Conectar
Efficient discharge for stroke patients is crucial but challenging. The study aimed to develop early predictive models to explore which patient characteristics and variables significantly influence the discharge planning of patients, based on the data available within 24 h of admission.
Prospective observational study.
A prospective cohort was conducted at a university hospital with 523 patients hospitalised for stroke. We built and trained six different machine learning (ML) models, followed by testing and tuning those models to find the best-suited predictor for discharge disposition, dichotomized into home and non-home. To evaluate the accuracy, reliability and interpretability of the best-performing models, we identified and analysed the features that had the greatest impact on the predictions.
In total, 523 patients met the inclusion criteria, with a mean age of 61 years. Of the patients with stroke, 30.01% had non-home discharge. Our model predicting non-home discharge achieved an area under the receiver operating characteristic curve of 0.95 and a precision of 0.776. After threshold was moved, the model had a recall of 0.809. Top 10 variables by importance were National Institutes of Health Stroke Scale (NIHSS) score, family income, Barthel index (BI) score, FRAIL score, fall risk, pressure injury risk, feeding method, depression, age and dysphagia.
The ML model identified higher NIHSS, BI, and FRAIL, family income, higher fall risk, pressure injury risk, older age, tube feeding, depression and dysphagia as the top 10 strongest risk predictors in identifying patients who required non-home discharge to higher levels of care. Modern ML techniques can support timely and appropriate clinical decision-making.
This study illustrates the characteristics and risk factors of non-home discharge in patients with stroke, potentially contributing to the improvement of the discharge process.
STROBE guidelines.
To investigate the correlation of blood glucose level with poor wound healing (PWH) after posterior lumbar interbody fusion (PLIF) in patients with type 2 diabetes (T2D). From January 2016 to January 2023, a case–control study was conducted to analyse the clinical data of 400 patients with T2D who were treated by PLIF and internal fixation at our hospital. The following data were recorded: gender; age; body mass index (BMI); surgical stage; average perioperative blood glucose level; perioperative blood glucose variance; perioperative blood glucose coefficient of variation; glycated haemoglobin level; preoperative levels of total protein, albumin and haemoglobin; postoperative levels of total protein, albumin and haemoglobin; surgical time; intraoperative bleeding volume; operator; postoperative drainage volume; and postoperative drainage tube removal time of each group. The indicators for monitoring blood glucose variability (GV) included the SD of blood glucose level (SDBG), coefficient of variation (CV) and maximum amplitude of variation (LAGE) before and after surgery. According to the diagnostic criteria for PWH, patients with postoperative PWH were determined and assigned to two groups: Group A (good wound healing group; n = 330 patients) and Group B (poor wound healing group; n = 70 patients). The preoperative and postoperative blood GV indicators, namely SDBG, CV and LAGE, were compared between these two groups. We also determined the relationship between perioperative blood GV parameters and PWH after PLIF surgery and its predictive value through correlation analysis and receiver-operating characteristic curve. Of the 400 enrolled patients, 70 patients had PWH. Univariate analysis revealed significant differences between the two groups in the course of diabetes, mean fasting blood glucose (MFBG), SDBG, CV, LAGE, preoperative hypoglycaemic program, surgical segment, postoperative drainage time, incision length and other factors (p < 0.05). However, no significant differences were noted in factors such as gender, age, body mass index, hypertension, coronary heart disease, admission fasting blood glucose, preoperative haemoglobin A1c, surgical time, intraoperative bleeding volume, intraoperative blood transfusion volume and postoperative drainage volume (p > 0.05). The area under the curve (AUC) values of preoperative SDBG, CV and LAGE were 0.6657, 0.6432 and 0.6584, respectively. The cut-off values were 1.13 mmol/L, 6.97% and 0.75 mmol/L, respectively. The AUC values for postoperative SDBG, CV and LAGE were 0.5885, 0.6255 and 0.6261, respectively. The cut-off values were 1.94 mmol/L, 24.32% and 2.75 mmol/L, respectively. The multivariate ridge regression analysis showed that preoperative MFBG, SDBG, CV and LAGE; postoperative SDBG, CV and LAGE; postoperative long drainage time; and multiple surgical segments were independent risk factors for T2D patients to develop surgical site infection after PLIF (p < 0.05). The perioperative blood GV in patients with T2D is closely related to the occurrence of PWH after PLIF. Reducing blood GV may help to reduce the occurrence of PWH after PLIF.
FreshRSS 