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.

Painful left bundle branch block syndrome successfully treated by His-bundle pacing

Painful left bundle branch block (LBBB) syndrome is a rare cause of episodic chest pain associated with transient LBBB in the absence of flow-limiting coronary artery disease and myocardial ischaemia on functional testing. The aetiology of this phenomenon is not clear, but in many reported cases, these transient episodes of LBBB are rate related. The mechanism of chest pain is not well understood. Still, it is postulated that sudden loss of the ventricular contraction synchrony, which happens in LBBB, will induce a different perception of heartbeat in the brain with possible translation to the chest pain. Various treatment modalities were attempted in the past, including exercise training, medical therapy with beta-blockers and calcium channel blockers or device therapy with right ventricle pacing, biventricular pacing and lately, His-bundle pacing. This case report presents a woman with intermittent episodes of typical angina with periodic LBBB changes on her ECG. Telemetry monitoring and treadmill exercise tests show a 100% association between angina episodes and LBBB changes on ECG. Her transthoracic echocardiogram shows normal left ventricle structure and function, and her coronary angiogram shows no flow-limiting coronary artery disease. She has been successfully treated by His-bundle pacing, and her symptoms entirely resolved on her serial follow-up.

Temporal endurance of exercise-induced benefits on hippocampus-dependent memory and synaptic plasticity in female mice

Exercise facilitates hippocampal neurogenesis and neuroplasticity that in turn, promotes cognitive function. Our previous studies have demonstrated that in male mice, voluntary exercise enables hippocampus-dependent learning in conditions that are normally subthreshold for long-term memory formation in sedentary animals. Such cognitive enhancement can be maintained long after exercise has ceased and can be re-engaged by a subsequent subthreshold exercise session, suggesting exercise-induced benefits are temporally dynamic. In females, the extent to which the benefits of exercise can be maintained and the mechanisms underlying this maintenance have yet to be defined. Here, we examined the exercise parameters required to initiate and maintain the benefits of exercise in female C57BL/6J mice. Using a subthreshold version of the hippocampus-dependent task called object-location memory (OLM) task, we show that 14d of voluntary exercise enables learning under subthreshold acquisition conditions in female mice. Following the initial exercise, a 7d sedentary delay results in diminished performance, which can be re-facilitated when animals receive 2d of reactivating exercise following the sedentary delay. Assessment of estrous cycle reveals enhanced wheel running activity during the estrus phase relative to the diestrus phase, whereas estrous phase on training or test had no effect on OLM performance. Utilizing the same exercise parameters, we demonstrate that 14d of exercise enhances long-term potentiation (LTP) in the CA1 region of the hippocampus, an effect that persists throughout the sedentary delay and following the reactivating exercise session. Previous studies have proposed exercise-induced BDNF upregulation as the mechanism underlying exercise-mediated benefits on synaptic plasticity and cognition. However, our assessment of hippocampal Bdnf mRNA expression following memory retrieval reveals no difference between exercise conditions and control, suggesting that persistent Bdnf upregulation may not be required for maintenance of exercise-induced benefits. Together, our data indicate that 14d of voluntary exercise can initiate long-lasting benefits on neuroplasticity and cognitive function in female mice, establishing the first evidence on the temporal endurance of exercise-induced benefits in females.

Age-Related Variations in Takotsubo Syndrome

BACKGROUND

Takotsubo syndrome (TTS) occurs predominantly in post-menopausal women but is also found in younger patients.

OBJECTIVES

This study aimed to investigate age-related differences in TTS.

METHODS

Patients diagnosed with TTS and enrolled in the International Takotsubo Registry between January 2011 and February 2017 were included in this analysis and were stratified by age (younger: ≤50 years, middle-age: 51 to 74 years, elderly: ≥75 years). Baseline characteristics, hospital course, as well as short- and long-term mortality were compared among groups.

RESULTS

Of 2,098 TTS patients, 242 (11.5%) patients were ≤50 years of age, 1,194 (56.9%) were 51 to 74 years of age, and 662 (31.6%) were ≥75 years of age. Younger patients were more often men (12.4% vs. 10.9% vs. 6.3%; p = 0.002) and had an increased prevalence of acute neurological (16.3% vs. 8.4% vs. 8.8%; p = 0.001) or psychiatric disorders (14.1% vs. 10.3% vs. 5.6%; p < 0.001) compared with middle-aged and elderly TTS patients. Furthermore, younger patients had more often cardiogenic shock (15.3% vs. 9.1% vs. 8.1%; p = 0.004) and had a numerically higher in-hospital mortality (6.6% vs. 3.6% vs. 5.1%; p = 0.07). At multivariable analysis, younger (odds ratio: 1.60; 95% confidence interval: 0.86 to 3.01; p = 0.14) and older age (odds ratio: 1.09; 95% confidence interval: 0.66 to 1.80; p = 0.75) were not independently associated with in-hospital mortality using the middle-aged group as a reference. There were no differences in 60-day mortality rates among groups.

CONCLUSIONS

A substantial proportion of TTS patients are younger than 50 years of age. TTS is associated with severe complications requiring intensive care, particularly in younger patients.

Solvent-free iridium-catalyzed CO2 hydrosilylation: experiments and kinetic modeling

Solvent-free iridium(iii)-catalyzed CO₂ hydrosilylation to silylformate and kinetic modeling of such reaction are reported.

Ureteroneocystostomy with and without the use of an intravesical catheter

PURPOSE: Assessment of postoperative pain, analgesic requirements, bladder spasms, nosocomial urinary tract infections, length of hospital stay and outcome of "no catheter" versus catheterized intravesical ureteric reimplantation. MATERIALS AND METHODS: Over a 1 year period, 33 patients (24F, 9M) aged 3-14 years with surgical indications for ureteroneocystostomy were randomly assigned to a "no catheter" or "catheter" group. Intravesical ureteric reimplantation was performed in all patients. Post-operatively patients were given intravenous morphine for pain control and pain was assessed by a pain scale and by interviewing patients and parents regarding pain control. Urine cultures were performed on the day of surgery, and first and third postoperative days. Patients were followed post-operatively at 6 weeks with a renal ultrasound and at 3 months with a voiding or nuclear cystogram. Postoperative analgesic requirements, occurrence of bladder spasms, urinary tract infection rate, length of hospital stay and outcome as regards cure of vesicoureteric reflux were recorded. Student's paired t test was used for evaluation of statistical difference between groups. RESULTS: There was no difference in sex distribution, mean age or body weight, or nosocomial urinary tract infection rate between the 2 groups. Post-operative intravenous morphine requirement was significantly lower (p<0.05) in the "no catheter" group (mean +/- Standard Error of Mean (SEM) 0.51 +/- 0.4 mg/kg) versus the "catheter" group (0.89 +/- 0.5 mg/kg). Bladder spasms occurred in 80% of catheterized patients and 30% of non-catheterized patients. Length of hospital stay was significantly shorter (p<0.05) in the "no catheter" group (87.2+/- 19.4 hours) versus the "catheter" group (109.1 +/- 20.9 hours). All patients had stable kidneys by renal ultrasound at 6 weeks and cure of reflux by cystogram at 3 months, regardless of catheter status. CONCLUSION: Intravesical ureteroneocystostomy without a catheter is safe, well tolerated, and associated with significantly lower postoperative intravenous analgesic requirements, shorter hospital stay and fewer bladder spasms than the use of bladder catheters post-reimplantation. "No-catheter" reimplantation did not alter the expected outcome as regards cure of reflux.