Background: Hip fracture is the most common type of fracture in elderly individuals. Numerous deep learning (DL) algorithms for plain pelvic radiographs (PXRs) have been applied to improve the accuracy of hip fracture diagnosis. However, their efficacy is still undetermined. Objective: The objective of this study is to develop and validate a human-algorithm integration (HAI) system to improve the accuracy of hip fracture diagnosis in a real clinical environment. Methods: The HAI system with hip fracture detection ability was developed using a deep learning algorithm trained on trauma registry data and 3605 PXRs from August 2008 to December 2016. To compare their diagnostic performance before and after HAI system assistance using an independent testing dataset, 34 physicians were recruited. We analyzed the physicians’ accuracy, sensitivity, specificity, and agreement with the algorithm; we also performed subgroup analyses according to physician specialty and experience. Furthermore, we applied the HAI system in the emergency departments of different hospitals to validate its value in the real world. Results: With the support of the algorithm, which achieved 91% accuracy, the diagnostic performance of physicians was significantly improved in the independent testing dataset, as was revealed by the sensitivity (physician alone, median 95%; HAI, median 99%; P<.001), specificity (physician alone, median 90%; HAI, median 95%; P<.001), accuracy (physician alone, median 90%; HAI, median 96%; P<.001), and human-algorithm agreement [physician alone κ, median 0.69 (IQR 0.63-0.74); HAI κ, median 0.80 (IQR 0.76-0.82); P<.001. With the help of the HAI system, the primary physicians showed significant improvement in their diagnostic performance to levels comparable to those of consulting physicians, and both the experienced and less-experienced physicians benefited from the HAI system. After the HAI system had been applied in 3 departments for 5 months, 587 images were examined. The sensitivity, specificity, and accuracy of the HAI system for detecting hip fractures were 97%, 95.7%, and 96.08%, respectively. Conclusions: HAI currently impacts health care, and integrating this technology into emergency departments is feasible. The developed HAI system can enhance physicians’ hip fracture diagnostic performance.

Abdominal compartment syndrome can be treated through decompressive surgery if intraabdominal hypertension (IAH) can be detected in time. Treatment delays due to manual, conventional intravesical pressure (IVP) monitoring using a Foley catheter have been reported. In this work, we present an innovative gastrointestinal intraluminal pressure (GIP) measurement-based method to monitor and improve pressure-guided relief of intraabdominal pressure (IAP). A novel algorithm for detecting IAH in the gastrointestinal tract of a live porcine model is reported. A wireless pressure-sensing capsule (10 × 13 mm) was developed for absolute measurement. The IAP was estimated during artificial pneumoperitoneum. The pressure waveform-based measurements indicated that the wireless pressure sensor could be used to predict IAP. To enhance GIP monitoring for predicting IAH, the proposed continuous ingestible wireless electronics-based pressure waveform measurement device can be used as a complement to existing modalities. The use of the proposed pressure measurement and communication technology can help provide valuable data for digital health platforms.

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.

Automated detection of the region of interest (ROI) is a critical step in the two-step classification system in several medical image applications. However, key information such as model parameter selection, image annotation rules, and ROI confidence score are essential but usually not reported. In this study, we proposed a practical framework of ROI detection by analyzing hip joints seen on 7399 anteroposterior pelvic radiographs (PXR) from three diverse sources. We presented a deep learning-based ROI detection framework utilizing a single-shot multi-box detector with a customized head structure based on the characteristics of the obtained datasets. Our method achieved average intersection over union (IoU) = 0.8115, average confidence = 0.9812, and average precision with threshold IoU = 0.5 (AP50) = 0.9901 in the independent testing set, suggesting that the detected hip regions appropriately covered the main features of the hip joints. The proposed approach featured flexible loose-fitting labeling, customized model design, and heterogeneous data testing. We demonstrated the feasibility of training a robust hip region detector for PXRs. This practical framework has a promising potential for a wide range of medical image applications.

Intra-abdominal pressure (IAP) is defined as the steady-state pressure within the abdominal cavity. Elevated IAP has been implicated in many medical complications. This article reviews the current state-of-the-art in innovative sensors for the measurement of IAP. A systematic review was conducted on studies on the development and application of IAP sensors. Publications from 2010 to 2021 were identified by performing structured searches in databases, review articles, and major textbooks. Sixteen studies were eligible for the final systematic review. Of the 16 articles that describe the measurement of IAP, there were 5 in vitro studies (31.3%), 7 in vivo studies (43.7%), and 4 human trials (25.0%). In addition, with the advancement of wireless communication technology, an increasing number of wireless sensing systems have been developed. Among the studies in this review, five presented wireless sensing systems (31.3%) to monitor IAP. In this systematic review, we present recent developments in different types of intra-abdominal pressure sensors and discuss their inherent advantages due to their small size, remote monitoring, and multiplexing.