A Population-Based Cohort Study Evaluating Outcomes and Costs for Syncope Presentations to the Emergency Department

Role of Artificial Intelligence in Improving Syncope Management

Syncope is common in the general population and a common presenting symptom in acute care settings. Substantial costs are attributed to the care of patients with syncope. Current challenges include differentiating syncope from its mimickers, identifying serious underlying conditions that caused the syncope, and wide variations in current management. Although validated risk tools exist, especially for short-term prognosis, there is inconsistent application, and the current approach does not meet patient needs and expectations. Artificial intelligence (AI) techniques, such as machine learning methods including natural language processing, can potentially address the current challenges in syncope management. Preliminary evidence from published studies indicates that it is possible to accurately differentiate syncope from its mimickers and predict short-term prognosis and hospitalisation. More recently, AI analysis of electrocardiograms has shown promise in detection of serious structural and functional cardiac abnormalities, which has the potential to improve syncope care. Future AI studies have the potential to address current issues in syncope management. AI can automatically prognosticate risk in real time by accessing traditional and nontraditional data. However, steps to mitigate known problems such as generalisability, patient privacy, data protection, and liability will be needed. In the past AI has had limited impact due to underdeveloped analytical methods, lack of computing power, poor access to powerful computing systems, and availability of reliable high-quality data. All impediments except data have been solved. AI will live up to its promise to transform syncope care if the health care system can satisfy AI requirement of large scale, robust, accurate, and reliable data.

Classification of vasovagal syncope from physiological signals on tilt table testing

BACKGROUND

The diagnostic test for vasovagal syncope (VVS), the most common cause of syncope is head-up tilt test (HUTT) assessment. During the test, subjects experienced clinical symptoms such as nausea, sweating, pallor, the feeling of palpitations, being on the verge of passing out, and fainting. The study's goal is to develop an algorithm to classify VVS patients based on physiological signals blood pressure (BP) and electrocardiography (ECG) obtained from the HUTT.

METHODS

After 10 min of supine rest, the subject was tilted at a 70-degree angle on a tilt table for approximately a total of 35 min. 400 µg of glyceryl trinitrate (GTN) was administered sublingually after the first 20 min and monitoring continued for another 15 min. Mean imputation and K-nearest neighbors (KNN) imputation approaches to handle missing values. Next, feature selection techniques were implemented, including genetic algorithm, recursive feature elimination, and feature importance, to determine the crucial features. The Mann-Whitney U test was then performed to determine the statistical difference between two groups. Patients with VVS are categorized via machine learning models including Support Vector Machine (SVM), Gaussian Naïve Bayes (GNB), Multinomial Naïve Bayes (MNB), KNN, Logistic Regression (LR), and Random Forest (RF). The developed model is interpreted using an explainable artificial intelligence (XAI) model known as partial dependence plot.

RESULTS

A total of 137 subjects aged between 9 and 93 years were recruited for this study, 54 experienced clinical symptoms were considered positive tests, while the remaining 83 tested negative. Optimal results were obtained by combining the KNN imputation technique and three tilting features with SVM with 90.5% accuracy, 87.0% sensitivity, 92.7% specificity, 88.6% precision, 87.8% F1 score, and 95.4% ROC (receiver operating characteristics) AUC (area under curve).

CONCLUSIONS

The proposed algorithm effectively classifies VVS patients with over 90% accuracy. However, the study was confined to a small sample size. More clinical datasets are required to ensure that our approach is generalizable.

Developing Implementation Strategies to Support the Uptake of a Risk Tool to Aid Physicians in the Clinical Management of Patients With Syncope: Systematic Theoretical and User-Centered Design Approach

BACKGROUND

The Canadian Syncope Risk Score (CSRS) was developed to improve syncope management in emergency department settings. Evidence-based tools often fail to have the intended impact because of suboptimal uptake or poor implementation.

OBJECTIVE

In this paper, we aimed to describe the process of developing evidence-based implementation strategies to support the deployment and use of the CSRS in real-world emergency department settings to improve syncope management among physicians.

METHODS

We followed a systematic approach for intervention development, including identifying who needs to do what differently, identifying the barriers and enablers to be addressed, and identifying the intervention components and modes of delivery to overcome the identified barriers. We used the Behaviour Change Wheel to guide the selection of implementation strategies. We engaged CSRS end users (ie, emergency medicine physicians) in a user-centered design approach to generate and refine strategies. This was achieved over a series of 3 qualitative user-centered design workshops lasting 90 minutes each with 3 groups of emergency medicine physicians.

RESULTS

A total of 14 physicians participated in the workshops. The themes were organized according to the following intervention development steps: theme 1-identifying and refining barriers and theme 2-identifying the intervention components and modes of delivery. Theme 2 was subdivided into two subthemes: (1) generating high-level strategies and developing strategies prototypes and (2) refining and testing strategies. The main strategies identified to overcome barriers included education in the format of meetings, videos, journal clubs, and posters (to address uncertainty around when and how to apply the CSRS); the development of a web-based calculator and integration into the electronic medical record (to address uncertainty in how to apply the CSRS); a local champion (to address the lack of team buy-in); and the dissemination of evidence summaries and feedback through email communications (to address a lack of evidence about impact).

CONCLUSIONS

The ability of the CSRS to effectively improve patient safety and syncope management relies on broad buy-in and uptake across physicians. To ensure that the CSRS is well positioned for impact, a comprehensive suite of strategies was identified to address known barriers.

Impact of Admission of Patients With Syncope in Non-Teaching Hospitals Versus Teaching Hospitals: A Nationwide Analysis

Syncope is a common condition affecting many individuals, and it remains uncertain whether admission to academic medical centers (AMCs) leads to better outcomes than non-AMCs. This study is aimed to investigate whether there is a difference in mortality, length of stay (LoS), and total hospital charges between patients admitted with syncope to AMCs and non-AMCs. This retrospective cohort study used the National Inpatient Database (NIS) to examine patients aged 18 years and older admitted with a primary diagnosis of syncope to AMCs and non-AMCs from 2016 to 2020. Univariate and multivariate logistic regression analyses were conducted, adjusting for confounders, to assess the primary outcome of all-cause in-hospital mortality and secondary outcomes, including hospital LoS and total cost of admission. Patient characteristics were also described. Of the 451,820 patients who met the inclusion criteria, 69.6% were admitted to AMCs and 30.4% to non-AMCs. Patient age was similar between the two groups (68 years in AMC versus 70 years in non-AMC; p < 0.001), as was sex distribution (52% female in AMC versus 53% in non-AMC; 48% male in AMC versus 47% in non-AMC; p < 0.002). Most patients in both groups were white, while the percentages of black and Hispanic patients were slightly higher in non-AMCs. The study found no difference in all-cause mortality between patients admitted to AMCs and non-AMCs (p = 0.33). However, LoS was marginally longer in AMC patients (2.6 days in AMC versus 2.4 days in the non-AMC group; p < 0.001), and the total cost was higher for AMCs by $3,526 per admission. The estimated total economic burden related to syncope was over 3 billion USD per year. This study suggests that the teaching status of hospitals did not significantly affect the mortality of patients admitted with syncope. However, it may have contributed to marginally longer hospital LoS and higher total hospital charges.

A Rational Evaluation of the Syncope Patient: Optimizing the Emergency Department Visit

Syncope accounts for up to 2% of emergency department visits and results in the hospitalization of 12–86% of patients. There is often a low diagnostic yield, with up to 50% of hospitalized patients being discharged with no clear diagnosis. We will outline a structured approach to the syncope patient in the emergency department, highlighting the evidence supporting the role of clinical judgement and the initial electrocardiogram (ECG) in making the preliminary diagnosis and in safely identifying the patients at low risk of short- and long-term adverse events or admitting the patient if likely to benefit from urgent intervention. Clinical decision tools and additional testing may aid in further stratifying patients and may guide disposition. While hospital admission does not seem to offer additional mortality benefit, the efficient utilization of outpatient testing may provide similar diagnostic yield, preventing unnecessary hospitalizations.

The Impact of a Nurse-Led Syncope Clinic: Experience from a single UK tertiary center

Background

Syncope is a leading cause of hospital admission and is associated with significant morbidity and mortality. Our Syncope Clinic commenced in 2014 and we sought to evaluate its impact on outcomes (1‐yr mortality and syncope re‐hospitalization) in patients discharged following syncope admission.

Methods

A single‐center study of all consecutive patients discharged with syncope (ICD‐10 R55) between April 2012 and 2017. Patient demographics, comorbidities, hospital stay, syncope re‐hospitalization, and mortality at one‐year were collected. Those subsequently referred and seen in Syncope Clinic were compared with those who were not and predictors of poor outcome were evaluated.

Results

In total 2950 patients were discharged from hospital with syncope (median age: 73years, 51% male) with 1220 (41%) discharged same‐day; after commencement of Syncope Clinic 231were subsequently reviewed here. Overall mortality was 11%, which was lower in the Syncope Clinic group (3% vs 12%, P < .001). Temporal analysis revealed reduced re‐hospitalization following commencement of Syncope Clinic (2% vs 6%, P = .027). Independent predictors of mortality were increasing age (HR 1.03, 95% CI 1.03‐1.04), AF (HR 1.6, 95% CI 1.2‐2.1), HF (HR 2.2, 95% CI 1.6‐3.0), COPD (HR 1.9, 95% CI 1.4‐2.7), and CHADS₂ score ≥ 1 (HR 1.45, 95% CI 1,12‐1.87). Syncope Clinic attendance was associated with reduced mortality (HR 0.3, 95% CI 0.1‐0.6).

Conclusions

Syncope patients discharged from hospital had reduced 1yr mortality if seen in subsequent Syncope Clinic. Independent predictors of mortality were COPD, HF, AF, and CHADS₂ ≥1. Prospective randomized trials of Syncope Clinics are warranted.

Lack of benefit from hospitalization in patients with syncope: A propensity analysis

STUDY OBJECTIVE

Patients with syncope are frequently admitted to the hospital, but whether this improves outcome is unknown. We tested whether hospitalization reduced mortality in patients who presented to emergency departments (EDs) with syncope.

METHODS

We conducted a propensity analysis of the outcomes of patients ≥18 years old presenting to EDs with a primary diagnosis of syncope in April 2004-March 2013. The model used 1:1 nearest-neighbor matching to predicted admission using age, sex, urban residence, household income, and 14 significant comorbidities from 4 administrative databases of the province of Alberta. The primary outcome was death.

RESULTS

There were 57,417 ED patients with a primary diagnosis of syncope; 8864 were admitted, and 48,553 were discharged in <24 hours. Admitted patients were older (median 76 vs 49 years), male (53% vs 45%), rural (23% vs 18%), and had lower income (median $58,599 vs $61,422); all P < 0.001. All comorbidities were higher in admitted patients (mean Charlson scores, 1.9 vs 0.7; P < 0.001). The propensity-matched hospitalized patients had higher 30-day mortality (3.5% vs 1.0%) and 1-year mortality (14.1% vs 8.6%); both P < 0.001. Mortality in all propensity quintiles was higher in the hospitalized group (all P < 0.001). The most common causes of death in 2719 patients included chronic ischemic heart disease, 14%; lung cancer, 7.1%; acute myocardial infarction, 6.9%; stroke, 3.7%; chronic obstructive pulmonary disease, 3.6%; dementia, 2.6%; and heart failure, 2.5%.

CONCLUSIONS

Hospital admission did not reduce early or late mortality in patients who presented to the ED with syncope. Mortality is associated with comorbidities.

Canadian Cardiovascular Society Clinical Practice Update on the Assessment and Management of Syncope

Syncope is a symptom that occurs in multiple settings and has a variety of underlying causes, ranging from benign to life threatening. Determining the underlying diagnosis and prognosis can be challenging and often results in an unstructured approach to evaluation, which is ineffective and costly. In this first ever document, the Canadian Cardiovascular Society (CCS) provides a clinical practice update on the assessment and management of syncope. It highlights similarities and differences between the 2017 American College of Cardiology/American Heart Association/Heart Rhythm Society and the 2018 European Society of Cardiology guidelines, draws on new data following a thorough review of medical literature, and takes the best available evidence and clinical experience to provide clinical practice tips. Where appropriate, a focus on a Canadian perspective is emphasized in order to illuminate larger international issues. This document represents the consensus of a Canadian panel comprised of multidisciplinary experts on this topic with a mandate to formulate disease-specific advice. The primary writing panel wrote the document, followed by peer review from the secondary writing panel. The CCS Guidelines Committee reviewed and approved the statement. The practice tips represent the consensus opinion of the primary writing panel authors, endorsed by the CCS. The CCS clinical practice update on the assessment and management of syncope focuses on epidemiology, the initial evaluation including risk stratification and disposition from the emergency department, initial diagnostic work-up, management of vasovagal syncope and orthostatic hypotension, and syncope and driving.

The Current and Future Hospitalization Cost Burden of Syncope in Canada

BACKGROUND

Single-center studies have shown the high costs associated with the hospital evaluation of syncope. National cost estimates for syncope-related hospitalizations are sparse, and none exist in Canada.

METHODS

The Canadian Institute for Health Information Discharge Abstract Database was used to identify acute care hospitalizations with a primary diagnosis of syncope between fiscal years (FY) 2004 and 2015 in all provinces and territories (except Quebec). We used multiple linear regression to calculate the trends in prevalence of hospital admissions and generalized linear regression to estimate the costs of a hospitalization. The syncope hospitalization rate and the cost per hospitalization in Quebec were assumed to be the average of the rest of the country. The future hospitalization cost burden of syncope was projected to 2030.

RESULTS

There were 128,263 hospitalizations for a primary diagnosis of syncope over the 10-year study period, resulting in a total cost of $619.9 million (Canadian). An estimate of 41,044 syncope hospitalizations occurred in Quebec, costing $198.7 million. The total hospitalization cost of syncope in Canada was estimated at $818.5 million. The annual costs of syncope hospitalizations increased from $66.6 to $68.5 million between FY2004 and FY2015, respectively, and are projected to increase to $87.1 million in 2030.

CONCLUSION

Hospitalization costs for syncope in Canada are high and rising. Research is needed to identify opportunities to deliver more efficient and cost-effective care.

Syncope in the Emergency Department

Syncope is a common presentation to Emergency Departments (EDs). Estimates on the frequency of visits (0.6–1.7%) and subsequent rates of hospitalizations (12–85%) vary according to country. The initial ED evaluation for syncope consists of a detailed history, physical examination and 12-lead electrocardiogram (ECG). The use of additional diagnostic testing and specialist evaluation should be based on this initial evaluation rather than an unstructured approach of broad-based testing. Risk stratification performed in the ED is important for estimating prognosis, triage decisions and to establish urgency of any further work-up. The primary approach to risk stratification focuses on identifying high- and low-risk predictors. The use of prediction tools may be used to aid in physician decision-making; however, they have not performed better than the clinical judgment of emergency room physicians. Following risk stratification, decision for hospitalization should be based on the seriousness of the underlying cause for syncope or based on high-risk features, or the severity of co-morbidities. For those deemed intermediate risk, access to specialist assessment and related testing may occur in a syncope unit in the emergency department, as an outpatient, or in a less formal care pathway and is highly dependent on the local healthcare system. For syncope patients presenting to the ED, ~0.8% die and 10.3% suffer a non-fatal severe outcome within 30 days.

Long-term outcomes in syncope patients presenting to the emergency department: A systematic review

INTRODUCTION

Long-term outcomes among syncope patients are not well studied to guide physicians regarding outpatient testing and follow-up. The objective of this study was to conduct a systematic review for outcomes at 1-year or later among ED syncope patients.

METHODS

We searched Cochrane Central, Medline, Medline in Process, PubMed, Embase, and the Cumulative Index to Nursing databases from inception to December 2018. We included studies that reported long-term outcomes among ED syncope patients. We excluded studies on patients <16 years old, studies that included syncope mimickers (pre-syncope, seizure, intoxication, loss of consciousness after head trauma), case reports, letters to the editor, non-English and review articles. Outcomes included death, syncope recurrence requiring hospitalization, arrhythmias and procedural interventions for arrhythmias. Meta-analysis was performed by pooling the outcomes using random effects model.

RESULTS

Initial literature search generated 2,094 articles duplicate removal. Of the 50 articles selected for full-text review, 19 articles with 98,211 patients were included in this review: of which 12 were included in the 1-year outcome meta-analysis. Pooled analysis showed : 7.0% mortality; 16.0% syncope recurrence requiring hospitalization; 6.0% with device insertion. 1-year arrhythmias reported in two studies were 1.1 and 26.4%. Pooled analysis for outcome at 31 to 365 days showed: 5.0% mortality and 1% device insertion. Two studies reported 4.9% and 21% mortality at 30 months and 4.2 years follow-up.

CONCLUSIONS

An important proportion of ED syncope patients suffer long-term morbidity and mortality. Appropriate follow-up is needed and future research to identify patients at risk is needed.

Clinical Benefit of Hospitalization for Older Adults With Unexplained Syncope: A Propensity-Matched Analysis

STUDY OBJECTIVE

Many adults with syncope are hospitalized solely for observation and testing. We seek to determine whether hospitalization versus outpatient management for older adults with unexplained syncope is associated with a reduction in postdisposition serious adverse events at 30 days.

METHODS

We performed a propensity score analysis using data from a prospective, observational study of older adults with unexplained syncope or near syncope who presented to 11 emergency departments (EDs) in the United States. We enrolled adults (≥60 years) who presented with syncope or near syncope. We excluded patients with a serious diagnosis identified in the ED. Clinical and laboratory data were collected on all patients. The primary outcome was rate of post-ED serious adverse events at 30 days.

RESULTS

We enrolled 2,492 older adults with syncope and no serious ED diagnosis from April 2013 to September 2016. Mean age was 73 years (SD 8.9 years), and 51% were women. The incidence of serious adverse events within 30 days after the index visit was 7.4% for hospitalized patients and 3.19% for discharged patients, representing an unadjusted difference of 4.2% (95% confidence interval 2.38% to 6.02%). After propensity score matching on risk of hospitalization, there was no statistically significant difference in serious adverse events at 30 days between the hospitalized group (4.89%) and the discharged group (2.82%) (risk difference 2.07%; 95% confidence interval -0.24% to 4.38%).

CONCLUSION

In our propensity-matched sample of older adults with unexplained syncope, for those with clinical characteristics similar to that of the discharged cohort, hospitalization was not associated with improvement in 30-day serious adverse event rates.