Validation of a Deep Learning Algorithm for Continuous, Real-Time Detection of Atrial Fibrillation Using a Wrist-Worn Device in an Ambulatory Environment.

BACKGROUND: Wearable devices may be useful for identification, quantification and characterization, and management of atrial fibrillation (AF). To date, consumer wrist-worn devices for AF detection using photoplethysmography-based algorithms perform only periodic checks when the user is stationary and are US Food and Drug Administration cleared for prediagnostic uses without intended use for clinical decision-making. There is an unmet need for medical-grade diagnostic wrist-worn devices that provide long-term, continuous AF monitoring. METHODS AND RESULTS: We evaluated the performance of a wrist-worn device with lead-I ECG and continuous photoplethysmography (Verily Study Watch) and photoplethysmography-based convolutional neural network for AF detection and burden estimation in a prospective multicenter study that enrolled 117 patients with paroxysmal AF. A 14-day continuous ECG monitor (Zio XT) served as the reference device to evaluate algorithm sensitivity and specificity for detection of AF in 15-minute intervals. A total of 91 857 intervals were contributed by 111 subjects with evaluable reference and test data (18.3 h/d median watch wear time). The watch was 96.1% sensitive (95% CI, 92.7%-98.0%) and 98.1% specific (95% CI, 97.2%-99.1%) for interval-level AF detection. Photoplethysmography-derived AF burden estimation was highly correlated with the reference device burden (R2=0.986) with a mean difference of 0.8% (95% limits of agreement, -6.6% to 8.2%). CONCLUSIONS: Continuous monitoring using a photoplethysmography-based convolutional neural network incorporated in a wrist-worn device has clinical-grade performance for AF detection and burden estimation. These findings suggest that monitoring can be performed with wrist-worn wearables for diagnosis and clinical management of AF. REGISTRATION INFORMATION: URL: https://www.clinicaltrials.gov; Unique identifier: NCT04546763.

Sparse multi-output Gaussian processes for online medical time series prediction.

BACKGROUND: For real-time monitoring of hospital patients, high-quality inference of patients' health status using all information available from clinical covariates and lab test results is essential to enable successful medical interventions and improve patient outcomes. Developing a computational framework that can learn from observational large-scale electronic health records (EHRs) and make accurate real-time predictions is a critical step. In this work, we develop and explore a Bayesian nonparametric model based on multi-output Gaussian process (GP) regression for hospital patient monitoring. METHODS: We propose MedGP, a statistical framework that incorporates 24 clinical covariates and supports a rich reference data set from which relationships between observed covariates may be inferred and exploited for high-quality inference of patient state over time. To do this, we develop a highly structured sparse GP kernel to enable tractable computation over tens of thousands of time points while estimating correlations among clinical covariates, patients, and periodicity in patient observations. MedGP has a number of benefits over current methods, including (i) not requiring an alignment of the time series data, (ii) quantifying confidence regions in the predictions, (iii) exploiting a vast and rich database of patients, and (iv) inferring interpretable relationships among clinical covariates. RESULTS: We evaluate and compare results from MedGP on the task of online prediction for three patient subgroups from two medical data sets across 8,043 patients. We find MedGP improves online prediction over baseline and state-of-the-art methods for nearly all covariates across different disease subgroups and hospitals. CONCLUSIONS: The MedGP framework is robust and efficient in estimating the temporal dependencies from sparse and irregularly sampled medical time series data for online prediction. The publicly available code is at https://github.com/bee-hive/MedGP .

An Optimal Policy for Patient Laboratory Tests in Intensive Care Units.

Laboratory testing is an integral tool in the management of patient care in hospitals, particularly in intensive care units (ICUs). There exists an inherent trade-off in the selection and timing of lab tests between considerations of the expected utility in clinical decision-making of a given test at a specific time, and the associated cost or risk it poses to the patient. In this work, we introduce a framework that learns policies for ordering lab tests which optimizes for this trade-off. Our approach uses batch off-policy reinforcement learning with a composite reward function based on clinical imperatives, applied to data that include examples of clinicians ordering labs for patients. To this end, we develop and extend principles of Pareto optimality to improve the selection of actions based on multiple reward function components while respecting typical procedural considerations and prioritization of clinical goals in the ICU. Our experiments show that we can estimate a policy that reduces the frequency of lab tests and optimizes timing to minimize information redundancy. We also find that the estimated policies typically suggest ordering lab tests well ahead of critical onsets-such as mechanical ventilation or dialysis-that depend on the lab results. We evaluate our approach by quantifying how these policies may initiate earlier onset of treatment.

Bayesian nonparametric discovery of isoforms and individual specific quantification.

Most human protein-coding genes can be transcribed into multiple distinct mRNA isoforms. These alternative splicing patterns encourage molecular diversity, and dysregulation of isoform expression plays an important role in disease etiology. However, isoforms are difficult to characterize from short-read RNA-seq data because they share identical subsequences and occur in different frequencies across tissues and samples. Here, we develop BIISQ, a Bayesian nonparametric model for isoform discovery and individual specific quantification from short-read RNA-seq data. BIISQ does not require isoform reference sequences but instead estimates an isoform catalog shared across samples. We use stochastic variational inference for efficient posterior estimates and demonstrate superior precision and recall for simulations compared to state-of-the-art isoform reconstruction methods. BIISQ shows the most gains for low abundance isoforms, with 36% more isoforms correctly inferred at low coverage versus a multi-sample method and 170% more versus single-sample methods. We estimate isoforms in the GEUVADIS RNA-seq data and validate inferred isoforms by associating genetic variants with isoform ratios.

GE11-modified liposomes for non-small cell lung cancer targeting: preparation, ex vitro and in vivo evaluation.

Non-small cell lung cancer (NSCLC) is a serious threat to human health, and 40%-80% of NSCLCs express high levels of epidermal growth factor receptor (EGFR). GE11 is a novel peptide and exhibits high affinity for EGFR binding. The aim of this study was to construct and evaluate GE11-modified liposomes for targeted drug delivery to EGFR-positive NSCLC. Doxorubicin, a broad-spectrum antitumor agent, was chosen as the payload. GE11 was conjugated to the distal end of DSPE-PEG2000-Mal by an addition reaction with a conjugation efficiency above 90%. Doxorubicin-loaded liposomes containing GE11 (GE11-LP/DOX) at densities ranging from 0% to 15% were prepared by combination of a thin film hydration method and a post insertion method. Irrespective of GE11 density, the physicochemical properties of these targeted liposomes, including particle size, zeta potential, and drug entrapment efficiency, were nearly identical. Interestingly, the cytotoxic effect of the liposomes on A549 tumor cells was closely related to GE11 density, and liposomes with 10% GE11 had the highest tumor cell killing activity and a 2.6-fold lower half maximal inhibitory concentration than that of the nontargeted counterpart (PEG-LP/DOX). Fluorescence microscopy and flow cytometry analysis revealed that GE11 significantly increased cellular uptake of the liposomes, which could be ascribed to specific EGFR-mediated endocytosis. It was found that multiple endocytic pathways were involved in entry of GE11-LP/DOX into cells, but GE11 assisted in cellular internalization mainly via the clathrin-mediated endocytosis pathway. Importantly, the GE11-modified liposomes showed enhanced accumulation and prolonged retention in tumor tissue, as evidenced by a 2.2-fold stronger mean fluorescence intensity in tumor tissue than the unmodified liposomes at 24 hours. In summary, GE11-modified liposomes may be a promising platform for targeted delivery of chemotherapeutic drugs in NSCLC.

Architecture design of the multi-functional wavelet-based ECG microprocessor for realtime detection of abnormal cardiac events.

Most of the abnormal cardiac events such as myocardial ischemia, acute myocardial infarction (AMI) and fatal arrhythmia can be diagnosed through continuous electrocardiogram (ECG) analysis. According to recent clinical research, early detection and alarming of such cardiac events can reduce the time delay to the hospital, and the clinical outcomes of these individuals can be greatly improved. Therefore, it would be helpful if there is a long-term ECG monitoring system with the ability to identify abnormal cardiac events and provide realtime warning for the users. The combination of the wireless body area sensor network (BASN) and the on-sensor ECG processor is a possible solution for this application. In this paper, we aim to design and implement a digital signal processor that is suitable for continuous ECG monitoring and alarming based on the continuous wavelet transform (CWT) through the proposed architectures--using both programmable RISC processor and application specific integrated circuits (ASIC) for performance optimization. According to the implementation results, the power consumption of the proposed processor integrated with an ASIC for CWT computation is only 79.4 mW. Compared with the single-RISC processor, about 91.6% of the power reduction is achieved.