Decoding 2.3 million ECGs: interpretable deep learning for advancing cardiovascular diagnosis and mortality risk stratification.

Aims: Electrocardiogram (ECG) is widely considered the primary test for evaluating cardiovascular diseases. However, the use of artificial intelligence (AI) to advance these medical practices and learn new clinical insights from ECGs remains largely unexplored. We hypothesize that AI models with a specific design can provide fine-grained interpretation of ECGs to advance cardiovascular diagnosis, stratify mortality risks, and identify new clinically useful information. Methods and results: Utilizing a data set of 2 322 513 ECGs collected from 1 558 772 patients with 7 years follow-up, we developed a deep-learning model with state-of-the-art granularity for the interpretable diagnosis of cardiac abnormalities, gender identification, and hypertension screening solely from ECGs, which are then used to stratify the risk of mortality. The model achieved the area under the receiver operating characteristic curve (AUC) scores of 0.998 (95% confidence interval (CI), 0.995-0.999), 0.964 (95% CI, 0.963-0.965), and 0.839 (95% CI, 0.837-0.841) for the three diagnostic tasks separately. Using ECG-predicted results, we find high risks of mortality for subjects with sinus tachycardia (adjusted hazard ratio (HR) of 2.24, 1.96-2.57), and atrial fibrillation (adjusted HR of 2.22, 1.99-2.48). We further use salient morphologies produced by the deep-learning model to identify key ECG leads that achieved similar performance for the three diagnoses, and we find that the V1 ECG lead is important for hypertension screening and mortality risk stratification of hypertensive cohorts, with an AUC of 0.816 (0.814-0.818) and a univariate HR of 1.70 (1.61-1.79) for the two tasks separately. Conclusion: Using ECGs alone, our developed model showed cardiologist-level accuracy in interpretable cardiac diagnosis and the advancement in mortality risk stratification. In addition, it demonstrated the potential to facilitate clinical knowledge discovery for gender and hypertension detection which are not readily available.

Does the liver facilitate aging-related cognitive impairment: Conversation between liver and brain during exercise?

Liver, an important regulator of metabolic homeostasis, is critical for healthy brain function. In particular, age-related neurodegenerative diseases seriously reduce the quality of life for the elderly. As population aging progresses rapidly, unraveling the mechanisms that effectively delay aging has become critical. Appropriate exercise is reported to improve aging-related cognitive impairment. Whereas current studies focused on exploring the effect of exercise on the aging brain itself, ignoring the persistent effects of peripheral organs on the brain through the blood circulation. The aim of this paper is to summarize the communication and aging processes of the liver and brain and to emphasize the metabolic mechanisms of the liver-brain axis about exercise ameliorating aging-related neurodegenerative diseases. A comprehensive understanding of the potential mechanisms about exercise ameliorating aging is critical for improving adaptation to age-related brain changes and formulating effective interventions against age-related cognitive decline.

HGCTNet: Handcrafted Feature-Guided CNN and Transformer Network for Wearable Cuffless Blood Pressure Measurement.

Biosignals collected by wearable devices, such as electrocardiogram and photoplethysmogram, exhibit redundancy and global temporal dependencies, posing a challenge in extracting discriminative features for blood pressure (BP) estimation. To address this challenge, we propose HGCTNet, a handcrafted feature-guided CNN and transformer network for cuffless BP measurement based on wearable devices. By leveraging convolutional operations and self-attention mechanisms, we design a CNN-Transformer hybrid architecture to learn features from biosignals that capture both local information and global temporal dependencies. Then, we introduce a handcrafted feature-guided attention module that utilizes handcrafted features extracted from biosignals as query vectors to eliminate redundant information within the learned features. Finally, we design a feature fusion module that integrates the learned features, handcrafted features, and demographics to enhance model performance. We validate our approach using two large wearable BP datasets: the CAS-BP dataset and the Aurora-BP dataset. Experimental results demonstrate that HGCTNet achieves an estimation error of 0.9 ± 6.5 mmHg for diastolic BP (DBP) and 0.7 ± 8.3 mmHg for systolic BP (SBP) on the CAS-BP dataset. On the Aurora-BP dataset, the corresponding errors are -0.4 ± 7.0 mmHg for DBP and -0.4 ± 8.6 mmHg for SBP. Compared to the current state-of-the-art approaches, HGCTNet reduces the mean absolute error of SBP estimation by 10.68% on the CAS-BP dataset and 9.84% on the Aurora-BP dataset. These results highlight the potential of HGCTNet in improving the performance of wearable cuffless BP measurements. The dataset and source code are available at https://github.com/zdzdliu/HGCTNet.

ScribFormer: Transformer Makes CNN Work Better for Scribble-Based Medical Image Segmentation.

Most recent scribble-supervised segmentation methods commonly adopt a CNN framework with an encoder-decoder architecture. Despite its multiple benefits, this framework generally can only capture small-range feature dependency for the convolutional layer with the local receptive field, which makes it difficult to learn global shape information from the limited information provided by scribble annotations. To address this issue, this paper proposes a new CNN-Transformer hybrid solution for scribble-supervised medical image segmentation called ScribFormer. The proposed ScribFormer model has a triple-branch structure, i.e., the hybrid of a CNN branch, a Transformer branch, and an attention-guided class activation map (ACAM) branch. Specifically, the CNN branch collaborates with the Transformer branch to fuse the local features learned from CNN with the global representations obtained from Transformer, which can effectively overcome limitations of existing scribble-supervised segmentation methods. Furthermore, the ACAM branch assists in unifying the shallow convolution features and the deep convolution features to improve model's performance further. Extensive experiments on two public datasets and one private dataset show that our ScribFormer has superior performance over the state-of-the-art scribble-supervised segmentation methods, and achieves even better results than the fully-supervised segmentation methods. The code is released at https://github.com/HUANGLIZI/ScribFormer.

Meta-analysis of the Correlation between Helicobacter Pylori Infection and the risk of Colorectal Neoplasia.

Objective: To study the association of H. pylori infection with colorectal adenomas. Methods: Web searches of PubMed, Embase, and Scopus databases for randomized controlled trials, class-experimental studies, and cohort studies on the association between H. pylori and colorectal adenomas were performed from May 2000 to May 2023. Literature was screened based on inclusion and exclusion criteria, data were extracted and evaluated for quality, and statistical analyses were performed using RevMan 5.2 software. Results: A total of 15 studies were included, and meta-analysis showed a statistically significant difference between colorectal neoplastic polyp cases in the H. pylori-positive and H. pylori-negative groups [OR=1.80, 95%CI: (1.31, 2.47), P < .01, I2 = 95%]. Analysis based on subgroups of different H. pylori detection methods showed that the correlation between H. pylori infection and colorectal polyp incidence is not affected by their detection methods, with serological detection subgroup: [OR=0.13, 95%CI: (0.05, 0.21), P < .01, I2 = 88%], and non-serological detection subgroup: [OR=0.13, 95%CI: (0.04, 0.22), P < .01, I2 = 95%]. Subgroup analysis of pathological types showed that H. pylori infection is not significantly associated with the development of non-neoplastic polyps [OR=1.47, 95%CI: 0.98-2.22, P = .06], whereas it is correlated with the development of neoplastic polyps [95%CI: 1.69-3.22, P < .01]. In the subgroup analysis of geographic differences in the population, H. pylori infection was correlated with the development of colorectal polyps in different geographic populations (P < .01). Conclusion: H. pylori infection is a risk factor for colorectal polyp neoplasia, its infection is associated with colorectal neoplasia, and the correlation is not affected by the different methods of H. pylori detection and the different geographic regions of the population.

Multi-View Cross-Fusion Transformer Based on Kinetic Features for Non-Invasive Blood Glucose Measurement Using PPG Signal.

Noninvasive blood glucose (BG) measurement could significantly improve the prevention and management of diabetes. In this paper, we present a robust novel paradigm based on analyzing photoplethysmogram (PPG) signals. The method includes signal pre-processing optimization and a multi-view cross-fusion transformer (MvCFT) network for non-invasive BG assessment. Specifically, a multi-size weighted fitting (MSWF) time-domain filtering algorithm is proposed to optimally preserve the most authentic morphological features of the original signals. Meanwhile, the spatial position encoding-based kinetics features are reconstructed and embedded as prior knowledge to discern the implicit physiological patterns. In addition, a cross-view feature fusion (CVFF) module is designed to incorporate pairwise mutual information among different views to adequately capture the potential complementary features in physiological sequences. Finally, the subject- wise 5- fold cross-validation is performed on a clinical dataset of 260 subjects. The root mean square error (RMSE) and mean absolute error (MAE) of BG measurements are 1.129 mmol/L and 0.659 mmol/L, respectively, and the optimal Zone A in the Clark error grid, representing none clinical risk, is 87.89%. The results indicate that the proposed method has great potential for homecare applications.

Uncertainties in the Analysis of Heart Rate Variability: A Systematic Review.

Heart rate variability (HRV) is an important metric with a variety of applications in clinical situations such as cardiovascular diseases, diabetes mellitus, and mental health. HRV data can be potentially obtained from electrocardiography and photoplethysmography signals, then computational techniques such as signal filtering and data segmentation are used to process the sampled data for calculating HRV measures. However, uncertainties arising from data acquisition, computational models, and physiological factors can lead to degraded signal quality and affect HRV analysis. Therefore, it is crucial to address these uncertainties and develop advanced models for HRV analysis. Although several reviews of HRV analysis exist, they primarily focus on clinical applications, trends in HRV methods, or specific aspects of uncertainties such as measurement noise. This paper provides a comprehensive review of uncertainties in HRV analysis, quantifies their impacts, and outlines potential solutions. To the best of our knowledge, this is the first study that presents a holistic review of uncertainties in HRV methods and quantifies their impacts on HRV measures from an engineer's perspective. This review is essential for developing robust and reliable models, and could serve as a valuable future reference in the field, particularly for dealing with uncertainties in HRV analysis.

Semi-Supervised Learning for Multi-Label Cardiovascular Diseases Prediction: A Multi-Dataset Study.

Electrocardiography (ECG) is a non-invasive tool for predicting cardiovascular diseases (CVDs). Current ECG-based diagnosis systems show promising performance owing to the rapid development of deep learning techniques. However, the label scarcity problem, the co-occurrence of multiple CVDs and the poor performance on unseen datasets greatly hinder the widespread application of deep learning-based models. Addressing them in a unified framework remains a significant challenge. To this end, we propose a multi-label semi-supervised model (ECGMatch) to recognize multiple CVDs simultaneously with limited supervision. In the ECGMatch, an ECGAugment module is developed for weak and strong ECG data augmentation, which generates diverse samples for model training. Subsequently, a hyperparameter-efficient framework with neighbor agreement modeling and knowledge distillation is designed for pseudo-label generation and refinement, which mitigates the label scarcity problem. Finally, a label correlation alignment module is proposed to capture the co-occurrence information of different CVDs within labeled samples and propagate this information to unlabeled samples. Extensive experiments on four datasets and three protocols demonstrate the effectiveness and stability of the proposed model, especially on unseen datasets. As such, this model can pave the way for diagnostic systems that achieve robust performance on multi-label CVDs prediction with limited supervision.

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.

Up-regulation of miR-155 protects against chronic heart failure by inhibiting HIF-1α.

BACKGROUND: Despite a crucial role of miR-155 in human cancers, its function in heart failure (HF) is still under investigation. This study was designed to explore its association with HF. METHODS: The abdominal transverse aortic constriction (TAC) was adopted for establishment of mouse HF models. qRT-PCR and WB were adopted to detect the changes of miR-155, HIF-1α, Cle-caspase-3, BCL2 and Bax levels in myocardial cells and heart tissues. The changes of cardiac function were checked by ultrasound. Additionally, luciferase reporter gene was adopted for interaction analysis of miR-155 with HIF-1α, and in situ end labelling method was used for detecting myocardial apoptosis. RESULTS: MiR-155 in myocardial tissue of HF mice was significantly down regulated. In HF mice injected with agomiR-155, the up-regulation of miR-155 strongly improved cardiac function, and also significantly lowered the protein levels of apoptosis-associated markers, C-caspase-3 and Bax, but up regulated Bcl-2. Additionally, HIF-1α was identified as the direct target of miR-155. As expected, over-expression of HIF-1α greatly reversed the effects of agomiR-155 on cardiac function and the expression of apoptosis-associated markers in heart tissues of HF mice. CONCLUSION: MiR-155 overexpression can suppress myocardial cell apoptosis through HIF-1α, and strongly alleviate the cardiac function damage in HF mice, indicating the potential of miR-155/HIF-1α axis to be a target for the diagnosis and therapy of HF.

Mass Spectrometry Chromatography-Based Metabolomics: The Effect of Long-Term Aerobic Exercise on Learning Ability and the Metabolism of Intestinal Contents in Mice with Alzheimer's Disease.

This study aimed to investigate the effect of long-term aerobic exercise on the metabolism of intestinal contents in APP/PS1 mice was studied using a non-targeted metabolomics technique based on high-performance liquid chromatography-mass spectrometry (HPLC-MS) coupling, providing a theoretical basis for exercise to regulate the metabolism of Alzheimer's disease (AD) organisms. Three-month-old male C57BL/6JNju mice, six wild-type (NC, n = 6); 12 APP/PS1 double transgenic species in total, were randomly divided into AD model (AM, n = 6) and AD model exercise (AE, n = 6) groups. The mice in the NC group were fed naturally, the mice in the AM group were statically placed on a running platform, and the mice in the AE group received a 20-week long-term moderate intensity running platform exercise intervention. Following the exercise intervention, the cecum contents of the mice in each group were collected and analyzed using the HPLC-MS technique, with those meeting both variable important in projection (VIP)> 1.5 and p < 0.05 being screened as differential metabolites. A total of 32 different metabolites were detected between the AM and NC groups, with 19 up-regulated in the AM group such as phosphatidic acid (PA) (18:4(6Z,9Z,12Z,15Z)/21:0) and 13 down-regulated in the AM group, such as 4,8-dimethylnonanoyl, compared to the NC group; 98 different metabolites were found between the AM and AE groups, 41 of which were upregulated such as Lyso phosphatidylcholine (LysoPC) and 57 of which were downregulated compared to the AM group such as Phosphatidylinositol (PI). The regulation of linoleic acid metabolism, glycerophospholipid metabolism, bile secretion, phenylalanine metabolism, and other pathways was predominantly regulated by nine metabolites, which were subsequently identified as indicators of exercise intervention to enhance metabolism in AD mice. The metabolomic technique can identify the metabolic problems of intestinal contents in AD mice and initially screen the biomarkers of exercise to improve the metabolic disorders in AD. These findings can help us better understand the impact of aerobic exercise on AD metabolism.

AMPK-Dependent YAP Inhibition Mediates the Protective Effect of Metformin against Obesity-Associated Endothelial Dysfunction and Inflammation.

Hyperglycemia is a crucial risk factor for cardiovascular diseases. Chronic inflammation is a central characteristic of obesity, leading to many of its complications. Recent studies have shown that high glucose activates Yes-associated protein 1 (YAP) by suppressing AMPK activity in breast cancer cells. Metformin is a commonly prescribed anti-diabetic drug best known for its AMPK-activating effect. However, the role of YAP in the vasoprotective effect of metformin in diabetic endothelial cell dysfunction is still unknown. The present study aimed to investigate whether YAP activation plays a role in obesity-associated endothelial dysfunction and inflammation and examine whether the vasoprotective effect of metformin is related to YAP inhibition. Reanalysis of the clinical sequencing data revealed YAP signaling, and the YAP target genes CTGF and CYR61 were upregulated in aortic endothelial cells and retinal fibrovascular membranes from diabetic patients. YAP overexpression impaired endothelium-dependent relaxations (EDRs) in isolated mouse aortas and increased the expression of YAP target genes and inflammatory markers in human umbilical vein endothelial cells (HUVECs). High glucose-activated YAP in HUVECs and aortas was accompanied by increased production of oxygen-reactive species. AMPK inhibition was found to induce YAP activation, resulting in increased JNK activity. Metformin activated AMPK and promoted YAP phosphorylation, ultimately improving EDRs and suppressing the JNK activity. Targeting the AMPK-YAP-JNK axis could become a therapeutic strategy for alleviating vascular dysfunction in obesity and diabetes.

Thin, soft, wearable system for continuous wireless monitoring of artery blood pressure.

Continuous monitoring of arterial blood pressure (BP) outside of a clinical setting is crucial for preventing and diagnosing hypertension related diseases. However, current continuous BP monitoring instruments suffer from either bulky systems or poor user-device interfacial performance, hampering their applications in continuous BP monitoring. Here, we report a thin, soft, miniaturized system (TSMS) that combines a conformal piezoelectric sensor array, an active pressure adaptation unit, a signal processing module, and an advanced machine learning method, to allow real wearable, continuous wireless monitoring of ambulatory artery BP. By optimizing the materials selection, control/sampling strategy, and system integration, the TSMS exhibits improved interfacial performance while maintaining Grade A level measurement accuracy. Initial trials on 87 volunteers and clinical tracking of two hypertension individuals prove the capability of the TSMS as a reliable BP measurement product, and its feasibility and practical usability in precise BP control and personalized diagnosis schemes development.

The 2023 wearable photoplethysmography roadmap.

Photoplethysmography is a key sensing technology which is used in wearable devices such as smartwatches and fitness trackers. Currently, photoplethysmography sensors are used to monitor physiological parameters including heart rate and heart rhythm, and to track activities like sleep and exercise. Yet, wearable photoplethysmography has potential to provide much more information on health and wellbeing, which could inform clinical decision making. This Roadmap outlines directions for research and development to realise the full potential of wearable photoplethysmography. Experts discuss key topics within the areas of sensor design, signal processing, clinical applications, and research directions. Their perspectives provide valuable guidance to researchers developing wearable photoplethysmography technology.

European Society of Hypertension recommendations for the validation of cuffless blood pressure measuring devices: European Society of Hypertension Working Group on Blood Pressure Monitoring and Cardiovascular Variability.

BACKGROUND: There is intense effort to develop cuffless blood pressure (BP) measuring devices, and several are already on the market claiming that they provide accurate measurements. These devices are heterogeneous in measurement principle, intended use, functions, and calibration, and have special accuracy issues requiring different validation than classic cuff BP monitors. To date, there are no generally accepted protocols for their validation to ensure adequate accuracy for clinical use. OBJECTIVE: This statement by the European Society of Hypertension (ESH) Working Group on BP Monitoring and Cardiovascular Variability recommends procedures for validating intermittent cuffless BP devices (providing measurements every >30 sec and usually 30-60 min, or upon user initiation), which are most common. VALIDATION PROCEDURES: Six validation tests are defined for evaluating different aspects of intermittent cuffless devices: static test (absolute BP accuracy); device position test (hydrostatic pressure effect robustness); treatment test (BP decrease accuracy); awake/asleep test (BP change accuracy); exercise test (BP increase accuracy); and recalibration test (cuff calibration stability over time). Not all these tests are required for a given device. The necessary tests depend on whether the device requires individual user calibration, measures automatically or manually, and takes measurements in more than one position. CONCLUSION: The validation of cuffless BP devices is complex and needs to be tailored according to their functions and calibration. These ESH recommendations present specific, clinically meaningful, and pragmatic validation procedures for different types of intermittent cuffless devices to ensure that only accurate devices will be used in the evaluation and management of hypertension.

MCM5 is an oncogene of colon adenocarcinoma and promotes progression through cell cycle control.

Many patients with colon adenocarcinoma (COAD) are diagnosed at an advanced stage, and the molecular mechanism of COAD progression is intricate and controversial. Therefore, there is an urgent need to identify more novel prognosis biomarkers for COAD and elucidate the molecular mechanism of this disease. The present study aimed to screen out key genes correlated with COAD prognosis. In this study, a key module was identified and four hub genes (MCM5 (encoding minichromosome maintenance complex component 5), NOLC1 (encoding nucleolar and coiled-body phosphoprotein 1), MYC (encoding MYC proto-oncogene, BHLH transcription factor), and CDK4 (encoding cyclin dependent kinase 4)) were selected that correlated with COAD prognosis, based on the GSE9348 dataset in Gene Expression Omnibus database. Gene ontology enrichment and Kyoto Encyclopedia of Genes and Genomes pathway analysis indicated that MCM5 correlated with the cell cycle. Furthermore, MCM5 expression was upregulated in tumor tissues of patients with COAD compared with that in adjacent tissues, based on various databases, including The Cancer Genome Atlas, the Clinical Proteomic Tumor Analysis Consortium database, and the Human Protein Atlas database. Small interfering RNA-mediated knockdown of MCM5 inhibited the cell cycle and migration of colorectal cancer cells in vitro. And western blotting results indicated that factors correlated with cell cycle (CDK2/6, Cyclin D3, P21) were downregulated after knockdown of MCM5 in vitro. Besides, downregulation of MCM5 was demonstrated to inhibit lung metastasis of COAD in nude mice model. In conclusion, MCM5 is an oncogene of COAD that promotes COAD progression via cell cycle control.

Cuffless Blood Pressure Measurement Using Smartwatches: A Large-Scale Validation Study.

This study aimed to evaluate the performance of cuffless blood pressure (BP) measurement techniques in a large and diverse cohort of participants. We enrolled 3077 participants (aged 18-75, 65.16% women, 35.91% hypertensive participants) and conducted followed-up for approximately 1 month. Electrocardiogram, pulse pressure wave, and multiwavelength photoplethysmogram signals were simultaneously recorded using smartwatches; dual-observer auscultation systolic BP (SBP) and diastolic BP (DBP) reference measurements were also obtained. Pulse transit time, traditional machine learning (TML), and deep learning (DL) models were evaluated with calibration and calibration-free strategy. TML models were developed using ridge regression, support vector machine, adaptive boosting, and random forest; while DL models using convolutional and recurrent neural networks. The best-performing calibration-based model yielded estimation errors of 1.33 ± 6.43 mmHg for DBP and 2.31 ± 9.57 mmHg for SBP in the overall population, with reduced SBP estimation errors in normotensive (1.97 ± 7.85 mmHg) and young (0.24 ± 6.61 mmHg) subpopulations. The best-performing calibration-free model had estimation errors of -0.29 ± 8.78 mmHg for DBP and -0.71 ± 13.04 mmHg for SBP. We conclude that smartwatches are effective for measuring DBP for all participants and SBP for normotensive and younger participants with calibration; performance degrades significantly for heterogeneous populations including older and hypertensive participants. The availability of cuffless BP measurement without calibration is limited in routine settings. Our study provides a large-scale benchmark for emerging investigations on cuffless BP measurement, highlighting the need to explore additional signals or principles to enhance the accuracy in large-scale heterogeneous populations.

Emerging sensing and modeling technologies for wearable and cuffless blood pressure monitoring.

Cardiovascular diseases (CVDs) are a leading cause of death worldwide. For early diagnosis, intervention and management of CVDs, it is highly desirable to frequently monitor blood pressure (BP), a vital sign closely related to CVDs, during people's daily life, including sleep time. Towards this end, wearable and cuffless BP extraction methods have been extensively researched in recent years as part of the mobile healthcare initiative. This review focuses on the enabling technologies for wearable and cuffless BP monitoring platforms, covering both the emerging flexible sensor designs and BP extraction algorithms. Based on the signal type, the sensing devices are classified into electrical, optical, and mechanical sensors, and the state-of-the-art material choices, fabrication methods, and performances of each type of sensor are briefly reviewed. In the model part of the review, contemporary algorithmic BP estimation methods for beat-to-beat BP measurements and continuous BP waveform extraction are introduced. Mainstream approaches, such as pulse transit time-based analytical models and machine learning methods, are compared in terms of their input modalities, features, implementation algorithms, and performances. The review sheds light on the interdisciplinary research opportunities to combine the latest innovations in the sensor and signal processing research fields to achieve a new generation of cuffless BP measurement devices with improved wearability, reliability, and accuracy.

Causal inference based cuffless blood pressure estimation: A pilot study.

Enabled by wearable sensing, e.g., photoplethysmography (PPG) and electrocardiography (ECG), and machine learning techniques, study on cuffless blood pressure (BP) measurement with data-driven methods has become popular in recent years. However, causality has been overlooked in most of current studies. In this study, we aim to examine the feasibility of causal inference for cuffless BP estimation. We first attempt to detect wearable features that are causally related, rather than correlated, to BP changes by identifying causal graphs of interested variables with fast causal inference (FCI) algorithm. With identified causal features, we then employ time-lagged link to integrate the mechanism of causal inference into the BP estimated model. The proposed method was validated on 62 subjects with their continuous ECG, PPG and BP signals being collected. We found new causal features that can better track BP changes than pulse transit time (PTT). Further, the developed causal-based estimation model achieved an estimation error of mean absolute difference (MAD) being 5.10 mmHg and 2.85 mmHg for SBP and DBP, respectively, which outperformed traditional model without consideration of causality. To the best of our knowledge, this work is the first to study the causal inference for cuffless BP estimation, which can shed light on the mechanism, method and application of cuffless BP measurement.

Self-Healing Electronics for Prognostic Monitoring of Methylated Circulating Tumor DNAs.

Methylated circulating DNAs (ctDNAs) have recently been reported as a promising biomarker for early cancer diagnostics, but limited tools are currently available for continuous and dynamic profiling of ctDNAs and their methylation levels, especially when such assays need to be conducted in point-of-care (POC) scenarios. Here, a self-healing bioelectronic patch (iMethy) is developed that combines transdermal interstitial fluid (ISF) extraction and field effect transistor-based (FET-based) biosensing for dynamic monitoring of methylated ctDNAs as a prognostic approach for cancer risk management. The projection micro-stereolithography-based 3D patterning of an Eutectic Gallium-Indium (EGaIn) circuit with an unprecedented 10 µm resolution enables the construction of self-healing EGaIn microfluidic circuits that remain conductive under 100% strain and self-healing under severe destruction. In combination with continuous transdermal ISF sampling of methylated ctDNAs, iMethy can detect ctDNAs as low as 10-16  m in cellular models and is capable of phenotypic analysis of tumor growth in rodent animals. As the first demonstration of a wearable device for real-time in vivo analysis of disease-indicative biomarkers, this proof-of-concept study well demonstrated the potential of the iMethy platform for cancer risk management based on dynamic transdermal surveillance of methylated ctDNAs via a painless and self-administrable procedure.