained, validated, and tested using 1D-CNN. Results: As the degree of arterial embolization increased, the PPG amplitude upstream of the embolization site progressively increased, while the downstream amplitude progressively decreased, and the gap between the upstream and downstream amplitudes at the embolization site progressively widened. 1D-CNN was evaluated in the skin flap arterial model and rabbit skin flap model, achieving average accuracies of 98.36% and 95.90%, respectively. Conclusion: The combined monitoring approach of DL and PPG can effectively identify the degree of embolism and locate the embolic site within the skin flap artery.
Asunto(s)
Aprendizaje Profundo , Fotopletismografía , Colgajos Quirúrgicos , Conejos , Animales , Colgajos Quirúrgicos/irrigación sanguínea , Redes Neurales de la Computación , Monitoreo Fisiológico , Periodo Posoperatorio , EmboliaRESUMEN
BACKGROUND: The associations of risk factors with vascular impairment in type 1 diabetes patients seem more complex than that in type 2 diabetes patients. Therefore, we analyzed the associations between traditional and novel cardiovascular risk factors and vascular parameters in individuals with T1D and modifications of these associations according to sex and genetic factors. METHODS: In a cross-sectional study, we analyzed the association of risk factors in T1D individuals younger than 65 years using vascular parameters, such as ankle brachial index (ABI) and toe brachial index (TBI), duplex ultrasound, measuring the presence of plaques in carotid and femoral arteries (Belcaro score) and intima media thickness of carotid arteries (CIMT). We also used photoplethysmography, which measured the interbranch index expressed as the Oliva-Roztocil index (ORI), and analyzed renal parameters, such as urine albumin/creatinine ratio (uACR) and glomerular filtration rate (GFR). We evaluated these associations using multivariate regression analysis, including interactions with sex and the gene for connexin 37 (Cx37) polymorphism (rs1764391). RESULTS: In 235 men and 227 women (mean age 43.6 ± 13.6 years; mean duration of diabetes 22.1 ± 11.3 years), pulse pressure was strongly associated with unfavorable values of most of the vascular parameters under study (ABI, TBI, Belcaro scores, uACR and ORI), whereas plasma lipids, represented by remnant cholesterol (cholesterol - LDL-HDL cholesterol), the atherogenic index of plasma (log (triglycerides/HDL cholesterol) and Lp(a), were associated primarily with renal impairment (uACR, GFR and lipoprotein (a)). Plasma non-HDL cholesterol was not associated with any vascular parameter under study. In contrast to pulse pressure, the associations of lipid factors with kidney and vascular parameters were modified by sex and the Cx37 gene. CONCLUSION: In addition to known information, easily obtainable risk factor, such as pulse pressure, should be considered in individuals with T1D irrespective of sex and genetic background. The associations of plasma lipids with kidney function are complex and associated with sex and genetic factors. The decision of whether pulse pressure, remnant lipoproteins, Lp(a) and other determinants of vascular damage should become treatment targets in T1D should be based on the results of future clinical trials.
Asunto(s)
Diabetes Mellitus Tipo 1 , Proteína alfa-4 de Unión Comunicante , Adulto , Femenino , Humanos , Masculino , Persona de Mediana Edad , Índice Tobillo Braquial , Grosor Intima-Media Carotídeo , Estudios Transversales , Diabetes Mellitus Tipo 1/genética , Diabetes Mellitus Tipo 1/fisiopatología , Angiopatías Diabéticas/genética , Angiopatías Diabéticas/fisiopatología , Proteína alfa-4 de Unión Comunicante/genética , Predisposición Genética a la Enfermedad , Tasa de Filtración Glomerular , Factores de Riesgo de Enfermedad Cardiaca , Fenotipo , Fotopletismografía , Polimorfismo Genético , Factores SexualesRESUMEN
Deep learning (DL) models have shown promise for the accurate detection of atrial fibrillation (AF) from electrocardiogram/photoplethysmography (ECG/PPG) data, yet deploying these on resource-constrained wearable devices remains challenging. This study proposes integrating a customized channel attention mechanism to compress DL neural networks for AF detection, allowing the model to focus only on the most salient time-series features. The results demonstrate that applying compression through channel attention significantly reduces the total number of model parameters and file size while minimizing loss in detection accuracy. Notably, after compression, performance increases for certain model variants in key AF databases (ADB and C2017DB). Moreover, analyzing the learned channel attention distributions after training enhances the explainability of the AF detection models by highlighting the salient temporal ECG/PPG features most important for its diagnosis. Overall, this research establishes that integrating attention mechanisms is an effective strategy for compressing large DL models, making them deployable on low-power wearable devices. We show that this approach yields compressed, accurate, and explainable AF detectors ideal for wearables. Incorporating channel attention enables simpler yet more accurate algorithms that have the potential to provide clinicians with valuable insights into the salient temporal biomarkers of AF. Our findings highlight that the use of attention is an important direction for the future development of efficient, high-performing, and interpretable AF screening tools for wearable technology.
Asunto(s)
Algoritmos , Fibrilación Atrial , Aprendizaje Profundo , Electrocardiografía , Redes Neurales de la Computación , Dispositivos Electrónicos Vestibles , Fibrilación Atrial/diagnóstico , Fibrilación Atrial/fisiopatología , Humanos , Electrocardiografía/métodos , Fotopletismografía/métodos , Procesamiento de Señales Asistido por ComputadorRESUMEN
Transcatheter aortic valve implantation (TAVI) was initially developed for adult patients, but there is a growing interest to expand this procedure to younger individuals with longer life expectancies. However, the gradual degradation of biological valve leaflets in transcatheter heart valves (THV) presents significant challenges for this extension. This study aimed to establish a multiphysics computational framework to analyze structural and flow measurements of TAVI and evaluate the integration of optical fiber and photoplethysmography (PPG) sensors for monitoring valve function. A two-way fluid-solid interaction (FSI) analysis was performed on an idealized aortic vessel before and after the virtual deployment of the SAPIEN 3 Ultra (S3) THV. Subsequently, an analytical analysis was conducted to estimate the PPG signal using computational flow predictions and to analyze the effect of different pressure gradients and distances between PPG sensors. Circumferential strain estimates from the embedded optical fiber in the FSI model were highest in the sinus of Valsalva; however, the optimal fiber positioning was found to be distal to the sino-tubular junction to minimize bending effects. The findings also demonstrated that positioning PPG sensors both upstream and downstream of the bioprosthesis can be used to effectively assess the pressure gradient across the valve. We concluded that computational modeling allows sensor design to quantify vessel wall strain and pressure gradients across valve leaflets, with the ultimate goal of developing low-cost monitoring systems for detecting valve deterioration.