Search

Purpose of review Refinement in machine learning (ML) techniques and approaches has rapidly expanded artificial intelligence applications for the diagnosis and classification of heart failure (HF). This review is designed to provide the clinician with the basics of ML, as well as this technologies future utility in HF diagnosis and the potential impact on patient outcomes. Recent findings Recent studies applying ML methods to unique data sets available from electrocardiography, vectorcardiography, echocardiography, and electronic health records show significant promise for improving diagnosis, enhancing detection, and advancing treatment of HF. Innovations in both supervised and unsupervised methods have heightened the diagnostic accuracy of models developed to identify the presence of HF and further augmentation of model capabilities are likely utilizing ensembles of ML algorithms derived from different techniques. Summary This article is an overview of recent applications of ML to achieve improved diagnosis of HF and the resultant implications for patient management.

Background and Objective Coronary artery disease (CAD) and heart failure are the most common cardiovascular diseases. Non-invasive diagnostic testing for CAD requires radiation, heart rate acceleration, and imaging infrastructure. Early detection of left ventricular dysfunction is critical in heart failure management, the best measure of which is an elevated left ventricular end-diastolic pressure (LVEDP) that can only be measured using invasive cardiac catheterization. There exists a need for non-invasive, safe, and fast diagnostic testing for CAD and elevated LVEDP. This research employs nonlinear dynamics to assess for significant CAD and elevated LVEDP using non-invasively acquired photoplethysmographic (PPG) and three-dimensional orthogonal voltage gradient (OVG) signals. PPG (variations of the blood volume perfusing the tissue) and OVG (mechano-electrical activity of the heart) signals represent the dynamics of the cardiovascular system. Methods PPG and OVG were simultaneously acquired from two cohorts, (i) symptomatic subjects that underwent invasive cardiac catheterization, the gold standard test (408 CAD positive with stenosis≥ 70% and 186 with LVEDP≥ 20 mmHg) and (ii) asymptomatic healthy controls (676). A set of Poincare-based synchrony features were developed to characterize the interactions between the OVG and PPG signals. The extracted features were employed to train machine learning models for CAD and LVEDP. Five-fold cross-validation was used and the best model was selected based on the average area under the receiver operating characteristic curve (AUC) across 100 runs, then assessed using a hold-out test set. Results The Elastic Net model developed on the synchrony features can effectively classify CAD positive subjects from healthy controls with an average validation AUC=0.90±0.03 and an AUC= 0.89 on the test set. The developed model for LVEDP can discriminate subjects with elevated LVEDP from healthy controls with an average validation AUC=0.89±0.03 and an AUC=0.89 on the test set. The feature contributions results showed that the selection of a proper registration point for Poincare analysis is essential for the development of predictive models for different disease targets. Conclusions Nonlinear features from simultaneously-acquired signals used as inputs to machine learning can assess CAD and LVEDP safely and accurately with an easy-to-use, portable device, utilized at the point-of-care without radiation, contrast, or patient preparation.

Background Artificial intelligence (AI) techniques are increasingly applied to cardiovascular (CV) medicine in arenas ranging from genomics to cardiac imaging analysis. Cardiac Phase Space Tomography Analysis (cPSTA), employing machine-learned linear models from an elastic net method optimized by a genetic algorithm, analyzes thoracic phase signals to identify unique mathematical and tomographic features associated with the presence of flow-limiting coronary artery disease (CAD). This novel approach does not require radiation, contrast media, exercise, or pharmacological stress. The objective of this trial was to determine the diagnostic performance of cPSTA in assessing CAD in patients presenting with chest pain who had been referred by their physician for coronary angiography. Methods This prospective, multicenter, non-significant risk study was designed to: 1) develop machine-learned algorithms to assess the presence of CAD (defined as one or more ≥ 70% stenosis, or fractional flow reserve ≤ 0.80) and 2) test the accuracy of these algorithms prospectively in a naive verification cohort. This report is an analysis of phase signals acquired from 606 subjects at rest just prior to angiography. From the collective phase signal data, features were extracted and paired with the known angiographic results. A development set, consisting of signals from 512 subjects, was used for machine learning to determine an algorithm that correlated with significant CAD. Verification testing of the algorithm was performed utilizing previously untested phase signals from 94 subjects. Results The machine-learned algorithm had a sensitivity of 92% (95% CI: 74%-100%) and specificity of 62% (95% CI: 51%-74%) on blind testing in the verification cohort. The negative predictive value (NPV) was 96% (95% CI: 85%-100%). Conclusions These initial multicenter results suggest that resting cPSTA may have comparable diagnostic utility to functional tests currently used to assess CAD without requiring cardiac stress (exercise or pharmacological) or exposure of the patient to radioactivity.

We present a method for automating the measurement of upper thermal limits in small aquatic organisms. Upper thermal limits are frequently defined by the cessation of movement at high temperature, with measurement being performed by manual observation. Consequently, estimates of upper thermal limits may be subject to error and bias, both within and among observers. Our method utilises video-based tracking software to record the movement of individuals when exposed to high, lethal temperatures. We develop an algorithm in the R computing language that can objectively identify the loss of locomotory function from tracking data. Using independent experimental data, we validate our approach by demonstrating the expected response in upper thermal limits to acclimation temperature. © 2018. Published by The Company of Biologists Ltd http://creativecommons.org/licenses/by/3.0 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution and reproduction in any medium provided that the original work is properly attributed.

Machine learning utilizing convolutional neural networks and elastic net combined with a novel cardiac phase space tomography (cPST) now permits rapid analysis of thoracic phase signals for the assessment of coronary artery disease. This new approach does not require radiation, exercise, or

All NHS hospital trusts are required to operate morbidity and mortality (M&M) meetings as a part of their clinical governance. Typically, these review deaths occurring among inpatients and are regarded as an important patient safety measure despite heterogeneous approaches and a lack of proven

Machine learning through convolutional neural networks and elastic net combined with a novel form of cardiac phase space tomography (cPST) now permits rapid analysis of thoracic phase signals for the assessment of coronary artery disease (CAD). Single photon emission computed tomography (SPECT) is

A new pedestrian crossing opened in 2015 to visitors of Harlech Castle providing level access to the castle from the newly opened visitor centre. The installation of the new footbridge was possibly the most ambitious construction project to take place at Harlech since the building of the castle itself. This paper details how the client’s aspirations for the footbridge have been fulfilled by the designers, the fabricator and the wider construction team and the challenges they all faced to ensure the scheme made a successful contribution to the local econony.

The various models of the role of the personnel function tend to allude only in part, if at all, to personnel's role in change management. In examining personnel's role in change processes, the authors devised a five-fold model or typology—the ‘charabanc of change’, based on a metaphorical coach journey designed to capture the dynamic, mobile qualities of change. Early research demonstrated that the model was valid and comprehensible for both personnel practitioners and employees in general, and that the ‘navigator's’ role was likely to be an appropriate one for a personnel specialist involved in organizational change. This article: —Briefly reviews the changing role of personnel—over time, between organisations and within organizations; —recaps on existing models of the function; —delineates the ‘charabanc of change’ typology; —reports on the initial research, based on the management change initiative ‘Investors in People’ at a large UK hospital. The authors conclude that the effectiveness of their metaphorical typology rests on: the ease with which the analogy is grasped; the degree to which it is capable of further extension; and its value as a heuristic device leading to deeper levels of understanding of personnel's role in change initiatives. They consider that an area for further research would involve utilizing the ‘charabanc of change’ model to investigate the combinations of roles that are exhibited by the personnel function in an organization undergoing change. © 1998 John Wiley & Sons, Ltd.

Some beta-blockers are less effective in reducing central blood pressure than other antihypertensive drugs, which may explain the higher rate of events in subjects randomized to atenolol in recent trials. We hypothesized that nebivolol, a mixed beta-blocker/nitro-vasodilator, would be more effective than atenolol in reducing central blood pressure and augmentation index (AIx). The aim of the present study was to test this in a double-blind, randomized, cross-over study, in a cohort of subjects with isolated systolic hypertension.Following a 2-week placebo run-in, 16 never-treated hypertensive subjects received atenolol (50 mg), nebivolol (5 mg) and placebo, each for 5 weeks, in a random order. Seated brachial blood pressure and heart rate were measured. Aortic blood pressure, AIx and pulse wave velocity (PWV) were assessed non-invasively.The placebo-corrected fall in brachial pressure was similar between nebivolol and atenolol, as was the reduction in PWV (mean change +/- SEM: -1.0 +/- 0.3 and -1.2 +/- 0.2 m/s; P = 0.2). However, there was less reduction in heart rate (-19 +/- 2 versus -23 +/- 2 beats/min; P0.01) and increase in AIx (+6 +/- 1 versus +10 +/- 1%; P = 0.04), following nebivolol. Aortic pulse pressure was significantly lower (50 +/- 2 versus 54 +/- 2 mmHg; P = 0.02) after nebivolol. N-terminal pro-B-type natriuretic peptide (proBNP) rose on both drugs (100 +/- 33 versus 75 +/- 80 pg/ml; P0.01 for both, NS for comparison).Nebivolol and atenolol have similar effects on brachial blood pressure and aortic stiffness. However, nebivolol reduces aortic pulse pressure more than atenolol, which may be related to a less pronounced rise in AIx and bradycardia. Whether this will translate into differences in clinical outcome requires further investigation.

Statistical Energy Analysis (SEA) has traditionally been effective at predicting the transmission of acoustic power between structure and fluid and acoustic transmission between two fluids through a plate. Until recently, SEA has been less effective at predicting the vibrational power transmission directly between structural components. Modern predictive SEA, incorporating multi-wave beam and shell subsystems and more sophisticated models of the dynamics of structural joints, is better equipped to predict the direct vibration transmission problem. We compare predictions using the modern predictive SEA code AutoSEA with measurements of noise and vibration response on a carefully constructed laboratory test structure that incorporates some of the complexities seen in real aerospace structural-acoustic design applications. The test structure consists of 26 plates bounding five interior acoustic cavities, and connected together by “L” and “T” section beam-like elements. A series of comparisons between predictive SEA and test include both structural vibration and interior sound-pressure-level response to structural excitation. These calculations and comparisons reveal uncertainties and biases in the predictions that are significant but small enough to allow the method to be used with confidence.

A beam which is line-connected to a plate is a commonly encountered arrangement in structure-borne noise studies (Figure 1). The modeling of the transmission of vibrational energy through this assembly using Statistical Energy Analysis (SEA) raises several issues. [1]

The author describes methods of handling medication in resistant patients. He shows us how such methods can aid psychiatrists and nonmedical staff in collaborating against barriers to effective treatment.