A predictive ambulance dispatch algorithm to the scene of a motor vehicle crash: the search for optimal over and under triage rates.

BACKGROUND: Calls for emergency medical assistance at the scene of a motor vehicle crash (MVC) substantially contribute to the demand on ambulance services. Triage by emergency medical dispatch systems is therefore important, to ensure the right care is provided to the right patient, in the right amount of time. A lights and sirens (L&S) response is the highest priority ambulance response, also known as a priority one or hot response. In this context, over triage is defined as dispatching an ambulance with lights and sirens (L&S) to a low acuity MVC and under triage is not dispatching an ambulance with L&S to those who require urgent medical care. We explored the potential for crash characteristics to be used during emergency ambulance calls to identify those MVCs that required a L&S response. METHODS: We conducted a retrospective cohort study using ambulance and police data from 2014 to 2016. The predictor variables were crash characteristics (e.g. road surface), and Medical Priority Dispatch System (MPDS) dispatch codes. The outcome variable was the need for a L&S ambulance response. A Chi-square Automatic Interaction Detector technique was used to develop decision trees, with over/under triage rates determined for each tree. The model with an under/over triage rate closest to that prescribed by the American College of Surgeons Committee on Trauma (ACS COT) will be deemed to be the best model (under triage rate of ≤ 5% and over triage rate of between 25-35%. RESULTS: The decision tree with a 2.7% under triage rate was closest to that specified by the ACS COT, had as predictors-MPDS codes, trapped, vulnerable road user, anyone aged 75 + , day of the week, single versus multiple vehicles, airbag deployment, atmosphere, surface, lighting and accident type. This model had an over triage rate of 84.8%. CONCLUSIONS: We were able to derive a model with a reasonable under triage rate, however this model also had a high over triage rate. Individual EMS may apply the findings here to their own jurisdictions when dispatching to the scene of a MVC.

Do differences in emergency medical services (EMS) response time to an arrest account for the survival differences between EMS-witnessed and bystander-witnessed out of hospital cardiac arrest?

Introduction: Out-of-hospital cardiac arrests (OHCA) witnessed by Emergency Medical Services (EMS) are reported to have more favourable survival than bystander-witnessed arrests, even after adjusting for patient and arrest factors known to be associated with increased OHCA survival. This study aims to determine whether the survival advantage in EMS-witnessed arrests can be attributed to differences in the EMS response time to the arrest. Methods: Using registry data we conducted a retrospective, population-based cohort study of bystander- and EMS-witnessed OHCAs of medical aetiology who received an EMS resuscitation attempt in Western Australia between 2018-2021. EMS response time to arrest was assumed to be zero for EMS-witnessed arrests. Multivariable logistic regression was used to compare 30-day OHCA survival by witness and bystander CPR (B-CPR) status, adjusting for EMS response time to arrest, and patient and arrest characteristics. Results: Of 2,130 OHCA cases, 510 (23.9%) were EMS-witnessed and 1620 were bystander-witnessed: 1318/1620 (81.4%) with B-CPR, and 302/1620 (18.6%) with no B-CPR. The median EMS response time to bystander-witnessed arrests who received B-CPR was 9.9 [Q1,Q3: 7.4, 13.3] minutes. After adjusting for the EMS response time and patient and arrest factors, 30-day survival remained significantly lower in both the bystander-witnessed group with B-CPR (aOR 0.56; 95% CI 0.34 - 0.91) and bystander-witnessed group without B-CPR (aOR 0.23; 95% CI 0.11 - 0.46). Conclusion: An increased EMS response time does not fully account for the higher OHCA survival in EMS-witnessed arrests compared to bystander-witnessed arrests.

Use of ketamine wafer for pain management by volunteer emergency medical technicians in rural Western Australia.

OBJECTIVE: To describe the use of sublingual ketamine wafers administered by volunteer emergency medical technicians (EMTs) for pain management to patients in rural Western Australia (WA). METHODS: This retrospective cohort study included patients older than 12 years who were attended by volunteer EMTs in Esperance, Lancelin and Kalbarri, WA and received analgesic medications from 2018 to 2021. Patients who received ketamine wafers with/without other analgesics were compared to (i) patients who received only oral paracetamol and (ii) patients who received inhalational methoxyflurane without ketamine wafers with/without paracetamol. RESULTS: The present study included 826 patients, among whom 149 patients received ketamine wafer with/without other analgesics, 82 paracetamol only and 595 methoxyflurane with/without paracetamol. Patients who received ketamine wafers were younger (median age 49 years vs 54 years for the paracetamol group vs 58 years for the methoxyflurane group), required a longer median transport interval (56 min vs 20 min vs 8 min), trauma-related (73% vs 35% vs 54%), and presented higher median initial pain score (9 vs 3 vs 8 out of 10) than those who received paracetamol and those who received methoxyflurane, respectively. Eight in the ketamine wafers group (5.4%) had a record of nausea/vomiting after the administration of ketamine wafers. CONCLUSIONS: Sublingual ketamine wafer was administered by volunteer EMTs without any evidence of major adverse events in rural WA and deemed useful as an additional pain management option when long transport to hospital was needed. No other symptoms that may be associated with the use of ketamine were recorded.

Out-of-hospital cardiac arrest in residential aged care facilities is independently associated with lower survival in Perth, Australia.

Aim: To compare out-of-hospital cardiac arrest (OHCA) characteristics and outcomes between people aged ≥ 65 years who arrested in a residential aged care facility (RACF) versus a private residence in Perth, Australia. Methods: We undertook a retrospective cohort study of OHCA cases attended by emergency medical services (EMS) in Perth, January 2018-December 2021. OHCA patient and event characteristics and survival outcomes were compared via univariate analysis. Multivariable logistic regression was used to investigate the relationship between residency type and (i) return of spontaneous circulation (ROSC) at emergency department (ED) and (ii) 30-day survival. Results: A total of 435 OHCA occurred in RACFs versus 3,395 in private residences. RACF patients were significantly older (median age: 86 [IQR 79, 91] vs 78 [71, 85] years; p < 0.001), more commonly female (50.1% vs 36.8%; p < 0.001), bystander-witnessed arrests (34.9% vs 21.5%; p < 0.001), received bystander cardiopulmonary resuscitation (42.1% vs 28.6%; p < 0.001), had less shockable first monitored rhythms (4.0% vs 8.1%; p = 0.002) and more frequently had a "do not resuscitate" order identified (46.0% vs 13.6%; <0.001). Among those with EMS-attempted resuscitation or with defibrillation before EMS arrival, ROSC at ED and 30-day survival were significantly lower in the RACF group (6.2% vs 18.9%; p < 0.001 and 1.9% vs 7.7%; p < 0.001). The adjusted odds of ROSC at ED (aOR: 0.22 [95%CI: 0.10, 0.46]) and 30-day survival (aOR: 0.20 [95%CI 0.05, 0.92]) were significantly lower for RACF residents. Conclusion: RACF residency was an independent predictor of lower survival from OHCA, highlighting the importance of end-of-life planning for RACF residents.

Ambulance dispatch prioritisation for traffic crashes using machine learning: A natural language approach.

INTRODUCTION: Demand for emergency ambulances is increasing, therefore it is important that ambulance dispatch is prioritised appropriately. This means accurately identifying which incidents require a lights and sirens (L&S) response and those that do not. For traffic crashes, it can be difficult to identify the needs of patients based on bystander reports during the emergency phone call; as traffic crashes are complex events, often with multiple patients at the same crash with varying medical needs. This study aims to determine how well the text sent to paramedics en-route to the traffic crash scene by the emergency medical dispatcher (EMD), in combination with dispatch codes, can predict the need for a L&S ambulance response to traffic crashes. METHODS: A retrospective cohort study was conducted using data from 2014 to 2016 traffic crashes attended by emergency ambulances in Perth, Western Australia. Machine learning algorithms were used to predict the need for a L&S response or not. The features were the Medical Priority Dispatch System (MPDS) determinant codes and EMD text. EMD text was converted for computation using natural language processing (Bag of Words approach). Machine learning algorithms were used to predict the need for a L&S response, defined as where one or more patients (a) died before hospital admission, (b) received L&S transport to hospital, or (c) had one or more high-acuity indicators (based on an a priori list of medications, interventions or observations. RESULTS: There were 11,971 traffic crashes attended by ambulances during the study period, of which 22.3 % were retrospectively determined to have required a L&S response. The model with the highest accuracy was using an Ensemble machine learning algorithm with a score of 0.980 (95 % CI 0.976-0.984). This model predicted the need for an L&S response using both MPDS determinant codes and EMD text. DISCUSSION: We found that a combination of EMD text and MPDS determinate codes can predict which traffic crashes do and do not require a lights and sirens ambulance response to the scene with a high degree of accuracy. Emergency medical services could deploy machine learning algorithms to improve the accuracy of dispatch to traffic crashes, which has the potential to result in improved system efficiency.