Standard vs. Calorie-Dense Immune Nutrition in Haemodynamically Compromised Cardiac Patients: A Prospective Randomized Controlled Pilot Study

The effect of protein provision and exercise therapy on patient-reported and clinical outcomes in intensive care unit survivors: A systematic review

BACKGROUND

Intensive care unit (ICU) survivors deal with long-term health problems, which negatively affect their quality of life (QoL). Nutritional and exercise intervention could prevent the decline of muscle mass and physical functioning which occurs during critical illness. Despite the growing amount of research, robust evidence is lacking.

METHODS

For this systematic review, Embase, PubMed and Cochrane Central Register of Controlled Trials databases were searched. The effect of protein provision (PP) or combined protein and exercise therapy (CPE) during or after ICU admission on QoL, physical functioning, muscle health, protein/energy intake and mortality was assessed compared to standard care.

RESULTS

Four thousand nine hundred and fifty-seven records were identified. After screening, data were extracted for 15 articles (9 randomised controlled trials and 6 non-randomised studies). Two studies reported improvements in muscle mass, of which one found higher independency in activities of daily living. No significant effect was found on QoL. Overall, protein targets were seldom met and often below recommendations.

CONCLUSION

Evidence for the effect of PP or CPE on patient-reported outcomes in ICU survivors is limited due to study heterogeneity and lack of high-quality studies. Future research and clinical practice should focus on adequate protein delivery with exercise interventions to improve long-term outcomes.

Development of machine learning models for mortality risk prediction after cardiac surgery

BACKGROUND

We developed machine learning models that combine preoperative and intraoperative risk factors to predict mortality after cardiac surgery.

METHODS

Machine learning involving random forest, neural network, support vector machine, and gradient boosting machine was developed and compared with the risk scores of EuroSCORE I and II, Society of Thoracic Surgeons (STS), as well as a logistic regression model. Clinical data were collected from patients undergoing adult cardiac surgery at the First Medical Centre of Chinese PLA General Hospital between December 2008 and December 2017. The primary outcome was post-operative mortality. Model performance was estimated using several metrics, including sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC). The visualization algorithm was implemented using Shapley's additive explanations.

RESULTS

A total of 5,443 patients were enrolled during the study period. The mean EuroSCORE II score was 3.7%, and the actual in-hospital mortality rate was 2.7%. For predicting operative mortality after cardiac surgery, the AUC scores were 0.87, 0.79, 0.81, and 0.82 for random forest, neural network, support vector machine, and gradient boosting machine, compared with 0.70, 0.73, 0.71, and 0.74 for EuroSCORE I and II, STS, and logistic regression model. Shapley's additive explanations analysis of random forest yielded the top-20 predictors and individual-level explanations for each prediction.

CONCLUSIONS

Machine learning models based on available clinical data may be superior to clinical scoring tools in predicting postoperative mortality in patients following cardiac surgery. Explanatory models show the potential to provide personalized risk profiles for individuals by accounting for the contribution of influencing factors. Additional prospective multicenter studies are warranted to confirm the clinical benefit of these machine learning-driven models.

Consumption of Nutrition Supplements Is Associated with Less Hypoglycemia during Admission-Results from the MENU Project

Aim: We studied the effect of the addition of an oral nutrition supplement (ONS) on the rate of hypoglyemia among hospitalized type 2 diabetes mellitus (DM) patients. Methods: In this retrospective analysis, all DM patients with hypoalbuminemia (albumin < 3.5 g/dL) admitted to internal medicine “E” at Wolfson Medical Center between 1 June 2016 and 30 April 2017 were included. One bottle of ONS (Glucerna, 330 KCAL, 28 g carbohydrates, 17 g protein, 17 g fat) was added to the morning meal. The consumption of the ONS was verified during the morning rounds. All glucose measurements were recorded automatically in the patients’ electronic medical records. A logistic regression model was used to evaluate the effect of the nutrition support on the occurrence of hypoglycemia. Results: 218 patients (mean age 77.4 ± 12.0 years, 63.3% female, mean albumin 3.13 ± 0.32 g/dL), of whom 27.9% had documented hypoglycemia during hospitalization were included. The patients consumed 69.5% ± 37.1 of the ONS provided, and ONS was started 4.3 ± 5.3 days from admission. A logistic regression model indicated that age (Odds ratio [OR] 1.048, 95% CI 1.014–1.083, p = 0.005), insulin treatment (OR 3.059, 95% CI 1.497–6.251, p = 0.002), and the day of ONS started from admission (OR 1.094, 95% CI 1.021–1.173, p = 0.011) were associated with an increased risk of hypoglycemia. Complete consumption of the ONS was associated with a reduced risk of hypoglycemia: OR 0.364, 95% CI 0.149–0.890, p = 0.027. Age, other DM medications and serum albumin did not affect the risk. Conclusion: The intake of a complete serving of ONS may be associated with a reduction of the risk of hypoglycemia among diabetes in-patients with hypoalbuminemia.