Prehospital triage of patients with acute cardiac complaints: study protocol of HART-c, a multicentre prospective study

AI Algorithm to Predict Acute Coronary Syndrome in Prehospital Cardiac Care: Retrospective Cohort Study

BACKGROUND

Overcrowding of hospitals and emergency departments (EDs) is a growing problem. However, not all ED consultations are necessary. For example, 80% of patients in the ED with chest pain do not have an acute coronary syndrome (ACS). Artificial intelligence (AI) is useful in analyzing (medical) data, and might aid health care workers in prehospital clinical decision-making before patients are presented to the hospital.

OBJECTIVE

The aim of this study was to develop an AI model which would be able to predict ACS before patients visit the ED. The model retrospectively analyzed prehospital data acquired by emergency medical services' nurse paramedics.

METHODS

Patients presenting to the emergency medical services with symptoms suggestive of ACS between September 2018 and September 2020 were included. An AI model using a supervised text classification algorithm was developed to analyze data. Data were analyzed for all 7458 patients (mean 68, SD 15 years, 54% men). Specificity, sensitivity, positive predictive value (PPV), and negative predictive value (NPV) were calculated for control and intervention groups. At first, a machine learning (ML) algorithm (or model) was chosen; afterward, the features needed were selected and then the model was tested and improved using iterative evaluation and in a further step through hyperparameter tuning. Finally, a method was selected to explain the final AI model.

RESULTS

The AI model had a specificity of 11% and a sensitivity of 99.5% whereas usual care had a specificity of 1% and a sensitivity of 99.5%. The PPV of the AI model was 15% and the NPV was 99%. The PPV of usual care was 13% and the NPV was 94%.

CONCLUSIONS

The AI model was able to predict ACS based on retrospective data from the prehospital setting. It led to an increase in specificity (from 1% to 11%) and NPV (from 94% to 99%) when compared to usual care, with a similar sensitivity. Due to the retrospective nature of this study and the singular focus on ACS it should be seen as a proof-of-concept. Other (possibly life-threatening) diagnoses were not analyzed. Future prospective validation is necessary before implementation.

Management of patients suspected for non-ST elevation-acute coronary syndrome in the prehospital phase

The management of patients with suspected acute coronary syndrome, especially in prehospital settings, is challenging. This Special Report focuses on studies in emergency medical services concerning chest pain patients' triage and risk stratification. In addition, it emphasizes advancements in point-of-care cardiac troponin testing. These developments are compared with in-hospital guidelines, proposing an initial framework for a new acute care pathway. This pathway integrates a risk stratification tool with high-sensitivity cardiac troponin testing, aiming to deliver optimal care and collaboration within the acute care chain. It has the potential to contribute to a significant reduction in hospital referrals, reduce observation time and overcrowding at emergency departments and hospital admissions.

Consequences of different cut-off values for high-sensitivity cardiac troponin for risk stratification of patients suspected for NSTE-ACS with a modified HEART score

Aim: This study aims to enhance prehospital risk assessment for suspected non-ST-elevation acute coronary syndrome (NSTE-ACS) patients using the HEART-score. By incorporating novel point-of-care high-sensitivity cardiac troponin devices, a modified HEART-score was developed and compared with the conventional approach. Patients & methods: Troponin points within the modified HEART-score are based on values below the limit of quantitation (LoQ), between the LoQ and 99th percentile and above the 99th percentile of the used device. A total HEART-score of three or lower is considered low-risk for major adverse cardiac events. Results & conclusion: The number of low-risk patients decreased based on the modified HEART-score. The sensitivity and negative predictive value increased which suggests increasing safety in ruling out patients with suspected NSTE-ACS.

Improved prehospital triage for acute cardiac care: results from HART-c, a multicentre prospective study

BACKGROUND

Cardiac symptoms are one of the most prevalent reasons for emergency department visits. However, over 80% of patients with such symptoms are sent home after acute cardiovascular disease has been ruled out.

OBJECTIVE

The Hollands-Midden Acute Regional Triage-cardiology (HART-c) study aimed to investigate whether a novel prehospital triage method, combining prehospital and hospital data with expert consultation, could increase the number of patients who could safely stay at home after emergency medical service (EMS) consultation.

METHODS

The triage method combined prehospital EMS data, such as electrocardiographic and vital parameters in real time, and data from regional hospitals (including previous medical records and admission capacity) with expert consultation. During the 6‑month intervention and control periods 1536 and 1376 patients, respectively, were consulted by the EMS. The primary endpoint was the percentage change of patients who could stay at home after EMS consultation.

RESULTS

The novel triage method led to a significant increase in patients who could safely stay at home, 11.8% in the intervention group versus 5.9% in the control group: odds ratio 2.31 (95% confidence interval (CI) 1.74-3.05). Of 181 patients staying at home, only 1 (< 1%) was later diagnosed with ACS; no patients died. Furthermore the number of interhospital transfers decreased: relative risk 0.81 (95% CI 0.67-0.97).

CONCLUSION

The HART‑c triage method led to a significant decrease in interhospital transfers and an increase in patients with cardiac symptoms who could safely stay at home. The presented method thereby reduced overcrowding and, if implemented throughout the country and for other medical specialties, could potentially reduce the number of cardiac and non-cardiac hospital visits even further.

Chest Pain Management Using Prehospital Point-of-Care Troponin and Paramedic Risk Assessment

Importance

Prehospital point-of-care troponin testing and paramedic risk stratification might improve the efficiency of chest pain care pathways compared with existing processes with equivalent health outcomes, but the association with health care costs is unclear.

Objective

To analyze whether prehospital point-of-care troponin testing and paramedic risk stratification could result in cost savings compared with existing chest pain care pathways.

Design, Setting, and Participants

In this economic evaluation of adults with acute chest pain without ST-segment elevation, cost-minimization analysis was used to assess linked ambulance, emergency, and hospital attendance in the state of Victoria, Australia, between January 1, 2015, and June 30, 2019.

Interventions

Paramedic risk stratification and point-of-care troponin testing.

Main Outcomes and Measures

The outcome was estimated mean annualized statewide costs for acute chest pain. Between May 17 and June 25, 2022, decision tree models were developed to estimate costs under 3 pathways: (1) existing care, (2) paramedic risk stratification and point-of-care troponin testing without prehospital discharge, or (3) prehospital discharge and referral to a virtual emergency department (ED) for low-risk patients. Probabilities for the prehospital pathways were derived from a review of the literature. Multivariable probabilistic sensitivity analysis with 50 000 Monte Carlo iterations was used to estimate mean costs and cost differences among pathways.

Results

A total of 188 551 patients attended by ambulance for chest pain (mean [SD] age, 61.9 [18.3] years; 50.5% female; 49.5% male; Indigenous Australian, 2.0%) were included in the model. Estimated annualized infrastructure and staffing costs for the point-of-care troponin pathways, assuming a 5-year device life span, was $2.27 million for the pathway without prehospital discharge and $4.60 million for the pathway with prehospital discharge (incorporating virtual ED costs). In the decision tree model, total annual cost using prehospital point-of-care troponin and paramedic risk stratification was lower compared with existing care both without prehospital discharge (cost savings, $6.45 million; 95% uncertainty interval [UI], $0.59-$16.52 million; lower in 94.1% of iterations) and with prehospital discharge (cost savings, $42.84 million; 95% UI, $19.35-$72.26 million; lower in 100% of iterations).

Conclusions and Relevance

Prehospital point-of-care troponin and paramedic risk stratification for patients with acute chest pain could result in substantial cost savings. These findings should be considered by policy makers in decisions surrounding the potential utility of prehospital chest pain risk stratification and point-of-care troponin models provided that safety is confirmed in prospective studies.

Managing Hospital Capacity: Achievements and Lessons from the COVID-19 Pandemic

INTRODUCTION

The coronavirus disease 2019 (COVID-19) pandemic challenged health care systems in an unprecedented way. Due to the enormous amount of hospital ward and intensive care unit (ICU) admissions, regular care came to a standstill, thereby overcrowding ICUs and endangering (regular and COVID-19-related) critical care. Acute care coordination centers were set up to safely manage the influx of COVID-19 patients. Furthermore, treatments requiring ICU surveillance were postponed leading to increased waiting lists.

HYPOTHESIS

A coordination center organizing patient transfers and admissions could reduce overcrowding and optimize in-hospital capacity.

METHODS

The acute lack of hospital capacity urged the region West-Netherlands to form a new regional system for patient triage and transfer: the Regional Capacity and Patient Transfer Service (RCPS). By combining hospital capacity data and a new method of triage and transfer, the RCPS was able to effectively select patients for transfer to other hospitals within the region or, in close collaboration with the National Capacity and Patient Transfer Service (LCPS), transfer patients to hospitals in other regions within the Netherlands.

RESULTS

From March 2020 through December 2021 (22 months), the RCPS West-Netherlands was requested to transfer 2,434 COVID-19 patients. After adequate triage, 1,720 patients with a mean age of 62 (SD = 13) years were transferred with the help of the RCPS West-Netherlands. This concerned 1,166 ward patients (68%) and 554 ICU patients (32%). Overcrowded hospitals were relieved by transferring these patients to hospitals with higher capacity.

CONCLUSION

The health care system in the region West-Netherlands benefitted from the RCPS for both ward and ICU occupation. Due to the coordination by the RCPS, regional ICU occupation never exceeded the maximal ICU capacity, and therefore patients in need for acute direct care could always be admitted at the ICU. The presented method can be useful in reducing the waiting lists caused by the delayed care and for coordination and transfer of patients with new variants or other infectious diseases in the future.

Prehospital risk assessment in patients suspected of non-ST-segment elevation acute coronary syndrome: a systematic review and meta-analysis

OBJECTIVE

To review, inventory and compare available diagnostic tools and investigate which tool has the best performance for prehospital risk assessment in patients suspected of non-ST-segment elevation acute coronary syndrome (NSTE-ACS).

METHODS

Systematic review and meta-analysis. Medline and Embase were searched up till 1 April 2021. Prospective studies with patients, suspected of NSTE-ACS, presenting in the primary care setting or by emergency medical services (EMS) were included. The most important exclusion criteria were studies including only patients with ST-elevation myocardial infarction and studies before 1995, the pretroponin era. The primary end point was the final hospital discharge diagnosis of NSTE-ACS or major adverse cardiac events (MACE) within 6 weeks. Risk of bias was evaluated by the Quality Assessment of Diagnostic Accuracy Studies Criteria.

MAIN OUTCOME AND MEASURES

Sensitivity, specificity and likelihood ratio of findings for risk stratification in patients suspected of NSTE-ACS.

RESULTS

In total, 15 prospective studies were included; these studies reflected in total 26 083 patients. No specific variables related to symptoms, physical examination or risk factors were useful in risk stratification for NSTE-ACS diagnosis. The most useful electrocardiographic finding was ST-segment depression (LR+3.85 (95% CI 2.58 to 5.76)). Point-of-care troponin was found to be a strong predictor for NSTE-ACS in primary care (LR+14.16 (95% CI 4.28 to 46.90) and EMS setting (LR+6.16 (95% CI 5.02 to 7.57)). Combined risk scores were the best for risk assessment in an NSTE-ACS. From the combined risk scores that can be used immediately in a prehospital setting, the PreHEART score, a validated combined risk score for prehospital use, derived from the HEART score (History, ECG, Age, Risk factors, Troponin), was most useful for risk stratification in patients with NSTE-ACS (LR+8.19 (95% CI 5.47 to 12.26)) and for identifying patients without ACS (LR-0.05 (95% CI 0.02 to 0.15)).

DISCUSSION

Important study limitations were verification bias and heterogeneity between studies. In the prehospital setting, several diagnostic tools have been reported which could improve risk stratification, triage and early treatment in patients suspected for NSTE-ACS. On-site assessment of troponin and combined risk scores derived from the HEART score are strong predictors. These results support further studies to investigate the impact of these new tools on logistics and clinical outcome.

FUNDING

This study is funded by ZonMw, the Dutch Organisation for Health Research and Development.

TRIAL REGISTRATION NUMBER

This meta-analysis was published for registration in PROSPERO prior to starting (CRD York, CRD42021254122).