OBJECTIVE: To employ machine learning (ML) and stacked ensemble learning (EL) methods in predicting short- and long-term mortality in Asian patients diagnosed with NSTEMI/UA and to identify the associated features, subsequently evaluating these findings against established risk scores.
METHODS: We analyzed data from the National Cardiovascular Disease Database for Malaysia (2006-2019), representing a diverse NSTEMI/UA Asian cohort. Algorithm development utilized in-hospital records of 9,518 patients, 30-day data from 7,133 patients, and 1-year data from 7,031 patients. This study utilized 39 features, including demographic, cardiovascular risk, medication, and clinical features. In the development of the stacked EL model, four base learner algorithms were employed: eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Naive Bayes (NB), and Random Forest (RF), with the Generalized Linear Model (GLM) serving as the meta learner. Significant features were chosen and ranked using ML feature importance with backward elimination. The predictive performance of the algorithms was assessed using the area under the curve (AUC) as a metric. Validation of the algorithms was conducted against the TIMI for NSTEMI/UA using a separate validation dataset, and the net reclassification index (NRI) was subsequently determined.
RESULTS: Using both complete and reduced features, the algorithm performance achieved an AUC ranging from 0.73 to 0.89. The top-performing ML algorithm consistently surpassed the TIMI risk score for in-hospital, 30-day, and 1-year predictions (with AUC values of 0.88, 0.88, and 0.81, respectively, all p < 0.001), while the TIMI scores registered significantly lower at 0.55, 0.54, and 0.61. This suggests the TIMI score tends to underestimate patient mortality risk. The net reclassification index (NRI) of the best ML algorithm for NSTEMI/UA patients across these periods yielded an NRI between 40-60% (p < 0.001) relative to the TIMI NSTEMI/UA risk score. Key features identified for both short- and long-term mortality included age, Killip class, heart rate, and Low-Molecular-Weight Heparin (LMWH) administration.
CONCLUSIONS: In a broad multi-ethnic population, ML approaches outperformed conventional TIMI scoring in classifying patients with NSTEMI and UA. ML allows for the precise identification of unique characteristics within individual Asian populations, improving the accuracy of mortality predictions. Continuous development, testing, and validation of these ML algorithms holds the promise of enhanced risk stratification, thereby revolutionizing future management strategies and patient outcomes.
OBJECTIVE: The purpose of this report was to describe the prespecified long-term safety objective of Micra at 12 months and electrical performance through 24 months.
METHODS: The Micra Transcatheter Pacing Study was a prospective single-arm study designed to assess the safety and efficacy of the Micra VVIR leadless/intracardiac pacemaker. Enrolled patients met class I or II guideline recommendations for de novo ventricular pacing. The long-term safety objective was freedom from a system- or procedure-related major complication at 12 months. A predefined historical control group of 2667 patients with transvenous pacemakers was used to compare major complication rates.
RESULTS: The long-term safety objective was achieved with a freedom from major complication rate of 96.0% at 12 months (95% confidence interval 94.2%-97.2%; P < .0001 vs performance goal). The risk of major complications for patients with Micra (N = 726) was 48% lower than that for patients with transvenous systems through 12 months postimplant (hazard ratio 0.52; 95% confidence interval 0.35-0.77; P = .001). Across subgroups of age, sex, and comorbidities, Micra reduced the risk of major complications compared to transvenous systems. Electrical performance was excellent through 24 months, with a projected battery longevity of 12.1 years.
CONCLUSION: Long-term performance of the Micra transcatheter pacemaker remains consistent with previously reported data. Few patients experienced major complications through 12 months of follow-up, and all patient subgroups benefited as compared to transvenous pacemaker historical control group.
OBJECTIVE: The purpose of this study was to report the worldwide experience with successful retrieval of the Micra TPS.
METHODS: A list of all successful retrievals of the currently available leadless pacemakers (LPs) was obtained from the manufacturer of Micra TPS. Pertinent details of retrieval, such as indication, days postimplantation, equipment used, complications, and postretrieval management, were obtained from the database collected by the manufacturer. Other procedural details were obtained directly from the operators at each participating site.
RESULTS: Data from the manufacturer consisted of 40 successful retrievals of the Micra TPS. Operators for 29 retrievals (73%) provided the consent and procedural details. Of the 29 retrievals, 11 patients underwent retrieval during the initial procedure (immediate retrieval); the other 18 patients underwent retrieval during a separate procedure (delayed retrieval). Median duration before delayed retrieval was 46 days (range 1-95 days). The most common reason for immediate retrieval was elevated pacing threshold after tether removal. The most common reasons for delayed retrieval included elevated pacing threshold at follow-up, endovascular infection, and need for transvenous device. Mean procedure duration was 63.11 ± 56 minutes. All retrievals involved snaring via a Micra TPS delivery catheter or steerable sheath. No serious complications occurred during the reported retrievals.
CONCLUSION: Early retrieval of the Micra TPS is feasible and safe.
METHODS AND RESULTS: Sixty-two individuals (24 SARC+LVH-, 24 HCM, and 14 matched controls) were evaluated with multi-parametric CMR including stimulated echo acquisition mode DT-CMR, and blinded quantitative 12-lead ECG analysis. Mean diastolic fractional anisotropy (FA) was reduced in HCM compared with SARC+LVH- and controls (0.49 ± 0.05 vs. 0.52 ± 0.04 vs. 0.53 ± 0.04, P = 0.009), even after adjustment for differences in extracellular volume (ECV) (P = 0.038). Both HCM and SARC+LVH- had segments with significantly reduced diastolic FA relative to controls (54 vs. 25 vs. 0%, P = 0.002). Multiple repolarization parameters were prolonged in HCM and SARC+LVH-, with corrected JT interval (JTc) being most significant (354 ± 42 vs. 356 ± 26 vs. 314 ± 26 ms, P = 0.002). Among SARC+LVH-, JTc duration correlated negatively with mean diastolic FA (r = -0.6, P = 0.002). In HCM, the JTc interval showed a stronger association with ECV (r = 0.6 P = 0.019) than with mean diastolic FA (r = -0.1 P = 0.72). JTc discriminated SARC+LVH- from controls [area under the receiver operator curve 0.88, confidence interval 0.76-1.00, P < 0.001], and in HCM correlated with the European Society of Cardiology HCM sudden cardiac death risk score (r = 0.5, P = 0.014).
CONCLUSION: Low diastolic FA, suggestive of myocardial disarray, is present in both SARC+LVH- and HCM. Low FA and raised ECV were associated with repolarization prolongation. Myocardial disarray assessment using DT-CMR and repolarization parameters such as the JTc interval demonstrate significant potential as markers of disease activity in HCM.
METHODOLOGY: Study participants included a total of 60 final year medical undergraduates during their rotation in Medical Senior Posting. They participated in a simulation exercise using a high fidelity simulator, and their confidence level measured using a self-administered questionnaire.
RESULTS: The results found that the confidence levels of 'Assessment of an Emergency Patient', 'Diagnosing Arrhythmias', 'Emergency Airway Management', 'Performing Cardio-pulmonary Resuscitation', 'Using the Defibrillator' and 'Using Emergency Drugs' showed a statistically significant increase in confidence levels after the simulation exercise. The mean confidence levels also rose from 2.85 to 3.83 (p<0.05).
CONCLUSION: We recommend further use of High Fidelity Simulation in medical education to improve the confidence levels of medical undergraduates.