Projects per year
Abstract
Background: CoDE-ACS is a validated clinical decision-support tool that uses machine learning with or without serial cardiac troponin measurements at a flexible timepoint to calculate the probability of myocardial infarction (MI). How CoDE-ACS performs at different timepoints for serial measurement and compares with guideline recommended diagnostic pathways that rely on fixed thresholds and timepoints is uncertain.
Methods: Patients with possible MI without ST-segment elevation were enrolled at 12 sites in five countries and underwent serial high-sensitivity cardiac troponin I concentration measurement at 0, 1 and 2 hours. Diagnostic performance of the CoDE-ACS model at each timepoint was determined for index type 1 MI and the effectiveness of previously validated low- and high-probability scores compared with guideline recommended ESC 0/1h, ESC 0/2h and High-STEACS pathways.
Results: In total 4,105 patients (age 61 [50-74] years, 32% women) were included where 575 (14%) had type 1 MI. At presentation, CoDE-ACS identified 56% of patients as low-probability, with a negative predictive value and sensitivity of 99.7% (95% confidence interval [CI] 99.5-99.9%) and 99.0% (98.6-99.2%), ruling out more patients than the ESC 0h and High-STEACS (25% and 35%) pathways. CoDE-ACS incorporating a second cTn measurement identified 65% or 68% of patients as low probability at 1 or 2 hours, for an identical negative predictive value of 99.7% (99.5-99.9%), 19% or 18% as high-probability with a positive predictive value of 64.9% (63.5-66.4%) and 68.8% (67.3-70.1%), and 16% or 14% as intermediate probability. In comparison, the ESC 0/1h, ESC 0/2h and High-STEACS pathways after serial measurements identified 49%, 53% and 71% of patients as low-risk with a negative predictive value of 100% (99.9-100%), 100% (99.9-100%) and 99.7% (99.5-99.8%), and 20%, 19% or 29% as high-risk with a positive predictive value of 61.5% (60.0-63.0%), 65.8% (64.3-67.2%), and 48.3% (46.8-49.8%) resulting in 31%, 28% or 0% who require further observation in the Emergency Department, respectively.
Conclusions: CoDE-ACS performs consistently irrespective of the timing of serial cardiac troponin measurement identifying more patients as low-probability with comparable performance to guideline recommended pathways for MI. Whether care guided by probabilities can improve the early diagnosis of MI requires prospective evaluation.
Methods: Patients with possible MI without ST-segment elevation were enrolled at 12 sites in five countries and underwent serial high-sensitivity cardiac troponin I concentration measurement at 0, 1 and 2 hours. Diagnostic performance of the CoDE-ACS model at each timepoint was determined for index type 1 MI and the effectiveness of previously validated low- and high-probability scores compared with guideline recommended ESC 0/1h, ESC 0/2h and High-STEACS pathways.
Results: In total 4,105 patients (age 61 [50-74] years, 32% women) were included where 575 (14%) had type 1 MI. At presentation, CoDE-ACS identified 56% of patients as low-probability, with a negative predictive value and sensitivity of 99.7% (95% confidence interval [CI] 99.5-99.9%) and 99.0% (98.6-99.2%), ruling out more patients than the ESC 0h and High-STEACS (25% and 35%) pathways. CoDE-ACS incorporating a second cTn measurement identified 65% or 68% of patients as low probability at 1 or 2 hours, for an identical negative predictive value of 99.7% (99.5-99.9%), 19% or 18% as high-probability with a positive predictive value of 64.9% (63.5-66.4%) and 68.8% (67.3-70.1%), and 16% or 14% as intermediate probability. In comparison, the ESC 0/1h, ESC 0/2h and High-STEACS pathways after serial measurements identified 49%, 53% and 71% of patients as low-risk with a negative predictive value of 100% (99.9-100%), 100% (99.9-100%) and 99.7% (99.5-99.8%), and 20%, 19% or 29% as high-risk with a positive predictive value of 61.5% (60.0-63.0%), 65.8% (64.3-67.2%), and 48.3% (46.8-49.8%) resulting in 31%, 28% or 0% who require further observation in the Emergency Department, respectively.
Conclusions: CoDE-ACS performs consistently irrespective of the timing of serial cardiac troponin measurement identifying more patients as low-probability with comparable performance to guideline recommended pathways for MI. Whether care guided by probabilities can improve the early diagnosis of MI requires prospective evaluation.
| Original language | English |
|---|---|
| Journal | Circulation |
| DOIs | |
| Publication status | Published - 12 Feb 2024 |
Fingerprint
Dive into the research topics of 'Machine learning for myocardial infarction compared to guideline recommended diagnostic pathways'. Together they form a unique fingerprint.-
High-Sensitivity Cardiac Troponin Beyond the Acute Coronary Syndrome
Mills, N. (Principal Investigator), Anand, A. (Co-investigator), Chapman, A. (Co-investigator), Ferry, A. (Co-investigator), Newby, D. (Co-investigator), Strachan, F. (Co-investigator) & Tsanas, T. (Co-investigator)
1/06/20 → 31/05/25
Project: Research
-
Machine learning and the diagnosis of myocardial infarction
Newby, D. (Principal Investigator) & Mills, N. (Co-investigator)
1/02/21 → 31/01/23
Project: Research
-
Research Excellence Award Number 3
Baker, A. (Principal Investigator)
1/04/19 → 31/03/24
Project: Research
Equipment
-
British Heart Foundation (BHF) Cardiovascular Biomarker Laboratory
Fujisawa, T. (Manager)
Deanery of Clinical SciencesFacility/equipment: Facility