Automatic detection of cardiac conditions from photos of electrocardiogram captured by smartphones.

BACKGROUND: Researchers have developed machine learning-based ECG diagnostic algorithms that match or even surpass cardiologist level of performance. However, most of them cannot be used in real-world, as older generation ECG machines do not permit installation of new algorithms. OBJECTIVE: To develop a smartphone application that automatically extract ECG waveforms from photos and to convert them to voltage-time series for downstream analysis by a variety of diagnostic algorithms built by researchers. METHODS: A novel approach of using objective detection and image segmentation models to automatically extract ECG waveforms from photos taken by clinicians was devised. Modular machine learning models were developed to sequentially perform waveform identification, gridline removal, and scale calibration. The extracted data were then analysed using a machine learning-based cardiac rhythm classifier. RESULTS: Waveforms from 40 516 scanned and 444 photographed ECGs were automatically extracted. 12 828 of 13 258 (96.8%) scanned and 5399 of 5743 (94.0%) photographed waveforms were correctly cropped and labelled. 11 604 of 12 735 (91.1%) scanned and 5062 of 5752 (88.0%) photographed waveforms achieved successful voltage-time signal extraction after automatic gridline and background noise removal. In a proof-of-concept demonstration, an atrial fibrillation diagnostic algorithm achieved 91.3% sensitivity, 94.2% specificity, 95.6% positive predictive value, 88.6% negative predictive value and 93.4% F1 score, using photos of ECGs as input. CONCLUSION: Object detection and image segmentation models allow automatic extraction of ECG signals from photos for downstream diagnostics. This novel pipeline circumvents the need for costly ECG hardware upgrades, thereby paving the way for large-scale implementation of machine learning-based diagnostic algorithms.

Protocol for Home-Based Solution for Remote Atrial Fibrillation Screening to Prevent Recurrence Stroke (HUA-TUO AF Trial): a randomised controlled trial.

INTRODUCTION: Current international guidelines recommend ECG monitoring after an ischaemic stroke to detect atrial fibrillation (AF) in order to prevent stroke recurrence. However, optimal strategies to detect AF and the downstream management to prevent stroke recurrence remain to be established. The objective of the study was to explore the use of long-term home-based ECG monitoring for AF detection and stroke prevention in patients with a history of stroke. METHODS AND ANALYSIS: This prospective, randomised, open-label trial with blinded endpoint adjudication aimed to evaluate the efficacy of long-term home-based ECG monitoring for AF detection and stroke prevention in a 24-month period. Patients aged >18 years with a history of ischaemic stroke will be stratified according to the time from the index ischaemic stroke: <1, 1-3 and >3 years and then randomised in 1:1 to (1) home-based AF screening and (2) control. The home-based AF screening system comprises (1) a handheld single-lead ECG recorder (Comfit Healthcare Devices, Hong Kong SAR, China) and (2) a patient-facing smartphone application specially designed for the study. Patients randomised to the home-based AF group will record a 30 s single-lead ECG using a specially designed handheld ECG device every morning or when symptomatic. All remotely obtained data will be automatically transmitted in real-time through the study smartphone application to a secured cloud hosting and analysed using an artificial intelligence-based diagnostic system. When a diagnosis of AF is made with the system, the patients will be called back for a formal cardiology consultation within 1 week. The primary endpoint is the time to first detection of AF at 24 months of follow-up. Secondary endpoints include recurrent stroke or transient ischaemic attack, initiation of long-term anticoagulation therapy, hospitalisation for heart failure, cardiovascular death and all-cause death. ETHICS AND DISSEMINATION: The study protocol has been approved by the institutional review board of The University of Hong Kong, and Hong Kong West Cluster, Hospital Authority, Hong Kong SAR, China. Results will be published in peer-reviewed journals. TRIAL REGISTRATION NUMBER: NCT04523649.

Daily ambulatory remote monitoring system for drug escalation in chronic heart failure with reduced ejection fraction: pilot phase of DAVID-HF study.

Aims: Underutilization of guideline-directed heart failure with reduced ejection fraction (HFrEF) medications contributes to poor outcomes. Methods and results: A pilot study to evaluate the safety and efficacy of a home-based remote monitoring system for HFrEF management was performed. The system included wearable armband monitors paired with the smartphone application. An HFrEF medication titration algorithm was used to adjust medication daily. The primary endpoint was HFrEF medication utilization at 120 days. Twenty patients (60.5 ± 8.2 years, men: 85%) with HFrEF were recruited. All received angiotensin-converting enzyme inhibitor (ACEI)/angiotensin receptor blocker (ARB)/angiotensin receptor-neprilysin inhibitor (ARNI) at recruitment; 45% received ≥50% maximal targeted dose (MTD) with % MTD of 44.4 ± 31.7%. At baseline, 90 and 70% received beta-adrenergic blocker and mineralocorticoid receptor antagonist (MRA), 35% received ≥50% MTD beta-adrenergic blocker with % MTD of 34.1 ± 29.6%, and 25% received ≥50% MTD MRA with % MTD of 25.0 ± 19.9%. At 120 days, 70% received ≥50% MTD ACEI/ARB/ARNI (P = 0.110) with % MTD increased to 64.4 ± 33.5% (P = 0.060). The proportion receiving ≥50% MTD ARNI increased from 15 to 55% (P = 0.089) with % MTD ARNI increased from 20.6 ± 30.9 to 53.1 ± 39.5% (P = 0.006*). More patients received ≥50% MTD MRA (65 vs. 25%, P = 0.011*) with % MTD MRA increased from 25.0 ± 19.9 to 46.2 ± 28.8% (P = 0.009*). Ninety-five per cent of patients had reduced NT-proBNP with the percentage reduction of 26.7 ± 19.7%. Conclusion: Heart failure with reduced ejection fraction medication escalation with remote monitoring appeared feasible.

A theory of general intelligence.

This paper proposes a theoretical framework for the biological learning mechanism as a general learning system. The proposal is as follows. The bursting and tonic modes of firing patterns found in many neuron types in the brain correspond to two separate modes of information processing, with one mode resulting in awareness, and another mode being subliminal. In such a coding scheme, a neuron in bursting state codes for the highest level of perceptual abstraction representing a pattern of sensory stimuli, or volitional abstraction representing a pattern of muscle contraction sequences. Within the 50-250 ms minimum integration time of experience, the bursting neurons form synchrony ensembles to allow for binding of related percepts. The degree which different bursting neurons can be merged into the same synchrony ensemble depends on the underlying cortical connections that represent the degree of perceptual similarity. These synchrony ensembles compete for selective attention to remain active. The dominant synchrony ensemble triggers episodic memory recall in the hippocampus, while forming new episodic memory with current sensory stimuli, resulting in a stream of thoughts. Neuromodulation modulates both top-down selection of synchrony ensembles, and memory formation. Episodic memory stored in the hippocampus is transferred to semantic and procedural memory in the cortex during rapid eye movement sleep, by updating cortical neuron synaptic weights with spike timing dependent plasticity. With the update of synaptic weights, new neurons become bursting while previous bursting neurons become tonic, allowing bursting neurons to move up to a higher level of perceptual abstraction. Finally, the proposed learning mechanism is compared with the back-propagation algorithm used in deep neural networks, and a proposal of how the credit assignment problem can be addressed by the current theory is presented.

A Novel Calibration Procedure of Pulse Transit Time based Blood Pressure measurement with Heart Rate and Respiratory Rate.

Pulse transit time (PTT) has been a promising non-invasive and cuff-less method to measure blood pressure (BP). However, to achieve acceptable accuracy, subject specific and frequent calibration is required to model the complex non-Iinear dynamic between BP and PTT, limiting the practicality of PTT-based methods. The BP-PTT relationship is often modelled by the Moens-Korteweg (M-K) equation. Previous studies have found that the M-K equation is only able to model high frequency variations of BP, with low frequency variations modulated by the vasomotor tone, which is regulated by the sympathetic nervous system (SNS). In this paper we present a novel calibration procedure that accounts for the influence of the SNS on the BP-PTT relationship. This is achieved by identifying the state of the SNS during calibration based on heart rate (HR), respiratory rate (RR), and PTT itself. The performance of the proposed procedure has been tested on 10 subjects over a period of 4 weeks. The results showed that the measurement differences were 1.04 mmHg ± 6.88 mmHg, and -2.16mmHg ± 6.60 mmHg for systolic and diastolic blood pressure, respectively. Furthermore, the proposed procedure was found to make a significant improvement of measurement precision when compared to the previous one-point calibration method, demonstrating the potential of the new procedure for accurate long-term BP tracking.