Dataset Information

Personalized diagnosis in suspected myocardial infarction.

ABSTRACT:

Background

In suspected myocardial infarction (MI), guidelines recommend using high-sensitivity cardiac troponin (hs-cTn)-based approaches. These require fixed assay-specific thresholds and timepoints, without directly integrating clinical information. Using machine-learning techniques including hs-cTn and clinical routine variables, we aimed to build a digital tool to directly estimate the individual probability of MI, allowing for numerous hs-cTn assays.

Methods

In 2,575 patients presenting to the emergency department with suspected MI, two ensembles of machine-learning models using single or serial concentrations of six different hs-cTn assays were derived to estimate the individual MI probability (ARTEMIS model). Discriminative performance of the models was assessed using area under the receiver operating characteristic curve (AUC) and logLoss. Model performance was validated in an external cohort with 1688 patients and tested for global generalizability in 13 international cohorts with 23,411 patients.

Results

Eleven routinely available variables including age, sex, cardiovascular risk factors, electrocardiography, and hs-cTn were included in the ARTEMIS models. In the validation and generalization cohorts, excellent discriminative performance was confirmed, superior to hs-cTn only. For the serial hs-cTn measurement model, AUC ranged from 0.92 to 0.98. Good calibration was observed. Using a single hs-cTn measurement, the ARTEMIS model allowed direct rule-out of MI with very high and similar safety but up to tripled efficiency compared to the guideline-recommended strategy.

Conclusion

We developed and validated diagnostic models to accurately estimate the individual probability of MI, which allow for variable hs-cTn use and flexible timing of resampling. Their digital application may provide rapid, safe and efficient personalized patient care.

Trial registration numbers

Data of following cohorts were used for this project: BACC ( www.

Clinicaltrials

gov ; NCT02355457), stenoCardia ( www.

Clinicaltrials

gov ; NCT03227159), ADAPT-BSN ( www.australianclinicaltrials.gov.au ; ACTRN12611001069943), IMPACT ( www.australianclinicaltrials.gov.au , ACTRN12611000206921), ADAPT-RCT ( www.anzctr.org.au ; ANZCTR12610000766011), EDACS-RCT ( www.anzctr.org.au ; ANZCTR12613000745741); DROP-ACS ( https://www.umin.ac.jp , UMIN000030668); High-STEACS ( www.

Clinicaltrials

gov ; NCT01852123), LUND ( www.

Clinicaltrials

gov ; NCT05484544), RAPID-CPU ( www.

Clinicaltrials

gov ; NCT03111862), ROMI ( www.

Clinicaltrials

gov ; NCT01994577), SAMIE ( https://anzctr.org.au ; ACTRN12621000053820), SEIGE and SAFETY ( www.

Clinicaltrials

gov ; NCT04772157), STOP-CP ( www.

Clinicaltrials

gov ; NCT02984436), UTROPIA ( www.

Clinicaltrials

gov ; NCT02060760).

SUBMITTER: Neumann JT

PROVIDER: S-EPMC10449973 | biostudies-literature | 2023 Sep

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Personalized diagnosis in suspected myocardial infarction.

Neumann Johannes Tobias JT Twerenbold Raphael R Ojeda Francisco F Aldous Sally J SJ Allen Brandon R BR Apple Fred S FS Babel Hugo H Christenson Robert H RH Cullen Louise L Di Carluccio Eleonora E Doudesis Dimitrios D Ekelund Ulf U Giannitsis Evangelos E Greenslade Jaimi J Inoue Kenji K Jernberg Tomas T Kavsak Peter P Keller Till T Lee Kuan Ken KK Lindahl Bertil B Lorenz Thiess T Mahler Simon A SA Mills Nicholas L NL Mokhtari Arash A Parsonage William W Pickering John W JW Pemberton Christopher J CJ Reich Christoph C Richards A Mark AM Sandoval Yader Y Than Martin P MP Toprak Betül B Troughton Richard W RW Worster Andrew A Zeller Tanja T Ziegler Andreas A Blankenberg Stefan S

Clinical research in cardiology : official journal of the German Cardiac Society 20230502 9

<h4>Background</h4>In suspected myocardial infarction (MI), guidelines recommend using high-sensitivity cardiac troponin (hs-cTn)-based approaches. These require fixed assay-specific thresholds and timepoints, without directly integrating clinical information. Using machine-learning techniques including hs-cTn and clinical routine variables, we aimed to build a digital tool to directly estimate the individual probability of MI, allowing for numerous hs-cTn assays.<h4>Methods</h4>In 2,575 patient ...[more]

PMID: 37131096

Similar Datasets

Project description:BackgroundThe 99th centile of cardiac troponin, derived from a healthy reference population, is recommended as the diagnostic threshold for myocardial infarction, but troponin concentrations are strongly influenced by age. Our aim was to assess the diagnostic performance of cardiac troponin in older patients presenting with suspected myocardial infarction.MethodsIn a secondary analysis of a multicenter trial of consecutive patients with suspected myocardial infarction, we assessed the diagnostic accuracy of high-sensitivity cardiac troponin I at presentation for the diagnosis of type 1, type 2, or type 4b myocardial infarction across 3 age groups (<50, 50-74, and ≥75 years) using guideline-recommended sex-specific and age-adjusted 99th centile thresholds.ResultsIn 46 435 consecutive patients aged 18 to 108 years (mean, 61±17 years), 5216 (11%) had a diagnosis of myocardial infarction. In patients <50 (n=12 379), 50 to 74 (n=22 380), and ≥75 (n=11 676) years, the sensitivity of the guideline-recommended threshold was similar at 79.2% (95% CI, 75.5-82.9), 80.6% (95% CI, 79.2-82.1), and 81.6% (95% CI, 79.8-83.2), respectively. The specificity decreased with advancing age from 98.3% (95% CI, 98.1-98.5) to 95.5% (95% CI, 95.2-95.8), and 82.6% (95% CI, 81.9-83.4). The use of age-adjusted 99th centile thresholds improved the specificity (91.3% [90.8%-91.9%] versus 82.6% [95% CI, 81.9%-83.4%]) and positive predictive value (59.3% [57.0%-61.5%] versus 51.5% [49.9%-53.3%]) for myocardial infarction in patients ≥75 years but failed to prevent the decrease in either parameter with increasing age and resulted in a marked reduction in sensitivity compared with the use of the guideline-recommended threshold (55.9% [53.6%-57.9%] versus 81.6% [79.8%-83.3%].ConclusionsAge alters the diagnostic performance of cardiac troponin, with reduced specificity and positive predictive value in older patients when applying the guideline-recommended or age-adjusted 99th centiles. Individualized diagnostic approaches rather than the adjustment of binary thresholds are needed in an aging population.

Project description:IntroductionCurrent assays based on the 0-hour/1-hour (0-/1-h) algorithm using high-sensitivity cardiac troponin (hs-cTn) are limited to only Abbott Architect hs-cTnI, Siemens Vista hs-cTnI, and Roche Elecsys hs-cTnT.ObjectiveThis study aimed to evaluate this new hs-cTnI assay, LumipulsePresto hs Troponin I, for diagnosis of acute myocardial infarction (AMI) on admission and on 0-/1-h algorithm to stratify AMI patients precisely.MethodsThis prospective cohort study included 442 patients with suspected non-ST-elevation myocardial infarction in three hospitals in Japan and Taiwan from June 2016 to January 2019. We enrolled patients presenting to the emergency department with symptoms suggestive of AMI and collected blood samples on admission and 1 hour later. Two independent cardiologists centrally adjudicated final diagnoses; all clinical information was reviewed twice: first, using serial hs-cTnT (Roche-Elecsys, primary analysis) and Lumipulse Presto Lumipulse Presto, second, using the Lumipulse Presto hs-cTnI measurements. At first, we compared diagnostic accuracy quantified using receiver operating characteristic (ROC) curves for AMI. Then, we evaluated major adverse cardiovascular events (cardiac death, AMI) in the rule-out group according to a 0-hour/1-hour algorithm at the 30-day follow-up.ResultsDiagnostic accuracy at presentation by the ROC curve for AMI was very high and similar for the LumipulsePresto hs-cTnI and hs-cTnT,(area under the curve [AUC]: LumipulsePresto hs-cTnI, 0.89, 95% confidence interval [CI] 0.86-0.93; hs-cTnT, 0.89, 95% CI 0.85-0.93; p = 0.82). In early presenters, the LumipulsePresto hs-cTnI appeared to maintain the diagnostic performance of hs-cTn for patients with <3 h (AUC: LumipulsePresto hs-cTnI, 0.87, 95% CI 0.81-0.92; hs-cTnT, 0.86, 95% CI 0.80-0.92; p = 0.81). The algorithm using the LumipulsePresto hs-cTnI ruled out AMI in 200 patients with negative predictive value and sensitivity of 100% (95% CI 97.3%-100%) and 100% (95% CI 92.7%-100%), respectively, in the rule-out group.ConclusionDiagnostic accuracy and clinical utility of the novel LumipulsePresto hs-cTnI assay are high and comparable with the established hs-cTn assays.

Dataset Information

Personalized diagnosis in suspected myocardial infarction.

Background

Methods

Results

Conclusion

Trial registration numbers

Clinicaltrials

Clinicaltrials

Clinicaltrials

Clinicaltrials

Clinicaltrials

Clinicaltrials

Clinicaltrials

Clinicaltrials

Clinicaltrials

Publications

Personalized diagnosis in suspected myocardial infarction.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets