Multi-task deep learning for cardiac rhythm detection in wearable devices

Transforming Cardiovascular Care With Artificial Intelligence: From Discovery to Practice: JACC State-of-the-Art Review

Artificial intelligence (AI) has the potential to transform every facet of cardiovascular practice and research. The exponential rise in technology powered by AI is defining new frontiers in cardiovascular care, with innovations that span novel diagnostic modalities, new digital native biomarkers of disease, and high-performing tools evaluating care quality and prognosticating clinical outcomes. These digital innovations promise expanded access to cardiovascular screening and monitoring, especially among those without access to high-quality, specialized care historically. Moreover, AI is propelling biological and clinical discoveries that will make future cardiovascular care more personalized, precise, and effective. The review brings together these diverse AI innovations, highlighting developments in multimodal cardiovascular AI across clinical practice and biomedical discovery, and envisioning this new future backed by contemporary science and emerging discoveries. Finally, we define the critical path and the safeguards essential to realizing this AI-enabled future that helps achieve optimal cardiovascular health and outcomes for all.

Enhancing psychiatric rehabilitation outcomes through a multimodal multitask learning model based on BERT and TabNet: An approach for personalized treatment and improved decision-making

Evaluating the rehabilitation status of individuals with serious mental illnesses (SMI) necessitates a comprehensive analysis of multimodal data, including unstructured text records and structured diagnostic data. However, progress in the effective assessment of rehabilitation status remains limited. Our study develops a deep learning model integrating Bidirectional Encoder Representations from Transformers (BERT) and TabNet through a late fusion strategy to enhance rehabilitation prediction, including referral risk, dangerous behaviors, self-awareness, and medication adherence, in patients with SMI. BERT processes unstructured textual data, such as doctor's notes, whereas TabNet manages structured diagnostic information. The model's interpretability function serves to assist healthcare professionals in understanding the model's predictive decisions, improving patient care. Our model exhibited excellent predictive performance for all four tasks, with an accuracy exceeding 0.78 and an area under the curve of 0.70. In addition, a series of tests proved the model's robustness, fairness, and interpretability. This study combines multimodal and multitask learning strategies into a model and applies it to rehabilitation assessment tasks, offering a promising new tool that can be seamlessly integrated with the clinical workflow to support the provision of optimized patient care.

Learning From Alarms: A Robust Learning Approach for Accurate Photoplethysmography-Based Atrial Fibrillation Detection Using Eight Million Samples Labeled With Imprecise Arrhythmia Alarms

Atrial fibrillation (AF) is a common cardiac arrhythmia with serious health consequences if not detected and treated early. Detecting AF using wearable devices with photoplethysmography (PPG) sensors and deep neural networks has demonstrated some success using proprietary algorithms in commercial solutions. However, to improve continuous AF detection in ambulatory settings towards a population-wide screening use case, we face several challenges, one of which is the lack of large-scale labeled training data. To address this challenge, we propose to leverage AF alarms from bedside patient monitors to label concurrent PPG signals, resulting in the largest PPG-AF dataset so far (8.5 M 30-second records from 24,100 patients) and demonstrating a practical approach to build large labeled PPG datasets. Furthermore, we recognize that the AF labels thus obtained contain errors because of false AF alarms generated from imperfect built-in algorithms from bedside monitors. Dealing with label noise with unknown distribution characteristics in this case requires advanced algorithms. We, therefore, introduce and open-source a novel loss design, the cluster membership consistency (CMC) loss, to mitigate label errors. By comparing CMC with state-of-the-art methods selected from a noisy label competition, we demonstrate its superiority in handling label noise in PPG data, resilience to poor-quality signals, and computational efficiency.

Photoplethysmography based atrial fibrillation detection: a continually growing field

Objective. Atrial fibrillation (AF) is a prevalent cardiac arrhythmia associated with significant health ramifications, including an elevated susceptibility to ischemic stroke, heart disease, and heightened mortality. Photoplethysmography (PPG) has emerged as a promising technology for continuous AF monitoring for its cost-effectiveness and widespread integration into wearable devices. Our team previously conducted an exhaustive review on PPG-based AF detection before June 2019. However, since then, more advanced technologies have emerged in this field.Approach. This paper offers a comprehensive review of the latest advancements in PPG-based AF detection, utilizing digital health and artificial intelligence (AI) solutions, within the timeframe spanning from July 2019 to December 2022. Through extensive exploration of scientific databases, we have identified 57 pertinent studies.Significance. Our comprehensive review encompasses an in-depth assessment of the statistical methodologies, traditional machine learning techniques, and deep learning approaches employed in these studies. In addition, we address the challenges encountered in the domain of PPG-based AF detection. Furthermore, we maintain a dedicated website to curate the latest research in this area, with regular updates on a regular basis.

A lightweight xAI approach to cervical cancer classification

Cervical cancer is caused in the vast majority of cases by the human papilloma virus (HPV) through sexual contact and requires a specific molecular-based analysis to be detected. As an HPV vaccine is available, the incidence of cervical cancer is up to ten times higher in areas without adequate healthcare resources. In recent years, liquid cytology has been used to overcome these shortcomings and perform mass screening. In addition, classifiers based on convolutional neural networks can be developed to help pathologists diagnose the disease. However, these systems always require the final verification of a pathologist to make a final diagnosis. For this reason, explainable AI techniques are required to highlight the most significant data to the healthcare professional, as it can be used to determine the confidence in the results and the areas of the image used for classification (allowing the professional to point out the areas he/she thinks are most important and cross-check them against those detected by the system in order to create incremental learning systems). In this work, a 4-phase optimization process is used to obtain a custom deep-learning classifier for distinguishing between 4 severity classes of cervical cancer with liquid-cytology images. The final classifier obtains an accuracy over 97% for 4 classes and 100% for 2 classes with execution times under 1 s (including the final report generation). Compared to previous works, the proposed classifier obtains better accuracy results with a lower computational cost.

Adopting artificial intelligence in cardiovascular medicine: a scoping review

Recent years have witnessed significant transformations in cardiovascular medicine, driven by the rapid evolution of artificial intelligence (AI). This scoping review was conducted to capture the breadth of AI applications within cardiovascular science. Employing a structured approach, we sourced relevant articles from PubMed, with an emphasis on journals encompassing general cardiology and digital medicine. We applied filters to highlight cardiovascular articles published in journals focusing on general internal medicine, cardiology and digital medicine, thereby identifying the prevailing trends in the field. Following a comprehensive full-text screening, a total of 140 studies were identified. Over the preceding 5 years, cardiovascular medicine's interplay with AI has seen an over tenfold augmentation. This expansive growth encompasses multiple cardiovascular subspecialties, including but not limited to, general cardiology, ischemic heart disease, heart failure, and arrhythmia. Deep learning emerged as the predominant methodology. The majority of AI endeavors in this domain have been channeled toward enhancing diagnostic and prognostic capabilities, utilizing resources such as hospital datasets, electrocardiograms, and echocardiography. A significant uptrend was observed in AI's application for omics data analysis. However, a clear gap persists in AI's full-scale integration into the clinical decision-making framework. AI, particularly deep learning, has demonstrated robust applications across cardiovascular subspecialties, indicating its transformative potential in this field. As we continue on this trajectory, ensuring the alignment of technological progress with medical ethics becomes crucial. The abundant digital health data today further accentuates the need for meticulous systematic reviews, tailoring them to each cardiovascular subspecialty.

A high altitude respiration and SpO2 dataset for assessing the human response to hypoxia

This report presents the Harespod dataset, an open dataset for high altitude hypoxia research, which includes respiration and SpO2 data. The dataset was collected from 15 college students aged 23-31 in a hypobaric oxygen chamber, during simulated altitude changes and induced hypoxia. Real-time physiological data, such as oxygen saturation waveforms, oxygen saturation, respiratory waveforms, heart rate, and pulse rate, were obtained at 100 Hz. Approximately 12 hours of valid data were collected from all participants. Researchers can easily identify the altitude corresponding to physiological signals based on their inherent patterns. Time markers were also recorded during altitude changes to facilitate realistic annotation of physiological signals and analysis of time-difference-of-arrival between various physiological signals for the same altitude change event. In high altitude scenarios, this dataset can be used to enhance the detection of human hypoxia states, predict respiratory waveforms, and develop related hardware devices. It will serve as a valuable and standardized resource for researchers in the field of high altitude hypoxia research, enabling comprehensive analysis and comparison.

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

OBJECTIVE

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.

METHODS

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.

RESULTS

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.

CONCLUSION

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.

SIGNIFICANCE

PPG signals collected from wearables are vulnerable to MNA, which limits their use as a reliable measurement, particularly in uncontrolled real-life environments.

Survey of Transfer Learning Approaches in the Machine Learning of Digital Health Sensing Data

Machine learning and digital health sensing data have led to numerous research achievements aimed at improving digital health technology. However, using machine learning in digital health poses challenges related to data availability, such as incomplete, unstructured, and fragmented data, as well as issues related to data privacy, security, and data format standardization. Furthermore, there is a risk of bias and discrimination in machine learning models. Thus, developing an accurate prediction model from scratch can be an expensive and complicated task that often requires extensive experiments and complex computations. Transfer learning methods have emerged as a feasible solution to address these issues by transferring knowledge from a previously trained task to develop high-performance prediction models for a new task. This survey paper provides a comprehensive study of the effectiveness of transfer learning for digital health applications to enhance the accuracy and efficiency of diagnoses and prognoses, as well as to improve healthcare services. The first part of this survey paper presents and discusses the most common digital health sensing technologies as valuable data resources for machine learning applications, including transfer learning. The second part discusses the meaning of transfer learning, clarifying the categories and types of knowledge transfer. It also explains transfer learning methods and strategies, and their role in addressing the challenges in developing accurate machine learning models, specifically on digital health sensing data. These methods include feature extraction, fine-tuning, domain adaptation, multitask learning, federated learning, and few-/single-/zero-shot learning. This survey paper highlights the key features of each transfer learning method and strategy, and discusses the limitations and challenges of using transfer learning for digital health applications. Overall, this paper is a comprehensive survey of transfer learning methods on digital health sensing data which aims to inspire researchers to gain knowledge of transfer learning approaches and their applications in digital health, enhance the current transfer learning approaches in digital health, develop new transfer learning strategies to overcome the current limitations, and apply them to a variety of digital health technologies.

Data-efficient machine learning methods in the ME-TIME study: Rationale and design of a longitudinal study to detect atrial fibrillation and heart failure from wearables

Background

Smartwatches enable continuous and noninvasive time series monitoring of cardiovascular biomarkers like heart rate (from photoplethysmograms), step counter, skin temperature, et cetera; as such, they have promise in assisting in early detection and prevention of cardiovascular disease. Although these biomarkers may not be directly useful to physicians, a machine learning (ML) model could find clinically relevant patterns. Unfortunately, ML models typically need supervised (ie, annotated) data, and labeling of large amounts of continuous data is very labor intensive. Therefore, ML methods that are data efficient, ie, needing a low number of labels, are required to detect potential clinical value in patterns found in wearable data.

Objective

The primary study objective of the ME-TIME (Machine Learning Enabled Time Series Analysis in Medicine) study is to design an ML model that can detect atrial fibrillation (AF) and heart failure (HF) from wearable data in a data-efficient manner. To achieve this, self-supervised and weakly supervised learning techniques are used.

Methods

Two hundred subjects (100 reference, 50 AF, and 50 HF) are being invited to participate in wearing a Fitbit fitness tracker for 3 months. Interested volunteers are sent a questionnaire to determine their health, in particular cardiovascular health. Volunteers without any (history of) serious illness are assigned to the reference group. Participants with AF and HF are recruited in the Haga teaching hospital in The Hague, The Netherlands.

Results

Enrollment commenced on May 1, 2022, and as of the time of this report, 62 subjects have been included in the study. Preliminary analysis of the data reveals significant inter-subject variability. Notably, we identified heart rate recovery curves and time-delayed correlations between heart rate and step count as potential strong indicators for heart disease.

Conclusion

Using self-supervised and multiple-instance learning techniques, we hypothesize that patterns specific to AF and HF can be found in continuous data obtained from smartwatches.

Multifractal foundations of biomarker discovery for heart disease and stroke

Any reliable biomarker has to be specific, generalizable, and reproducible across individuals and contexts. The exact values of such a biomarker must represent similar health states in different individuals and at different times within the same individual to result in the minimum possible false-positive and false-negative rates. The application of standard cut-off points and risk scores across populations hinges upon the assumption of such generalizability. Such generalizability, in turn, hinges upon this condition that the phenomenon investigated by current statistical methods is ergodic, i.e., its statistical measures converge over individuals and time within the finite limit of observations. However, emerging evidence indicates that biological processes abound with nonergodicity, threatening this generalizability. Here, we present a solution for how to make generalizable inferences by deriving ergodic descriptions of nonergodic phenomena. For this aim, we proposed capturing the origin of ergodicity-breaking in many biological processes: cascade dynamics. To assess our hypotheses, we embraced the challenge of identifying reliable biomarkers for heart disease and stroke, which, despite being the leading cause of death worldwide and decades of research, lacks reliable biomarkers and risk stratification tools. We showed that raw R-R interval data and its common descriptors based on mean and variance are nonergodic and non-specific. On the other hand, the cascade-dynamical descriptors, the Hurst exponent encoding linear temporal correlations, and multifractal nonlinearity encoding nonlinear interactions across scales described the nonergodic heart rate variability more ergodically and were specific. This study inaugurates applying the critical concept of ergodicity in discovering and applying digital biomarkers of health and disease.

Perspectives in Wearable Systems in the Human-Robot Interaction (HRI) Field

Due to the advantages of ease of use, less motion disturbance, and low cost, wearable systems have been widely used in the human-machine interaction (HRI) field. However, HRI in complex clinical rehabilitation scenarios has further requirements for wearable sensor systems, which has aroused the interest of many researchers. However, the traditional wearable system has problems such as low integration, limited types of measurement data, and low accuracy, causing a gap with the actual needs of HRI. This paper will introduce the latest progress in the current wearable systems of HRI from four aspects. First of all, it introduces the breakthroughs of current research in system integration, which includes processing chips and flexible sensing modules to reduce the system's volume and increase battery life. After that, this paper reviews the latest progress of wearable systems in electrochemical measurement, which can extract single or multiple biomarkers from biological fluids such as sweat. In addition, the clinical application of non-invasive wearable systems is introduced, which solves the pain and discomfort problems caused by traditional clinical invasive measurement equipment. Finally, progress in the combination of current wearable systems and the latest machine-learning methods is shown, where higher accuracy and indirect acquisition of data that cannot be directly measured is achieved. From the evidence presented, we believe that the development trend of wearable systems in HRI is heading towards high integration, multi-electrochemical measurement data, and clinical and intelligent development.

Few-shot transfer learning for personalized atrial fibrillation detection using patient-based siamese network with single-lead ECG records

The proliferation of wearable devices has allowed the collection of electrocardiogram (ECG) recordings daily to monitor heart rhythm and rate. For example, 24-hour Holter monitors, cardiac patches, and smartwatches are widely used for ECG gathering and application. An automatic atrial fibrillation (AF) detector is required for timely ECG interpretation. Deep learning models can accurately identify AFs if large amounts of annotated data are available for model training. However, it is impractical to request sufficient labels for ECG recordings for an individual patient to train a personalized model. We propose a Siamese-network-based approach for transfer learning to address this issue. A pre-trained Siamese convolutional neural network is created by comparing two labeled ECG segments from the same patient. We sampled 30-second ECG segments with a 50% overlapping window from the ECG recordings of patients in the MIT-BIH Atrial Fibrillation Database. Subsequently, we independently detected the occurrence of AF in each patient in the Long-Term AF Database. By fine-tuning the model with the 1, 3, 5, 7, 9, or 11 ECG segments ranging from 30 to 180 s, our method achieved macro-F1 scores of 96.84%, 96.91%, 96.97%, 97.02%, 97.05%, and 97.07%, respectively.

Markov model for detection of ECG instability prior to cardiac arrest in single-ventricle patients

OBJECTIVES

Assess the degree of instability in the electrocardiogram (ECG) waveform in patients with single-ventricle physiology before a cardiac arrest and compare them with similar patients who did not experience a cardiac arrest.

METHODS

Retrospective control study in patients with single-ventricle physiology who underwent Norwood, Blalock-Taussig shunt, pulmonary artery band, and aortic arch repair from 2013 to 2018. Electronic medical records were obtained for all included patients. For each subject, 6 h of ECG data were analyzed. In the arrest group, the end of the sixth hour coincides with the cardiac arrest. In the control group, the 6-h windows were randomly selected. We used a Markov chain framework and the likelihood ratio test to measure the degree of ECG instability and to classify the arrest and control groups.

RESULTS

The study dataset consists of 38 cardiac arrest events and 67 control events. Our Markov model was able to classify the arrest and control groups based on the ECG instability with an ROC AUC of 82% at the hour preceding the cardiac arrests.

CONCLUSION

We designed a method using the Markov chain framework to measure the level of instability in the beat-to-beat ECG morphology. Furthermore, we were able to show that the Markov model performed well to distinguish patients in the arrest group compared to the control group.

A Robust Ensemble of Convolutional Neural Networks for the Detection of Monkeypox Disease from Skin Images

Monkeypox is a smallpox-like disease that was declared a global health emergency in July 2022. Because of this resemblance, it is not easy to distinguish a monkeypox rash from other similar diseases; however, due to the novelty of this disease, there are no widely used databases for this purpose with which to develop image-based classification algorithms. Therefore, three significant contributions are proposed in this work: first, the development of a publicly available dataset of monkeypox images; second, the development of a classification system based on convolutional neural networks in order to automatically distinguish monkeypox marks from those produced by other diseases; and, finally, the use of explainable AI tools for ensemble networks. For point 1, free images of monkeypox cases and other diseases have been searched in government databases and processed until we are left with only a section of the skin of the patients in each case. For point 2, various pre-trained models were used as classifiers and, in the second instance, combinations of these were used to form ensembles. And, for point 3, this is the first documented time that an explainable AI technique (like GradCAM) is applied to the results of ensemble networks. Among all the tests, the accuracy reaches 93% in the case of single pre-trained networks, and up to 98% using an ensemble of three networks (ResNet50, EfficientNetB0, and MobileNetV2). Comparing these results with previous work, a substantial improvement in classification accuracy is observed.

Domain and Patient Adversarial Multi-Task Learning for Arrhythmia Classification

Manual screening of electrocardiograms (ECGs) for heart arrhythmias by clinicians is time-consuming and labor-intensive. A machine learning model for the automated diagnosis of heart arrhythmia from ECG signals can facilitate improved diagnosis, greater accessibility and earlier intervention for patients. The potential of such models is limited however by the small size of clinical datasets available for training. Methods that can be trained with multiple datasets to classify heart arrhythmia are needed to overcome this problem.In this paper, we propose using adversarial multi-task learning (AMTL) to extract domain and patient invariant features from two electrocardiogram databases. We further investigated the influence of beat segmentation location and beat normalization on domain invariance. Our proposed methods were tested on the MIT-BIH Arrhythmia and the St Petersburg INCART 12-lead Arrhythmia Databases. The domain adversarial models achieved a higher accuracy and average F1 score than their counterparts without domain adversarial learning. In particular, the patient and domain adversarial model improved the F1 scores on the two tested databases from 70% and 74% to 77% each.Clinical Relevance-This establishes that adversarial multitask learning with multiple datasets and multiple adversarial tasks can improve the F1 score of arrhythmia classification.

False Atrial Fibrillation Alerts from Smartwatches are Associated with Decreased Perceived Physical Well-being and Confidence in Chronic Symptoms Management

Wrist-based wearables have been FDA approved for AF detection. However, the health behavior impact of false AF alerts from wearables on older patients at high risk for AF are not known. In this work, we analyzed data from the Pulsewatch (NCT03761394) study, which randomized patients (≥50 years) with history of stroke or transient ischemic attack to wear a patch monitor and a smartwatch linked to a smartphone running the Pulsewatch application vs to only the cardiac patch monitor over 14 days. At baseline and 14 days, participants completed validated instruments to assess for anxiety, patient activation, perceived mental and physical health, chronic symptom management self-efficacy, and medicine adherence. We employed linear regression to examine associations between false AF alerts with change in patient-reported outcomes. Receipt of false AF alerts was related to a dose-dependent decline in self-perceived physical health and levels of disease self-management. We developed a novel convolutional denoising autoencoder (CDA) to remove motion and noise artifacts in photoplethysmography (PPG) segments to optimize AF detection, which substantially reduced the number of false alerts. A promising approach to avoid negative impact of false alerts is to employ artificial intelligence driven algorithms to improve accuracy.

Co-Design, Development, and Evaluation of a Health Monitoring Tool Using Smartwatch Data: A Proof-of-Concept Study

Computational analysis and integration of smartwatch data with Electronic Medical Records (EMR) present potential uses in preventing, diagnosing, and managing chronic diseases. One of the key requirements for the successful clinical application of smartwatch data is understanding healthcare professional (HCP) perspectives on whether these devices can play a role in preventive care. Gaining insights from the vast amount of smartwatch data is a challenge for HCPs, thus tools are needed to support HCPs when integrating personalized health monitoring devices with EMR. This study aimed to develop and evaluate an application prototype, co-designed with HCPs and employing design science research methodology and diffusion of innovation frameworks to identify the potential for clinical integration. A machine learning algorithm was developed to detect possible health anomalies in smartwatch data, and these were presented visually to HCPs in a web-based platform. HCPs completed a usability questionnaire to evaluate the prototype, and over 60% of HCPs scored positively on usability. This preliminary study tested the proposed research to solve the practical challenges of HCP in interpreting smartwatch data before fully integrating smartwatches into the EMR. The findings provide design directions for future applications that use smartwatch data to improve clinical decision-making and reduce HCP workloads.

Shifting machine learning for healthcare from development to deployment and from models to data

In the past decade, the application of machine learning (ML) to healthcare has helped drive the automation of physician tasks as well as enhancements in clinical capabilities and access to care. This progress has emphasized that, from model development to model deployment, data play central roles. In this Review, we provide a data-centric view of the innovations and challenges that are defining ML for healthcare. We discuss deep generative models and federated learning as strategies to augment datasets for improved model performance, as well as the use of the more recent transformer models for handling larger datasets and enhancing the modelling of clinical text. We also discuss data-focused problems in the deployment of ML, emphasizing the need to efficiently deliver data to ML models for timely clinical predictions and to account for natural data shifts that can deteriorate model performance.

Applying Artificial Intelligence to Wearable Sensor Data to Diagnose and Predict Cardiovascular Disease: A Review

Cardiovascular disease (CVD) is the world's leading cause of mortality. There is significant interest in using Artificial Intelligence (AI) to analyse data from novel sensors such as wearables to provide an earlier and more accurate prediction and diagnosis of heart disease. Digital health technologies that fuse AI and sensing devices may help disease prevention and reduce the substantial morbidity and mortality caused by CVD worldwide. In this review, we identify and describe recent developments in the application of digital health for CVD, focusing on AI approaches for CVD detection, diagnosis, and prediction through AI models driven by data collected from wearables. We summarise the literature on the use of wearables and AI in cardiovascular disease diagnosis, followed by a detailed description of the dominant AI approaches applied for modelling and prediction using data acquired from sensors such as wearables. We discuss the AI algorithms and models and clinical applications and find that AI and machine-learning-based approaches are superior to traditional or conventional statistical methods for predicting cardiovascular events. However, further studies evaluating the applicability of such algorithms in the real world are needed. In addition, improvements in wearable device data accuracy and better management of their application are required. Lastly, we discuss the challenges that the introduction of such technologies into routine healthcare may face.

Mucosa-interfacing electronics

The surface mucosa that lines many of our organs houses myriad biometric signals and, therefore, has great potential as a sensor-tissue interface for high-fidelity and long-term biosensing. However, progress is still nascent for mucosa-interfacing electronics owing to challenges with establishing robust sensor-tissue interfaces; device localization, retention and removal; and power and data transfer. This is in sharp contrast to the rapidly advancing field of skin-interfacing electronics, which are replacing traditional hospital visits with minimally invasive, real-time, continuous and untethered biosensing. This Review aims to bridge the gap between skin-interfacing electronics and mucosa-interfacing electronics systems through a comparison of the properties and functions of the skin and internal mucosal surfaces. The major physiological signals accessible through mucosa-lined organs are surveyed and design considerations for the next generation of mucosa-interfacing electronics are outlined based on state-of-the-art developments in bio-integrated electronics. With this Review, we aim to inspire hardware solutions that can serve as a foundation for developing personalized biosensing from the mucosa, a relatively uncharted field with great scientific and clinical potential.

Optimized Signal Quality Assessment for Photoplethysmogram Signals Using Feature Selection

OBJECTIVE

With the increasing use of wearable healthcare devices for remote patient monitoring, reliable signal quality assessment (SQA) is required to ensure the high accuracy of interpretation and diagnosis on the recorded data from patients. Photoplethysmographic (PPG) signals non-invasively measured by wearable devices are extensively used to provide information about the cardiovascular system and its associated diseases. In this study, we propose an approach to optimize the quality assessment of the PPG signals.

METHODS

We used an ensemble-based feature selection scheme to enhance the prediction performance of the classification model to assess the quality of the PPG signals. Our approach for feature and subset size selection yielded the best-suited feature subset, which was optimized to differentiate between the clean and artifact corrupted PPG segments.

CONCLUSION

A high discriminatory power was achieved between two classes on the test data by the proposed feature selection approach, which led to strong performance on all dependent and independent test datasets. We achieved accuracy, sensitivity, and specificity rates of higher than 0.93, 0.89, and 0.97, respectively, for dependent test datasets, independent of heartbeat type, i.e., atrial fibrillation (AF) or non-AF data including normal sinus rhythm (NSR), premature atrial contraction (PAC), and premature ventricular contraction (PVC). For independent test datasets, accuracy, sensitivity, and specificity rates were greater than 0.93, 0.89, and 0.97, respectively, on PPG data recorded from AF and non-AF subjects. These results were found to be more accurate than those of all of the contemporary methods cited in this work.

SIGNIFICANCE

As the results illustrate, the advantage of our proposed scheme is its robustness against dynamic variations in the PPG signal during long-term 14-day recordings accompanied with different types of physical activities and a diverse range of fluctuations and waveforms caused by different individual hemodynamic characteristics, and various types of recording devices. This robustness instills confidence in the application of the algorithm to various kinds of wearable devices as a reliable PPG signal quality assessment approach.

Smart Consumer Wearables as Digital Diagnostic Tools: A Review

The increasing usage of smart wearable devices has made an impact not only on the lifestyle of the users, but also on biological research and personalized healthcare services. These devices, which carry different types of sensors, have emerged as personalized digital diagnostic tools. Data from such devices have enabled the prediction and detection of various physiological as well as psychological conditions and diseases. In this review, we have focused on the diagnostic applications of wrist-worn wearables to detect multiple diseases such as cardiovascular diseases, neurological disorders, fatty liver diseases, and metabolic disorders, including diabetes, sleep quality, and psychological illnesses. The fruitful usage of wearables requires fast and insightful data analysis, which is feasible through machine learning. In this review, we have also discussed various machine-learning applications and outcomes for wearable data analyses. Finally, we have discussed the current challenges with wearable usage and data, and the future perspectives of wearable devices as diagnostic tools for research and personalized healthcare domains.

Applications of deep learning for phishing detection: a systematic literature review

Phishing attacks aim to steal confidential information using sophisticated methods, techniques, and tools such as phishing through content injection, social engineering, online social networks, and mobile applications. To avoid and mitigate the risks of these attacks, several phishing detection approaches were developed, among which deep learning algorithms provided promising results. However, the results and the corresponding lessons learned are fragmented over many different studies and there is a lack of a systematic overview of the use of deep learning algorithms in phishing detection. Hence, we performed a systematic literature review (SLR) to identify, assess, and synthesize the results on deep learning approaches for phishing detection as reported by the selected scientific publications. We address nine research questions and provide an overview of how deep learning algorithms have been used for phishing detection from several aspects. In total, 43 journal articles were selected from electronic databases to derive the answers for the defined research questions. Our SLR study shows that except for one study, all the provided models applied supervised deep learning algorithms. The widely used data sources were URL-related data, third party information on the website, website content-related data, and email. The most used deep learning algorithms were deep neural networks (DNN), convolutional neural networks, and recurrent neural networks/long short-term memory networks. DNN and hybrid deep learning algorithms provided the best performance among other deep learning-based algorithms. 72% of the studies did not apply any feature selection algorithm to build the prediction model. PhishTank was the most used dataset among other datasets. While Keras and Tensorflow were the most preferred deep learning frameworks, 46% of the articles did not mention any framework. This study also highlights several challenges for phishing detection to pave the way for further research.

Deep Learning in mHealth for Cardiovascular Disease, Diabetes, and Cancer: Systematic Review

Background

Major chronic diseases such as cardiovascular disease (CVD), diabetes, and cancer impose a significant burden on people and health care systems around the globe. Recently, deep learning (DL) has shown great potential for the development of intelligent mobile health (mHealth) interventions for chronic diseases that could revolutionize the delivery of health care anytime, anywhere.

Objective

The aim of this study is to present a systematic review of studies that have used DL based on mHealth data for the diagnosis, prognosis, management, and treatment of major chronic diseases and advance our understanding of the progress made in this rapidly developing field.

Methods

A search was conducted on the bibliographic databases Scopus and PubMed to identify papers with a focus on the deployment of DL algorithms that used data captured from mobile devices (eg, smartphones, smartwatches, and other wearable devices) targeting CVD, diabetes, or cancer. The identified studies were synthesized according to the target disease, the number of enrolled participants and their age, and the study period as well as the DL algorithm used, the main DL outcome, the data set used, the features selected, and the achieved performance.

Results

In total, 20 studies were included in the review. A total of 35% (7/20) of DL studies targeted CVD, 45% (9/20) of studies targeted diabetes, and 20% (4/20) of studies targeted cancer. The most common DL outcome was the diagnosis of the patient’s condition for the CVD studies, prediction of blood glucose levels for the studies in diabetes, and early detection of cancer. Most of the DL algorithms used were convolutional neural networks in studies on CVD and cancer and recurrent neural networks in studies on diabetes. The performance of DL was found overall to be satisfactory, reaching >84% accuracy in most studies. In comparison with classic machine learning approaches, DL was found to achieve better performance in almost all studies that reported such comparison outcomes. Most of the studies did not provide details on the explainability of DL outcomes.

Conclusions

The use of DL can facilitate the diagnosis, management, and treatment of major chronic diseases by harnessing mHealth data. Prospective studies are now required to demonstrate the value of applied DL in real-life mHealth tools and interventions.

Diagnostic Features and Potential Applications of PPG Signal in Healthcare: A Systematic Review

Recent research indicates that Photoplethysmography (PPG) signals carry more information than oxygen saturation level (SpO2) and can be utilized for affordable, fast, and noninvasive healthcare applications. All these encourage the researchers to estimate its feasibility as an alternative to many expansive, time-wasting, and invasive methods. This systematic review discusses the current literature on diagnostic features of PPG signal and their applications that might present a potential venue to be adapted into many health and fitness aspects of human life. The research methodology is based on the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines 2020. To this aim, papers from 1981 to date are reviewed and categorized in terms of the healthcare application domain. Along with consolidated research areas, recent topics that are growing in popularity are also discovered. We also highlight the potential impact of using PPG signals on an individual’s quality of life and public health. The state-of-the-art studies suggest that in the years to come PPG wearables will become pervasive in many fields of medical practices, and the main domains include cardiology, respiratory, neurology, and fitness. Main operation challenges, including performance and robustness obstacles, are identified.

Transfer learning for non-image data in clinical research: A scoping review

BACKGROUND

Transfer learning is a form of machine learning where a pre-trained model trained on a specific task is reused as a starting point and tailored to another task in a different dataset. While transfer learning has garnered considerable attention in medical image analysis, its use for clinical non-image data is not well studied. Therefore, the objective of this scoping review was to explore the use of transfer learning for non-image data in the clinical literature.

METHODS AND FINDINGS

We systematically searched medical databases (PubMed, EMBASE, CINAHL) for peer-reviewed clinical studies that used transfer learning on human non-image data. We included 83 studies in the review. More than half of the studies (63%) were published within 12 months of the search. Transfer learning was most often applied to time series data (61%), followed by tabular data (18%), audio (12%) and text (8%). Thirty-three (40%) studies applied an image-based model to non-image data after transforming data into images (e.g. spectrograms). Twenty-nine (35%) studies did not have any authors with a health-related affiliation. Many studies used publicly available datasets (66%) and models (49%), but fewer shared their code (27%).

CONCLUSIONS

In this scoping review, we have described current trends in the use of transfer learning for non-image data in the clinical literature. We found that the use of transfer learning has grown rapidly within the last few years. We have identified studies and demonstrated the potential of transfer learning in clinical research in a wide range of medical specialties. More interdisciplinary collaborations and the wider adaption of reproducible research principles are needed to increase the impact of transfer learning in clinical research.

Artificial intelligence for the detection, prediction, and management of atrial fibrillation

The present article reviews the state of the art of machine learning algorithms for the detection, prediction, and management of atrial fibrillation (AF), as well as of the development and evaluation of artificial intelligence (AI) in cardiology and beyond. Today, AI detects AF with a high accuracy using 12-lead or single-lead electrocardiograms or photoplethysmography. The prediction of paroxysmal or future AF currently operates at a level of precision that is too low for clinical use. Further studies are needed to determine whether patient selection for interventions may be possible with machine learning.

Machine Learning for Cardiovascular Outcomes From Wearable Data: Systematic Review From a Technology Readiness Level Point of View

BACKGROUND

Wearable technology has the potential to improve cardiovascular health monitoring by using machine learning. Such technology enables remote health monitoring and allows for the diagnosis and prevention of cardiovascular diseases. In addition to the detection of cardiovascular disease, it can exclude this diagnosis in symptomatic patients, thereby preventing unnecessary hospital visits. In addition, early warning systems can aid cardiologists in timely treatment and prevention.

OBJECTIVE

This study aims to systematically assess the literature on detecting and predicting outcomes of patients with cardiovascular diseases by using machine learning with data obtained from wearables to gain insights into the current state, challenges, and limitations of this technology.

METHODS

We searched PubMed, Scopus, and IEEE Xplore on September 26, 2020, with no restrictions on the publication date and by using keywords such as "wearables," "machine learning," and "cardiovascular disease." Methodologies were categorized and analyzed according to machine learning-based technology readiness levels (TRLs), which score studies on their potential to be deployed in an operational setting from 1 to 9 (most ready).

RESULTS

After the removal of duplicates, application of exclusion criteria, and full-text screening, 55 eligible studies were included in the analysis, covering a variety of cardiovascular diseases. We assessed the quality of the included studies and found that none of the studies were integrated into a health care system (TRL<6), prospective phase 2 and phase 3 trials were absent (TRL<7 and 8), and group cross-validation was rarely used. These issues limited these studies' ability to demonstrate the effectiveness of their methodologies. Furthermore, there seemed to be no agreement on the sample size needed to train these studies' models, the size of the observation window used to make predictions, how long participants should be observed, and the type of machine learning model that is suitable for predicting cardiovascular outcomes.

CONCLUSIONS

Although current studies show the potential of wearables to monitor cardiovascular events, their deployment as a diagnostic or prognostic cardiovascular clinical tool is hampered by the lack of a realistic data set and proper systematic and prospective evaluation.

Artificial Intelligence for Detection of Cardiovascular-Related Diseases from Wearable Devices: A Systematic Review and Meta-Analysis

PURPOSE

Several artificial intelligence (AI) models for the detection and prediction of cardiovascular-related diseases, including arrhythmias, diabetes, and sleep apnea, have been reported. This systematic review and meta-analysis aimed to identify AI models developed for or applicable to wearable and mobile devices for diverse cardiovascular-related diseases.

MATERIALS AND METHODS

The searched databases included Medline, Embase, and Cochrane Library. For AI models for atrial fibrillation (AF) detection, a meta-analysis of diagnostic accuracy was performed to summarize sensitivity and specificity.

RESULTS

A total of 102 studies were included in the qualitative review. There were AI models for the detection of arrythmia (n=62), followed by sleep apnea (n=11), peripheral vascular diseases (n=6), diabetes mellitus (n=5), hyper/hypotension (n=5), valvular heart disease (n=4), heart failure (n=3), myocardial infarction and cardiac arrest (n=2), and others (n=4). For quantitative analysis of 26 studies reporting AI models for AF detection, meta-analyzed sensitivity was 94.80% and specificity was 96.96%. Deep neural networks showed superior performance [meta-analyzed area under receiver operating characteristics curve (AUROC) of 0.981] compared to conventional machine learning algorithms (meta-analyzed AUROC of 0.961). However, AI models tested with proprietary dataset (meta-analyzed AUROC of 0.972) or data acquired from wearable devices (meta-analyzed AUROC of 0.977) showed inferior performance than those with public dataset (meta-analyzed AUROC of 0.986) or data from in-hospital devices (meta-analyzed AUROC of 0.983).

CONCLUSION

This review found that AI models for diverse cardiovascular-related diseases are being developed, and that they are gradually developing into a form that is suitable for wearable and mobile devices.

AI and the cardiologist: when mind, heart and machine unite

Artificial intelligence (AI) and deep learning has made much headway in the consumer and advertising sector, not only affecting how and what people purchase these days, but also affecting behaviour and cultural attitudes. It is poised to influence nearly every aspect of our being, and the field of cardiology is not an exception. This paper aims to brief the clinician on the advances in AI and machine learning in the field of cardiology, its applications, while also recognising the potential for future development in these two mammoth fields. With the advent of big data, new opportunities are emerging to build AI tools, with better accuracy, that will directly aid not only the clinician but also allow nations to provide better healthcare to its citizens.

A Machine Learning Driven Pipeline for Automated Photoplethysmogram Signal Artifact Detection

Recent advances in Critical Congenital Heart Disease (CCHD) research using Photoplethysmography (PPG) signals have yielded an Internet of Things (IoT) based enhanced screening method that performs CCHD detection comparable to SpO2 screening. The use of PPG signals, however, poses a challenge due to its measurements being prone to artifacts. To comprehensively study the most effective way to remove the artifact segments from PPG waveforms, we performed feature engineering and investigated both Machine Learning (ML) and rule based algorithms to identify the optimal method of artifact detection. Our proposed artifact detection system utilizes a 3-stage ML model that incorporates both Gradient Boosting (GB) and Random Forest (RF). The proposed system achieved 84.01% of Intersection over Union (IoU), which is competitive to state-of-the-art artifact detection methods tested on higher resolution PPG.

AI-Enabled Algorithm for Automatic Classification of Sleep Disorders Based on Single-Lead Electrocardiogram

Healthy sleep is an essential physiological process for every individual to live a healthy life. Many sleep disorders both destroy the quality and decrease the duration of sleep. Thus, a convenient and accurate detection or classification method is important for screening and identifying sleep disorders. In this study, we proposed an AI-enabled algorithm for the automatic classification of sleep disorders based on a single-lead electrocardiogram (ECG). An AI-enabled algorithm—named a sleep disorder network (SDN)—was designed for automatic classification of four major sleep disorders, namely insomnia (INS), periodic leg movement (PLM), REM sleep behavior disorder (RBD), and nocturnal frontal-lobe epilepsy (NFE). The SDN was constructed using deep convolutional neural networks that can extract and analyze the complex and cyclic rhythm of sleep disorders that affect ECG patterns. The SDN consists of five layers, a 1D convolutional layer, and is optimized via dropout and batch normalization. The single-lead ECG signal was extracted from the 35 subjects with the control (CNT) and the four sleep disorder groups (seven subjects of each group) in the CAP Sleep Database. The ECG signal was pre-processed, segmented at 30 s intervals, and divided into the training, validation, and test sets consisting of 74,135, 18,534, and 23,168 segments, respectively. The constructed SDN was trained and evaluated using the CAP Sleep Database, which contains not only data on sleep disorders, but also data of the control group. The proposed SDN algorithm for the automatic classification of sleep disorders based on a single-lead ECG showed very high performances. We achieved F1 scores of 99.0%, 97.0%, 97.0%, 95.0%, and 98.0% for the CNT, INS, PLM, RBD, and NFE groups, respectively. We proposed an AI-enabled method for the automatic classification of sleep disorders based on a single-lead ECG signal. In addition, it represents the possibility of the sleep disorder classification using ECG only. The SDN can be a useful tool or an alternative screening method based on single-lead ECGs for sleep monitoring and screening.

Role of Deep Learning in Predicting Aging-Related Diseases: A Scoping Review

Aging refers to progressive physiological changes in a cell, an organ, or the whole body of an individual, over time. Aging-related diseases are highly prevalent and could impact an individual’s physical health. Recently, artificial intelligence (AI) methods have been used to predict aging-related diseases and issues, aiding clinical providers in decision-making based on patient’s medical records. Deep learning (DL), as one of the most recent generations of AI technologies, has embraced rapid progress in the early prediction and classification of aging-related issues. In this paper, a scoping review of publications using DL approaches to predict common aging-related diseases (such as age-related macular degeneration, cardiovascular and respiratory diseases, arthritis, Alzheimer’s and lifestyle patterns related to disease progression), was performed. Google Scholar, IEEE and PubMed are used to search DL papers on common aging-related issues published between January 2017 and August 2021. These papers were reviewed, evaluated, and the findings were summarized. Overall, 34 studies met the inclusion criteria. These studies indicate that DL could help clinicians in diagnosing disease at its early stages by mapping diagnostic predictions into observable clinical presentations; and achieving high predictive performance (e.g., more than 90% accurate predictions of diseases in aging).

The Role of Artificial Intelligence in Arrhythmia Monitoring

Arrhythmia management has been revolutionized by the ability to monitor the cardiac rhythm in a patient's home environment in real-time using high-fidelity prescription-grade and commercially available wearable electrodes. The vast amount of digitally acquired electrophysiological signals has generated the need for scalable and efficient data processing with actionable output that can be provided directly to clinicians and patients. In this setting, artificial intelligence applications are increasingly important in arrhythmia monitoring, ranging from conventional algorithmic analysis for rhythm determination to more complex deep machine learning methods that have led to the realization of fully automated humanlike rhythm determination in real-time.

AFibNet: an implementation of atrial fibrillation detection with convolutional neural network

Background

Generalization model capacity of deep learning (DL) approach for atrial fibrillation (AF) detection remains lacking. It can be seen from previous researches, the DL model formation used only a single frequency sampling of the specific device. Besides, each electrocardiogram (ECG) acquisition dataset produces a different length and sampling frequency to ensure sufficient precision of the R–R intervals to determine the heart rate variability (HRV). An accurate HRV is the gold standard for predicting the AF condition; therefore, a current challenge is to determine whether a DL approach can be used to analyze raw ECG data in a broad range of devices. This paper demonstrates powerful results for end-to-end implementation of AF detection based on a convolutional neural network (AFibNet). The method used a single learning system without considering the variety of signal lengths and frequency samplings. For implementation, the AFibNet is processed with a computational cloud-based DL approach. This study utilized a one-dimension convolutional neural networks (1D-CNNs) model for 11,842 subjects. It was trained and validated with 8232 records based on three datasets and tested with 3610 records based on eight datasets. The predicted results, when compared with the diagnosis results indicated by human practitioners, showed a 99.80% accuracy, sensitivity, and specificity.

Result

Meanwhile, when tested using unseen data, the AF detection reaches 98.94% accuracy, 98.97% sensitivity, and 98.97% specificity at a sample period of 0.02 seconds using the DL Cloud System. To improve the confidence of the AFibNet model, it also validated with 18 arrhythmias condition defined as Non-AF-class. Thus, the data is increased from 11,842 to 26,349 instances for three-class, i.e., Normal sinus (N), AF and Non-AF. The result found 96.36% accuracy, 93.65% sensitivity, and 96.92% specificity.

Conclusion

These findings demonstrate that the proposed approach can use unknown data to derive feature maps and reliably detect the AF periods. We have found that our cloud-DL system is suitable for practical deployment

Deep transfer learning and data augmentation improve glucose levels prediction in type 2 diabetes patients

Accurate prediction of blood glucose variations in type 2 diabetes (T2D) will facilitate better glycemic control and decrease the occurrence of hypoglycemic episodes as well as the morbidity and mortality associated with T2D, hence increasing the quality of life of patients. Owing to the complexity of the blood glucose dynamics, it is difficult to design accurate predictive models in every circumstance, i.e., hypo/normo/hyperglycemic events. We developed deep-learning methods to predict patient-specific blood glucose during various time horizons in the immediate future using patient-specific every 30-min long glucose measurements by the continuous glucose monitoring (CGM) to predict future glucose levels in 5 min to 1 h. In general, the major challenges to address are (1) the dataset of each patient is often too small to train a patient-specific deep-learning model, and (2) the dataset is usually highly imbalanced given that hypo- and hyperglycemic episodes are usually much less common than normoglycemia. We tackle these two challenges using transfer learning and data augmentation, respectively. We systematically examined three neural network architectures, different loss functions, four transfer-learning strategies, and four data augmentation techniques, including mixup and generative models. Taken together, utilizing these methodologies we achieved over 95% prediction accuracy and 90% sensitivity for a time period within the clinically useful 1 h prediction horizon that would allow a patient to react and correct either hypoglycemia and/or hyperglycemia. We have also demonstrated that the same network architecture and transfer-learning methods perform well for the type 1 diabetes OhioT1DM public dataset.

Use of Smartphones and Wearables for Arrhythmia Monitoring

Smartphones and other wearable electronic devices increasingly are used for ambulatory cardiac rhythm assessment. These consumer technologies have been evaluated in several studies for diagnosis and management of atrial fibrillation. Diverse mobile health applications, including management of other arrhythmias and medical conditions, are expanding alongside advances in technology. Electronic devices owned by millions of consumers have the potential to alter health care delivery as well as research design and implementation. This review provides an up-to-date discussion of the available mobile health technologies, specific applications and limitations for arrhythmia evaluation, their impact on health care systems, and key areas for future investigation.

How machine learning is impacting research in atrial fibrillation: implications for risk prediction and future management

There has been an exponential growth of artificial intelligence (AI) and machine learning (ML) publications aimed at advancing our understanding of atrial fibrillation (AF), which has been mainly driven by the confluence of two factors: the advances in deep neural networks (DeepNNs) and the availability of large, open access databases. It is observed that most of the attention has centred on applying ML for dvsetecting AF, particularly using electrocardiograms (ECGs) as the main data modality. Nearly a third of them used DeepNNs to minimize or eliminate the need for transforming the ECGs to extract features prior to ML modelling; however, we did not observe a significant advantage in following this approach. We also found a fraction of studies using other data modalities, and others centred in aims, such as risk prediction, AF management, and others. From the clinical perspective, AI/ML can help expand the utility of AF detection and risk prediction, especially for patients with additional comorbidities. The use of AI/ML for detection and risk prediction into applications and smart mobile health (mHealth) technology would enable ‘real time’ dynamic assessments. AI/ML could also adapt to treatment changes over time, as well as incident risk factors. Incorporation of a dynamic AI/ML model into mHealth technology would facilitate ‘real time’ assessment of stroke risk, facilitating mitigation of modifiable risk factors (e.g. blood pressure control). Overall, this would lead to an improvement in clinical care for patients with AF.