Machine learning-based prediction of in-hospital death for patients with takotsubo syndrome: The InterTAK-ML model

AIMS

Takotsubo syndrome (TTS) is associated with a substantial rate of adverse events. We sought to design a machine learning (ML)-based model to predict the risk of in-hospital death and to perform a clustering of TTS patients to identify different risk profiles.

METHODS AND RESULTS

A ridge logistic regression-based ML model for predicting in-hospital death was developed on 3482 TTS patients from the International Takotsubo (InterTAK) Registry, randomly split in a train and an internal validation cohort (75% and 25% of the sample size, respectively) and evaluated in an external validation cohort (1037 patients). Thirty-one clinically relevant variables were included in the prediction model. Model performance represented the primary endpoint and was assessed according to area under the curve (AUC), sensitivity and specificity. As secondary endpoint, a K-medoids clustering algorithm was designed to stratify patients into phenotypic groups based on the 10 most relevant features emerging from the main model. The overall incidence of in-hospital death was 5.2%. The InterTAK-ML model showed an AUC of 0.89 (0.85-0.92), a sensitivity of 0.85 (0.78-0.95) and a specificity of 0.76 (0.74-0.79) in the internal validation cohort and an AUC of 0.82 (0.73-0.91), a sensitivity of 0.74 (0.61-0.87) and a specificity of 0.79 (0.77-0.81) in the external cohort for in-hospital death prediction. By exploiting the 10 variables showing the highest feature importance, TTS patients were clustered into six groups associated with different risks of in-hospital death (28.8% vs. 15.5% vs. 5.4% vs. 1.0.8% vs. 0.5%) which were consistent also in the external cohort.

CONCLUSION

A ML-based approach for the identification of TTS patients at risk of adverse short-term prognosis is feasible and effective. The InterTAK-ML model showed unprecedented discriminative capability for the prediction of in-hospital death.

An Unusual Cause of Coronary Occlusion During an Abdominal Aortic Aneurysm Repair: Reperfusion With Diagnostic Angiography Only

We present a unique case of a type I peri-operative myocardial infarction during an extensive abdominal aortic aneurysm repair occurring due to the occlusion of a severe stable ostial plaque stenosis by a small overlying thrombus. During coronary angiography, the thrombus was dislodged by the diagnostic catheter which restored normal flow without stent placement. We demonstrate a care approach that was carefully arrived upon through multidisciplinary management with vascular surgery and anesthesiology colleagues.

Transcatheter mitral valve-in-valve and valve-in-ring replacement: Lessons learned from bioprosthetic surgical valve failures

INTRODUCTION

Limited data are available about the outcomes of transcatheter mitral valve replacement (TMVR) using transseptal approach in patients with prior mitral valve repair (valve-in-ring) or replacement (valve-in-valve) (TMViVR) and on modes of the prior surgical valve failures. We report our tertiary center TMVR experience in high surgical risk patients with prior mitral valve repair or replacement.

METHODS

From December 2016 to January 2020, patients with symptomatic severe mitral valve stenosis and/or insufficiency at increased redo surgical risk were included. TMViVR was performed off-label with Sapien S3 valve (Edwards Lifesciences). Patients were followed within 30-days and 1-year from the procedure.

RESULTS

Twenty-seven patients underwent transcatheter mitral valve-in-valve (n = 21) or valve-in-ring (n = 6) replacement. Mean ± SD age was 71.8 ± 11 years with Society of Thoracic Surgeons' calculated mortality 7.1 ± 4.6%. The etiology of valve failure was stenosis in 17 (63%) patients, insufficiency in 4 (14.8%) patients, and both in 6 (22.2%) patients. TMViVR technical success was 100% in all patients. Left ventricular outflow track (LVOT) obstruction was observed in only one (3.7%) patient. Zero patients had moderate or severe central mitral valve regurgitation or paravalvular leak. All patients had symptomatic improvement at 30 days. The mean transmitral diastolic pressure gradient decreased from 14.1 ± 4.6 to 6.9 ± 4.6 mm Hg (p < .001) at 30 days. The one patient with LOVT obstruction required readmission at 5-months. One-year survival was 95%. At 1-year mean gradients remained lower than the baseline (7.0 ± 3.0 vs. 12.4 ± 4.0, p = .002).

CONCLUSIONS

Transcatheter mitral valve-in-valve and valve-in-ring replacement is feasible and safe. The improvement in mitral valve hemodynamics appears to be durable.

Diagnostic Performance of High-Sensitivity Cardiac Troponin T Strategies and Clinical Variables in a Multisite US Cohort

BACKGROUND

European data support the use of low high-sensitivity troponin (hs-cTn) measurements or a 0/1-hour (0/1-h) algorithm for myocardial infarction to exclude major adverse cardiac events (MACEs) among patients in the emergency department with possible acute coronary syndrome. However, modest US data exist to validate these strategies. This study evaluated the diagnostic performance of an initial hs-cTnT measure below the limit of quantification (LOQ: 6 ng/L), a 0/1-h algorithm, and their combination with history, ECG, age, risk factors, and initial troponin (HEART) scores for excluding MACE in a multisite US cohort.

METHODS

A prospective cohort study was conducted at 8 US sites, enrolling adult patients in the emergency department with symptoms suggestive of acute coronary syndrome and without ST-elevation on ECG. Baseline and 1-hour blood samples were collected, and hs-cTnT (Roche; Basel, Switzerland) was measured. Treating providers blinded to hs-cTnT results prospectively calculated HEART scores. MACE (cardiac death, myocardial infarction, and coronary revascularization) at 30 days was adjudicated. The proportion of patients with initial hs-cTnT measures below the LOQ and risk according to a 0/1-h algorithm was determined. The negative predictive value (NPV) was calculated for both strategies when used alone or with a HEART score.

RESULTS

Among 1462 participants with initial hs-cTnT measures, 46.4% (678 of 1462) were women and 37.1% (542 of 1462) were Black with an age of 57.6±12.9 (mean±SD) years. MACEs at 30 days occurred in 14.4% (210 of 1462) of participants. Initial hs-cTnT measures below the LOQ occurred in 32.8% (479 of 1462), yielding an NPV of 98.3% (95% CI, 96.7-99.3) for 30-day MACEs. A low-risk HEART score with an initial hs-cTnT below the LOQ occurred in 20.1% (294 of 1462), yielding an NPV of 99.0% (95% CI, 97.0-99.8) for 30-day MACEs. A 0/1-h algorithm was complete in 1430 patients, ruling out 57.8% (826 of 1430) with an NPV of 97.2% (95% CI, 95.9-98.2) for 30-day MACEs. Adding a low HEART score to the 0/1-h algorithm ruled out 30.8% (441 of 1430) with an NPV of 98.4% (95% CI, 96.8-99.4) for 30-day MACEs.

CONCLUSIONS

In a prospective multisite US cohort, an initial hs-cTnT below the LOQ combined with a low-risk HEART score has a 99% NPV for 30-day MACEs. The 0/1-h hs-cTnT algorithm did not achieve an NPV >99% for 30-day MACEs when used alone or with a HEART score. Registration: URL: https://www.clinicaltrials.gov; Unique identifier: NCT02984436.

Evaluation of European Society of Cardiology (ESC) 0/1-hour algorithm in the diagnosis of 90-day major adverse cardiovascular events: a multicenter United States cohort study

Background

The ESC 0/1-hour algorithm using high sensitivity troponin (ESC 0/1-h) is a rapid triage protocol for diagnosing acute coronary syndrome, however the classification performance of the algorithm in the US population is uncertain. Further, evidence for the use of ESC 0/1-h in the long-term diagnosis of major adverse cardiovascular events (MACE) remains limited.

Purpose

To evaluate the performance of the ESC 0/1-h algorithm in diagnosing 90-day MACE in a diverse US cohort.

Methods

In this prospective, multicenter, observational cohort study, adult emergency department patients who were evaluated for suspected ACS were enrolled at eight sites in the US. Serial 1-hour blood samples were collected and high sensitivity troponin T (hs-cTnT) concentrations were measured in a central laboratory using the hs-cTnT assay. Primary outcome included major adverse cardiovascular events (MACE) within 90 (+30) days of enrollment. MACE defined as myocardial infarction (MI), cardiovascular or uncertain death, and coronary revascularization. Presence of MI and cardiovascular death were adjudicated by independent reviewers blinded to hs-cTnT results. Each participant was stratified to one of three risk groups as determined by ESC 0/1-h algorithm. Diagnostic classification performance metrics with exact confidence intervals (i.e. negative predictive value [NPV], positive predicted value [PPV], sensitivity, and specificity) were evaluated for each risk group where appropriate.

Results

Among 1430 eligible participants, 45.8% (655/1430) were women and 36.6% (524/1430) were African American with a mean age of 57.6±12.8 years. MACE at 90-days occurred in 15.5% (221/1430). ESC 0/1-h stratified 59.5% (851/1430) subjects in Rule-Out range and 13.0% (186/1430) subjects in Rule-In range. The Rule-Out criteria had an NPV and sensitivity for 90-day MACE of 96.8% (95% CI: 95.4–97.9%) and 87.8% (95% CI: 82.7–91.8%), respectively. For 90-day cardiovascular death or MI, Rule-Out criteria had an NPV of 98.2% (95% CI: 97.1–99.0%) and sensitivity was 92.4% (95% CI: 87.8–95.7%). The Rule-In criteria had a PPV of 60.8% (95% CI: 53.3–67.8%) for both outcomes. Rule-In criteria had a specificity for 90-day MACE and 90-day cardiovascular death or MI of 94.0% (95% CI: 92.5–95.2%) and 94.1% (95% CI: 92.6–95.3%), respectively. Among the 27.5% (393/1430) participants classified in neither risk groups, the prevalence of 90-day MACE was 20.6% (81/393) and the prevalence of 90-day cardiovascular death or MI was 17.8% (70/393)

Conclusion

In a prospective, multicenter, US cohort, the ESC 0/1-h algorithm was unable to achieve a sufficiently high NPV to safely exclude the diagnosis of MACE within 90 days after emergency department presentation. New hs-cTn algorithms specific to the US population may be warranted.

ESC 0/1-h 90 Day Outcomes

Funding Acknowledgement

Type of funding source: Private company. Main funding source(s): Roche Diagnostics