The study aimed to establish a machine learning-based scoring nomogram for early recognition of likely pressure injuries in an intensive care unit (ICU) using large-scale clinical data. A retrospective cohort study design was employed to develop and validate a top-performing clinical feature panel accessibly in the electronic medical records (EMRs), which was in the mode of a quantifiable nomogram. Clinical factors regarding demographics, admission cause, clinical laboratory index, medical history and nursing scales were extracted as risk candidates. The performance improvement was based on the application of the machine learning technique, comprising logistic regression, decision tree and random forest algorithm with five-fold cross-validation (CV) technique. The comprehensive assessment of sensitivity, specificity and the area under the receiver operating characteristic curve (AUROC) was considered in the evaluation of predictive performance. The receiver operating characteristic curves revealed the top performance for the logistic regression model in respect to machine learning improvement, achieving the highest sensitivity and AUC among three types of classifiers. Compared against the 23-point Braden scale routinely recorded online, an incorporated nomogram of logistic regression model and Braden scale achieved the best performance with an AUC of 0.87 ± 0.07 and 0.84 ± 0.05 in training and test cohort, respectively.Our findings suggest that the machine learning technique potentiated the limited predictive validity of routinely recorded clinical data on pressure injury development during ICU hospitalisation. Easily accessible electronic records held the potentials to substitute the traditional Braden score in the prediction of pressure injury in intensive care unit. Preoperative prediction of pressure injury facilitates the exemption from the severe consequences.

Sarcopenia is considered to be a new complication of type 2 diabetes (T2DM) leading to increased risk of adverse outcome. We performed a survey to evaluate glucose metabolism and nutritional status in sarcopenia patients with T2DM. Diabetic participants aged ≥50 years were grouped into a probable sarcopenia group with low muscle strength ( n = 405 ) and a nonsarcopenia group with normal muscle strength ( n = 720 ) according to the revised recommendations from EWGSOP2 (2018). Compared to the controls, the probable sarcopenia participants were older and had lower waist-to-hip ratio and BMI, longer diabetes duration, higher fasting plasma glucose level and glycosylated hemoglobin (HbA1c), decreased estimated glomerular filtration rate and lower bone mineral content, lower fatless upper arm circumference, lower appendicular skeletal muscle mass index (ASMI), and muscle quality in both genders. Multivariable logistic regression analysis showed increased age, male, low BMI, and increased HbA1c, combined with diabetic nephropathy and decreased serum albumin levels, were risk factors associated with low muscle strength in diabetes patients. In conclusion, diabetic patients with sarcopenia had worse glucose metabolism and nutritional status, decreased renal function and reduced muscle quality ,and muscle mass with a greater likelihood of osteoporosis, who need an overall health management to improve outcomes. This clinical trial registration is registered with the Chinese Clinical Trial Registry, ChiCTR-EOC-15006901.

Background: Persistent proteinuria is an important factor contributing to the progression of diabetic nephropathy. The present randomized double-blind placebo-controlled multicenter clinical study evaluated the efficacy and safety of telmisartan combined with the antioxidant probucol in reducing urinary protein levels in patients with type 2 diabetes (T2D). Methods: Patients with T2D and 24-h proteinuria 0.5-3 g were enrolled in the study and randomly assigned to one of two groups: a telmisartan or a probucol + telmisartan group. Both groups were given telmisartan 80 mg q.d. for 48 weeks. The probucol + telmisartan group was given probucol 500 mg b.i.d. for the first 24 weeks, with the dosage then reduced to 250 mg b.i.d. for the remaining 24 weeks. The telmisartan group was given probucol placebo. Results: In all, 160 patients were enrolled in the present study. The 24-h proteinuria levels were significantly reduced in the probucol + telmisartan compared with telmisartan group. For patients with baseline 24-h proteinuria levels <1.0 g, both treatments resulted in significant reductions in 24-h proteinuria levels after 48 weeks treatment. However, in patients with baseline 24-h proteinuria levels ≥1.0 g, 24-h proteinuria levels after 48 weeks treatment were only reduced in the probucol + telmisartan group. There was no significant difference between the two groups for either adverse cardiovascular or other events. Conclusions: In patients with diabetic nephropathy, probucol combined with telmisartan more effectively reduces urinary protein levels than telmisartan alone.

BackgroundBased on the 24-week, prospective, non-interventional, observational study, A1chieve®, we investigated how health-related quality of life (HRQoL) changed, and the predictors of such changes, in Chinese people with type 2 diabetes mellitus (T2DM) after starting with, or switching to, biphasic insulin aspart 30 (BIAsp 30).MethodsIn total, 8,578 people with T2DM starting treatment with, or switching to, BIAsp 30 were recruited from 130 urban hospitals in China. HRQoL was assessed at baseline and 24 weeks using the EuroQol-5 dimensions (EQ-5D) questionnaire. Descriptive statistics, paired t-test, and chi-square test were conducted and the linear ordinary least squares regression model was used to determine predictors for changes in EQ-5D score.ResultsHaemoglobin A1c (HbA1c) decreased from 9.5% to 7.0% after 24 weeks. The reported HRQoL measured by the EQ-5D visual analogue scale score increased by 6.2 (p < 0.001) from 75.8 to 82.0, and EQ-5D index score increased by 0.018 (p < 0.001) from 0.875 to 0.893 for the cohort over 24 weeks. The percentage of patients reporting no problems in the mobility, pain/discomfort, and anxiety/depression dimensions of EQ-5D increased significantly (p < 0.001) from 88.4% to 91.4%, 77.3% to 82.8%, and 74.2% to 77.1%, respectively. Patients with higher HbA1c levels at baseline, major hypoglycaemia or micro-complications exhibited significantly larger changes in EQ-5D scores than those with lower baseline HbA1c levels, without major hypoglycaemia or micro-complications after controlling for demographics and other baseline characteristics.ConclusionsBIAsp 30 treatment was associated with improved glycaemic control and HRQoL in T2DM patients in China. Patients with worse health conditions were more likely to experience larger improvements in HRQoL than those with better health conditions.Trial registrationClinicalTrials.gov, NCT00869908.Electronic supplementary materialThe online version of this article (doi:10.1186/s12955-014-0137-9) contains supplementary material, which is available to authorized users.

No abstract