Cardiac intensivists frequently assess patient readiness to wean off mechanical ventilation with an extubation readiness trial despite it being no more effective than clinician judgement alone. We evaluated the utility of high-frequency physiologic data and machine learning for improving the prediction of extubation failure in children with cardiovascular disease.

This was a retrospective analysis of clinical registry data and streamed physiologic extubation readiness trial data from one paediatric cardiac ICU (12/2016-3/2018). We analysed patients’ final extubation readiness trial. Machine learning methods (classification and regression tree, Boosting, Random Forest) were performed using clinical/demographic data, physiologic data, and both datasets. Extubation failure was defined as reintubation within 48 hrs. Classifier performance was assessed on prediction accuracy and area under the receiver operating characteristic curve.

Of 178 episodes, 11.2% (N = 20) failed extubation. Using clinical/demographic data, our machine learning methods identified variables such as age, weight, height, and ventilation duration as being important in predicting extubation failure. Best classifier performance with this data was Boosting (prediction accuracy: 0.88; area under the receiver operating characteristic curve: 0.74). Using physiologic data, our machine learning methods found oxygen saturation extremes and descriptors of dynamic compliance, central venous pressure, and heart/respiratory rate to be of importance. The best classifier in this setting was Random Forest (prediction accuracy: 0.89; area under the receiver operating characteristic curve: 0.75). Combining both datasets produced classifiers highlighting the importance of physiologic variables in determining extubation failure, though predictive performance was not improved.

Physiologic variables not routinely scrutinised during extubation readiness trials were identified as potential extubation failure predictors. Larger analyses are necessary to investigate whether these markers can improve clinical decision-making.

The aim of the study was to evaluate the early myocardial dysfunction detected by strain echocardiography in children with multisystem inflammatory syndrome related to SARS-CoV-2 infection.

This cross-sectional study was conducted with 47 patients diagnosed with MIS-C and 32 healthy age- and gender-matched children. All patients underwent two-dimensional, colour, pulsed, and tissue Doppler, and 2D speckle tracking echocardiography examination at admission, 2 weeks, and 2 months after discharge. The MIS-C patient group was compared with the control group. Echocardiographic changes in MIS-C patients during follow-up were evaluated.

Of 47 patients, 30 (63.8%) were male and 17 (36.2%) were female. The mean age at diagnosis was 9.1 ± 4.3 (1.25–17) years. At admission, 25 patients had abnormal findings on conventional echocardiography. Among them, eight patients had left ventricular systolic dysfunction. Ejection fraction and fractional shortening were significantly lower in the patient group at admission compared to controls (p = 0.013, p = 0.010, respectively). While the ejection fraction was <55% in eight patients, and global longitudinal strain was lower than −2SD in 29 patients at admission. Global longitudinal strain z-score <−2SD persisted in 13 patients at 2-month follow-up. Ejection fraction increased above 55% in 3.42 ± 0.53 days in 7 of 8 patients with left ventricular systolic dysfunction, ejection fraction was 51% at discharge in one patient, and left ventricular systolic dysfunction persisted at the 6-month of follow-up.

These results confirmed that speckle tracking echocardiography is more likely to detect subclinical myocardial damage compared to conventional echocardiography. In addition, it is a valuable method for follow-up in this patient group.

The present study aimed to investigate the outcomes of psychiatric symptoms and family functions on treatment adherence in children, in addition to sociodemographic characteristics and clinical factors related to the disease.

The research sample consisted of 43 children who were followed up with rheumatic heart disease diagnosis during the study. Clinical features were obtained from the patient files. The family assessment device evaluating family functioning and the strengths and difficulties questionnaire scale to screen emotional and behavioural problems in children were used.

Considering the regularity of treatment in our patients, there were 31 (72%) patients adherent to secondary prophylaxis regularly, 7 (6.9%) patients were partially adherent, and 5 (11.6%) patients non-adherent. Patients were divided into treatment adherent (Group 1) and non-adherent (Group 2). There was no statistically significant impact on treatment adherence whether the patients receive enough information, lifestyle, fear of developing adverse effects, fear of addiction, lack of health insurance, difficulties in reaching the drug or hospital. However, the fear of syringes on treatment adherence had an effect statistically significantly (p = 0.047). Forgetting to get a prescription and/or take the drug when the time comes was statistically higher in the non-adherent group (p = 0.009). There was no statistically significant effect of psychosocial factors on treatment adherence between groups.

Providing an effective active recall system, involving primary care workers, providing training on the disease and its management, and a comprehensive pain management programme can improve the process, especially for cases where secondary prophylaxis is missed.