Application of a deep learning algorithm in the detection of hip fractures.

This paper describes the development of a deep learning model for prediction of hip fractures on pelvic radiographs (X-rays). Developed using over 40,000 pelvic radiographs from a single institution, the model demonstrated high sensitivity and specificity when applied to a test set of emergency department radiographs. This study approximates the real-world application of a deep learning fracture detection model by including radiographs with sub-optimal image quality, other non-hip fractures, and metallic implants, which were excluded from prior published work. The study also explores the effect of ethnicity on model performance, as well as the accuracy of visualization algorithm for fracture localization.

Effectiveness of Autologous Tissue Grafts on Soft Tissue Ingrowth in Patients Following Partial Root Extraction with Socket Shield: A Retrospective Analysis of a Case Series.

PURPOSE: There is little knowledge about healing patterns for the socket with an intentionally retained root fragment: a socket shield. The clinical observation is soft tissue ingrowth next to the socket shield. The aim of this study was to evaluate the effectiveness of autologous grafting matrices in preventing soft tissue ingrowth. MATERIALS AND METHODS: Patient data from a private clinic were searched for sockets with a socket shield left to heal with blood clot or grafted with autologous materials: autologous platelet-rich fibrin (PRF), scraped particulate bone, cortical tuberosity bone plate, or particulate dentin and covered with PRF membranes. The included sites were exposed by the flap 4 months after the first surgery, and soft tissue ingrowth depth and width next to the root fragment were measured by a scaled probe and documented. RESULTS: Evaluation of 34 sites showed the greatest depth of soft tissue ingrowth in the nongrafted sockets (6.0 ± 0.0 mm). Grafting with PRF plugs (depth of 2.3 ± 0.2 mm) or particulate bone (depth of 2.7 ± 0.6 mm) decreased soft tissue ingrowth. Grafting with particulate dentin or cortical tuberosity bone plate resulted in a soft tissue ingrowth depth of only 1 mm, yielding the best clinical outcome. Radiography confirmed those findings. CONCLUSION: Autologous dentin particulate or tuberosity cortical bone plate is most effective for preventing soft tissue ingrowth.

Innovative use of health informatics to augment contact tracing during the COVID-19 pandemic in an acute hospital.

This case report describes the innovative design and build of an algorithm that integrates available data from separate hospital-based informatics systems, which perform different daily functions to augment the contact-tracing process of COVID-19 patients by identifying exposed neighboring patients and healthcare workers and assessing their risk. Prior to the establishment of the algorithm, contact-tracing teams comprising 6 members would spend up to 10 hours each to complete contact tracing for 5 new COVID-19 patients. With the augmentation by the algorithm, we observed ≥ 60% savings in overall man-hours needed for contact tracing when there were 5 or more daily new cases through a time-motion study and Monte Carlo simulation. This improvement to the hospital's contact-tracing process supported more expeditious and comprehensive downstream contact-tracing activities as well as improved manpower utilization in contact tracing.

Alveolar ridge preservation with the socket-plug technique utilizing an alloplastic putty bone substitute or a particulate xenograft: a histological pilot study.

Following tooth extraction, ridge preservation procedures are employed to regenerate bone in the extraction socket, limit consequent ridge resorption, and provide a stable base for implant placement. The purpose of this study is to histologically evaluate and compare bone regeneration in extraction sockets grafted with either a putty alloplastic bone substitute or particulate anorganic bovine xenograft utilizing the socket-plug technique. Nineteen patients underwent 20 tooth extractions and ridge preservation following a standardized protocol. Ten sites were grafted with calcium phosphosilicate putty (CPS group) and the remaining 10 with anorganic bovine bone substitute (BO group). Patients were recalled after 4-6 months to evaluate the bone regeneration and to proceed with implant placement. A bone core was obtained during the implant procedure from each site and was used for histologic analysis. Histomorphometry revealed that residual graft values were significantly higher in the BO group (25.60% ± 5.89%) compared to the CPS group (17.40% ± 9.39%) (P < .05). The amount of new bone regenerated was also statistically significant higher in the alloplast group (47.15% ± 8.5%) as compared to the xenograft group (22.2% ± 3.5%) (P < .05). Results suggest that ridge preservation using a putty calcium phosphosilicate alloplastic bone substitute demonstrates more timely graft substitution and increased bone regeneration when compared to an anorganic bovine bone xenograft.

Random parameter models of interstate crash frequencies by severity, number of vehicles involved, collision and location type.

A nine-year (1999-2007) continuous panel of crash histories on interstates in Washington State, USA, was used to estimate random parameter negative binomial (RPNB) models for various aggregations of crashes. A total of 21 different models were assessed in terms of four ways to aggregate crashes, by: (a) severity, (b) number of vehicles involved, (c) crash type, and by (d) location characteristics. The models within these aggregations include specifications for all severities (property damage only, possible injury, evident injury, disabling injury, and fatality), number of vehicles involved (one-vehicle to five-or-more-vehicle), crash type (sideswipe, same direction, overturn, head-on, fixed object, rear-end, and other), and location types (urban interchange, rural interchange, urban non-interchange, rural non-interchange). A total of 1153 directional road segments comprising of the seven Washington State interstates were analyzed, yielding statistical models of crash frequency based on 10,377 observations. These results suggest that in general there was a significant improvement in log-likelihood when using RPNB compared to a fixed parameter negative binomial baseline model. Heterogeneity effects are most noticeable for lighting type, road curvature, and traffic volume (ADT). Median lighting or right-side lighting are linked to increased crash frequencies in many models for more than half of the road segments compared to both-sides lighting. Both-sides lighting thereby appears to generally lead to a safety improvement. Traffic volume has a random parameter but the effect is always toward increasing crash frequencies as expected. However that the effect is random shows that the effect of traffic volume on crash frequency is complex and varies by road segment. The number of lanes has a random parameter effect only in the interchange type models. The results show that road segment-specific insights into crash frequency occurrence can lead to improved design policy and project prioritization.