Effect of early nutritional initiation on post‐cerebral infarction discharge destination: A propensity‐matched analysis using machine learning

Abstract

Aim: Malnutrition is associated with poor outcomes in cerebral infarction patients, with research indicating that early nutritional initiation may improve the short-term prognosis of patients. However, evidence supported by big data is lacking. Here, to determine the effect of nutritional initiation during the first 3 days after hospital admission on home discharge rates, propensity score matching was conducted in patients with acute cerebral infarction. Methods: This retrospective observational study, using the Diagnosis Procedure Combination anonymised database in Japan, included 41 477 ischaemic cerebral infarction patients hospitalised between 2016 and 2019. The patients were divided into two groups: those who received oral or enteral nutrition during the first 3 days of hospital admission (early nutrition group, n = 37 318) and those who did not (control group, n = 4159). One-to-one pair-matching was performed using propensity scores calculated via extreme gradient boosting to limit the confounding variables of the two groups.Results: After propensity score matching, 3541 pairs of patients were selected.The dependence of home discharge rates on early nutrition was significant (p < 0.05), and the effectiveness of early nutrition for home discharge showed an odds ratio of 1.79 (95% confidence interval of 1.59-2.03 in Fisher's exact test).Conclusions: Our findings revealed that early nutritional initiation during the first 3 days of admission resulted in higher home discharge rates.

Gastrointestinal failure, big data and intensive care

“…The dependence of home discharge rates on early nutrition was significant ( P < 0.05), and the effectiveness of early nutrition for home discharge showed an odds ratio of 1.79 (95% confidence interval of 1.59–2.03 in Fisher's exact test). One-to-one pair-matching was performed using propensity scores calculated via extreme gradient boosting to limit the confounding variables of the two groups [33]. In a recent study, involving neurosurgical patients, 350 patients were randomized to receive enteral feeding only or parenteral nutrition and low-energy enteral feeding administered progressively.…”

Artificial intelligence in malnutrition research: a bibliometric analysis

“…1 shows the number of publications per query string. The combination of the term AI, ML, NN, and DL in malnutrition research has a more dominant number of publications, with ML [7]- [11] being the most popular method widely combined. DL [12]- [14] is the least combined method.…”

Evidence as foundation of practice

“…Another approach is a retrospective study which can harness an existing database, like this issue's study by Izekawa et al 6 who use a large dataset of over 40 000 stroke patients to show that feeding early in the hospital admission is associated with increased likelihood of being discharged home. The constraints of the clinical setting need not constrain the quality of the evidence we obtain.…”

“…Alternatively a qualitative approach can be richly informative, like the New Zealand study of gestational diabetes management by North et al 5 also in this issue, which identifies gaps in primary care and how dietetics resources may be best employed in this area. Another approach is a retrospective study which can harness an existing database, like this issue's study by Izekawa et al 6 who use a large dataset of over 40 000 stroke patients to show that feeding early in the hospital admission is associated with increased likelihood of being discharged home. The constraints of the clinical setting need not constrain the quality of the evidence we obtain.…”