National trends in mechanical ventilation among patients hospitalized with heart failure: a population-based study in Spain (2001-2017)

Interpretable machine learning for 28-day all-cause in-hospital mortality prediction in critically ill patients with heart failure combined with hypertension: A retrospective cohort study based on medical information mart for intensive care database-IV and eICU databases

Background

Heart failure (HF) combined with hypertension is an extremely important cause of in-hospital mortality, especially for the intensive care unit (ICU) patients. However, under intense working pressure, the medical staff are easily overwhelmed by the large number of clinical signals generated in the ICU, which may lead to treatment delay, sub-optimal care, or even wrong clinical decisions. Individual risk stratification is an essential strategy for managing ICU patients with HF combined with hypertension. Artificial intelligence, especially machine learning (ML), can develop superior models to predict the prognosis of these patients. This study aimed to develop a machine learning method to predict the 28-day mortality for ICU patients with HF combined with hypertension.

Methods

We enrolled all critically ill patients with HF combined with hypertension in the Medical Information Mart for IntensiveCare Database-IV (MIMIC-IV, v.1.4) and the eICU Collaborative Research Database (eICU-CRD) from 2008 to 2019. Subsequently, MIMIC-IV was divided into training cohort and testing cohort in an 8:2 ratio, and eICU-CRD was designated as the external validation cohort. The least absolute shrinkage and selection operator (LASSO) Cox regression with internal tenfold cross-validation was used for data dimension reduction and identifying the most valuable predictive features for 28-day mortality. Based on its accuracy and area under the curve (AUC), the best model in the validation cohort was selected. In addition, we utilized the Shapley Additive Explanations (SHAP) method to highlight the importance of model features, analyze the impact of individual features on model output, and visualize an individual’s Shapley values.

Results

A total of 3,458 and 6582 patients with HF combined with hypertension in MIMIC-IV and eICU-CRD were included. The patients, including 1,756 males, had a median (Q1, Q3) age of 75 (65, 84) years. After selection, 22 out of a total of 58 clinical parameters were extracted to develop the machine-learning models. Among four constructed models, the Neural Networks (NN) model performed the best predictive performance with an AUC of 0.764 and 0.674 in the test cohort and external validation cohort, respectively. In addition, a simplified model including seven variables was built based on NN, which also had good predictive performance (AUC: 0.741). Feature importance analysis showed that age, mechanical ventilation (MECHVENT), chloride, bun, anion gap, paraplegia, rdw (RDW), hyperlipidemia, peripheral capillary oxygen saturation (SpO₂), respiratory rate, cerebrovascular disease, heart rate, white blood cell (WBC), international normalized ratio (INR), mean corpuscular hemoglobin concentration (MCHC), glucose, AIDS, mean corpuscular volume (MCV), N-terminal pro-brain natriuretic peptide (Npro. BNP), calcium, renal replacement therapy (RRT), and partial thromboplastin time (PTT) were the top 22 features of the NN model with the greatest impact. Finally, after hyperparameter optimization, SHAP plots were employed to make the NN-based model interpretable with an analytical description of how the constructed model visualizes the prediction of death.

Conclusion

We developed a predictive model to predict the 28-day mortality for ICU patients with HF combined with hypertension, which proved superior to the traditional logistic regression analysis. The SHAP method enables machine learning models to be more interpretable, thereby helping clinicians to better understand the reasoning behind the outcome and assess in-hospital outcomes for critically ill patients.

Association between Respiratory Failure and Clinical Outcomes in Patients with Acute Heart Failure: Analysis of 5 Pooled Clinical Trials

BACKGROUND

Despite a temporal increase in respiratory failure in patients hospitalized with acute heart failure (HF), clinical trials have largely not reported the incidence or associated clinical outcomes for patients requiring mechanical ventilation.

METHODS AND RESULTS

After pooling 5 acute HF clinical trials, we used multivariable logistic regression adjusted for demographics, comorbidities, examinations, and laboratory findings to assess associations between mechanical ventilation and clinical outcomes. Among the 8296 patients, 210 (2.5%) required mechanical ventilation. Age, sex, smoking history, baseline ejection fraction, HF etiology, and the proportion of patients randomized to treatment or placebo in the original clinical trial were similar between groups (all, P > 0.05). Baseline diabetes mellitus was more common in the mechanical ventilation group (P = 0.02), but other comorbidities, including chronic lung disease, were otherwise similar (all P > 0.05). HF rehospitalization at 30 days (12.7% vs 6.6%, P < 0.001) and all-cause 60-day mortality (33.3% vs 6.1%, P < 0.001) was higher among patients requiring mechanical ventilation. After multivariable adjustment, mechanical ventilation use was associated with an increased 30-day HF rehospitalization (odds ratio 2.03; 95% confidence interval, 1.29-3.21, P = 0.002), 30-day mortality (odds ratio 10.40; 95% confidence interval, 7.22-14.98, P < 0.001), and 60-day mortality (odds ratio 7.68; 95% confidence interval, 5.50-10.74, P < 0.001). The influence of mechanical ventilation did not differ by HF etiology or baseline ejection fraction (both, interaction P > 0.20).

CONCLUSIONS

Respiratory failure during an index hospitalization for acute HF was associated with increased rehospitalization and all-cause mortality. The development of respiratory failure during an acute HF admission identifies a particularly vulnerable population, which should be identified for closer monitoring.