Integration and Validation of a Natural Language Processing Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in the Emergency Department.

BACKGROUND: Emergency departments (ED) are an important intercept point for identifying suicide risk and connecting patients to care, however, more innovative, person-centered screening tools are needed. Natural language processing (NLP) -based machine learning (ML) techniques have shown promise to assess suicide risk, although whether NLP models perform well in differing geographic regions, at different time periods, or after large-scale events such as the COVID-19 pandemic is unknown. OBJECTIVE: To evaluate the performance of an NLP/ML suicide risk prediction model on newly collected language from the Southeastern United States using models previously tested on language collected in the Midwestern US. METHOD: 37 Suicidal and 33 non-suicidal patients from two EDs were interviewed to test a previously developed suicide risk prediction NLP/ML model. Model performance was evaluated with the area under the receiver operating characteristic curve (AUC) and Brier scores. RESULTS: NLP/ML models performed with an AUC of 0.81 (95% CI: 0.71-0.91) and Brier score of 0.23. CONCLUSION: The language-based suicide risk model performed with good discrimination when identifying the language of suicidal patients from a different part of the US and at a later time period than when the model was originally developed and trained.

External monitoring-induced pacemaker-driven tachycardia: a case report.

A 55-year-old African-American woman with a history of end-stage renal disease secondary to systemic lupus erythematosus, dual-chamber pacemaker placement secondary to sick sinus syndrome, and a previous subarachnoid hemorrhage presented via ambulance to our Emergency Department (ED) from an outside hospital with the report of altered mental status, hyperkalemia, and hypoglycemia. In the ED, the patient's initial physical examination revealed a stable, normal heart rate. Reassessment after placement of external monitoring devices found the patient to be tachycardic at approximately 132-135 beats/min, with minimal variation in rate. The patient was also tachypneic during this episode, up to a respiratory rate of 38 breaths/min. When misplaced external monitoring device leads were removed during pacemaker interrogation, the patient's heart rate dropped to the 70s. Reapplication of the external monitoring leads replicated the tachycardia. With permanent repositioning of the leads in the ED, the tachycardia did not return. The placement of the leads was determined to have caused a plethysmography-induced pacemaker-driven tachycardia.

Ketamine-propofol combination sedation for fracture reduction in the pediatric emergency department.

OBJECTIVES: To evaluate the time of onset and recovery from and the efficacy and safety of intravenous ketamine-propofol sedation for reduction of forearm fractures in the pediatric emergency department setting. STUDY DESIGN: Prospective, observational pilot study. METHODS: Children presenting to an urban pediatric emergency department requiring sedation for closed reduction of forearm fractures received ketamine 0.5 mg/kg and propofol 1 mg/kg. We measured time intervals from drug administration to reduction, recovery, and attainment of discharge criteria, and obtained ratings of depth of sedation, pain, and ease of reduction. A follow-up survey elicited patient recall, parental satisfaction, and delayed complications. Complications were recorded during the procedure and by chart review. RESULTS: Reduction was successful in 19 of 20 patients with one requiring open reduction. Median time intervals measured from initiation of ketamine injection were 5 minutes to reduction completion, 10 minutes to first purposeful response, and 38 minutes to suitability for discharge. Three patients recalled reduction or casting, but in no case was reduction reported to be the most painful aspect of visit. Emergency physicians and orthopedic residents rated sedation and ease of reduction favorably. Complications included mild hypoxia, vomiting, and transient ataxia. No apnea, hemodynamic compromise, dysphoria, or injection pain occurred. CONCLUSIONS: In this pilot study, the combination of ketamine and propofol provided effective sedation with rapid recovery and no clinically significant complications for children requiring closed reduction of forearm fractures.

Improved documentation of wound care with a structured encounter form in the pediatric emergency department.

OBJECTIVE: Accurate and complete documentation may enhance reimbursement and compliance with financial intermediary regulations, protect against litigation, and improve patient care. We measured the effect of introduction of a structured encounter form on the completeness of documentation of pediatric wound management in a teaching hospital. METHODS: The Children's Hospital Emergency Department introduced a structured encounter form for use in the documentation of wound care in place of the existing free-text dictation method. Attending physicians and trainees, all unaware of the study, had the option of using the form in place of free-text dictation for patients with lacerations requiring closure. We abstracted 100 consecutive free-text dictations from patients treated before the form's introduction. Following a 3-month run-in period, we abstracted 100 consecutive structured wound records. We compared the 2 chart types for completeness of documentation based on 20 predetermined criteria relevant to pediatric wound care. RESULTS: Overall completeness of documentation improved with structured forms (80% vs 68% for free text, P < .001), with significant improvements in 6 of 20 individual criteria. Trainees demonstrated improvement in documentation with the structured form, with the greatest improvements among senior-level residents. Documentation of the general physical examination worsened with structured charting. DISCUSSION: In an academic pediatric emergency department, the use of a structured complaint-specific form improved overall completeness of wound-care documentation. Structured encounter forms may provide for more standardized documentation for a variety of pediatric chief complaints, thereby facilitating communication and ultimately transition to template-driven systems in anticipation of an electronic medical record.

The use of pulse oximetry to exclude pneumonia in children.

The objective of this study was to determine whether pulse oximetry alone or in conjunction with the clinical examination is predictive of pneumonia in children who present to the emergency department with respiratory complaints. A retrospective comparison of children with radiographic pneumonia with children with respiratory complaints and negative chest radiography was used. The study took place in an emergency department of a large academic, tertiary care hospital. All children less than 24 months of age who presented with a respiratory complaint and underwent chest radiography during a 1-year period were included. Charts of children with radiographic pneumonia were compared with charts of children without pneumonia, retrospectively. Data abstracted onto data collection forms included: pulse oximetry measurement, vital signs, general appearance, lung examination, and final radiology interpretation of chest radiographs. Pneumonia was defined as a chest radiograph showing any opacity consistent with pneumonia as read by a board-prepared or -certified radiologist. A total of 803 children qualified for the study. Radiograph interpretations were available for 762, and 10.5% were found to have radiographic pneumonia. The median pulse oximetry reading of children with radiographic pneumonia was 97% (interquartile range 95th-98th percentile) compared with 98% (interquartile range 96th-99th percentile) in the control group. Forty-five percent (35 of 78) of the children with radiographic pneumonia showed oxygen saturations of 98% or higher with greater than 10% (8 of 78) displaying oxygen saturations of 100%. By using logistic regression, pulse oximetry was not found to be a statistically significant predictive variable for radiographic pneumonia. Pulse oximetry could not be used to rule out the presence of radiographic pneumonia in children less than 2 years of age who presented with respiratory complaints.