Using natural language processing in emergency medicine health service research: A systematic review and meta-analysis.

OBJECTIVES: Natural language processing (NLP) represents one of the adjunct technologies within artificial intelligence and machine learning, creating structure out of unstructured data. This study aims to assess the performance of employing NLP to identify and categorize unstructured data within the emergency medicine (EM) setting. METHODS: We systematically searched publications related to EM research and NLP across databases including MEDLINE, Embase, Scopus, CENTRAL, and ProQuest Dissertations & Theses Global. Independent reviewers screened, reviewed, and evaluated article quality and bias. NLP usage was categorized into syndromic surveillance, radiologic interpretation, and identification of specific diseases/events/syndromes, with respective sensitivity analysis reported. Performance metrics for NLP usage were calculated and the overall area under the summary of receiver operating characteristic curve (SROC) was determined. RESULTS: A total of 27 studies underwent meta-analysis. Findings indicated an overall mean sensitivity (recall) of 82%-87%, specificity of 95%, with the area under the SROC at 0.96 (95% CI 0.94-0.98). Optimal performance using NLP was observed in radiologic interpretation, demonstrating an overall mean sensitivity of 93% and specificity of 96%. CONCLUSIONS: Our analysis revealed a generally favorable performance accuracy in using NLP within EM research, particularly in the realm of radiologic interpretation. Consequently, we advocate for the adoption of NLP-based research to augment EM health care management.

Society of Critical Care Medicine Guidelines on Recognizing and Responding to Clinical Deterioration Outside the ICU: 2023.

RATIONALE: Clinical deterioration of patients hospitalized outside the ICU is a source of potentially reversible morbidity and mortality. To address this, some acute care hospitals have implemented systems aimed at detecting and responding to such patients. OBJECTIVES: To provide evidence-based recommendations for hospital clinicians and administrators to optimize recognition and response to clinical deterioration in non-ICU patients. PANEL DESIGN: The 25-member panel included representatives from medicine, nursing, respiratory therapy, pharmacy, patient/family partners, and clinician-methodologists with expertise in developing evidence-based Clinical Practice Guidelines. METHODS: We generated actionable questions using the Population, Intervention, Control, and Outcomes (PICO) format and performed a systematic review of the literature to identify and synthesize the best available evidence. We used the Grading of Recommendations Assessment, Development, and Evaluation Approach to determine certainty in the evidence and to formulate recommendations and good practice statements (GPSs). RESULTS: The panel issued 10 statements on recognizing and responding to non-ICU patients with critical illness. Healthcare personnel and institutions should ensure that all vital sign acquisition is timely and accurate (GPS). We make no recommendation on the use of continuous vital sign monitoring among unselected patients. We suggest focused education for bedside clinicians in signs of clinical deterioration, and we also suggest that patient/family/care partners' concerns be included in decisions to obtain additional opinions and help (both conditional recommendations). We recommend hospital-wide deployment of a rapid response team or medical emergency team (RRT/MET) with explicit activation criteria (strong recommendation). We make no recommendation about RRT/MET professional composition or inclusion of palliative care members on the responding team but suggest that the skill set of responders should include eliciting patients' goals of care (conditional recommendation). Finally, quality improvement processes should be part of a rapid response system. CONCLUSIONS: The panel provided guidance to inform clinicians and administrators on effective processes to improve the care of patients at-risk for developing critical illness outside the ICU.

Executive Summary: Society of Critical Care Medicine Guidelines on Recognizing and Responding to Clinical Deterioration Outside the ICU.

RATIONALE: Clinical deterioration of patients hospitalized outside the ICU is a source of potentially reversible morbidity and mortality. To address this, some acute care facilities have implemented systems aimed at detecting and responding to such patients. OBJECTIVES: To provide evidence-based recommendations for hospital clinicians and administrators to optimize recognition and response to clinical deterioration in non-ICU patients. PANEL DESIGN: The 25-member panel included representatives from medicine, nursing, respiratory therapy, pharmacy, patient/family partners, and clinician-methodologists with expertise in developing evidence-based clinical practice guidelines. METHODS: We generated actionable questions using the Population, Intervention, Control, and Outcomes format and performed a systematic review of the literature to identify and synthesize the best available evidence. We used the Grading of Recommendations Assessment, Development, and Evaluation approach to determine certainty in the evidence and to formulate recommendations and good practice statements (GPSs). RESULTS: The panel issued 10 statements on recognizing and responding to non-ICU patients with critical illness. Healthcare personnel and institutions should ensure that all vital sign acquisition is timely and accurate (GPS). We make no recommendation on the use of continuous vital sign monitoring among "unselected" patients due to the absence of data regarding the benefit and the potential harms of false positive alarms, the risk of alarm fatigue, and cost. We suggest focused education for bedside clinicians in signs of clinical deterioration, and we also suggest that patient/family/care partners' concerns be included in decisions to obtain additional opinions and help (both conditional recommendations). We recommend hospital-wide deployment of a rapid response team or medical emergency team (RRT/MET) with explicit activation criteria (strong recommendation). We make no recommendation about RRT/MET professional composition or inclusion of palliative care members on the responding team but suggest that the skill set of responders should include eliciting patients' goals of care (conditional recommendation). Finally, quality improvement processes should be part of a rapid response system (GPS). CONCLUSIONS: The panel provided guidance to inform clinicians and administrators on effective processes to improve the care of patients at-risk for developing critical illness outside the ICU.

The association between electronic health information usage and patient-centered communication: a cross sectional analysis from the Health Information National Trends Survey (HINTS).

BACKGROUND: Patient-provider communication can be assessed by the patient-centered communication (PCC) score. With rapid development of electronic health (eHealth) information usage, we are uncertain of their role in PCC. Our study aims to determine the association between PCC and eHealth usage with the analysis of national representative survey data. METHODS: This is a cross sectional analysis using the Health Information National Trends Survey 5 (HINTS 5) cycle 1 to cycle 4 data (2017-2020). Seven specific questions were used for PCC assessment, and eHealth usage was divided into two types (private-eHealth and public-eHealth usage). A multivariate logistic regression was performed to determine the association between PCC and eHealth usage after the adjustment of other social, demographic, and clinical variables. RESULTS: Our study analyzed a total of 13,055 unweighted participants representing a weighted population of 791,877,728. Approximately 43% of individuals used private eHealth and 19% used public eHealth. The adjusted odds ratio (AOR) of private-eHealth usage associated with positive PCC was 1.17 (95% CI 1.02-1.35, p = 0.027). The AOR of public-eHealth usage associated with positive PCC was 0.84 (95% CI 0.71-0.99, p = 0.043). CONCLUSION: Our study found that eHealth usage association with PCC varies. Private-eHealth usage was positively associated with PCC, whereas public-eHealth usage was negatively associated with PCC.

The Association of Name Recognition, Empathy Perception, and Satisfaction With Resident Physicians' Care Amongst Patients in an Academic Emergency Department.

Background: Recognition of the provider's name, provider empathy, and the patient's satisfaction with their care are patient-provider rapport measures. This study aimed to determine: 1) resident physicians' name recognition by patients in the emergency department; and 2) name recognition in association with patient perception of the resident's empathy and their satisfaction with the resident's care. Methods: This was a prospective observational study. A patient recognizing a resident physician was defined as the patient remembering a resident's name, understanding the level of training, and understanding a resident's role in patient care. A patient's perception of resident physician empathy was measured by the Jefferson Scale of Patient Perception of Physician Empathy (JSPPPE). Patient satisfaction of the resident was measured utilizing a real-time satisfaction survey. Multivariate logistic regressions were performed to determine the association amongst patient recognition of resident physicians, JSPPPE, and patient satisfaction after adjustments were made for demographics and resident training level. Results: We enrolled 30 emergency medicine resident physicians and 191 patients. Only 26% of studied patients recognized resident physicians. High JSPPPE scores were given by 39% of patients recognizing resident physicians compared to 5% of those who were not recognized (P = 0.013). High patient satisfaction scores were recorded in 31% of patients who recognized resident physicians compared to 7% who did not (P = 0.008). The adjusted odds ratios of patient recognition of resident physicians to high JSPPPE and high satisfaction scores were 5.29 (95% confidence interval (CI): 1.33 - 21.02, P = 0.018) and 6.12 (1.84 - 20.38, P = 0.003) respectively. Conclusions: Patient recognition of resident physicians is low in our study. However, patient recognition of resident physicians is associated with a higher patient perception of physician empathy and higher patient satisfaction. Our study suggests that resident education advocating for patient recognition of their healthcare provider's status needs to be emphasized as part of patient-centered health care.

Addressing end-of-life care in the chronically ill: Conversations in the emergency department.

Patients present to the emergency department in various stages of chronic illness. Advance directives (ADs) aid emergency physicians in making treatment decisions, but only a minority of Americans have completed an AD, and the percentage of those who have discussed their end-of-life wishes may be even lower. This article addresses the use of common ADs and roadblocks to their use from the perspectives of families, patients, and physicians. Cases to examine new approaches to optimizing end-of-life conversations in patients who are chronically ill, such as the Improving Palliative Care in Emergency Medicine Project, a decision-making framework that opens discussion for patients to gain understanding and determine preferences, and the Brief Negotiated Interview, a 7-minute, scripted, motivational interview that determines willingness for behavior change and initiates care planning, are used.

The influence of patient perception of physician empathy on patient satisfaction among attending physicians working with residents in an emergent care setting.

BACKGROUND: It is unclear whether the patient's perception of attending physician empathy and the patient's satisfaction can be affected when attending physicians work alongside residents. We aim to determine the influence residents may have on (1) patient perception of attending physician empathy and (2) patient satisfaction as it relates to their respective attending physicians. METHODS: This is a prospective single-center observational study. Patient perception of physician empathy was measured using Jefferson Scale of Patient Perception of Physician Empathy (JSPPPE) in both attendings and residents in the Emergency Department. Patient satisfaction with attending physicians and residents was measured by real-time patient satisfaction survey. Multivariate logistic regressions were performed to determine the association between patient satisfaction and JSPPPE after patient demographics, attending physician different experience, and residents with different years of training were adjusted. RESULTS: A total of 351 patients were enrolled. Mean JSPPPE scores were 30.1 among attending working alone, 30.1 in attending working with PGY-1 EM residents, 29.6 in attending working with PGY-2, and 27.8 in attending working with PGY-3 (p < 0.05). Strong correlation occurred between attending JSPPPE score and patient satisfaction to attending physicians (ρ > 0.5). The adjusted odds ratio was 1.32 (95% CI 1.23-1.41, p < 0.001) on attending's JSPPPE score predicting patient satisfaction to the attending physicians. However, there were no significant differences on patient satisfaction among four different groups. CONCLUSION: Empathy has strong correlation with patient satisfaction. Decreased patient perception of attending physician empathy was found when working with senior residents in comparison to working alone or with junior residents.

Association between burnout and wellness culture among emergency medicine providers.

OBJECTIVE: Burnout is a common occurrence among healthcare providers and has been associated with provider wellness culture. However, this association has not been extensively studied among emergency medicine (EM) providers. We aim to determine the association between EM provider burnout and their culture of wellness, and to elicit the independent wellness culture domains most predictive of burnout prevention. METHODS: This was a multi-center observational study. We enrolled EM physicians and advanced practice providers from sixteen different emergency departments (EDs). Provider wellness culture and burnout surveys were performed. The wellness culture domains included in this study are personal/organizational value alignment, provider appreciation, leadership quality, self-controlled scheduling, peer support, and family support. Correlations between each wellness culture domain and burnout were analyzed by Pearson correlation co-efficiency, and their associations were measured by multivariate logistic regression with adjustments of other confounders. RESULTS: A total of 242 ED provider surveys were entered for final analysis. The overall burnout rate was 54% (130/242). Moderate correlations were found between burnout and two wellness culture domains (value alignment: r=-0.43, P<0.001 and provider appreciation: r=-0.49, P<0.001). The adjusted odds ratio of provider appreciation associated with burnout was 0.44 (95% confidence interval, 0.25-0.77; P=0.004), adjusted odds ratio of family support was 0.67 (95% confidence interval, 0.48-0.95; P=0.025). CONCLUSION: ED providers have a relatively high burnout rate. Provider burnout might have certain associations with wellness culture domains. Provider appreciation and family support seem to play important roles in burnout protection.

Synergistic effects of emergency physician empathy and burnout on patient satisfaction: a prospective observational study.

BACKGROUND: Physician empathy and burnout have been shown to be independently associated with patient satisfaction. However, their correlations were uncertain in previous studies. We aimed to determine correlations among empathy, burnout, and patient satisfaction, and further analyse interactions among these factors. METHOD: A single centre prospective observational study was conducted from December 2018 to August 2019 at JPS Health Network, USA. Emergency physician (EP) self-assessed empathy and burnout were measured by the Jefferson Scale of Empathy (JSE) and the Copenhagen Burnout Inventory (CBI) separately. We assessed patient perception of physician empathy and patient satisfaction with their treating physician by the Jefferson Scale of Patient Perception of Physician Empathy and a patient assessed satisfaction survey. Spearman's correlation was used to determine associations among JSE, patient assessed physician empathy, CBI and patient satisfaction. Additionally, JSE, patient assessed physician empathy and CBI predictive of patient satisfaction were measured by multivariate logistic regression analysis. RESULTS: A total of 28 EPs and 423 patients were enrolled. Patient satisfaction had a weak correlation with JSE (ρ=0.11) but showed a strong correlation with patient assessed physician empathy (ρ=0.60). CBI showed no correlation with patient satisfaction (ρ<0.1). However, when JSE, patient assessed physician empathy and CBI were analysed together in relation to patient satisfaction, adjusted odds ratios (AOR) was 3.85 (95% CI 1.36 to 10.88) with high patient assessed physician empathy alone; AOR was 7.17 (2.62-19.67) when high patient assessed physician empathy was combined with low CBI; and AOR was 8.37 (3.07-22.83) when high patient assessed physician empathy, low CBI and high JSE were combined. CONCLUSION: Patient assessed physician empathy had a strong positive correlation with patient satisfaction. Moreover, higher patient satisfaction was achieved from EPs of high patient assessed physician empathy, low CBI and high JSE, indicating a positive synergistic effect. These findings suggest different interventions might be applied to EPs of different wellness features to maximise patient satisfaction.

Fulfillment, burnout and resilience in emergency medicine-Correlations and effects on patient and provider outcomes.

BACKGROUND: Healthcare provider wellness have been reported to correlate with patient care outcomes. It is not understood whether synergistic effects may exist between them. OBJECTIVE: We aim to investigate three provider wellness markers and determine their associations with provider self-reported medical errors and intent-to-leave outcomes among Emergency Department (ED) providers. DESIGN: This is a multi-center retrospective study. METHOD: Three wellness domains include professional fulfillment (PF), burnout (BO), and personal resilience (PR). Two outcomes measured as provider self-reported medical errors and provider intent-to-leave. Correlations between wellness markers and outcomes were analyzed. When adjusted for other confounders (provider demographics, provider experience, and operational environment), a multivariate logistic regression analysis was performed to further determine the interactions among these three domains on provider wellness affecting patient and provider related outcomes. RESULTS: Total 242 surveys were collected from providers at 16 different EDs. The median score of PF were 2.83 among physicians and 2.67 among APPs, BO were 1.00 (physicians) and 0.95 (APPs), and PR were 0.88 (physicians) and 0.81 (APPs). The median scores of self-reported medical errors were 1.50 (physicians) and 0.95 (APPs), and intent-to-leave were 1.00 (physicians and APPs). High correlations occurred among PF, BO, and PR. When analyzed together, high PF, low BO, and high PR functioned as a protective effect on provider intent-to-leave (adjusted odds ratios = 0.09, 95% CI 0.03-0.30). CONCLUSION: High correlations occurred among three provider wellness markers with no significant difference between physicians and APPs. Providers with high PR, low BO, and high PR tended to be more stable in their jobs.

Association Between Empathy and Burnout Among Emergency Medicine Physicians.

BACKGROUND: The association between physician self-reported empathy and burnout has been studied in the past with diverse findings. We aimed to determine the association between empathy and burnout among United States emergency medicine (EM) physicians using a novel combination of tools for validation. METHODS: This was a prospective single-center observational study. Data were collected from EM physicians. From December 1, 2018 to January 31, 2019, we used the Jefferson scale of empathy (JSE) to assess physician empathy and the Copenhagen burnout inventory (CBI) to assess burnout. We divided EM physicians into different groups (residents in each year of training, junior/senior attendings). Empathy, burnout scores and their association were analyzed and compared among these groups. RESULTS: A total of 33 attending physicians and 35 EM residents participated in this study. Median self-reported empathy scores were 113 (interquartile range (IQR): 105 - 117) in post-graduate year (PGY)-1, 112 (90 - 115) in PGY-2, 106 (93 - 118) in PGY-3 EM residents, 112 (105 - 116) in junior and 114 (101 - 125) in senior attending physicians. Overall burnout scores were 43 (33 - 50) in PGY-1, 51 (29 - 56) in PGY-2, 43 (42 - 53) in PGY-3 EM residents, 33 (24 - 47) in junior attending and 25 (22 - 53) in senior attending physicians separately. The Spearman correlation (ρ) was -0.11 and ß-weight was -0.23 between empathy and patient-related burnout scores. CONCLUSION: Self-reported empathy declines over the course of EM residency training and improves after graduation. Overall high burnout occurs among EM residents and improves after graduation. Our analysis showed a weak negative correlation between self-reported empathy and patient-related burnout among EM physicians.

Large observational study on risks predicting emergency department return visits and associated disposition deviations.

OBJECTIVE: A common emergency department (ED) patient care outcome metric is 72-hour ED return visits (EDRVs). Risks predictive of EDRV vary in different studies. However, risk differences associated with related versus unrelated EDRV and subsequent EDRV disposition deviations (EDRVDD) are rarely addressed. We aim to compare the potential risk patterns predictive of related and unrelated EDRV and further determine those potential risks predictive of EDRVDD. METHODS: We conducted a large retrospective observational study from September 1, 2015 through June 30, 2016. ED Patient demographic characteristics and clinical metrics were compared among patients of 1) related; 2) unrelated; and 3) no EDRVs. EDRVDD was defined as obvious disposition differences between initial ED visit and return visits. A multivariate multinomial logistic regression was performed to determine the independent risks predictive of EDRV and EDRVDD after adjusting for all confounders. RESULTS: A total of 63,990 patients were enrolled; 4.65% were considered related EDRV, and 1.80% were unrelated. The top risks predictive of EDRV were homeless, patient left without being seen, eloped, or left against medical advice. The top risks predictive of EDRVDD were geriatric and whether patients had primary care physicians regardless as to whether patient returns were related or unrelated to their initial ED visits. CONCLUSION: Over 6% of patients experienced ED return visits within 72 hours. Though risks predicting such revisits were multifactorial, similar risks were identified not only for ED return visits, but also for return ED visit disposition deviations.

Status of Emergency Department Seventy-Two Hour Return Visits Among Homeless Patients.

BACKGROUND: We aim to externally validate the status of emergency department (ED) appropriate utilization and 72-h ED returns among homeless patients. METHODS: This is a retrospective single-center observational study. Patients were divided into two groups (homeless versus non-homeless). Patients' general characteristics, clinical variables, ED appropriate utilization, and ED return disposition deviations were compared and analyzed separately. RESULTS: Study enrolled a total of 63,990 ED visits. Homeless patients comprised 9.3% (5,926) of visits. Higher ED 72-h returns occurred among homeless patients in comparison to the non-homeless patients (17% versus 5%, P < 0.001). Rate of significant ED disposition deviations (e.g., admission, triage to operation room, or death) on return visits were lower in homeless patients when compared to non-homeless patient populations (15% versus 23%, P < 0.001). CONCLUSIONS: Though ED return rate was higher among homeless patients, return visit case management seems appropriate, indicating that 72-h ED returns might not be an optimal healthcare quality measurement for homeless patients.