Ensemble machine learning algorithm for predicting acute kidney injury in patients admitted to the neurointensive care unit following brain surgery.

Acute kidney injury (AKI) is a common postoperative complication among patients in the neurological intensive care unit (NICU), often resulting in poor prognosis and high mortality. In this retrospective cohort study, we established a model for predicting AKI following brain surgery based on an ensemble machine learning algorithm using data from 582 postoperative patients admitted to the NICU at the Dongyang People's Hospital from March 1, 2017, to January 31, 2020. Demographic, clinical, and intraoperative data were collected. Four machine learning algorithms (C5.0, support vector machine, Bayes, and XGBoost) were used to develop the ensemble algorithm. The AKI incidence in critically ill patients after brain surgery was 20.8%. Intraoperative blood pressure; postoperative oxygenation index; oxygen saturation; and creatinine, albumin, urea, and calcium levels were associated with the postoperative AKI occurrence. The area under the curve value for the ensembled model was 0.85. The accuracy, precision, specificity, recall, and balanced accuracy values were 0.81, 0.86, 0.44, 0.91, and 0.68, respectively, indicating good predictive ability. Ultimately, the models using perioperative variables exhibited good discriminatory ability for early prediction of postoperative AKI risk in patients admitted to the NICU. Thus, the ensemble machine learning algorithm may be a valuable tool for forecasting AKI.

Macrophage in liver Fibrosis: Identities and mechanisms.

Liver fibrosis is a chronic disease characterized by the deposition of extracellular matrix and continuous loss of tissues that perform liver functions. Macrophages are crucial modulators of innate immunity and play important roles in liver fibrogenesis. Macrophages comprise heterogeneous subpopulations that exhibit different cellular functions. Understanding the identity and function of these cells is essential for understanding the mechanisms of liver fibrogenesis. According to different definitions, liver macrophages are divided into M1/M2 macrophages or monocyte-derived macrophages/Kupffer cells. Classic M1/M2 phenotyping corresponds to pro- or anti-inflammatory effects, and, therefore, influences the degree of fibrosis in later phases. In contrast, the origin of the macrophages is closely associated with their replenishment and activation during liver fibrosis. These two classifications of macrophages depict the function and dynamics of liver-infiltrating macrophages. However, neither description properly elucidates the positive or negative role of macrophages in liver fibrosis. Critical tissue cells mediating liver fibrosis include hepatic stellate cells and hepatic fibroblasts, with hepatic stellate cells being of particular interest because of their close association with macrophages in liver fibrosis. However, the molecular biological descriptions of macrophages are inconsistent between mice and humans, warranting further investigations. In liver fibrosis, macrophages can secrete various pro-fibrotic cytokines, such as TGF-ß, Galectin-3 and interleukins (ILs), and fibrosis-inhibiting cytokines, such as IL10. These different secretions may be associated with the specific identity and spatiotemporal characteristics of macrophages. Furthermore, during fibrosis dissipation, macrophages may degrade extracellular matrix by secreting matrix metalloproteinases (MMPs). Notably, using macrophages as therapeutic targets in liver fibrosis has been explored. The current therapeutic approaches for liver fibrosis can by categorized as follows: treatment with macrophage-related molecules and macrophage infusion therapy. Although there have been limited studies, macrophages have shown reliable potential for liver fibrosis treatment. In this review, we focu on the identity and function of macrophages and their relationship to the progression and regression of liver fibrosis.

Association between enteral nutrition support and neurological outcome in patients with acute intracranial haemorrhage: A retrospective cohort study.

Association between the amount of enteral nutrition (EN) caloric intake and Glasgow coma scale scores at discharge (GCSdis) in intracranial haemorrhage (ICH) was retrospectively investigated in 230 patients in a single center from 2015 and 2017. GCSdis was used as a dichotomous outcome (≤8 or >8: 56/230 vs. 174/230) and its association with the amount of EN caloric intake within 48 hours was analysed in four logistic models. Model 1 used EN as a continuous variable and showed association with favourable GCSdis (odds ratio [OR], 1.04; 95% confidence interval [CI], 1.01-1.08). Models 2 and 3 categorized EN into two (≤25 and >25 kcal/kg/48 hrs) and three caloric intake levels (≤10, 10~25, and >25 kcal/kg/48 hrs) respectively, and compared them with the lowest level; highest EN level associated with favourable GCSdis in both model 2 (OR, 2.77; 95%CI, 1.25-6.13) and 3 (OR, 4.68; 95%CI, 1.61-13.61). Model 4 transformed EN into four quartiles (Q1-Q4). Compared to Q1, OR increased stepwise from Q2 (OR 1.80, 95%CI 0.59-5.44) to Q4 (OR 4.71, 95%CI 1.49-14.80). Propensity score matching analysis of 69 matched pairs demonstrated consistent findings. In the early stage of ICH, increased EN was associated with favourable GCSdis.

Early low-energy versus high-energy enteral nutrition support in patients with traumatic intracerebral haemorrhage: protocol for a randomised controlled trial.

BACKGROUND: Early enteral nutrition (EN) is associated with shorter hospital stay and lower infection and mortality rates in patients with intracerebral haemorrhage. However, high-energy support always causes clinical complications, such as diarrhoea and aspiration pneumonia, and the true benefit of high-energy support in these patients has not been investigated. The appropriate amount of energy support still needs further investigation. Therefore, we are performing a randomised controlled trial to investigate whether early low-energy EN can decrease mortality and feeding-related complications and improve neurological outcomes as compared with high-energy EN in traumatic intracerebral haemorrhage (TICH) patients. METHODS/ANALYSIS: This is a randomised, single-blind clinical trial performed in one teaching hospital. 220 TICH patients will be randomly allocated to one of two groups in a 1:1 ratio: an intervention group, and a control group. The intervention group will receive early low-energy EN (10 kcal/kg/day) and the control group will receive high-energy EN (25 kcal/kg/day) for 7 days. All these patients will be followed up for 90 days. The primary outcome is all-cause 90-day mortality. Secondary outcomes include the modified Rankin score, Glasgow Outcome Scale (GOS) and the National Institutes of Health Stroke Scale (NIHSS). Outcomes will be assessed at admission, 7, 30 and 90 days after onset of this trial. The safety of EN strategies will be assessed every day during hospitalisation. ETHICS AND DISSEMINATION: The trial will be conducted in accordance with the Declaration of Helsinki and has been approved by the ethics committee of Dongyang People's Hospital. The findings will be published in peer-reviewed medical journals. TRIAL REGISTRATION NUMBER: ChiCTR-INR-17011384; Pre-results.