Improving HRQOL is the desired outcome for patients with stroke undergoing inpatient rehabilitation services. This study aimed to comprehensively identify the potential health-related quality of life (HRQOL) predictors in patients with stroke undergoing inpatient rehabilitation within the first year after stroke; thus far, such an investigation has not been conducted. We enrolled 119 patients (88 males, 31 females) with stroke, and examined 12 potential predictors: age, sex, stroke type, stroke side, duration after onset, cognition (Mini-Mental State Examination; MMSE), depression (Beck Depression Inventory-II), stroke severity (National Institutes of Health Stroke Scale; NIHSS), upper- and lower-extremity motor function scores of the Fugl–Meyer Assessment (FMA) scale, balance (Berg Balance Scale; BBS), and functional status (Functional Independence Measure). HRQOL was measured using Stroke Impact Scale (SIS) 3.0. NIHSS score predicted the strength domain and total SIS score (41.5 % and 41.7 % of the variances, respectively). BBS score was a major predictor of mobility and participation/role domains (48.6 % and 10 % of the variances, respectively). MMSE score predicted the memory and communication domains (22.5 % and 36.3 % of the variances, respectively). Upper extremity score of the FMA scale predicted the daily living/instrumental activities of daily life and hand function domains (40.3 % and 20.6 % of the variances, respectively). Stroke side predicted the emotion domain (11.6 % of the variance). NIHSS, MMSE, BBS, FMA, and stroke side predicted most HRQOL domains. These findings suggest that different factors predicted various HRQOL domains in patients with stroke.

Children with abusive head trauma tend to have worse outcomes than children with accidental head trauma. However, current predictors of poor outcomes for children with abusive head trauma are still limited. We aim to use clinical data to identify early predictors of poor outcome at discharge in children with abusive head trauma. In the 10-year observational retrospective cohort study, children aged between zero and four years with abusive or accidental head trauma were recruited. Multivariate logistic regression models were applied to evaluate factors associated with poor prognosis in children with abusive head trauma. The primary outcome was mortality or a Glasgow Coma Scale (GCS) motor component score of less than 6 at discharge. A total of 292 head trauma children were included. Among them, 59 children had abusive head trauma. In comparison to children with accidental head trauma, children with abusive head trauma were younger, had more severe head injuries, and experienced a higher frequency of post-traumatic seizures. Their radiologic findings showed common presence of subdural hemorrhage, cerebral edema, and less epidural hemorrhage. They were more in need of neurosurgical intervention. In the multivariate analysis for predictors of poor outcome in children with abusive head trauma, initial GCS ≤ 5 (versus GCS > 5 with the adjusted odds ratio (OR) = 25.7, 95% confidence interval (CI) = 1.5–432.8, p = 0.024) and older age (per year with the adjusted OR = 3.3, 95% CI = 1.2–9.5, p = 0.024) were independently associated with poor outcome. These findings demonstrate the characteristic clinical differences between children with abusive and accidental head trauma. Initial GCS ≤ 5 and older age are predictive of poor outcome at discharge in children with abusive head trauma.

Traumatic brain injury (TBI) is the leading cause of mortality in children. There are few studies focused on school-aged children with TBI. We conducted this study to identify the early predictors of in-hospital mortality in school-aged children with severe TBI. In this 10 year observational cohort study, a total of 550 children aged 7–18 years with TBI were enrolled. Compared with mild/moderate TBI, children with severe TBI were older; more commonly had injury mechanisms of traffic accidents; and more neuroimage findings of subarachnoid hemorrhage (SAH), subdural hemorrhage (SDH), parenchymal hemorrhage, cerebral edema, and less epidural hemorrhage (EDH). The in-hospital mortality rate of children with severe TBI in our study was 23%. Multivariate analysis showed that falls, being struck by objects, motor component of Glasgow coma scale (mGCS), early coagulopathy, and SAH were independent predictors of in-hospital mortality. We concluded that school-aged children with severe TBI had a high mortality rate. Clinical characteristics including injury mechanisms of falls and being struck, a lower initial mGCS, early coagulopathy, and SAH are predictive of in-hospital mortality.

Background: Total hip replacement (THR) is considered the gold standard of treatment for refractory degenerative hip disorders. Identifying patients who should receive THR in the short term is important. Some conservative treatments, such as intra-articular injection administered a few months before THR, may result in higher odds of arthroplasty infection. Delayed THR after functional deterioration may result in poorer outcomes and longer waiting times for those who have been flagged as needing THR. Deep learning (DL) in medical imaging applications has recently obtained significant breakthroughs. However, the use of DL in practical wayfinding, such as short-term THR prediction, is still lacking. Objective: In this study, we will propose a DL-based assistant system for patients with pelvic radiographs to identify the need for THR within 3 months. Methods: We developed a convolutional neural network–based DL algorithm to analyze pelvic radiographs, predict the hip region of interest (ROI), and determine whether or not THR is required. The data set was collected from August 2008 to December 2017. The images included 3013 surgical hip ROIs that had undergone THR and 1630 nonsurgical hip ROIs. The images were split, using split-sample validation, into training (n=3903, 80%), validation (n=476, 10%), and testing (n=475, 10%) sets to evaluate the algorithm performance. Results: The algorithm, called SurgHipNet, yielded an area under the receiver operating characteristic curve of 0.994 (95% CI 0.990-0.998). The accuracy, sensitivity, specificity, and F1-score of the model were 0.977, 0.920, 0932, and 0.944, respectively. Conclusions: The proposed approach has demonstrated that SurgHipNet shows the ability and potential to provide efficient support in clinical decision-making; it can assist physicians in promptly determining the optimal timing for THR.