Artificial Intelligence to Predict Billing Code Levels of Emergency Department Encounters.

STUDY OBJECTIVE: To use artificial intelligence (AI) to predict billing code levels for emergency department (ED) encounters. METHODS: We accessed ED encounters from our health system from January to September 2023. We developed an ensemble model using natural language processing and machine learning techniques to predict billing codes from clinical notes combined with clinical characteristics and orders. Explainable AI techniques were used to help determine the important model features. The main endpoint was to predict evaluation and management professional billing codes (levels 2 to 5 [Current Procedural Terminology codes 99282 to 99285] and critical care). Secondary endpoints included predicting professional billing codes at different decision boundary thresholds and generalizability of the model at other EDs. RESULTS: There were 321,893 adult ED encounters coded at levels 2 (<1%), 3 (5%), 4 (38%), 5 (51%), and critical care (5%). Model performance for professional billing code levels of 4 and 5 yielded area under the receiver operating characteristic curve values of 0.94 and 0.95, accuracy values of 0.80 and 0.92, and F1-scores of 0.79 and 0.91, respectively. At a 95% decision boundary threshold, level 5 predicted charts had a precision/positive predictive value of 0.99 and recall/sensitivity of 0.57. The most important features using Shapley Additive Explanations values were critical care note, number of orders, discharge disposition, cardiology, and psychiatry. CONCLUSION: Currently available AI models accurately predict billing code levels for ED encounters based on clinical notes, clinical characteristics, and orders. This has the potential to automate coding of ED encounters and save administrative costs and time.

More Than Just a Weed: An Exploration of the Antimicrobial Activity of Rumex crispus using a Multivariate Data Analysis Approach.

Plants have a long history of use for their medicinal properties. The complexity of botanical extracts presents unique challenges and necessitates the application of innovative approaches to correctly identify and quantify bioactive compounds. For this study, we used untargeted metabolomics to explore the antimicrobial activity of Rumex crispus (yellow dock), a member of the Polygonaceae family used as an herbal remedy for bacterial infections. Ultra-performance liquid chromatography coupled with high resolution mass-spectrometry (UPLC-MS) was used to identify and quantify the known antimicrobial compound emodin. In addition, we used biochemometric approaches to integrate data measuring antimicrobial activity from R. crispus root starting material and fractions against methicillin-resistant Staphylococcus aureus (MRSA) with UPLC-MS data. Our results support the hypothesis that multiple constituents, including the anthraquinone emodin, contribute to the antimicrobial activity of R. crispus against MRSA.

Impact of Scribes on Billed Relative Value Units in an Academic Emergency Department.

BACKGROUND: Scribe use throughout health care is becoming more common. There is limited peer-reviewed literature supporting this emerging role in health care despite rapid uptake of the role. OBJECTIVES: Our study assesses impact of scribes on relative value units (RVUs) in adult and pediatric emergency departments (EDs). METHODS: A prospective cohort study was developed in a tertiary academic ED. Charts were coded by an external billing and coding company, then returned and mapped by International Classification of Diseases, 9th revision diagnostic codes. After training by a staff member with significant experience in implementing scribe programs, scribes provided 1-to-1 support to a provider as staffing allowed. Comparisons were made between scribed and nonscribed visits. RESULTS: There were 49,389 patient visits during the study period (39,926 adult [80.84%] and 9463 pediatric [19.16%] visits), of which 7865 (15.9%) were scribed. For adults, scribed visits produced 0.20 additional RVUs per patient (p < 0.001). Scribes generated additional RVUs in Emergency Severity Index (ESI) 2 (p < 0.001) and 3 (p < 0.001) patients. There were variable effects of scribes on RVUs by diagnostic codes. For pediatric patients, scribed encounters generated 0.08 fewer RVUs per patient (p = 0.007). ESI score had no effect on RVUs. The impact of scribes on pediatric diagnostic groupings was inconsistent. CONCLUSIONS: Scribes had a positive impact on RVUs in adult but not pediatric patients. Among adults, scribes led to higher RVUs in ESI 2 and 3 but not 4 and 5 patients, perhaps suggesting a limitation to improve revenue capture on lower-acuity patients.

Impact of scribes on patient throughput in adult and pediatric academic EDs.

OBJECTIVES: Assess the impact of scribes on an academic emergency department's (ED) patient-specific throughput. METHODS: Study design, setting, participants: A prospective cohort design compared throughput metrics of patients managed when scribes were and were not a part of the treatment team during pre-defined study hours in a tertiary academic ED with both an adult and pediatric ED. INTERVENTION: Eight scribes were hired and trained on-site by a physician with experience in scribe implementation. Scribes provided 1-to-1 support for a provider's work shift. An alternating-day pattern in months 2 to 5 post implementation ensured balance between the scribe and non-scribe groups in time of day, day of week, and patient complexity. RESULTS: Adult: Overall length of stay (LOS) was significantly longer for scribed patients (265 vs. 255 minutes, P=.028). The remaining throughput measures analyzed (door to provider, provider to disposition, and patient duration in treatment room) had higher summary values, but were not significant. Subgroup analysis revealed that patients seen by postgraduate year (PGY) 3 residents had significantly shorter LOS when seen with a scribe (244 vs. 262 minutes, P=.021). Pediatric: Overall LOS (163 vs. 151 minutes, P=.011), door to provider (21 vs. 16 minutes, P<.001), and treatment room duration (130 vs. 123 minutes, P=.020) were significantly longer when the treatment team had a scribe. CONCLUSIONS: Scribes failed to improve patient-specific throughput metrics in the first few months post implementation. Future work is needed to understand whether throughput efficiencies may eventually be gained after scribe implementation.

Presentation and Medical Management of Fibrocartilaginous Embolism in the Emergency Department.

BACKGROUND: Fibrocartilaginous embolism is an exceedingly rare condition that was formerly a clinical diagnosis based on mechanism of injury, physical examination findings, and older magnetic resonance imaging (MRI) technologies without a specific histologic diagnosis. Spinal cord MRI diffusion-weighted imaging allows for a more specific diagnosis. CASE REPORT: A 14-year-old male felt a sudden pop in his back while running sprints in his gym class. He slowly developed bilateral lower extremity weakness and urinary incontinence, prompting an emergency department evaluation. A MRI scan of his lumbar spine revealed degeneration, desiccation, and bulging of the T12-L1 disc with an accompanying subacute Schmorl's nodule. There was adjacent cord swelling and central cord T2 hyperintensity, with accompanying restricted diffusion consistent with spinal cord infarction. These findings, in conjunction with paraplegia and mechanism of injury, were highly suggestive of fibrocartilaginous embolism. WHY SHOULD AN EMERGENCY PHYSICIAN BE AWARE OF THIS?: An emergent MRI scan with the proper sequencing and immediate consultation with a spine surgery specialist are important to exclude a compressive myelopathy that would necessitate acute surgical decompression. There is significant uncertainty in the initial management and stabilization of this rare condition that has not been addressed in the emergency medicine literature.

Defining the clinical and procedural opportunities available to residents during rural rotations.

Introduction: Many emergency medicine (EM) residency programs include clinical rotations in rural emergency departments ("rural rotations") as part of their curriculum. These rotations are designed to expose residents to clinical scenarios that are less frequently encountered in tertiary centers. The objective of this study was to determine the rate at which residents were exposed to certain clinical and procedural experiences (CPEs) while on rural rotations compared to their usual academic training hospital. Methods: We conducted a retrospective chart review of all patient encounters involving EM residents at a large academic hospital in Rochester, Minnesota, compared with two rural hospitals in Austin, Minnesota, and Albert Lea, Minnesota, from July 1, 2019, to June 30, 2020. The frequency of each CPE was calculated and expressed as the number of CPEs encountered per 100 clinical hours worked. These values were compared between the rural and academic sites. Results: A total of 33,417 patient encounters over a total of 41,700 resident clinical hours were analyzed between the three study sites. The two settings (rural vs. academic) had significant differences in baseline patient demographics including age, acuity, and admission rates. Several CPEs were found to occur at a higher frequency in the rural hospitals versus the academic hospital: ambulance necessity documentation (9.3/100 h rural vs. 0.07/100 h academic, p ≤ 0.0001), laceration repair (3.39/100 h rural vs. 2.0/100 h academic, p = 0.0004), and splint/cast application (1.53/100 h rural vs. 0.07/100 h academic, p ≤ 0.0001). Conclusions: Rural EM rotations provide residents exposure to a variety of valuable educational experiences. These rotations may provide residents with superior exposures to some clinical experiences compared to academic hospitals, particularly out-of-ED transfers and orthopedic procedures. Residency programs without a current rural rotation should consider creating this as an option for their trainees.

Association of limited English proficiency with emergency department irregular departures and return visits: A cross-sectional cohort study in the Upper Midwest between January 2018 and December 2021.

OBJECTIVES: Patients with limited English proficiency (LEP) have been shown to experience disparities in emergency department (ED) care. The objectives of this study were to examine the associations between LEP and irregular ED departures and return ED visits. METHODS: We conducted a multicenter cross-sectional analysis of 18 EDs within an integrated health system in the upper Midwest from January 1, 2018, to December 31, 2021. ED visits of pediatric and adult patients who were discharged on the index visit were included for analysis. We analyzed the association of LEP with irregular departures, 72-h and 7-day return visits, and ED disposition at the time of that return visit. Multivariable model associations were calculated using generalized estimating equations and reported as odds ratios (OR) with 95% confidence intervals (CIs). RESULTS: A total of 745,464 total ED visits were analyzed, including 27,906 (3.7%) visits among patients with LEP. The most common preferred languages among patients with LEP were Spanish (12,759; 45.7%), Somali (4978; 17.8%), and Arabic (3185; 11.4%). After multivariable adjustment there were no differences in proportions of irregular departures (OR 1.09, 95% CI 0.99-1.21), 72-h returns (OR 0.99, 95% CI 0.92-1.06), or 7-day returns (OR 0.99, 95% CI 0.93-1.05) between patients with LEP or English proficiency. Patients with LEP returning within 72 h (OR 1.19, 95% CI 1.01-1.40) and 7 days (OR 1.15, 95% CI 1.01-1.33) were more likely to be admitted to the hospital. CONCLUSIONS: After multivariable adjustment, we did not find an increased frequency of irregular ED departures or 72-h or 7-day returns among patients with LEP compared with people proficient in English. However, we did find that higher proportions of patients with LEP were admitted to the hospital at the time of the return ED visit.

Factors Associated With Improved Pediatric Resuscitative Care in General Emergency Departments.

OBJECTIVES: To describe the quality of pediatric resuscitative care in general emergency departments (GEDs) and to determine hospital-level factors associated with higher quality. METHODS: Prospective observational study of resuscitative care provided to 3 in situ simulated patients (infant seizure, infant sepsis, and child cardiac arrest) by interprofessional GED teams. A composite quality score (CQS) was measured and the association of this score with modifiable and nonmodifiable hospital-level factors was explored. RESULTS: A median CQS of 62.8 of 100 (interquartile range 50.5-71.1) was noted for 287 resuscitation teams from 175 emergency departments. In the unadjusted analyses, a higher score was associated with the modifiable factor of an affiliation with a pediatric academic medical center (PAMC) and the nonmodifiable factors of higher pediatric volume and location in the Northeast and Midwest. In the adjusted analyses, a higher CQS was associated with modifiable factors of an affiliation with a PAMC and the designation of both a nurse and physician pediatric emergency care coordinator, and nonmodifiable factors of higher pediatric volume and location in the Northeast and Midwest. A weak correlation was noted between quality and pediatric readiness scores. CONCLUSIONS: A low quality of pediatric resuscitative care, measured using simulation, was noted across a cohort of GEDs. Hospital factors associated with higher quality included: an affiliation with a PAMC, designation of a pediatric emergency care coordinator, higher pediatric volume, and geographic location. A weak correlation was noted between quality and pediatric readiness scores.

Capturing the antimicrobial profile of Rosmarinus officinalis against methicillin-resistant Staphylococcus aureus (MRSA) with bioassay-guided fractionation and bioinformatics.

Natural products have been a primary source of medicines throughout the history of human existence. It is estimated that close to 70 % of small molecule pharmaceuticals on the market are derived from natural products. With increasing antibiotic resistance, natural products remain an important source for the discovery of novel antimicrobial compounds. The plant rosemary (Rosmarinus officinalis), has been widely and commonly used as a food preservative due to its antimicrobial potential. To evaluate the antimicrobial profile of this plant, we used bioassay-guided fractionation and bioinformatics approaches. Through bioassay-guided fractionation, we tested in vitro activities of a R. officinalis extract and fractions thereof, as well as pure compounds micromeric acid (1), oleanolic acid (2), and ursolic acid (3) against methicillin-resistant Staphylococcus aureus (MRSA). Compounds 1 and 3 showed complete inhibition of MRSA (with MIC values of 32 µg/mL and 8 µg/mL, respectively) while compound 2 displayed only partial inhibition (MIC > 64 µg/mL). In addition, we utilized orthogonal partial least square-discriminant analysis (OPLS-DA) and selectivity ratio (SR) analysis to correlate the isolated compounds 1-3 with the observed antimicrobial activity, as well as to identify antimicrobials present in trace quantities. For mass spectrometry (MS) data collected in the negative ionization mode, compound 1 was the most positively correlated with activity, while for MS data collected in the positive ion mode, compounds 2-3 had the highest positive correlation. Using the bioinformatics approaches, we highlighted additional antimicrobials associated with the antimicrobial activity of R. officinalis, including genkwanin (4), rosmadial (5a) and/or 16-hydroxyrosmadial (5b), rosmanol (6), and hesperetin (7). Compounds 1-3 resulting from the bioassay-guided fractionation were identified by MS-MS fragmentation patterns and 1H NMR spectra. Among the compounds highlighted by the biochemical analysis, compound 6 was identified by comparison with its commercial standard by employed ultra-performance liquid chromatography-high resolution mass spectrometry (UHPLC-HRMS), while 4, 5a-b and 7 were putatively identified based on MS data and in comparison with the literature. This is the first reported antimicrobial activity of micromeric acid (1) against MRSA.

Ruptured Ectopic Pregnancy with an Intrauterine Device: Case Report and Sonographic Considerations.

INTRODUCTION: Ectopic pregnancy carries a high morbidity and mortality; patients are at risk for rupture and life-threatening hemorrhage. CASE REPORT: We present a rare case of ruptured abdominal ectopic pregnancy in a patient with a well-positioned intrauterine device (IUD) and discuss the diagnostic utility that transabdominal point-of-care ultrasound (POCUS) can have when performed at the bedside. CONCLUSION: While pregnancy with an IUD in place is rare, when it is encountered the emergency provider should maintain a high degree of suspicion for extrauterine pregnancy and perform prompt evaluation for hemorrhagic shock using diagnostic POCUS.

Targeted and untargeted analysis of secondary metabolites to monitor growth and quorum sensing inhibition for methicillin-resistant Staphylococcus aureus (MRSA).

Drug resistant infections are an increasing problem world-wide, responsible for an estimated 700,000 annual mortalities. The use of antibiotics to treat such infections has resulted in the development of resistant bacterial pathogens such as methicillin-resistant Staphylococcus aureus (MRSA). One potential alternative strategy for treating drug resistant bacterial infections is to inhibit the production of toxins, thereby making the bacteria less harmful to the host, a so called "anti-virulence" approach. In MRSA, the agr quorum sensing system is one of the major regulators of toxin production, and quorum sensing inhibitors that target this system are a promising anti-virulence strategy. With this study, we developed a method that enables the activity of quorum sensing inhibitors to be measured using ultra-performance liquid chromatography coupled to mass spectrometry (UPLC-MS). This method is an improvement over existing methods because it can be employed to distinguish antimicrobial activity from quorum sensing inhibition activity based on the UPLC-MS data. This is possible by simultaneously tracking production of metabolites regulated by the agr quorum sensing system (AIP-I and formylated δ-toxin) and a metabolite that appears not to be agr regulated under the conditions of this study (aureusimine B). The newly developed method provides more nuanced indication of how metabolite production changes over time and in response to quorum sensing or growth inhibition than is possible with commonly employed spectroscopic methods.

Payer Type and Emergency Department Visit Prices.

This cross-sectional study assesses list prices, cash prices, and negotiated rates for emergency department services.

Simultaneous determination of estrogens (ethinylestradiol and norgestimate) concentrations in human and bovine serum albumin by use of fluorescence spectroscopy and multivariate regression analysis.

The endocrine disruption property of estrogens necessitates the immediate need for effective monitoring and development of analytical protocols for their analyses in biological and human specimens. This study explores the first combined utility of a steady-state fluorescence spectroscopy and multivariate partial-least-square (PLS) regression analysis for the simultaneous determination of two estrogens (17α-ethinylestradiol (EE) and norgestimate (NOR)) concentrations in bovine serum albumin (BSA) and human serum albumin (HSA) samples. The influence of EE and NOR concentrations and temperature on the emission spectra of EE-HSA EE-BSA, NOR-HSA, and NOR-BSA complexes was also investigated. The binding of EE with HSA and BSA resulted in increase in emission characteristics of HSA and BSA and a significant blue spectra shift. In contrast, the interaction of NOR with HSA and BSA quenched the emission characteristics of HSA and BSA. The observed emission spectral shifts preclude the effective use of traditional univariate regression analysis of fluorescent data for the determination of EE and NOR concentrations in HSA and BSA samples. Multivariate partial-least-squares (PLS) regression analysis was utilized to correlate the changes in emission spectra with EE and NOR concentrations in HSA and BSA samples. The figures-of-merit of the developed PLS regression models were excellent, with limits of detection as low as 1.6×10(-8) M for EE and 2.4×10(-7) M for NOR and good linearity (R(2)>0.994985). The PLS models correctly predicted EE and NOR concentrations in independent validation HSA and BSA samples with a root-mean-square-percent-relative-error (RMS%RE) of less than 6.0% at physiological condition. On the contrary, the use of univariate regression resulted in poor predictions of EE and NOR in HSA and BSA samples, with RMS%RE larger than 40% at physiological conditions. High accuracy, low sensitivity, simplicity, low-cost with no prior analyte extraction or separation required makes this method promising, compelling, and attractive alternative for the rapid determination of estrogen concentrations in biomedical and biological specimens, pharmaceuticals, or environmental samples.