| 1. |
- Neumann, Johannes Tobias, et al.
(author)
-
Personalized diagnosis in suspected myocardial infarction
- 2023
-
In: Clinical Research in Cardiology. - : Springer. - 1861-0684 .- 1861-0692. ; 112, s. 1288-1301
-
Journal article (peer-reviewed)abstract
- Background: In suspected myocardial infarction (MI), guidelines recommend using high-sensitivity cardiac troponin (hscTn)- 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.
|
|
| 2. |
- Taggart, Caelan, et al.
(author)
-
Application of the Universal Definition of Myocardial Infarction in Clinical Practice in Scotland and Sweden
- 2024
-
In: JAMA Network Open. - : American Medical Association (AMA). - 2574-3805. ; 7:4
-
Journal article (peer-reviewed)abstract
- Importance: Whether the diagnostic classifications proposed by the universal definition of myocardial infarction (MI) to identify type 1 MI due to atherothrombosis and type 2 MI due to myocardial oxygen supply-demand imbalance have been applied consistently in clinical practice is unknown.Objective: To evaluate the application of the universal definition of MI in consecutive patients with possible MI across 2 health care systems.Design, Setting, and Participants: This cohort study used data from 2 prospective cohorts enrolling consecutive patients with possible MI in Scotland (2013-2016) and Sweden (2011-2014) to assess accuracy of clinical diagnosis of MI recorded in hospital records for patients with an adjudicated diagnosis of type 1 or type 2 MI. Data were analyzed from August 2022 to February 2023.Main Outcomes and Measures: The main outcome was the proportion of patients with a clinical diagnosis of MI recorded in the hospital records who had type 1 or type 2 MI, adjudicated by an independent panel according to the universal definition. Characteristics and risk of subsequent MI or cardiovascular death at 1 year were compared.Results: A total of 50 356 patients were assessed. The cohort from Scotland included 28 783 (15 562 men [54%]; mean [SD] age, 60 [17] years), and the cohort from Sweden included 21 573 (11 110 men [51%]; mean [SD] age, 56 [17] years) patients. In Scotland, a clinical diagnosis of MI was recorded in 2506 of 3187 patients with an adjudicated diagnosis of type 1 MI (79%) and 122 of 716 patients with an adjudicated diagnosis of type 2 MI (17%). Similar findings were observed in Sweden, with 970 of 1111 patients with adjudicated diagnosis of type 1 MI (87%) and 57 of 251 patients with adjudicated diagnosis of type 2 MI (23%) receiving a clinical diagnosis of MI. Patients with an adjudicated diagnosis of type 1 MI without a clinical diagnosis were more likely to be women (eg, 336 women [49%] vs 909 women [36%] in Scotland; P < .001) and older (mean [SD] age, 71 [14] v 67 [14] years in Scotland, P < .001) and, when adjusting for competing risk from noncardiovascular death, were at similar or increased risk of subsequent MI or cardiovascular death compared with patients with a clinical diagnosis of MI (eg, 29% vs 18% in Scotland; P < .001).Conclusions and Relevance: In this cohort study, the universal definition of MI was not consistently applied in clinical practice, with a minority of patients with type 2 MI identified, and type 1 MI underrecognized in women and older persons, suggesting uncertainty remains regarding the diagnostic criteria or value of the classification.
|
|
