Photoplethysmography Data Research Articles

Testing preload responsiveness by the tidal volume challenge assessed by the photoplethysmographic perfusion index

BackgroundTo 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%.MethodsIn 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.ResultsAmong 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.ConclusionsIn 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.

A general framework for generative self-supervised learning in non-invasive estimation of physiological parameters using photoplethysmography

Aligning physiological parameter labels with large-scale photoplethysmographic (PPG) data for deep learning is challenging and resource-intensive. While self-supervised representation learning (SSRL) can handle limited annotated data, the challenge lies in learning robust shared representations from vast unlabeled data and integrating various contextual cues to learn distinctive representations. To alleviate these challenges, a generative SSRL framework TS2TC is proposed to collaboratively utilize the temporal, spectrogram, and temporal-spectrogram mixed domains to explore and incorporate the unique features of PPG for universal and non-invasive physiological parameter estimation. Initially, a pretext task named Cross-Temporal Fusion Generative Anchor (CTFGA) is designed, modeling temporal dependencies and reconstructing independent segments at a coarse level to provide robust global feature extraction and local semantic contextual representation. The framework also includes sub-signals from PPG with diverse frequency scales and order derivatives reflecting hemodynamics to facilitate learning shared representations at varying semantic levels. Secondly, an advanced cognitive-inspired dual-process transfer (DPT) strategy is formulated, consisting of prior-dependent autonomous processes and posterior observation reasoning processes, to leverage the independent and integrated advantages of shared and specific representations. Furthermore, TS2TC introduces a novel bilinear temporal-spectrogram fusion method in the mixed domain, aligning latent representations from different domains, and establishing fine-grained contextual interactions at the feature level across multiple sources of information. Extensive experiments on physiological parameter estimation tasks showed that the joint performance of CTFGA and DPT outperforms standard generative learning significantly. TS2TC achieved an average 2.49% improvement in RMSE over the current state-of-the-art estimation methods with only 10% training data.

Open Access Data Repository and Common Data Model for Pulse Oximeter Performance Data.

The OpenOximetry Repository is a structured database storing clinical and lab pulse oximetry data, serving as a centralized repository and data model for pulse oximetry initiatives. It supports measurements of arterial oxygen saturation (SaO2) by arterial blood gas co-oximetry and pulse oximetry (SpO2), alongside processed and unprocessed photoplethysmography (PPG) data and other metadata. This includes skin color measurements, finger diameter, vital signs (e.g., arterial blood pressure, end-tidal carbon dioxide), and arterial blood gas parameters (e.g., acid-base balance, hemoglobin concentration). Data contributions are encouraged. All data, from desaturation studies to clinical trials, are collected prospectively to ensure accuracy. A common data model and standardized protocols for consistent archival and interpretation ensure consistent data archival and interpretation. The dataset aims to facilitate research on pulse oximeter performance across diverse human characteristics, addressing performance issues and promoting accurate pulse oximeters. The initial release includes controlled lab desaturation studies (CLDS), with ongoing updates planned as further data from clinical trials and CLDS become available.

The influence of diabetes on sleep-derived cardiorespiratory features of the finger pulse wave signal – The population-based SCAPIS study

Study objectivesAdvanced 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. MethodsThis 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. ResultsPulse 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) (β = −0.010, p = 0.012), as well as increased vascular stiffness (shortened pulse propagation time (β = −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. ConclusionsPhotoplethysmographic 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.

Intelligent Detection Method of Atrial Fibrillation by CEPNCC-BiLSTM Based on Long-Term Photoplethysmography Data.

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.

OSA diagnosis goes wearable: are the latest devices ready to shine?

Since 2019, the FDA has cleared nine novel obstructive sleep apnea (OSA)-detecting wearables for home sleep apnea testing, with many now commercially available for sleep clinicians to integrate into their clinical practices. To help clinicians comprehend these devices and their functionalities, we meticulously reviewed their operating mechanisms, sensors, algorithms, data output, and related performance evaluation literature. We collected information from PubMed, FDA clearance documents, ClinicalTrial.gov, and web sources, with direct industry input whenever feasible. In this "device-centered" review, we broadly categorized these wearables into two main groups: those that primarily harness Photoplethysmography (PPG) data and those that do not. The former include the peripheral arterial tonometry (PAT)-based devices. The latter was further broken down into two key subgroups: acoustic-based and respiratory effort-based devices. We provided a performance evaluation literature review and objectively compared device-derived metrics and specifications pertinent to sleep clinicians. Detailed demographics of study populations, exclusion criteria, and pivotal statistical analyses of the key validation studies are summarized. In the foreseeable future, these novel OSA-detecting wearables may emerge as primary diagnostic tools for patients at risk for moderate-to-severe OSA without significant comorbidities. While more devices are anticipated to join this category, there remains a critical need for cross-device comparison studies as well as independent performance evaluation and outcome research in diverse populations. Now is the moment for sleep clinicians to immerse themselves in understanding these emerging tools to ensure our patient-centered care is improved through the appropriate implementation and utilization of these novel sleep technologies.

Reconstruction of Missing Electrocardiography Signals from Photoplethysmography Data Using Deep Neural Network.

ECG helps in diagnosing heart disease by recording heart activity. During long-term measurements, data loss occurs due to sensor detachment. Therefore, research into the reconstruction of missing ECG data is essential. However, ECG requires user participation and cannot be used for continuous heart monitoring. Continuous monitoring of PPG signals is conversely low-cost and easy to carry out. In this study, a deep neural network model is proposed for the reconstruction of missing ECG signals using PPG data. This model is an end-to-end deep learning neural network utilizing WNet architecture as a basis, on which a bidirectional long short-term memory network is added in establishing a second model. The performance of both models is verified using 146 records from the MIMIC III matched subset. Compared with the reference, the ECG reconstructed using the proposed model has a Pearson's correlation coefficient of 0.851, root mean square error (RMSE) of 0.075, percentage root mean square difference (PRD) of 5.452, and a Fréchet distance (FD) of 0.302. The experimental results demonstrate that it is feasible to reconstruct missing ECG signals from PPG.

Evaluating reliability in wearable devices for sleep staging.

Sleep is crucial for physical and mental health, but traditional sleep quality assessment methods have limitations. This scoping review analyzes 35 articles from the past decade, evaluating 62 wearable setups with varying sensors, algorithms, and features. Our analysis indicates a trend towards combining accelerometer and photoplethysmography (PPG) data for out-of-lab sleep staging. Devices using only accelerometer data are effective for sleep/wake detection but fall short in identifying multiple sleep stages, unlike those incorporating PPG signals. To enhance the reliability of sleep staging wearables, we propose five recommendations: (1) Algorithm validation with equity, diversity, and inclusion considerations, (2) Comparative performance analysis of commercial algorithms across multiple sleep stages, (3) Exploration of feature impacts on algorithm accuracy, (4) Consistent reporting of performance metrics for objective reliability assessment, and (5) Encouragement of open-source classifier and data availability. Implementing these recommendations can improve the accuracy and reliability of sleep staging algorithms in wearables, solidifying their value in research and clinical settings.

Intelligent Electrocardiogram Acquisition Via Ubiquitous Photoplethysmography Monitoring.

Recent advances in machine learning, particularly deep neural network architectures, have shown substantial promise in classifying and predicting cardiac abnormalities from electrocardiogram (ECG) data. Such data are rich in information content, typically in morphology and timing, due to the close correlation between cardiac function and the ECG. However, the ECG is usually not measured ubiquitously in a passive manner from consumer devices, and generally requires 'active' sampling whereby the user prompts a device to take an ECG measurement. Conversely, photoplethysmography (PPG) data are typically measured passively by consumer devices, and therefore available for long-period monitoring and suitable in duration for identifying transient cardiac events. However, classifying or predicting cardiac abnormalities from the PPG is very difficult, because it is a peripherally-measured signal. Hence, the use of the PPG for predictive inference is often limited to deriving physiological parameters (heart rate, breathing rate, etc.) or for obvious abnormalities in cardiac timing, such as atrial fibrillation/flutter ("palpitations"). This work aims to combine the best of both worlds: using continuously-monitored, near-ubiquitous PPG to identify periods of sufficient abnormality in the PPG such that prompting the user to take an ECG would be informative of cardiac risk. We propose a dual-convolutional-attention network (DCA-Net) to achieve this ECG-based PPG classification. With DCA-Net, we prove the plausibility of this concept on MIMIC Waveform Database with high performance level (AUROC 0.9 and AUPRC 0.7) and receive satisfactory result when testing the model on an independent dataset (AUROC 0.7 and AUPRC 0.6) which it is not perfectly-matched to the MIMIC dataset.

Noise Reduction in Photoplethysmography Signals Using a Convolutional Denoising Autoencoder With Unconventional Training Scheme.

We propose an efficient approach based on a convolutional denoising autoencoder (CDA) network to reduce motion and noise artifacts (MNA) from corrupted atrial fibrillation (AF) and non-AF photoplethysmography (PPG) data segments so that an accurate PPG-signal-derived heart rate can be obtained. Our method's main innovation is the optimization of the CDA performance for both rhythms using more AF than non-AF data for training the AF-specific CDA model and vice versa for the non-AF CDA network. To evaluate this unconventional training scheme, our proposed network was trained and tested on 25-sec PPG data segments from 48 subjects from two different databases-the Pulsewatch dataset and Stanford University's publicly available PPG dataset. In total, our dataset contains 10,773 data segments: 7,001 segments for training and 3,772 independent segments from out-of-sample subjects for testing. Using real-life corrupted PPG segments, our approach significantly reduced the average heart rate root mean square error (RMSE) of the reconstructed PPG segments by 45.74% and 23% compared to the corrupted non-AF and AF data, respectively. Further, our approach exhibited lower RMSE, and higher sensitivity and PPV for detected peaks compared to the reconstructed data produced by the alternative methods. These results show the promise of our approach as a reliable denoising method, which should be used prior to AF detection algorithms for an accurate cardiac health monitoring involving wearable devices. PPG signals collected from wearables are vulnerable to MNA, which limits their use as a reliable measurement, particularly in uncontrolled real-life environments.

69 Derivation and validation of an intrapartum algorithm to predict postpartum hemorrhage risk using photoplethysmography data

69 Derivation and validation of an intrapartum algorithm to predict postpartum hemorrhage risk using photoplethysmography data

Predicting Blood Pressures for Pregnant Women by PPG and Personalized Deep Learning.

Blood pressure (BP) is predicted by this effort based on photoplethysmography (PPG) data to provide effective pre-warning of possible preeclampsia of pregnant women. Towards frequent BP measurement, a PPG sensor device is utilized in this study as a solution to offer continuous, cuffless blood pressure monitoring frequently for pregnant women. PPG data were collected using a flexible sensor patch from the wrist arteries of 194 subjects, which included 154 normal individuals and 40 pregnant women. Deep-learning models in 3 stages were built and trained to predict BP. The first stage involves developing a baseline deep-learning BP model using a dataset from common subjects. In the 2nd stage, this model was fine-tuned with data from pregnant women, using a 1-Dimensional Convolutional Neural Network (1D-CNN) with Convolutional Block Attention Module (CBAMs), followed by bi-directional Gated Recurrent Units (GRUs) layers and attention layers. The fine-tuned model results in a mean error (ME) of -1.40 ± 7.15 (standard deviation, SD) for systolic blood pressure (SBP) and -0.44 (ME) ± 5.06 (SD) for diastolic blood pressure (DBP). At the final stage is the personalization for individual pregnant women using transfer learning again, enhancing further the model accuracy to -0.17 (ME) ± 1.45 (SD) for SBP and 0.27 (ME) ± 0.64 (SD) for DBP showing a promising solution for continuous, non-invasive BP monitoring in precision by the proposed 3-stage of modeling, fine-tuning and personalization.

Cardio‐autonomic control and cognitive decline in older adults

AbstractBackgroundCardiovascular diseases may be linked to dementia pathogenesis. The cardio‐autonomic control (CAC) plays an important role in the development of cardiovascular diseases and may be implicated by dementia pathophysiology. We tested whether the CAC proxied by the complexity of beat‐to‐beat pulse rate intervals (PRI) predicted longitudinal cognitive decline in older adults.MethodContinuous overnight pulse oximetry (photoplethysmography) data from 594 participants (mean age = 82.76±7.11 at oximetry assessment; 76% female) in the Rush Memory and Aging projects were studied. All participants completed cognitive assessments at oximetry baseline. Eighty‐four participants who had at least one follow‐up cognitive assessment were included in the analyses. After quality control, the feet of pulse waves in the photoplethysmography data were detected, and the consecutive foot‐to‐foot internals (i.e., PRI) time‐series within each 10‐min window were analyzed using the distribution entropy that evaluated the complexity of PRI (i.e., greater distribution entropy means more complex dynamics). To reduce behavioral and circadian effects, we used the mean distribution entropy values during 12AM‐3AM for each individual. Mixed‐effects models were constructed to associate distribution entropy to longitudinal cognitive changes, adjusting for age, sex, and education.ResultAt baseline, distribution entropy was normally distributed (mean = 0.33±0.14). On average, the global cognition score was 0.12 units (SD = 0.60). This score declined at an annual rate of 0.15 units (SE = 0.04; p = 0.0001). The distribution entropy was not associated with global cognition at baseline, but greater distribution entropy predicted slower cognitive decline. Specifically, a 1‐SD increase in distribution entropy correlated with a drop of 0.11 (SE = 0.04; p = 0.005) in the rate of cognitive decline.ConclusionThe nighttime CAC (potentially during sleep) is linked with longitudinal cognitive profiles in older adults. As the CAC is regulated by an internal body clock—the circadian system, in which a dysfunction is involved in Alzheimer’s pathogenesis, it is possible that the CAC underlies the connections of cardiovascular disorders and circadian dysfunction with Alzheimer’s disease and its clinical outcomes. Future studies are warranted to test these hypotheses. Further studies should also investigate whether CAC at different times of the night has different correlations with cognitive changes and whether CAC predicts Alzheimer’s disease.

Machine learning-based classification analysis of knowledge worker mental stress.

The aim of this study is to analyze the performance of classifying stress and non-stress by measuring biosignal data using a wearable watch without interfering with work activities at work. An experiment is designed where participants wear a Galaxy Watch3 to measure HR and photoplethysmography data while performing stress-inducing and relaxation tasks. The classification model was constructed using k-NN, SVM, DT, LR, RF, and MLP classifiers. The performance of each classifier was evaluated using LOSO-CV as a verification method. When the top 9 features, including the average and minimum value of HR, average of NNI, SDNN, vLF, HF, LF, LF/HF ratio, and total power, were used in the classification model, it showed the best performance with an accuracy of 0.817 and an F1 score of 0.801. This study also finds that it is necessary to measure physiological data for more than 2 or 3 min to accurately distinguish stress states.

Implicit HbA1c Achieving 87% Accuracy within 90 Days in Non-Invasive Fasting Blood Glucose Measurements Using Photoplethysmography.

To reduce the error induced by overfitting or underfitting in predicting non-invasive fasting blood glucose (NIBG) levels using photoplethysmography (PPG) data alone, we previously demonstrated that incorporating HbA1c led to a notable 10% improvement in NIBG prediction accuracy (the ratio in zone A of Clarke's error grid). However, this enhancement came at the cost of requiring an additional HbA1c measurement, thus being unfriendly to users. In this study, the enhanced HbA1c NIBG deep learning model (blood glucose level predicted from PPG and HbA1c) was trained with 1494 measurements, and we replaced the HbA1c measurement (explicit HbA1c) with "implicit HbA1c" which is reversely derived from pretested PPG and finger-pricked blood glucose levels. The implicit HbA1c is then evaluated across intervals up to 90 days since the pretest, achieving an impressive 87% accuracy, while the remaining 13% falls near the CEG zone A boundary. The implicit HbA1c approach exhibits a remarkable 16% improvement over the explicit HbA1c method by covering personal correction items automatically. This improvement not only refines the accuracy of the model but also enhances the practicality of the previously proposed model that relied on an HbA1c input. The nonparametric Wilcoxon paired test conducted on the percentage error of implicit and explicit HbA1c prediction results reveals a substantial difference, with a p-value of 2.75 × 10-7.

Individualized Maternal Sleep Quality Evaluation

Being pregnant is a special moment when many moms become aware of their lifestyle choices and how they affect the developing foetus. To detect potential issues early and guarantee the health and wellbeing of the woman and her unborn child, high-quality prenatal care is required. Up to this point, various researches have recommended maternal health surveillance programmes. However, they are either restricted to questionnaires and quick data gathering techniques or created for a specific health issue. Furthermore, no extensive studies have been conducted to examine the demands and difficulties. A thorough structure that enables ongoing monitoring of expectant mothers is necessary for maternal health. In this study, we offer a system that uses the Internet of Things (IoT) to continuously monitor maternal health throughout pregnancy and the postpartum period. The system uses a variety of data loggers to monitor the mother's health. We further point out that the smartwatch utilised in our study can gather accurate photoplethysmography data and has a respectable energy efficiency for long-term monitoring.

Ensemble-Based AI System for Brain Stroke Prediction

Abstract: Timely detection and proactive measures to avert stroke are of utmost importance due to the significant likelihood of severe disabilities or fatal consequences associated with this condition. It is imperative to promptly administer appropriate thrombolytic or anticoagulant medications for both ischemic and hemorrhagic strokes. The pivotal and initial stage revolves around timely recognition of the initial indicators of a stroke, which may differ among individuals, and promptly seeking medical intervention within the prescribed treatment window. This research introduces a machine learning-based system that employs real-time measurements of electrocardiogram (ECG) and photoplethysmography (PPG) data to forecast and interpret stroke prognostic symptoms in a meaningful way. To achieve real-time stroke prediction, we have developed and implemented an ensemble structure voting classifier that combines SVM, Random Forest, and decision tree classifiers. This approach accurately forecasts stroke diagnosis in patients and can be easily implemented by utilizing a patient's ECG and PPG attribute data.

Wearable Technologies for Electrodermal and Cardiac Activity Measurements: A Comparison between Fitbit Sense, Empatica E4 and Shimmer GSR3.

The capability of measuring specific neurophysiological and autonomic parameters plays a crucial role in the objective evaluation of a human's mental and emotional states. These human aspects are commonly known in the scientific literature to be involved in a wide range of processes, such as stress and arousal. These aspects represent a relevant factor especially in real and operational environments. Neurophysiological autonomic parameters, such as Electrodermal Activity (EDA) and Photoplethysmographic data (PPG), have been usually investigated through research-graded devices, therefore resulting in a high degree of invasiveness, which could negatively interfere with the monitored user's activity. For such a reason, in the last decade, recent consumer-grade wearable devices, usually designed for fitness-tracking purposes, are receiving increasing attention from the scientific community, and are characterized by a higher comfort, ease of use and, therefore, by a higher compatibility with daily-life environments. The present preliminary study was aimed at assessing the reliability of a consumer wearable device, i.e., the Fitbit Sense, with respect to a research-graded wearable, i.e., the Empatica E4 wristband, and a laboratory device, i.e., the Shimmer GSR3+. EDA and PPG data were collected among 12 participants while they performed multiple resting conditions. The results demonstrated that the EDA- and PPG-derived features computed through the wearable and research devices were positively and significantly correlated, while the reliability of the consumer device was significantly lower.

Cascade forest regression algorithm for non-invasive blood pressure estimation using PPG signals

The regression and classification performances of deep-learning algorithms depend on the tuning of the model and require significant intervention to train the model. A blood pressure prediction (BP) method – which is an improved cascade forest regression method based on a deep forest framework – is proposed in this study to mitigate the adverse effects of hyperparameters on deep learning algorithms and human errors. The impact of hyperparameters on the model can be reduced using random forest regression and extra tree regression as base estimators and by applying them to bootstrap aggregation strategies for learning data. The photoplethysmography (PPG) data and ambulatory blood pressure obtained from the MIMIC II database were evenly divided into 5 s segments to accurately estimate blood pressure. Nonlinear indices of the time domain, frequency domain, and heart rate variability were obtained from the PPG signal as training characteristic values. This process is similar to collecting data directly from a wearable device for rapid blood pressure prediction. This improves the predictive performance of the model and reduces additional memory consumption. Our proposed algorithm achieved mean absolute errors of 1.760 and 2.896 mmHg for systolic blood pressure (SBP) and diastolic blood pressure (DBP), respectively. Additionally, our best model achieved R2 scores of 0.948 and 0.926 for SBP and DBP, respectively. According to the Association for the Advancement of Medical Instrumentation standards, the standard deviation and mean error of the predicted results for systolic and diastolic BPs were within the standard range. According to the British Hypertension Society standard, the results of the proposed algorithm reached grade A. This study confirmed the possibility of developing an algorithm that can accurately estimate blood pressure.

RT-TRAQ: An algorithm for real-time tracking of faint quasi-periodic signals in noisy time series.

We present an algorithm for live tracking of quasi-periodic faint signals in non-stationary, noisy, and phase-desynchronized time series measurements that commonly arise in embedded applications, such as wearable health monitoring. The first step of Rt-Traq is to continuously select fixed-length windows based on the rise or fall of data values in the stream. Subsequently, Rt-Traq calculates an averaged representative window, and its spectrum, whose frequency peaks reveal the underlying quasi-periodic signals. As each new data sample comes in, Rt-Traq incrementally updates the spectrum, to continuously track the signals through time. We develop several alternate implementations of the proposed algorithm. We evaluate their performance in tracking maternal and fetal heart rate using non-invasive photoplethysmography (PPG) data collected by a wearable device from animal experiments as well as a number of pregnant women who participated in our study. Our empirical results demonstrate improvements compared to competing approaches. We also analyze the memory requirement and complexity trade-offs between the implementations, which impact their demand on platform resources for real-time operation.