Nanosensor technologies and the digital transformation of healthcare.

Nanosensors are nanoscale devices that measure physical attributes and convert these signals into analyzable information. In preparation, for the impending reality of nanosensors in clinical practice, we confront important questions regarding the evidence supporting widespread device use. Our objectives are to demonstrate the value and implications for new nanosensors as they relate to the next phase of remote patient monitoring and to apply lessons learned from digital health devices through real-world examples.

Convolution Neural Network Algorithm for Shockable Arrhythmia Classification Within a Digitally Connected Automated External Defibrillator.

Background Diagnosis of shockable rhythms leading to defibrillation remains integral to improving out-of-hospital cardiac arrest outcomes. New machine learning techniques have emerged to diagnose arrhythmias on ECGs. In out-of-hospital cardiac arrest, an algorithm within an automated external defibrillator is the major determinant to deliver defibrillation. This study developed and validated the performance of a convolution neural network (CNN) to diagnose shockable arrhythmias within a novel, miniaturized automated external defibrillator. Methods and Results There were 26 464 single-lead ECGs that comprised the study data set. ECGs of 7-s duration were retrospectively adjudicated by 3 physician readers (N=18 total readers). After exclusions (N=1582), ECGs were divided into training (N=23 156), validation (N=721), and test data sets (N=1005). CNN performance to diagnose shockable and nonshockable rhythms was reported with area under the receiver operating characteristic curve analysis, F1, and sensitivity and specificity calculations. The duration for the CNN to output was reported with the algorithm running within the automated external defibrillator. Internal and external validation analyses included CNN performance among arrhythmias, often mistaken for shockable rhythms, and performance among ECGs modified with noise to mimic artifacts. The CNN algorithm achieved an area under the receiver operating characteristic curve of 0.995 (95% CI, 0.990-1.0), sensitivity of 98%, and specificity of 100% to diagnose shockable rhythms. The F1 scores were 0.990 and 0.995 for shockable and nonshockable rhythms, respectively. After input of a 7-s ECG, the CNN generated an output in 383±29 ms (total time of 7.383 s). The CNN outperformed adjudicators in classifying atrial arrhythmias as nonshockable (specificity of 99.3%-98.1%) and was robust against noise artifacts (area under the receiver operating characteristic curve range, 0.871-0.999). Conclusions We demonstrate high diagnostic performance of a CNN algorithm for shockable and nonshockable rhythm arrhythmia classifications within a digitally connected automated external defibrillator. Registration URL: https://clinicaltrials.gov/ct2/show/NCT03662802; Unique identifier: NCT03662802.

A Novel Earbud Detects Aortic Stenosis Murmur Before and After Transcatheter Aortic Valve Replacement.

Noninvasive infrasonic hemodynography using the MindMics earbuds captures low-frequency acoustic vibrations throughout the cardiac cycle. In an n-of-1 analysis, we propose a new method of assessing severe aortic stenosis by using infrasonic hemodynography to detect its characteristic systolic ejection murmur before and after transcatheter aortic valve replacement.

In-ear infrasonic hemodynography with a digital health device for cardiovascular monitoring using the human audiome.

Human bodily mechanisms and functions produce low-frequency vibrations. Our ability to perceive these vibrations is limited by our range of hearing. However, in-ear infrasonic hemodynography (IH) can measure low-frequency vibrations (<20 Hz) created by vital organs as an acoustic waveform. This is captured using a technology that can be embedded into wearable devices such as in-ear headphones. IH can acquire sound signals that travel within arteries, fluids, bones, and muscles in proximity to the ear canal, allowing for measurements of an individual's unique audiome. We describe the heart rate and heart rhythm results obtained in time-series analysis of the in-ear IH data taken simultaneously with ECG recordings in two dedicated clinical studies. We demonstrate a high correlation (r = 0.99) between IH and ECG acquired interbeat interval and heart rate measurements and show that IH can continuously monitor physiological changes in heart rate induced by various breathing exercises. We also show that IH can differentiate between atrial fibrillation and sinus rhythm with performance similar to ECG. The results represent a demonstration of IH capabilities to deliver accurate heart rate and heart rhythm measurements comparable to ECG, in a wearable form factor. The development of IH shows promise for monitoring acoustic imprints of the human body that will enable new real-time applications in cardiovascular health that are continuous and noninvasive.

Multicenter validation of a machine learning phase space electro-mechanical pulse wave analysis to predict elevated left ventricular end diastolic pressure at the point-of-care.

BACKGROUND: Phase space is a mechanical systems approach and large-scale data representation of an object in 3-dimensional space. Whether such techniques can be applied to predict left ventricular pressures non-invasively and at the point-of-care is unknown. OBJECTIVE: This study prospectively validated a phase space machine-learned approach based on a novel electro-mechanical pulse wave method of data collection through orthogonal voltage gradient (OVG) and photoplethysmography (PPG) for the prediction of elevated left ventricular end diastolic pressure (LVEDP). METHODS: Consecutive outpatients across 15 US-based healthcare centers with symptoms suggestive of coronary artery disease were enrolled at the time of elective cardiac catheterization and underwent OVG and PPG data acquisition immediately prior to angiography with signals paired with LVEDP (IDENTIFY; NCT #03864081). The primary objective was to validate a ML algorithm for prediction of elevated LVEDP using a definition of ≥25 mmHg (study cohort) and normal LVEDP ≤ 12 mmHg (control cohort), using AUC as the measure of diagnostic accuracy. Secondary objectives included performance of the ML predictor in a propensity matched cohort (age and gender) and performance for an elevated LVEDP across a spectrum of comparative LVEDP (<12 through 24 at 1 mmHg increments). Features were extracted from the OVG and PPG datasets and were analyzed using machine-learning approaches. RESULTS: The study cohort consisted of 684 subjects stratified into three LVEDP categories, ≤12 mmHg (N = 258), LVEDP 13-24 mmHg (N = 347), and LVEDP ≥25 mmHg (N = 79). Testing of the ML predictor demonstrated an AUC of 0.81 (95% CI 0.76-0.86) for the prediction of an elevated LVEDP with a sensitivity of 82% and specificity of 68%, respectively. Among a propensity matched cohort (N = 79) the ML predictor demonstrated a similar result AUC 0.79 (95% CI: 0.72-0.8). Using a constant definition of elevated LVEDP and varying the lower threshold across LVEDP the ML predictor demonstrated and AUC ranging from 0.79-0.82. CONCLUSION: The phase space ML analysis provides a robust prediction for an elevated LVEDP at the point-of-care. These data suggest a potential role for an OVG and PPG derived electro-mechanical pulse wave strategy to determine if LVEDP is elevated in patients with symptoms suggestive of cardiac disease.

Identifying novel phenotypes of elevated left ventricular end diastolic pressure using hierarchical clustering of features derived from electromechanical waveform data.

Introduction: Elevated left ventricular end diastolic pressure (LVEDP) is a consequence of compromised left ventricular compliance and an important measure of myocardial dysfunction. An algorithm was developed to predict elevated LVEDP utilizing electro-mechanical (EM) waveform features. We examined the hierarchical clustering of selected features developed from these EM waveforms in order to identify important patient subgroups and assess their possible prognostic significance. Materials and methods: Patients presenting with cardiovascular symptoms (N = 396) underwent EM data collection and direct LVEDP measurement by left heart catheterization. LVEDP was classified as non-elevated ( ≤ 12 mmHg) or elevated (≥25 mmHg). The 30 most contributive features to the algorithm output were extracted from EM data and input to an unsupervised hierarchical clustering algorithm. The resultant dendrogram was divided into five clusters, and patient metadata overlaid. Results: The cluster with highest LVEDP (cluster 1) was most dissimilar from the lowest LVEDP cluster (cluster 5) in both clustering and with respect to clinical characteristics. In contrast to the cluster demonstrating the highest percentage of elevated LVEDP patients, the lowest was predominantly non-elevated LVEDP, younger, lower BMI, and males with a higher rate of significant coronary artery disease (CAD). The next adjacent cluster (cluster 2) to that of the highest LVEDP (cluster 1) had the second lowest LVEDP of all clusters. Cluster 2 differed from Cluster 1 primarily based on features extracted from the electrical data, and those that quantified predictability and variability of the signal. There was a low predictability and high variability in the highest LVEDP cluster 1, and the opposite in adjacent cluster 2. Conclusion: This analysis identified subgroups of patients with varying degrees of LVEDP elevation based on waveform features. An approach to stratify movement between clusters and possible progression of myocardial dysfunction may include changes in features that differentiate clusters; specifically, reductions in electrical signal predictability and increases in variability. Identification of phenotypes of myocardial dysfunction evidenced by elevated LVEDP and knowledge of factors promoting transition to clusters with higher levels of left ventricular filling pressures could permit early risk stratification and improve patient selection for novel therapeutic interventions.

COVID-19 telehealth preparedness: a cross-sectional assessment of cardiology practices in the USA.

Aim: The COVID-19 pandemic forced medical practices to augment healthcare delivery to remote and virtual services. We describe the results of a nationwide survey of cardiovascular professionals regarding telehealth perspectives. Materials & methods: A 31-question survey was sent early in the pandemic to assess the impact of COVID-19 on telehealth adoption & reimbursement. Results: A total of 342 clinicians across 42 states participated. 77% were using telehealth, with the majority initiating usage 2 months after the COVID-19 shutdown. A variety of video-based systems were used. Telehealth integration requirements differed, with electronic medical record integration being mandated in more urban than rural practices (70 vs 59%; p < 0.005). Many implementation barriers surfaced, with over 75% of respondents emphasizing reimbursement uncertainty and concerns for telehealth generalizability given the complexity of cardiovascular diseases. Conclusion: Substantial variation exists in telehealth practices. Further studies and legislation are needed to improve access, reimbursement and the quality of telehealth-based cardiovascular care.

As the COVID-19 pandemic was just beginning, the American College of Cardiology administered a survey to cardiology professionals across the USA regarding their preparedness for telehealth and video-visits. The results demonstrated rapid adoption of video based telehealth services, however revealed uncertainty for how to best use these services in different practice settings. Many providers expressed concerns about how these visits will be compensated, but fortunately federal agencies have dramatically changed the way telehealth is reimbursed as the pandemic has progressed. Further studies are needed to explore the impact of telehealth on healthcare inequality, however we hope that rather it serves to increase healthcare access to all.

Artificial intelligence in healthcare: a primer for medical education in radiomics.

The application of artificial intelligence (AI) to healthcare has garnered significant enthusiasm in recent years. Despite the adoption of new analytic approaches, medical education on AI is lacking. We aim to create a usable AI primer for medical education. We discuss how to generate a clinical question involving AI, what data are suitable for AI research, how to prepare a dataset for training and how to determine if the output has clinical utility. To illustrate this process, we focused on an example of how medical imaging is employed in designing a machine learning model. Our proposed medical education curriculum addresses AI's potential and limitations for enhancing clinicians' skills in research, applied statistics and care delivery.

The application of artificial intelligence (AI) to healthcare has generated increasing interest in recent years; however, medical education on AI is lacking. With this primer, we provide an overview on how to understand AI, gain exposure to machine learning (ML) and how to develop research questions utilizing ML. Using an example of a ML application in imaging, we provide a practical approach to understanding and executing a ML analysis. Our proposed medical education curriculum provides a framework for healthcare education which we hope will propel healthcare institutions to implement ML laboratories and training environments and improve access to this transformative paradigm.

Framework for Digital Health Phenotypes in Heart Failure: From Wearable Devices to New Sensor Technologies.

Consider these 2 scenarios: Two individuals with heart failure (HF) have recently established with your clinic and followed for medical management and risk stratification. One is a 62-year-old man with nonischemic cardiomyopathy due to viral myocarditis, an ejection fraction (EF) of 40%, occasional rate-limiting dyspnea, and comorbidities of atrial fibrillation and hypertension. The other is a 75-year-old woman with ischemic cardiomyopathy, an EF of 35%, a prior hospitalization 6 months ago, and persistent symptoms of edema and orthopnea. Both have expressed interest in remote patient monitoring (RPM) with wearable and digital health devices that are commercially available such as a smartwatch-ECG, weight scales, and blood pressure monitoring technologies. While there is enthusiasm from both patients and their clinical teams to engage in a technology-driven approach to care, important questions arise such as "What are the patient requirements for participation in digital health programs?", "Can we anticipate improvements in HF status and lower the risk of future HF events including hospitalizations?", "Do the same type of devices in different patients provide accurate information on physiologic changes toward individualized risk assessments?", and "What are the systematic approaches to integrate digital health workflows and datasets from RPM into clinical HF programs?". Given the importance of such questions, embracing new technologies, as a core competency of a modern health care system requires a deeper understanding of how effective digital health programs can be designed to meet the needs of patients and their clinical teams. In this review, we propose a new framework of "Digital Phenotypes in HF" for how new devices and sensors and their respective datasets can be used to guide treatment and to predict disease trajectories within the heterogeneity of HF. Our objectives are to generate a systematic approach to evaluate digital health devices as they relate to the next phase of RPM in HF, to critically analyze the literature, and to apply the lessons learned from digital devices through present-day, real-world evidence examples.

Development of a culturally and linguistically sensitive virtual reality educational platform to improve vaccine acceptance within a refugee population: the SHIFA community engagement-public health innovation programme.

OBJECTIVES: To combat misinformation, engender trust and increase health literacy, we developed a culturally and linguistically appropriate virtual reality (VR) vaccination education platform using community-engaged approaches within a Somali refugee community. DESIGN: Community-based participatory research (CBPR) methods including focus group discussions, interviews, and surveys were conducted with Somali community members and expert advisors to design the educational content. Co-design approaches with community input were employed in a phased approach to develop the VR storyline. PARTICIPANTS: 60 adult Somali refugees and seven expert advisors who specialise in healthcare, autism research, technology development and community engagement. SETTING: Somali refugees participated at the offices of a community-based organisation, Somali Family Service, in San Diego, California and online. Expert advisors responded to surveys virtually. RESULTS: We find that a CBPR approach can be effectively used for the co-design of a VR educational programme. Additionally, cultural and linguistic sensitivities can be incorporated within a VR educational programme and are essential factors for effective community engagement. Finally, effective VR utilisation requires flexibility so that it can be used among community members with varying levels of health and technology literacy. CONCLUSION: We describe using community co-design to create a culturally and linguistically sensitive VR experience promoting vaccination within a refugee community. Our approach to VR development incorporated community members at each step of the process. Our methodology is potentially applicable to other populations where cultural sensitivities and language are common health education barriers.

Machine learning for holistic visualization of STEMI registry data.

BACKGROUND: Widespread adoption of evidence-based guidelines and treatment pathways in ST-Elevation Myocardial Infarction (STEMI) patients has considerably improved cardiac survival and decreased the risk of recurrent myocardial infarction. However, survival outcomes appear to have plateaued over the last decade. The hope underpinning the current study is to engage data visualization to develop a more holistic understanding of the patient space, supported by principles and techniques borrowed from traditionally disparate disciplines, like cartography and machine learning. METHODS AND RESULTS: The Minnesota Heart Institute Foundation (MHIF) STEMI database is a large prospective regional STEMI registry consisting of 180 variables of heterogeneous data types on more than 5000 patients spanning 15 years. Initial assessment and preprocessing of the registry database was undertaken, followed by a first proof-of-concept implementation of an analytical workflow that involved machine learning, dimensionality reduction, and data visualization. 38 pre-admission variables were analyzed in an all-encompassing representation of pre-index STEMI event data. We aim to generate a holistic visual representation - a map of the multivariate patient space - by training a high-resolution self-organizing neural network consisting of several thousand neurons. The resulting 2-D lattice arrangement of n-dimensional neuron vectors allowed patients to be represented as point locations in a 2-D display space. Patient attributes were then visually examined and contextualized in the same display space, from demographics to pre-existing conditions, event-specific procedures, and STEMI outcomes. Data visualizations implemented in this study include a small-multiple display of neural component planes, composite visualization of the multivariate patient space, and overlay visualization of non-training attributes. CONCLUSION: Our study represents the first known marriage of cartography and machine learning techniques to obtain visualizations of the multivariate space of a regional STEMI registry. Combining cartographic mapping techniques and artificial neural networks permitted the transformation of the STEMI database into novel, two-dimensional visualizations of patient characteristics and outcomes. Notably, these visualizations also drive the discovery of anomalies in the data set, informing corrections applied to detected outliers, thereby further refining the registry for integrity and accuracy. Building on these advances, future efforts will focus on supporting further understanding of risk factors and predictors of outcomes in STEMI patients. More broadly, the thorough visual exploration of display spaces generated through a conjunction of dimensionality reduction with the mature technology base of geographic information systems appears a promising direction for biomedical research.

Gerotechnology for Older Adults With Cardiovascular Diseases: JACC State-of-the-Art Review.

The growing population of older adults (age ≥65 years) is expected to lead to higher rates of cardiovascular disease. The expansion of digital health (encompassing telehealth, telemedicine, mobile health, and remote patient monitoring), Internet access, and cellular technologies provides an opportunity to enhance patient care and improve health outcomes-opportunities that are particularly relevant during the current coronavirus disease-2019 pandemic. Insufficient dexterity, visual impairment, and cognitive dysfunction, found commonly in older adults should be taken into consideration in the development and utilization of existing technologies. If not implemented strategically and appropriately, these can lead to inequities propagating digital divides among older adults, across disease severities and socioeconomic distributions. A systematic approach, therefore, is needed to study and implement digital health strategies in older adults. This review will focus on current knowledge of the benefits, barriers, and use of digital health in older adults for cardiovascular disease management.

Cardiac Stress Testing After Coronary Revascularization.

Unless prompted by symptoms or change in clinical status, the appropriate use criteria consider cardiac stress testing (CST) within 2 years of percutaneous coronary intervention (PCI) and 5 years of coronary artery bypass grafting (CABG) to be rarely appropriate. Little is known regarding use and yield of CST after PCI or CABG. We studied 39,648 patients treated with coronary revascularization (29,497 PCI; 10,151 CABG) between April 2004 and March 2012 in Alberta, Canada. Frequency of CST between 60 days and 2 years after revascularization was determined from linked provincial databases. Yield was defined as subsequent rates of coronary angiography and revascularization after CST. Post PCI, 14,195 (48.1%) patients underwent CST between 60 days and 2 years, while post CABG, 4,469 (44.0%) patients underwent CST. Compared with patients not undergoing CST, patients undergoing CST were more likely to be of younger age, reside in an urban area, have higher neighborhood median household income, but less medical comorbidities. Among PCI patients undergoing CST, 5.2% underwent subsequent coronary angiography, and 2.6% underwent repeat revascularization within 60 days of CST. Rates of coronary angiography and repeat revascularization post-CST among CABG patients were 3.6% and 1.1%, respectively. Approximately one-half of patients undergo CST within 2 years of PCI or CABG in Alberta, Canada. Yield of CST is low, with only 1 out of 38 tested post-PCI patients and 1 out of 91 tested post-CABG patients undergoing further revascularization. In conclusion, additional research is required to determine patients most likely to benefit from CST after revascularization.

Toward precision health: applying artificial intelligence analytics to digital health biometric datasets.

The rapid development of digital health devices has enabled patients to engage in their care to an unprecedented degree and holds the possibility of significantly improving the diagnosis, treatment and monitoring of many medical conditions. Combined with the emergence of artificial intelligence algorithms, biometric datasets produced from these digital health devices present new opportunities to create precision-based, personalized approaches for healthcare delivery. For effective implementation of such innovations to patient care, clinicians will require an understanding of the types of datasets produced from digital health technologies; the types of analytic methods including feature selection, convolution neural networking, and deep learning that can be used to analyze digital data; and how the interpretation of these findings are best translated to patient care. In this perspective, we aim to provide the groundwork for clinicians to be able to apply artificial intelligence to this transformation of healthcare.

Digital Health: Opportunities and Challenges to Develop the Next-Generation Technology-Enabled Models of Cardiovascular Care.

The wide gap between the development of new healthcare technologies and their integration into clinical practice argues for a deeper understanding of how effective quality improvement can be designed to meet the needs of patients and their clinical teams. The COVID-19 pandemic has forced us to address this gap and create long-term strategies to bridge it. On the one hand, it has enabled the rapid implementation of telehealth. On the other hand, it has raised important questions about our preparedness to adopt and employ new digital tools as part of a new process of care. While healthcare organizations are seeking to improve the quality of care by integrating innovations in digital health, they must also address key issues such as patient experience, develop clinical decision support systems that analyze digital health data trends, and create efficient clinical workflows. Given the breadth of such requirements, embracing new technologies as a core competency of a modern healthcare system introduces a host of questions, such as "How best do patients participate in digital health programs that promote behavioral changes and mitigate risk?" and "What type of data analytics are required that enable a deeper understanding of disease phenotypes and corresponding treatment decisions?" This review presents the challenges in implementing digital health technology and discusses how patient-centered digital health programs are designed within real-world models of remote monitoring. It also provides a framework for developing new devices and wearables for the next generation of data-driven, technology-enabled cardiovascular care.

Privacy-Preserving Generative Deep Neural Networks Support Clinical Data Sharing.

BACKGROUND: Data sharing accelerates scientific progress but sharing individual-level data while preserving patient privacy presents a barrier. METHODS AND RESULTS: Using pairs of deep neural networks, we generated simulated, synthetic participants that closely resemble participants of the SPRINT trial (Systolic Blood Pressure Trial). We showed that such paired networks can be trained with differential privacy, a formal privacy framework that limits the likelihood that queries of the synthetic participants' data could identify a real a participant in the trial. Machine learning predictors built on the synthetic population generalize to the original data set. This finding suggests that the synthetic data can be shared with others, enabling them to perform hypothesis-generating analyses as though they had the original trial data. CONCLUSIONS: Deep neural networks that generate synthetic participants facilitate secondary analyses and reproducible investigation of clinical data sets by enhancing data sharing while preserving participant privacy.

Virtual Care 2.0-a Vision for the Future of Data-Driven Technology-Enabled Healthcare.

A busy community cardiologist finished reading eight echocardiograms over lunch and started clinic at 1 pm. As three patients waited, "Jane," a 45-year-old graphic designer was seen for "skipped heart beat." She works about 50 h a week, exercises at the local gym, and enjoys eating a healthy diet. About 4 months ago Jane began experiencing her heart "skipping beats." She initially attributed the symptoms to long hours in the office and caffeine. But, over the holiday, her brother purchased a smart watch and she began digitally recording her cardiac rhythm. About a month ago, the device detected possible atrial fibrillation, so she called and scheduled this visit for a cardiology consultation. Upon that visitation, she and her physician reviewed the device readings. While it appeared to be an irregular rhythm, before either considered a treatment plan, they began to ask questions ranging from the following: "Is this an accurate diagnosis?" "What other data are available to better understand the risk of a cardiac arrhythmia?" "How is this data analyzed so that the best treatment plan can be made?" "And, what type of clinical decision support system is required to 'virtually' monitor people like me using digital health devices to improve the efficiency and quality of care delivered in population health?"

Coronary risk equivalence of diabetes assessed by SPECT-MPI.

BACKGROUND: Several publications and guidelines designate diabetes mellitus (DM) as a coronary artery disease (CAD) risk equivalent. The aim of this investigation was to examine DM cardiac risk equivalence from the perspective of stress SPECT myocardial perfusion imaging (MPI). METHODS AND RESULTS: We examined cardiovascular outcomes (cardiac death or nonfatal MI) of 17,499 patients referred for stress SPECT-MPI. Patients were stratified into four categories: non-DM without CAD, non-DM with CAD, DM without CAD, and DM with CAD, and normal or abnormal perfusion. Cardiac events occurred in 872 (5%), with event-free survival best among non-DM without CAD, worst in DM with CAD, and intermediate in DM without CAD, and non-DM with CAD. After multivariate adjustment, risk remained comparable between DM without CAD and non-DM with CAD [AHR 1.0 (95% CI 0.84-1.28), P =0.74]. Annualized event rates for normal subjects were 1.4% and 1.6% for non-DM with CAD and DM without CAD, respectively (P = 0.48) and 3.5% (P = 0.95) for both abnormal groups. After multivariate adjustment, outcomes were comparable within normal [AHR 1.4 (95% CI 0.98-1.96) P = 0.06] and abnormal [AHR 1.1 (95% CI 0.83-1.50) P = 0.49] MPI. CONCLUSIONS: Diabetic patients without CAD have comparable risk of cardiovascular events as non-diabetic patients with CAD after stratification by MPI results. These findings support diabetes as a CAD equivalent and suggest that MPI provides additional prognostic information in such patients.