Automated stratification of trauma injury severity across multiple body regions using multi-modal, multi-class machine learning models.

Objective: The timely stratification of trauma injury severity can enhance the quality of trauma care but it requires intense manual annotation from certified trauma coders. The objective of this study is to develop machine learning models for the stratification of trauma injury severity across various body regions using clinical text and structured electronic health records (EHRs) data.

Materials And Methods: Our study utilized clinical documents and structured EHR variables linked with the trauma registry data to create 2 machine learning models with different approaches to representing text.

Simulation-Based Medical Education: Development of an Assessment Tool for Novice Use.

Background: Simulation-based medical education, an educational model in which students engage in simulated patient scenarios, improves performance. However, assessment tools including the Oxford Non-Technical Skills (NOTECHS) scale require expert assessors. We modified this tool for novice use.

Experiential Learning of Interdisciplinary Care Skills in Surgery Assessed From Student Reflections.

Introduction: Interdisciplinary healthcare collaboration improves patient outcomes, increases workplace satisfaction, and reduces costs. Our medical school utilizes an experiential learning tool for teaching interprofessionalism known as the Longitudinal Patient Project (LPP). Medical students are directed to identify a surgical patient to establish continuity with by observing them throughout preoperative, intraoperative, and postoperative periods, and follow-up with the patient after their procedure.

Which hospital-acquired conditions matter the most in trauma? An evidence-based approach for prioritizing trauma program improvement.

Background: Prevention of hospital-acquired conditions (HACs) is a focus of trauma center quality improvement. The relative contributions of various HACs to postinjury hospital outcomes are unclear. We sought to quantify and compare the impacts of six HACs on early clinical outcomes and resource utilization in hospitalized trauma patients.

"Rhythm of the Night": Medical student reflections on overnight trauma call.

Introduction: On their surgical clerkship, students reflected on their experience on a traditional overnight call. We explored whether perceived learning experiences differ between students who identify surgical specialties as their career compared to those who do not.

Methods: Medical students participated in traditional call at a Level 1 Trauma Center and submitted guided reflections.

Comparison and interpretability of machine learning models to predict severity of chest injury.

Objective: Trauma quality improvement programs and registries improve care and outcomes for injured patients. Designated trauma centers calculate injury scores using dedicated trauma registrars; however, many injuries arrive at nontrauma centers, leaving a substantial amount of data uncaptured. We propose automated methods to identify severe chest injury using machine learning (ML) and natural language processing (NLP) methods from the electronic health record (EHR) for quality reporting.

Prediction of severe chest injury using natural language processing from the electronic health record.

Introduction: Trauma injury severity scores are currently calculated retrospectively from the electronic health record (EHR) using manual annotation by certified trauma coders. Natural language processing (NLP) of clinical documents in the EHR may enable automated injury scoring. We hypothesize that NLP with machine learning can discriminate between cases of severe and non-severe injury to the thorax after trauma.

Comparison of the Perspectives of Medical Students and Residents on the Surgery Learning Environment.

Background: The learning environment plays a critical role in learners' satisfaction and outcomes. However, we often lack insight into learners' perceptions and assessments of these environments. It can be difficult to discern learners' expectations, making their input critical.

Safety in Allowing Residents to Independently Perform Appendectomy: A Retrospective Review.

Background: In an era of competency-based education and concern about graduating resident readiness for practice, early resident autonomy and the ability to safely teach junior residents is becoming increasingly important. In this study, we aimed to understand the effect of "teaching resident" (2 residents operating under the supervision of an attending physician) appendectomy cases on outcomes.

Study Design: We performed a single-center retrospective review of 928 patients who underwent appendectomy within the University of Wisconsin hospital system, from October 2014 to December 2017.

Proficiency development for graduating medical students, using skills-level-appropriate mastery learning versus traditional learning for chest tube placement: Assessing anxiety, confidence, and performance.

Background: Mastery learning is an effective educational tool to assess basic procedural skill proficiency and may also be beneficial for more complex skills along the continuum of surgical training. In addition, anxiety and confidence have effects on cognitive and decision-making performance, both in educational and clinical settings. This study evaluates anxiety and confidence in a skills-level-appropriate mastery learning module for chest tube insertion in graduating medical students.

Patient-Centered Outcome Spectrum: An Evidence-based Framework to Aid in Shared Decision-making.

Objective: Our objective was to develop an alternate construct for reporting anticipated outcomes after emergency general surgery (EGS) that presents risk in terms of a composite measure.

Background: Currently available prediction tools generate risk outputs for discrete as opposed to composite measures of postoperative outcomes. A construct to synthesize multiple discrete estimates into a global understanding of a patient's likely postoperative health status is lacking and could augment shared decision-making conversations.

Number of rib fractures thresholds independently predict worse outcomes in older patients with blunt trauma.

Background: There have been conflicting reports regarding whether the number of rib fractures sustained in blunt trauma is associated independently with worse patient outcomes. We sought to investigate this risk-adjusted relationship among the lesser-studied population of older adults.

Methods: A retrospective review of the National Trauma Data Bank was performed for patients with blunt trauma who were ≥65 years old and had rib fractures between 2009 and 2012 (N = 67,695).

Nonoperative Management Is as Effective as Immediate Splenectomy for Adult Patients with High-Grade Blunt Splenic Injury.

Background: The comparative effectiveness of nonoperative management (NOM) vs immediate splenectomy (IS) for hemodynamically stable adult patients with grade IV or V blunt splenic injury (BSI) has not been clearly established in the literature.

Study Design: We performed a retrospective analysis of adult patients, from the 2013 to 2014 American College of Surgeons Trauma Quality Improvement Program (TQIP) Participant Use Data Files, who sustained grade IV or V BSI. Outcomes after IS vs attempted NOM were compared using propensity score analysis in order to adjust for patient- and injury-related variables.

Research and Evaluations of the Health Aspects of Disasters, Part IX: Risk-Reduction Framework.

A disaster is a failure of resilience to an event. Mitigating the risks that a hazard will progress into a destructive event, or increasing the resilience of a society-at-risk, requires careful analysis, planning, and execution. The Disaster Logic Model (DLM) is used to define the value (effects, costs, and outcome(s)), impacts, and benefits of interventions directed at risk reduction.

Research and Evaluations of the Health Aspects of Disasters, Part VIII: Risk, Risk Reduction, Risk Management, and Capacity Building.

There is a cascade of risks associated with a hazard evolving into a disaster that consists of the risk that: (1) a hazard will produce an event; (2) an event will cause structural damage; (3) structural damage will create functional damages and needs; (4) needs will create an emergency (require use of the local response capacity); and (5) the needs will overwhelm the local response capacity and result in a disaster (ie, the need for outside assistance). Each step along the continuum/cascade can be characterized by its probability of occurrence and the probability of possible consequences of its occurrence, and each risk is dependent upon the preceding occurrence in the progression from a hazard to a disaster. Risk-reduction measures are interventions (actions) that can be implemented to: (1) decrease the risk that a hazard will manifest as an event; (2) decrease the amounts of structural and functional damages that will result from the event; and/or (3) increase the ability to cope with the damage and respond to the needs that result from an event.

Research and Evaluations of the Health Aspects of Disasters, Part VII: The Relief/Recovery Framework.

The principal goal of research relative to disasters is to decrease the risk that a hazard will result in a disaster. Disaster studies pursue two distinct directions: (1) epidemiological (non-interventional); and (2) interventional. Both interventional and non-interventional studies require data/information obtained from assessments of function.

Research and Evaluations of the Health Aspects of Disasters, Part VI: Interventional Research and the Disaster Logic Model.

Disaster-related interventions are actions or responses undertaken during any phase of a disaster to change the current status of an affected community or a Societal System. Interventional disaster research aims to evaluate the results of such interventions in order to develop standards and best practices in Disaster Health that can be applied to disaster risk reduction. Considering interventions as production functions (transformation processes) structures the analyses and cataloguing of interventions/responses that are implemented prior to, during, or following a disaster or other emergency.

Research and Evaluations of the Health Aspects of Disasters, Part IV: Framework for Societal Structures: the Societal Systems.

For the purposes of research and/or evaluation, a community/society is organized into 13 Societal Systems under the umbrella of an overall Coordination and Control System. This organization facilitates descriptions of a community/society or a component of a community for assessment at any designated time across the Temporal Phases of a disaster. Such assessments provide a picture of the functional status of one or more Systems that comprise a community.

Research and Evaluations of the Health Aspects of Disasters, Part V: Epidemiological Disaster Research.

Studies of the health aspect of disasters focus either on the epidemiology of disasters to define the causes and the progression from a hazard to a disaster, or the evaluations of interventions provided during any phase of a disaster. Epidemiological disaster research studies are undertaken for the purposes of: (1) understanding the mechanisms by which hazards evolve into a disaster; (2) determining ways to mitigate the risk(s) that a specific hazard will progress into a disaster; (3) predicting the likely damages and needs of the population-at-risk for an event; and (4) identifying potential measures to increase the resilience of a community to future events. Epidemiological disaster research utilizes the Conceptual, Temporal, and Societal Frameworks to define what occurs when a hazard manifests as an event that causes a disaster.

Research and Evaluations of the Health Aspects of Disasters, Part III: Framework for the Temporal Phases of Disasters.

Each of the elements described in the Conceptual Framework for disasters has a temporal designation; each has a beginning and end time. The Temporal Framework defines these elements as phases that are based on characteristics rather than on absolute times. The six temporal phases include the: (1) Pre-event; (2) Event; (3) Structural Damage; (4) Functional Damage (changes in levels of functions of the Societal Systems); (5) Relief; and (6) Recovery phases.

Research and Evaluations of the Health Aspects of Disasters, Part II: The Disaster Health Conceptual Framework Revisited.

A Conceptual Framework upon which the study of disasters can be organized is essential for understanding the epidemiology of disasters, as well as the interventions/responses undertaken. Application of the structure provided by the Conceptual Framework should facilitate the development of the science of Disaster Health. This Framework is based on deconstructions of the commonly used Disaster Management Cycle.

Research and Evaluations of the Health Aspects of Disasters, Part I: An Overview.

The ultimate goals of conducting disaster research are to obtain information to: (1) decrease risks that a hazard will produce a disaster; (2) decrease the mortality associated with disasters; (3) decrease the morbidity associated with disasters; and (4) enhance recovery of the affected community. And decrease the risks that a hazard will produce a disaster. Two principal, but inter-related, branches of disaster research are: (1) Epidemiological; and (2) Interventional.

Disaster Research/Evaluation Frameworks, Part 1: An Overview-RETRACTED.

The goals of conducting disaster research are to obtain information to: (1) decrease the human, environmental, and economic losses; (2) decrease morbidity; (3) decrease pain and suffering; and (4) enhance the recovery of the affected population. Two principal, but inter-related, branches of disaster research are: (1) Epidemiological; and (2) Interventional. In response to the need for the discipline of disaster health to build its science on data that are generalizable and comparable, a set of five Frameworks have been developed to structure the information and research of the health aspects of disasters: (1) Conceptual; (2) Longitudinal; (3) Transectional Societal; (4) Relief-Recovery; and (5) Risk-Reduction.