Predictors of recognition of out of hospital cardiac arrest by emergency medical services call handlers in England: a mixed methods diagnostic accuracy study

Bystander cardiopulmonary resuscitation differences by sex - The role of arrest recognition

PURPOSE

To assess whether bystander cardiopulmonary resuscitation (CPR) differed by patient sex among bystander-witnessed out-of-hospital cardiac arrests (OHCA).

METHODS

This study is a retrospective analysis of paramedic-attended OHCA in New South Wales (NSW) between January 2017 to December 2019 (restricted to bystander-witnessed cases). Exclusions included OHCA in aged care, medical facilities, with advance care directives, from non-medical causes. Multivariate logistic regression examined the association of patient sex with bystander CPR. Secondary outcomes were OHCA recognition, bystander AED application, initial shockable rhythm, and survival outcomes.

RESULTS

Of 4,491cases, females were less likely to receive bystander CPR in private residential (Adjusted Odds ratio [AOR]: 0.82, 95%CI: 0.70-0.95) and public locations (AOR: 0.58, 95%CI:0.39-0.88). OHCA recognition during the emergency call was lower for females arresting in public locations (84.6% vs 91.6%, p = 0.002) and this partially explained the association of sex with bystander CPR (∼44%). This difference in recognition was not observed in private residential locations (p = 0.2). Bystander AED use was lower for females (4.8% vs 9.6%, p < 0.001); however, after adjustment for location and other covariates, this relationship was no longer significant (AOR: 0.83, 95%CI: 0.60-1.12). Females were less likely to be in an initial shockable rhythm (AOR: 0.52, 95%CI: 0.44-0.61), but more likely to survive the event (AOR: 1.34, 95%CI: 1.15-1.56). There was no sex difference in survival to hospital discharge (AOR: 0.96, 95%CI: 0.77-1.19).

CONCLUSION

OHCA recognition and bystander CPR differ by patient sex in NSW. Research is needed to understand why this difference occurs and to raise public awareness of this issue.

When the machine is wrong. Characteristics of true and false predictions of Out-of-Hospital Cardiac arrests in emergency calls using a machine-learning model

BACKGROUND

A machine-learning model trained to recognize emergency calls regarding Out-of-Hospital Cardiac Arrest (OHCA) was tested in clinical practice at Copenhagen Emergency Medical Services (EMS) from September 2018 to December 2019. We aimed to investigate emergency call characteristics where the machine-learning model failed to recognize OHCA or misinterpreted a call as being OHCA.

METHODS

All emergency calls were linked to the dispatch database and verified OHCAs were identified by linkage to the Danish Cardiac Arrest Registry. Calls with either false negative or false positive predictions of OHCA were evaluated by trained auditors. Descriptive analyses were performed with absolute numbers and percentages reported.

RESULTS

The machine-learning model processed 169,236 calls to Copenhagen EMS and suspected 5,811 (3.4%) of the calls as OHCA, resulting in 84.5% sensitivity and 97.1% specificity. Among OHCAs not recognised by machine-learning model, a condition completely different from OHCA was presented by caller in 31% of the cases. In 28% of unrecognised calls, patient was reported breathing normally, and language barriers were identified in 23% of the cases. Among falsely suspected OHCA, the patient was reported unconscious in 28% of the cases, and in 13% of the false positive cases the machine-learning model interpreted calls regarding dead patients with irreversible signs of death as OHCA.

CONCLUSION

Continuous optimization of the language model is needed to improve the prediction of OHCA and thereby improve sensitivity and specificity of the machine-learning model on recognising OHCA in emergency telephone calls.

Artificial intelligence in Emergency Medical Services dispatching: assessing the potential impact of an automatic speech recognition software on stroke detection taking the Capital Region of Denmark as case in point

BACKGROUND AND PURPOSE

Stroke recognition at the Emergency Medical Services (EMS) impacts the stroke treatment and thus the related health outcome. At the EMS Copenhagen 66.2% of strokes are detected by the Emergency Medical Dispatcher (EMD) and in Denmark approximately 50% of stroke patients arrive at the hospital within the time-to-treatment. An automatic speech recognition software (ASR) can increase the recognition of Out-of-Hospital cardiac arrest (OHCA) at the EMS by 16%. This research aims to analyse the potential impact an ASR could have on stroke recognition at the EMS Copenhagen and the related treatment.

METHODS

Stroke patient data (n = 9049) from the years 2016-2018 were analysed retrospectively, regarding correlations between stroke detection at the EMS and stroke specific, as well as personal characteristics such as stroke type, sex, age, weekday, time of day, year, EMS number contacted, and treatment. The possible increase in stroke detection through an ASR and the effect on stroke treatment was calculated based on the impact of an existing ASR to detect OHCA from CORTI AI.

RESULTS

The Chi-Square test with the respective post-hoc test identified a negative correlation between stroke detection and females, the 1813-Medical Helpline, as well as weekends, and a positive correlation between stroke detection and treatment and thrombolysis. While the association analysis showed a moderate correlation between stroke detection and treatment the correlation to the other treatment options was weak or very weak. A potential increase in stroke detection to 61.19% with an ASR and hence an increase of thrombolysis by 5% in stroke patients calling within time-to-treatment was predicted.

CONCLUSIONS

An ASR can potentially improve stroke recognition by EMDs and subsequent stroke treatment at the EMS Copenhagen. Based on the analysis results improvement of stroke recognition is particularly relevant for females, younger stroke patients, calls received through the 1813-Medical Helpline, and on weekends.

TRIAL REGISTRATION

This study was registered at the Danish Data Protection Agency (PVH-2014-002) and the Danish Patient Safety Authority (R-21013122).

Features of Emergency Medical System calls that facilitate or inhibit Emergency Medical Dispatcher recognition that a patient is in, or at imminent risk of, cardiac arrest: A systematic mixed studies review

Aim

To identify and appraise evidence relating to the features of an Emergency Medicine System call interaction that enable, or inhibit, an Emergency Medical Dispatcher’s recognition that a patient is in out-of-hospital cardiac arrest, or at imminent risk of out-of-hospital cardiac arrest.

Methods

All study designs were eligible for inclusion. Data sources included Medline, BNI, CINAHL, EMBASE, PubMed, Cochrane Database of Systematic Reviews, AMED and OpenGrey. Stakeholder resources were screened and experts in resuscitation were asked to review the studies identified. Studies were appraised using the Mixed Methods Appraisal Tool. Synthesis was completed using a segregated mixed research synthesis approach.

Results

Thirty-two studies were included in the review. Three main themes were identified: Key features of the Emergency Medical Service call interaction; Managing the Emergency Medical Service call; Emotional distress.

Conclusion

A dominant finding is the difficulty in recognising abnormal/agonal breathing during the Emergency Medical Service call. The interaction between the caller and the Emergency Medical Dispatcher is critical in the recognition of patients who suffer an out-of-hospital cardiac arrest. Emergency Medical Dispatchers adapt their approach to the Emergency Medical Service call, and regular training for Emergency Medical Dispatchers is recommended to optimise out-of-hospital cardiac arrest recognition. Further research is required with a focus on the Emergency Medical Service call interaction of patients who are alive at the time of the Emergency Medical Service call and who later deteriorate into OHCA.

PROSPERO registration: CRD42019155458.

The Feasibility of Using Machine Learning to Classify Calls to South African Emergency Dispatch Centres According to Prehospital Diagnosis, by Utilising Caller Descriptions of the Incident

This paper presents the application of machine learning for classifying time-critical conditions namely sepsis, myocardial infarction and cardiac arrest, based off transcriptions of emergency calls from emergency services dispatch centers in South Africa. In this study we present results from the application of four multi-class classification algorithms: Support Vector Machine (SVM), Logistic Regression, Random Forest and K-Nearest Neighbor (kNN). The application of machine learning for classifying time-critical diseases may allow for earlier identification, adequate telephonic triage, and quicker response times of the appropriate cadre of emergency care personnel. The data set consisted of an original data set of 93 examples which was further expanded through the use of data augmentation. Two feature extraction techniques were investigated namely; TF-IDF and handcrafted features. The results were further improved using hyper-parameter tuning and feature selection. In our work, within the limitations of a limited data set, classification results yielded an accuracy of up to 100% when training with 10-fold cross validation, and 95% accuracy when predicted on unseen data. The results are encouraging and show that automated diagnosis based on emergency dispatch centre transcriptions is feasible. When implemented in real time, this can have multiple utilities, e.g. enabling the call-takers to take the right action with the right priority.

Unrecognized Out of Hospital Cardiac Arrest Symptoms during Thailand’s Emergency Medical Services

BACKGROUND: To improve survival rate, the main focus of adult cardiac arrest management includes rapid recognition, prompt administration of cardiopulmonary resuscitation (CPR), defibrillation for shockable rhythms, post-return of spontaneous circulation (ROSC) care, and identification and treatment of underlying causes. This study aimed to identify the determinants of unrecognized cardiac arrest, and to study the recognition rate of out-of-hospital cardiac arrest (OHCA) by emergency medical services call handlers. METHODS: We included OHCA patients who were transferred to hospital via Emergency Medical Services (EMS) of Srinagarind hospital, Khon Kaen, Thailand, from 1st January 2020 to 31st December 2020. The primary outcome was to identify symptoms that lead to an unrecognized cardiac arrest by the EMS call handlers. Secondary outcomes were to identify the recognition rate of OHCA by emergency medical services call handlers, and assess the outcome of CPR performed on OHCA patients. RESULTS: There were a total of 58 patients in the present study, 26 patients (44.8%) and 32 patients (55.2%) belonged to the unrecognized and recognized cardiac arrest groups, respectively. The most common symptoms that led to unrecognized cardiac arrest were a state of unconsciousness (46.2%), major trauma (15.4%), and seizure-like activity (11.5%). The rate of ROSC was higher in the unrecognized cardiac arrest group (34.6% vs. 15.6%) but the rate of survival to hospital discharge was higher in the recognized cardiac arrest group (6.3% vs 0%). CONCLUSIONS: Falling unconscious is the most common symptom of unrecognized OHCA cases seen by EMS in Thailand. Basic life support, especially an immediate assessment of a patient’s respiratory status should be taught in health programs in school or through public service channels.