Simulation device for shoulder reductions: overview of prototyping, testing, and design instructions.

BACKGROUND: Shoulder dislocations are common occurrences, yet there are few simulation devices to train medical personnel on how to reduce these dislocations. Reductions require a familiarity with the shoulder and a nuanced motion against strong muscle tension. The goal of this work is to describe the design of an easily replicated, low-cost simulator for training shoulder reductions. MATERIALS AND METHODS: An iterative, stepwise engineering design process was used to design and implement ReducTrain. A needs analysis with clinical experts led to the selection of the traction-countertraction and external rotation methods as educationally relevant techniques to include. A set of design requirements and acceptance criteria was established that considered durability, assembly time, and cost. An iterative prototyping development process was used to meet the acceptance criteria. Testing protocols for each design requirement are also presented. Step-by-step instructions are provided to allow the replication of ReducTrain from easily sourced materials, including plywood, resistance bands, dowels, and various fasteners, as well as a 3D-printed shoulder model, whose printable file is included at a link in the Additional file 1: Appendix. RESULTS: A description of the final model is given. The total cost for all materials for one ReducTrain model is under US $200, and it takes about 3 h and 20 min to assemble. Based on repetitive testing, the device should not see any noticeable changes in durability after 1000 uses but may exhibit some changes in resistance band strength after 2000 uses. DISCUSSION: The ReducTrain device fills a gap in emergency medicine and orthopedic simulation. Its wide variety of uses points to its utility in several instructional formats. With the rise of makerspaces and public workshops, the construction of the device can be easily completed. While the device has some limitations, its robust design allows for simple upkeep and a customizable training experience. CONCLUSION: A simplified anatomical design allows for the ReducTrain model to serve as a viable training device for shoulder reductions.

Point-of-Care Laboratory Data Collection During Critical Care Transport.

OBJECTIVE: Critical care transport involves a high level of intensive clinical care in a resource-limited environment. These patients require multiple assessments guiding specialty treatments, including blood product administration, intravenous electrolyte replacement, ventilator management, and extracorporeal membrane oxygenation. This study aims to measure the usage of point-of-care (POC) laboratory data during critical care transport. METHODS: Data were collected via electronic medical record review over 1 year of use in a hospital-based critical care rotor wing, fixed wing, and ground critical care transport team in the Southeastern United States. RESULTS: One hundred twenty POC tests were performed during 1,075 critical care transports over the 1-year period (8.9%). Patient transportations involved 35 extracorporeal membrane oxygenation, 21 medical, 17 cardiac, 13 neonatal, 11 respiratory failure, 8 gastrointestinal bleeding, 6 neurologic, 5 pediatrics, 3 trauma, and 1 organ donor. Seventy-eight POC laboratory tests (65%) required intervention, including ventilator changes (39.7%), electrolyte replacement (35.8%), blood products (7.6%), and other (12.8%). The remaining 42 (35%) POC laboratory tests confirmed no intervention was necessary (n = 35) and that ongoing treatments were effective (n = 7). CONCLUSION: POC laboratory testing performed during critical care transport guides providers in performing essential emergent interventions in a timelier manner that may benefit critically ill patients.

Real-World Integration of a Sepsis Deep Learning Technology Into Routine Clinical Care: Implementation Study.

BACKGROUND: Successful integrations of machine learning into routine clinical care are exceedingly rare, and barriers to its adoption are poorly characterized in the literature. OBJECTIVE: This study aims to report a quality improvement effort to integrate a deep learning sepsis detection and management platform, Sepsis Watch, into routine clinical care. METHODS: In 2016, a multidisciplinary team consisting of statisticians, data scientists, data engineers, and clinicians was assembled by the leadership of an academic health system to radically improve the detection and treatment of sepsis. This report of the quality improvement effort follows the learning health system framework to describe the problem assessment, design, development, implementation, and evaluation plan of Sepsis Watch. RESULTS: Sepsis Watch was successfully integrated into routine clinical care and reshaped how local machine learning projects are executed. Frontline clinical staff were highly engaged in the design and development of the workflow, machine learning model, and application. Novel machine learning methods were developed to detect sepsis early, and implementation of the model required robust infrastructure. Significant investment was required to align stakeholders, develop trusting relationships, define roles and responsibilities, and to train frontline staff, leading to the establishment of 3 partnerships with internal and external research groups to evaluate Sepsis Watch. CONCLUSIONS: Machine learning models are commonly developed to enhance clinical decision making, but successful integrations of machine learning into routine clinical care are rare. Although there is no playbook for integrating deep learning into clinical care, learnings from the Sepsis Watch integration can inform efforts to develop machine learning technologies at other health care delivery systems.