Deep learning model to predict exercise stress test results: Optimizing the diagnostic test selection strategy and reduce wastage in suspected coronary artery disease patients.

BACKGROUND: Cardiac exercise stress testing (EST) offers a non-invasive way in the management of patients with suspected coronary artery disease (CAD). However, up to 30% EST results are either inconclusive or non-diagnostic, which results in significant resource wastage. Our aim was to build machine learning (ML) based models, using patients demographic (age, sex) and pre-test clinical information (reason for performing test, medications, blood pressure, heart rate, and resting electrocardiogram), capable of predicting EST results beforehand including those with inconclusive or non-diagnostic results. METHODS: A total of 30,710 patients (mean age 54.0 years, 69% male) were included in the study with 25% randomly sampled in the test set, and the remaining samples were split into a train and validation set with a ratio of 9:1. We constructed different ML models from pre-test variables and compared their discriminant power using the area under the receiver operating characteristic curve (AUC). RESULTS: A network of Oblivious Decision Trees provided the best discriminant power (AUC=0.83, sensitivity=69%, specificity=0.78%) for predicting inconclusive EST results. A total of 2010 inconclusive ESTs were correctly identified in the testing set. CONCLUSIONS: Our ML model, developed using demographic and pre-test clinical information, can accurately predict EST results and could be used to identify patients with inconclusive or non-diagnostic results beforehand. Our system could thus be used as a personalised decision support tool by clinicians for optimizing the diagnostic test selection strategy for CAD patients and to reduce healthcare expenditure by reducing nondiagnostic or inconclusive ESTs.

Prognostic value of chronic total occlusions detected on coronary computed tomographic angiography.

OBJECTIVE: Data describing clinical relevance of chronic total occlusion (CTO) identified by coronary CT angiography (CCTA) have not been reported to date. We investigated the prognosis of CTO on CCTA. METHODS: We identified 22 828 patients without prior known coronary artery disease (CAD), who were followed for a median of 26 months. Based on CCTA, coronary lesions were graded as normal (no atherosclerosis), non-obstructive (1%-49%), moderate-to-severe (50%-99%) or totally occluded (100%). All-cause mortality, and major adverse cardiac events defined as mortality, non-fatal myocardial infarction and late coronary revascularisation (≥90 days after CCTA) were assessed. RESULTS: The distribution of patients with normal coronaries, non-obstructive CAD, moderate-to-severe CAD and CTO was 10 034 (44%), 7965 (34.9%), 4598 (20.1%) and 231 (1%), respectively. The mortality rate per 1000 person-years of CTO patients was non-significantly different from patients with moderate-to-severe CAD (22.95; 95% CI 12.71 to 41.45 vs 14.46; 95% CI 12.34 to 16.94; p=0.163), and significantly higher than of those with normal coronaries and non-obstructive CAD (p<0.001 for both). Among 14 382 individuals with follow-up for the composite end point, patients with CTO had a higher rate of events than those with moderate-to-severe CAD (106.56; 95% CI 76.51 to 148.42 vs 65.45; 95% CI 58.01 to 73.84, p=0.009). This difference was primarily driven by an increase in late revascularisations in CTO patients (27 of 35 events). After multivariable adjustment, compared with individuals with normal coronaries, the presence of CTO conferred the highest risk for adverse cardiac events (14.54; 95% CI 9.11 to 23.20, p<0.001). CONCLUSIONS: The detection of CTO on non-invasive CCTA is associated with increased rate of late revascularisation but similar 2-year mortality as compared with moderate-to-severe CAD. TRIAL REGISTRATION NUMBER: NCT01443637.

Oral salt and water versus intravenous saline for the prevention of acute kidney injury following contrast-enhanced computed tomography: study protocol for a pilot randomized trial.

BACKGROUND: Although intravenous saline is the accepted prophylactic measure for the prevention of contrast- induced acute kidney injury, the oral route could offer an equivalent, practical, and cost saving approach. A systematic review of randomized trials that compared oral versus intravenous volume expansion for the prevention of radiocontrast-induced nephropathy in patients receiving arterial contrast reported no significant difference in the risk of contrast induced acute kidney injury between the oral and intravenous arms. Most trials for contrast nephropathy prevention have been in the setting of arterial contrast such as with cardiac catheterization, and not with venous contrast, such as computed tomography. The aim of this paper is to describe the protocol of a pilot trial comparing the effect of oral salt and water versus intravenous saline on the prevention of Acute Kidney Injury following contrast-enhanced computed tomography. METHODS: Our study is a pilot, single-centre parallel randomized controlled trial. To be included, participants must be at stage 4 of chronic kidney disease as defined by a glomerular filtration rate <30 mL/min/1.73 m(2), aged greater than 18 years and to undergo an outpatient contrast-enhanced computer tomography of the chest or abdomen. A total 50 patients will be randomised to receive either oral salt and water or intravenous isotonic saline. The primary outcome is feasibility, including estimates of recruitment rate, adherence to intervention and completeness of follow-up to assist in planning the definitive trial. The secondary outcome is safety and includes adverse events with oral salt and water loading as compared to intravenous isotonic saline. DISCUSSION: The results of this pilot trial will provide critical information to plan a definitive trial to test the efficacy of the route of volume loading regimens in prevention of acute kidney injury after contrast-enhanced CT scans. TRIAL REGISTRATION: The trial is registered at the US National Institutes of Health (ClinicalTrials.gov) # NCT02084771.

CONTEXTE: L'administration prophylactique de solution saline par voie intraveineuse est utilisée pour la prévention de l'insuffisance rénale aiguë (IRA) secondaire aux produits de contraste iodés (PCI). Cependant, une administration par voie orale pourrait être un traitement alternatif équivalent, pratique et économique. Une revue systématique des essais cliniques à répartition aléatoire, qui comparaient les volémies post-administration orale, d'une part, et intraveineuse, d'autre part, de solution saline dans la prévention des néphropathies secondaires aux PCI de patients qui recevaient un agent de contraste par voie artérielle, a été effectuée. Aucun écart significatif en matière de risque d'IRA secondaire aux PCI n'a été observé entre les deux groupes à l'étude. La plupart des essais traitant de prévention des néphropathies secondaire aux PCI ont été effectués en contexte d'administration artérielle, comme par cathétérisme cardiaque, et non d'administration veineuse, comme par tomodensitométrie. Le but de cet article est de décrire le protocole d'un essai comparatif pilote des effets d' une solution saline administrée par voie orale à ceux d'une solution saline isotonique administrée par voie intraveineuse dans la prévention de l'insuffisance rénale aiguë secondaire à la tomodensitométrie avec injection d'agent de contraste. MÉTHODE: Notre étude est un essai comparatif pilote, unicentrique, à répartition aléatoire. Seuls les participants atteints de maladie rénale chronique de stade 4, définie par un débit de filtration glomérulaire < 30 ml/min/1,73m2, âgés de plus de 18 ans, et devant subir une tomodensitométrie avec agent de contraste du thorax ou de l'abdomen en clinique externe, pourront faire partie de l'échantillon. L'administration d'eau salée par voie orale ou de solution saline isotonique par voie intraveineuse sera répartie aléatoirement sur 50 patients. Les premières conclusions de l'étude aideront à planifier l'essai définitif. Celles-ci concernent la faisabilité, dont les estimations du taux de recrutement, d'adhésion à l'intervention et d'achèvement du suivi. Les conclusions secondaires se rapportent à la sécurité et font part, entre autres, d'une comparaison des effets indésirables de l'administration orale d'eau salée et de l'administration intraveineuse de solution saline isotonique. DISCUSSION: Les résultats de cet essai pilote fourniront de l'information cruciale pour la planification de l'essai définitif visant à tester l'efficacité des voies d'administration des traitements de prévention d'IRA après les tomodensitométries avec agent de contraste.

Individual patient data meta-analysis for the clinical assessment of coronary computed tomography angiography: protocol of the Collaborative Meta-Analysis of Cardiac CT (CoMe-CCT).

BACKGROUND: Coronary computed tomography angiography has become the foremost noninvasive imaging modality of the coronary arteries and is used as an alternative to the reference standard, conventional coronary angiography, for direct visualization and detection of coronary artery stenoses in patients with suspected coronary artery disease. Nevertheless, there is considerable debate regarding the optimal target population to maximize clinical performance and patient benefit. The most obvious indication for noninvasive coronary computed tomography angiography in patients with suspected coronary artery disease would be to reliably exclude significant stenosis and, thus, avoid unnecessary invasive conventional coronary angiography. To do this, a test should have, at clinically appropriate pretest likelihoods, minimal false-negative outcomes resulting in a high negative predictive value. However, little is known about the influence of patient characteristics on the clinical predictive values of coronary computed tomography angiography. Previous regular systematic reviews and meta-analyses had to rely on limited summary patient cohort data offered by primary studies. Performing an individual patient data meta-analysis will enable a much more detailed and powerful analysis and thus increase representativeness and generalizability of the results. The individual patient data meta-analysis is registered with the PROSPERO database (CoMe-CCT, CRD42012002780). METHODS/DESIGN: The analysis will include individual patient data from published and unpublished prospective diagnostic accuracy studies comparing coronary computed tomography angiography with conventional coronary angiography. These studies will be identified performing a systematic search in several electronic databases. Corresponding authors will be contacted and asked to provide obligatory and additional data. Risk factors, previous test results and symptoms of individual patients will be used to estimate the pretest likelihood of coronary artery disease. A bivariate random-effects model will be used to calculate pooled mean negative and positive predictive values as well as sensitivity and specificity. The primary outcome of interest will be positive and negative predictive values of coronary computed tomography angiography for the presence of coronary artery disease as a function of pretest likelihood of coronary artery disease, analyzed by meta-regression. As a secondary endpoint, factors that may influence the diagnostic performance and clinical value of computed tomography, such as heart rate and body mass index of patients, number of detector rows, and administration of beta blockade and nitroglycerin, will be investigated by integrating them as further covariates into the bivariate random-effects model. DISCUSSION: This collaborative individual patient data meta-analysis should provide answers to the pivotal question of which patients benefit most from noninvasive coronary computed tomography angiography and thus help to adequately select the right patients for this test.