Machine learning can support dispatchers to better and faster recognize out-of-hospital cardiac arrest during emergency calls: A retrospective study

Optimising telecommunicator recognition of out-of-hospital cardiac arrest: A scoping review

Aim

To summarize existing literature and identify knowledge gaps regarding barriers and enablers of telecommunicators' recognition of out-of-hospital cardiac arrest (OHCA).

Methods

This scoping review was undertaken by an International Liaison Committee on Resuscitation (ILCOR) Basic Life Support scoping review team and guided by the Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for scoping reviews (PRISMA-ScR). Studies were eligible for inclusion if they were peer-reviewed and explored barriers and enablers of telecommunicator recognition of OHCA. We searched Ovid MEDLINE® and Embase and included articles from database inception till June 18th, 2024.

Results

We screened 9,244 studies and included 62 eligible studies on telecommunicator recognition of OHCA. The studies ranged in methodology. The majority were observational studies of emergency calls. The barriers most frequently described to OHCA recognition were breathing status and agonal breathing. The most frequently tested enabler for recognition was a variety of dispatch protocols focusing on breathing assessment. Only one randomized controlled trial (RCT) was identified, which found no difference in OHCA recognition with the addition of machine learning alerting telecommunicators in suspected OHCA cases.

Conclusion

Most studies were observational, assessed barriers to recognition of OHCA and compared different dispatch protocols. Only one RCT was identified. Randomized trials should be conducted to inform how to improve telecommunicator recognition of OHCA, including recognition of pediatric OHCAs and assessment of dispatch protocols.

Pre-Hospital Stroke Care beyond the MSU

PURPOSE OF REVIEW

Mobile stroke units (MSU) have established a new, evidence-based treatment in prehospital stroke care, endorsed by current international guidelines and can facilitate pre-hospital research efforts. In addition, other novel pre-hospital modalities beyond the MSU are emerging. In this review, we will summarize existing evidence and outline future trajectories of prehospital stroke care & research on and off MSUs.

RECENT FINDINGS

The proof of MSUs' positive effect on patient outcomes is leading to their increased adoption in emergency medical services of many countries. Nevertheless, prehospital stroke care worldwide largely consists of regular ambulances. Advancements in portable technology for detecting neurocardiovascular diseases, telemedicine, AI and large-scale ultra-early biobanking have the potential to transform prehospital stroke care also beyond the MSU concept. The increasing implementation of telemedicine in emergency medical services is demonstrating beneficial effects in the pre-hospital setting. In synergy with telemedicine the exponential growth of AI-technology is already changing and will likely further transform pre-hospital stroke care in the future. Other promising areas include the development and validation of miniaturized portable devices for the pre-hospital detection of acute stroke. MSUs are enabling large-scale screening for ultra-early blood-based biomarkers, facilitating the differentiation between ischemia, hemorrhage, and stroke mimics. The development of suitable point-of-care tests for such biomarkers holds the potential to advance pre-hospital stroke care outside the MSU-concept. A multimodal approach of AI-supported telemedicine, portable devices and blood-based biomarkers appears to be an increasingly realistic scenario for improving prehospital stroke care in regular ambulances in the future.

Precision emergency medicine

BACKGROUND

Precision health is a burgeoning scientific discipline that aims to incorporate individual variability in biological, behavioral, and social factors to develop personalized health solutions. To date, emergency medicine has not deeply engaged in the precision health movement. However, rapid advances in health technology, data science, and medical informatics offer new opportunities for emergency medicine to realize the promises of precision health.

METHODS

In this article, we conceptualize precision emergency medicine as an emerging paradigm and identify key drivers of its implementation into current and future clinical practice. We acknowledge important obstacles to the specialty-wide adoption of precision emergency medicine and offer solutions that conceive a successful path forward.

RESULTS

Precision emergency medicine is defined as the use of information and technology to deliver acute care effectively, efficiently, and authentically to individual patients and their communities. Key drivers and opportunities include leveraging human data, capitalizing on technology and digital tools, providing deliberate access to care, advancing population health, and reimagining provider education and roles. Overcoming challenges in equity, privacy, and cost is essential for success. We close with a call to action to proactively incorporate precision health into the clinical practice of emergency medicine, the training of future emergency physicians, and the research agenda of the specialty.

CONCLUSIONS

Precision emergency medicine leverages new technology and data-driven artificial intelligence to advance diagnostic testing, individualize patient care plans and therapeutics, and strategically refine the convergence of the health system and the community.

Artificial intelligence to advance acute and intensive care medicine

PURPOSE OF REVIEW

This review explores recent key advancements in artificial intelligence for acute and intensive care medicine. As artificial intelligence rapidly evolves, this review aims to elucidate its current applications, future possibilities, and the vital challenges that are associated with its integration into emergency medical dispatch, triage, medical consultation and ICUs.

RECENT FINDINGS

The integration of artificial intelligence in emergency medical dispatch (EMD) facilitates swift and accurate assessment. In the emergency department (ED), artificial intelligence driven triage models leverage diverse patient data for improved outcome predictions, surpassing human performance in retrospective studies. Artificial intelligence can streamline medical documentation in the ED and enhances medical imaging interpretation. The introduction of large multimodal generative models showcases the future potential to process varied biomedical data for comprehensive decision support. In the ICU, artificial intelligence applications range from early warning systems to treatment suggestions.

SUMMARY

Despite promising academic strides, widespread artificial intelligence adoption in acute and critical care is hindered by ethical, legal, technical, organizational, and validation challenges. Despite these obstacles, artificial intelligence's potential to streamline clinical workflows is evident. When these barriers are overcome, future advancements in artificial intelligence have the potential to transform the landscape of patient care for acute and intensive care medicine.

Applications and Performance of Machine Learning Algorithms in Emergency Medical Services: A Scoping Review

OBJECTIVE

The aim of this study was to summarize the literature on the applications of machine learning (ML) and their performance in Emergency Medical Services (EMS).

METHODS

Four relevant electronic databases were searched (from inception through January 2024) for all original studies that employed EMS-guided ML algorithms to enhance the clinical and operational performance of EMS. Two reviewers screened the retrieved studies and extracted relevant data from the included studies. The characteristics of included studies, employed ML algorithms, and their performance were quantitively described across primary domains and subdomains.

RESULTS

This review included a total of 164 studies published from 2005 through 2024. Of those, 125 were clinical domain focused and 39 were operational. The characteristics of ML algorithms such as sample size, number and type of input features, and performance varied between and within domains and subdomains of applications. Clinical applications of ML algorithms involved triage or diagnosis classification (n = 62), treatment prediction (n = 12), or clinical outcome prediction (n = 50), mainly for out-of-hospital cardiac arrest/OHCA (n = 62), cardiovascular diseases/CVDs (n = 19), and trauma (n = 24). The performance of these ML algorithms varied, with a median area under the receiver operating characteristic curve (AUC) of 85.6%, accuracy of 88.1%, sensitivity of 86.05%, and specificity of 86.5%. Within the operational studies, the operational task of most ML algorithms was ambulance allocation (n = 21), followed by ambulance detection (n = 5), ambulance deployment (n = 5), route optimization (n = 5), and quality assurance (n = 3). The performance of all operational ML algorithms varied and had a median AUC of 96.1%, accuracy of 90.0%, sensitivity of 94.4%, and specificity of 87.7%. Generally, neural network and ensemble algorithms, to some degree, out-performed other ML algorithms.

CONCLUSION

Triaging and managing different prehospital medical conditions and augmenting ambulance performance can be improved by ML algorithms. Future reports should focus on a specific clinical condition or operational task to improve the precision of the performance metrics of ML models.

Clinical decision support system in emergency telephone triage: A scoping review of technical design, implementation and evaluation

OBJECTIVES

Emergency department overcrowding could be improved by upstream telephone triage. Emergency telephone triage aims at managing and orientating adequately patients as early as possible and distributing limited supply of staff and materials. This complex task could be improved with the use of Clinical decision support systems (CDSS). The aim of this scoping review was to identify literature gaps for the future development and evaluation of CDSS for Emergency telephone triage.

MATERIALS AND METHODS

We present here a scoping review of CDSS designed for emergency telephone triage, and compared them in terms of functional characteristics, technical design, health care implementation and methodologies used for evaluation, following the PRISMA-ScR guidelines.

RESULTS

Regarding design, 19 CDSS were retrieved: 12 were knowledge based CDSS (decisional algorithms built according to guidelines or clinical expertise) and 7 were data driven (statistical, machine learning, or deep learning models). Most of them aimed at assisting nurses or non-medical staff by providing patient orientation and/or severity/priority assessment. Eleven were implemented in real life, and only three were connected to the Electronic Health Record. Regarding evaluation, CDSS were assessed through various aspects: intrinsic characteristics, impact on clinical practice or user apprehension. Only one pragmatic trial and one randomized controlled trial were conducted.

CONCLUSION

This review highlights the potential of a hybrid system, user tailored, flexible, connected to the electronic health record, which could work with oral, video and digital data; and the need to evaluate CDSS on intrinsic characteristics and impact on clinical practice, iteratively at each distinct stage of the IT lifecycle.

Artificial intelligence to support out-of-hospital cardiac arrest care: A scoping review

Background

Artificial intelligence (AI) has demonstrated significant potential in supporting emergency medical services personnel during out-of-hospital cardiac arrest (OHCA) care; however, the extent of research evaluating this topic is unknown. This scoping review examines the breadth of literature on the application of AI in early OHCA care.

Methods

We conducted a search of PubMed®, Embase, and Web of Science in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews guidelines. Articles focused on non-traumatic OHCA and published prior to January 18th, 2023 were included. Studies were excluded if they did not use an AI intervention (including machine learning, deep learning, or natural language processing), or did not utilize data from the prehospital phase of care.

Results

Of 173 unique articles identified, 54 (31%) were included after screening. Of these studies, 15 (28%) were from the year 2022 and with an increasing trend annually starting in 2019. The majority were carried out by multinational collaborations (20/54, 38%) with additional studies from the United States (10/54, 19%), Korea (5/54, 10%), and Spain (3/54, 6%). Studies were classified into three major categories including ECG waveform classification and outcome prediction (24/54, 44%), early dispatch-level detection and outcome prediction (7/54, 13%), return of spontaneous circulation and survival outcome prediction (15/54, 20%), and other (9/54, 16%). All but one study had a retrospective design.

Conclusions

A small but growing body of literature exists describing the use of AI to augment early OHCA care.

Trends in survival from out-of-hospital cardiac arrest with a shockable rhythm and its association with bystander resuscitation: a retrospective study

OBJECTIVE

Over 300 000 cases of out-of-hospital cardiac arrests (OHCAs) occur each year in the USA and Europe. Despite decades of investment and research, survival remains disappointingly low. We report the trends in survival after a ventricular fibrillation/pulseless ventricular tachycardia OHCA, over a 13-year period, in a French urban region, and describe the simultaneous evolution of the rescue system.

METHODS

We investigated four 18-month periods between 2005 and 2018. The first period was considered baseline and included patients from the randomised controlled trial 'DEFI 2005'. The three following periods were based on the Paris Sudden Death Expertise Center Registry (France). Inclusion criteria were non-traumatic cardiac arrests treated with at least one external electric shock with an automated external defibrillator from the basic life support team and resuscitated by a physician-staffed ALS team. Primary outcome was survival at hospital discharge with a good neurological outcome.

RESULTS

Of 21 781 patients under consideration, 3476 (16%) met the inclusion criteria. Over all study periods, survival at hospital discharge increased from 12% in 2005 to 25% in 2018 (p<0.001), and return of spontaneous circulation at hospital admission increased from 43% to 58% (p=0.004).Lay-rescuer cardiopulmonary resuscitation (CPR) and telephone CPR (T-CPR) rates increased significantly, but public defibrillator use remained limited.

CONCLUSION

In a two-tiered rescue system, survival from OHCA at hospital discharge doubled over a 13-year study period. Concomitantly, the system implemented an OHCA patient registry and increased T-CPR frequency, despite a consistently low rate of public defibrillator use.

Large Language Models for Epidemiological Research via Automated Machine Learning: Case Study Using Data From the British National Child Development Study

Background

Large language models have had a huge impact on natural language processing (NLP) in recent years. However, their application in epidemiological research is still limited to the analysis of electronic health records and social media data.

objectives

To demonstrate the potential of NLP beyond these domains, we aimed to develop prediction models based on texts collected from an epidemiological cohort and compare their performance to classical regression methods.

Methods

We used data from the British National Child Development Study, where 10,567 children aged 11 years wrote essays about how they imagined themselves as 25-year-olds. Overall, 15% of the data set was set aside as a test set for performance evaluation. Pretrained language models were fine-tuned using AutoTrain (Hugging Face) to predict current reading comprehension score (range: 0-35) and future BMI and physical activity (active vs inactive) at the age of 33 years. We then compared their predictive performance (accuracy or discrimination) with linear and logistic regression models, including demographic and lifestyle factors of the parents and children from birth to the age of 11 years as predictors.

Results

NLP clearly outperformed linear regression when predicting reading comprehension scores (root mean square error: 3.89, 95% CI 3.74-4.05 for NLP vs 4.14, 95% CI 3.98-4.30 and 5.41, 95% CI 5.23-5.58 for regression models with and without general ability score as a predictor, respectively). Predictive performance for physical activity was similarly poor for the 2 methods (area under the receiver operating characteristic curve: 0.55, 95% CI 0.52-0.60 for both) but was slightly better than random assignment, whereas linear regression clearly outperformed the NLP approach when predicting BMI (root mean square error: 4.38, 95% CI 4.02-4.74 for NLP vs 3.85, 95% CI 3.54-4.16 for regression). The NLP approach did not perform better than simply assigning the mean BMI from the training set as a predictor.

Conclusions

Our study demonstrated the potential of using large language models on text collected from epidemiological studies. The performance of the approach appeared to depend on how directly the topic of the text was related to the outcome. Open-ended questions specifically designed to capture certain health concepts and lived experiences in combination with NLP methods should receive more attention in future epidemiological studies.

AI and machine learning in resuscitation: Ongoing research, new concepts, and key challenges

Aim

Artificial intelligence (AI) and machine learning (ML) are important areas of computer science that have recently attracted attention for their application to medicine. However, as techniques continue to advance and become more complex, it is increasingly challenging for clinicians to stay abreast of the latest research. This overview aims to translate research concepts and potential concerns to healthcare professionals interested in applying AI and ML to resuscitation research but who are not experts in the field.

Main text

We present various research including prediction models using structured and unstructured data, exploring treatment heterogeneity, reinforcement learning, language processing, and large-scale language models. These studies potentially offer valuable insights for optimizing treatment strategies and clinical workflows. However, implementing AI and ML in clinical settings presents its own set of challenges. The availability of high-quality and reliable data is crucial for developing accurate ML models. A rigorous validation process and the integration of ML into clinical practice is essential for practical implementation. We furthermore highlight the potential risks associated with self-fulfilling prophecies and feedback loops, emphasizing the importance of transparency, interpretability, and trustworthiness in AI and ML models. These issues need to be addressed in order to establish reliable and trustworthy AI and ML models.

Conclusion

In this article, we overview concepts and examples of AI and ML research in the resuscitation field. Moving forward, appropriate understanding of ML and collaboration with relevant experts will be essential for researchers and clinicians to overcome the challenges and harness the full potential of AI and ML in resuscitation.

Artificial intelligence and machine learning in prehospital emergency care: A scoping review

Our scoping review provides a comprehensive analysis of the landscape of artificial intelligence (AI) applications in prehospital emergency care (PEC). It contributes to the field by highlighting the most studied AI applications and identifying the most common methodological approaches across 106 included studies. The findings indicate a promising future for AI in PEC, with many unique use cases, such as prognostication, demand prediction, resource optimization, and the Internet of Things continuous monitoring systems. Comparisons with other approaches showed AI outperforming clinicians and non-AI algorithms in most cases. However, most studies were internally validated and retrospective, highlighting the need for rigorous prospective validation of AI applications before implementation in clinical settings. We identified knowledge and methodological gaps using an evidence map, offering a roadmap for future investigators. We also discussed the significance of explainable AI for establishing trust in AI systems among clinicians and facilitating real-world validation of AI models.

Tele-Instruction Tool for Multiple Lay Responders Providing Cardiopulmonary Resuscitation in Telehealth Emergency Dispatch Services: Mixed Methods Study

BACKGROUND

Telephone-assisted cardiopulmonary resuscitation (T-CPR) has proven to be a crucial intervention in enhancing the ability of lay responders to perform cardiopulmonary resuscitation (CPR) during telehealth emergency services. While the majority of established T-CPR protocols primarily focus on guiding individual rescuers, there is a lack of emphasis on instructing and coordinating multiple lay responders to perform resuscitation collaboratively.

OBJECTIVE

This study aimed to develop an innovative team-based tele-instruction tool to efficiently organize and instruct multiple lay responders on the CPR process and to evaluate the effectiveness and feasibility of the tool.

METHODS

We used a mixed methods design in this study. We conducted a randomized controlled simulation trial to conduct the quantitative analysis. The intervention groups used the team-based tele-instruction tool for team resuscitation, while the control groups did not have access to the tool. Baseline resuscitation was performed during the initial phase (phase I test). Subsequently, all teams watched a team-based CPR education training video and finished a 3-person practice session with teaching followed by a posttraining test (phase II test). In the qualitative analysis, we randomly selected an individual from each team and 4 experts in emergency medical services to conduct semistructured interviews. The purpose of these interviews was to evaluate the effectiveness and feasibility of this tool.

RESULTS

The team-based tele-instruction tool significantly improved the quality of chest compression in both phase I and phase II tests. The average compression rates were more appropriate in the intervention groups compared to the control groups (median 104.5, IQR 98.8-111.8 min-1 vs median 112, IQR 106-120.8 min-1; P=.04 in phase I and median 117.5, IQR 112.3-125 min-1 vs median 111, IQR 105.3-119 min-1; P=.03 in phase II). In the intervention group, there was a delay in the emergency response time compared to that in the control group (time to first chest compression: median 20, IQR 15-24.8 seconds vs median 25, IQR 20.5-40.3 seconds; P=.03; time to open the airway: median 48, IQR 36.3-62 seconds vs median 73.5, IQR 54.5-227.8 seconds; P=.01). However, this delay was partially mitigated after the phase II test. The qualitative results confirmed the compatibility and generalizability of the team-based tele-instruction tool, demonstrating its ability to effectively guide multiple lay responders through teamwork and effective communication with telecommunicators.

CONCLUSIONS

The use of the team-based tele-instruction tool offers an effective solution to enhance the quality of chest compression among multiple lay responders. This tool facilitated the organization of resuscitation teams by dispatchers and enabled efficient cooperation. Further assessment of the widespread adoption and practical application of the team-based tele-instruction tools in real-life rescue scenarios within the telehealth emergency services system is warranted.

The role of emergency incident type in identifying first responders' health exposure risks

Fire-based emergency management service (EMS) personnel are dispatched to various incidents daily, many of which have unique occupational risks. To fully understand the variability of incident types and how to best prepare and respond, an exploration of the U.S. coding system of incident types is necessary. This study uses potential exposure to SARS-CoV-2 as a case example to understand if and how coding categories for incident call types may be updated to improve data standardization and emergency response decision making. Researchers received emergency response incident data generated by three fire department computer-aided dispatch (CAD) systems between March and September 2020. Each incident was labeled EMS, Fire, or Other. Of the 162,766 incidents, approximately 8.1% (n = 13,144) noted potential SARS-CoV-2 exposure within their narrative descriptions of which 86.3% were coded as EMS, 9.9% as Fire, and 3.9% as Other. To assess coding variability across incident types, researchers used the original 3-incident type variable and a new 5-incident type variable reassigned by researchers into EMS, Fire, Other, Hazmat, and Motor Vehicle. Logit regressions compared differences in potential exposure using the 3- and 5-incident type variables. When evaluating the 3-incident type variable, those responding to a Fire versus an EMS incident were 84% less likely to be associated with potential exposure to SARS-CoV-2. For the 5-incident type variable, those responding to Fire incidents were 77% less likely to be associated with a potential exposure than those responding to EMS incidents. Changes in potential exposure between the 3- and 5-incident type models show the need to understand how incident types are assigned. This demonstrates the need for data standardization to accurately categorize incident types to improve emergency preparedness and response. Results have implications for incident type coding at fire department municipality and national levels.

Information governance as a socio-technical process in the development of trustworthy healthcare AI

In this paper we describe our experiences of managing information governance (IG) processes for the assurance of healthcare AI, using the example of an out-of-hospital-cardiac-arrest recognition software within the context of the Welsh Ambulance Service. We frame IG as a socio-technical process. IG processes for the development of trustworthy healthcare AI rely on information governance work, which entails dialogue, negotiation, and trade-offs around the legal basis for data sharing, data requirements and data control. Information governance work should start early in the design life cycle and will likely continue throughout. This includes a focus on establishing and building relationships, as well as a focus on organizational readiness and deeper understanding of both AI technologies as well as their safety assurance requirements.

Differences between the dispatch priority assessments of emergency medical dispatchers and emergency medical services: a prospective register-based study in Finland

BACKGROUND

Responsive and efficient emergency medical services (EMS) require accurate telephone triage. In Finland, such services are provided by Emergency Response Centre Agency (ERC Agency). In 2018, a new Finnish computer-assisted emergency dispatch system was introduced: the Emergency Response Integrated Common Authorities (ERICA). After the introduction of ERICA, the appropriateness of EMS dispatch has not been investigated yet. The study´s objective is to determine the consistency between the priority triage of the emergency medical dispatcher (EMD) and the on-scene priority assessment of the EMS, and whether the priority assessment consistency varied among the dispatch categories.

METHODS

This was a prospective register-based study. All EMS dispatches registered in the Tampere University Hospital area from 1 August 2021 to 31 August 2021 were analysed. The EMD's mission priority triaged during the emergency call was compared with the on-scene EMS's assessment of the priority, derived from the pre-set criteria. The test performance levels were measured from the crosstabulation of true or false positive and negative values of the priority assessment. Statistical significance was analysed using the chi-square test and the Kruskal-Wallis H test, and p-values < 0.05 were considered significant.

RESULTS

Of the 6416 EMS dispatches analysed in this study, 36% (2341) were urgent according to the EMD's dispatch priority, and of these, only 29% (688) were urgent according to the EMS criteria. On the other hand, 64% (4075) of the dispatches were non-urgent according to the EMD's dispatch priority, of which 97% (3949) were non-urgent according to the EMS criteria. Moreover, there were differences between the EMD and EMS priority assessments among the dispatch categories (p < 0.001). The overall efficiency was 72%, sensitivity 85%, specificity 71%, positive predictive value 29%, and negative predictive value 97%.

CONCLUSION

While the EMD recognised the non-urgent dispatches with high consistency with the EMS criteria, most of the EMD's urgent dispatches were not urgent according to the same criteria. This may diminish the availability of the EMS for more urgent missions. Thus, measures are needed to ensure more accurate and therefore, more efficient use of EMS resources in the future.

Performance of the medical priority dispatch system in correctly classifying out-of-hospital cardiac arrests as appropriate for resuscitation

BACKGROUND

Emergency dispatch centres receive emergency calls and assign resources. Out-of-hospital cardiac arrests (OHCA) can be classified as appropriate (requiring emergent response) or inappropriate (requiring non-emergent response) for resuscitation. We sought to determine system accuracy in emergency medical services (EMS) OHCA response allocation.

METHODS

We analyzed EMS-assessed non-traumatic OHCA records from the British Columbia (BC) Cardiac Arrest registry (January 1, 2019-June 1, 2021), excluding EMS-witnessed cases. In BC the "Medical Priority Dispatch System" is used. We classified EMS dispatch as "emergent" or "non-emergent" and compared to the gold standard of whether EMS personnel decided treatment was appropriate upon scene arrival. We calculated sensitivity, specificity, and positive and negative predictive values (PPV, NPV), with 95% CI's.

RESULTS

Of 15,371 non-traumatic OHCAs, the median age was 65 (inter quartile range 51-78), and 4834 (31%) were women; 7152 (47%) were EMS-treated, of whom 651 (9.1%) survived). Among EMS-treated cases 6923/7152 had an emergent response (sensitivity = 97%, 95% CI 96-97) and among EMS-untreated cases 3951/8219 had a non-emergent response (specificity = 48%, 95% CI, 47 to 49). Among cases with emergent dispatch, 6923/11191 were EMS-treated (PPV = 62%, 95% CI 61-62), and among those with non-emergent dispatch, 3951/4180 were EMS-untreated (NPV = 95%, 95% CI 94-95); 229/4180 (5.5%) with a non-emergent dispatch were treated by EMS.

CONCLUSION

The dispatch system in BC has a high sensitivity and moderate specificity in sending the appropriate responses for OHCAs deemed appropriate for treatment by paramedics. Future research may address strategies to increase system specificity, and decrease the incidence of non-emergent dispatch to EMS-treated cases.

Machine Learning-Based Text Analysis to Predict Severely Injured Patients in Emergency Medical Dispatch: Model Development and Validation

Background

Early recognition of severely injured patients in prehospital settings is of paramount importance for timely treatment and transportation of patients to further treatment facilities. The dispatching accuracy has seldom been addressed in previous studies.

Objective

In this study, we aimed to build a machine learning–based model through text mining of emergency calls for the automated identification of severely injured patients after a road accident.

Methods

Audio recordings of road accidents in Taipei City, Taiwan, in 2018 were obtained and randomly sampled. Data on call transfers or non-Mandarin speeches were excluded. To predict cases of severe trauma identified on-site by emergency medical technicians, all included cases were evaluated by both humans (6 dispatchers) and a machine learning model, that is, a prehospital-activated major trauma (PAMT) model. The PAMT model was developed using term frequency–inverse document frequency, rule-based classification, and a Bernoulli naïve Bayes classifier. Repeated random subsampling cross-validation was applied to evaluate the robustness of the model. The prediction performance of dispatchers and the PAMT model, in severe cases, was compared. Performance was indicated by sensitivity, specificity, positive predictive value, negative predictive value, and accuracy.

Results

Although the mean sensitivity and negative predictive value obtained by the PAMT model were higher than those of dispatchers, they obtained higher mean specificity, positive predictive value, and accuracy. The mean accuracy of the PAMT model, from certainty level 0 (lowest certainty) to level 6 (highest certainty), was higher except for levels 5 and 6. The overall performances of the dispatchers and the PAMT model were similar; however, the PAMT model had higher accuracy in cases where the dispatchers were less certain of their judgments.

Conclusions

A machine learning–based model, called the PAMT model, was developed to predict severe road accident trauma. The results of our study suggest that the accuracy of the PAMT model is not superior to that of the participating dispatchers; however, it may assist dispatchers when they lack confidence while making a judgment.

How technology can save lives in cardiac arrest

PURPOSE OF REVIEW

Technology is being increasingly implemented in the fields of cardiac arrest and cardiopulmonary resuscitation. In this review, we describe how recent technological advances have been implemented in the chain of survival and their impact on outcomes after cardiac arrest. Breakthrough technologies that are likely to make an impact in the future are also presented.

RECENT FINDINGS

Technology is present in every link of the chain of survival, from prediction, prevention, and rapid recognition of cardiac arrest to early cardiopulmonary resuscitation and defibrillation. Mobile phone systems to notify citizen first responders of nearby out-of-hospital cardiac arrest have been implemented in numerous countries with improvement in bystanders' interventions and outcomes. Drones delivering automated external defibrillators and artificial intelligence to support the dispatcher in recognising cardiac arrest are already being used in real-life out-of-hospital cardiac arrest. Wearables, smart speakers, surveillance cameras, and artificial intelligence technologies are being developed and studied to prevent and recognize out-of-hospital and in-hospital cardiac arrest.

SUMMARY

This review highlights the importance of technology applied to every single step of the chain of survival to improve outcomes in cardiac arrest. Further research is needed to understand the best role of different technologies in the chain of survival and how these may ultimately improve outcomes.

Assuring safe artificial intelligence in critical ambulance service response: study protocol

Introduction: Early recognition of out-of-hospital cardiac arrest (OHCA) by ambulance service call centre operators is important so that cardiopulmonary resuscitation can be delivered immediately, but around 25% of OHCAs are not picked up by call centre operators. An artificial intelligence (AI) system has been developed to support call centre operators in the detection of OHCA. The study aims to (1) explore ambulance service stakeholder perceptions on the safety of OHCA AI decision support in call centres, and (2) develop a clinical safety case for the OHCA AI decision-support system.Methods and analysis: The study will be undertaken within the Welsh Ambulance Service. The study is part research and part service evaluation. The research utilises a qualitative study design based on thematic analysis of interview data. The service evaluation consists of the development of a clinical safety case based on document analysis, analysis of the AI model and its development process and informal interviews with the technology developer.Conclusions: AI presents many opportunities for ambulance services, but safety assurance requirements need to be understood. The ASSIST project will continue to explore and build the body of knowledge in this area.

Swedish dispatchers’ compliance with the American Heart Association performance goals for dispatch-assisted cardiopulmonary resuscitation and its association with survival in out-of-hospital cardiac arrest: A retrospective study

Aim

We aimed 1) to investigate how Swedish dispatchers perform during emergency calls in accordance with the American Heart Association (AHA) goals for dispatcher-assisted cardiopulmonary resuscitation (DA-CPR), 2) calculate the potential impact on 30-day survival.

Methods

This observational study includes a random sample of 1000 out-of-hospital cardiac arrest (OHCA) emergency ambulance calls during 2018 in Sweden. Voice logs were audited to evaluate dispatchers’ handling of emergency calls according to the AHA performance goals. Number of possible additional survivors was estimated assuming the timeframes of the AHA performance goals was achieved.

Results

A total of 936 cases were included. An OHCA was recognized by a dispatcher in 79% (AHA goal 75%). In recognizable OHCA, dispatchers recognized 85% (AHA goal 95%). Dispatch-directed compressions were given in 61% (AHA goal 75%). Median time to OHCA recognition was 113 s [interquartile range (IQR), 62, 204 s] (AHA goal < 60 s). The first dispatch-directed compression was performed at a median time of 240 s [IQR, 176, 332 s] (AHA goal < 90 s). If eligible patients receive dispatch-directed compressions within the AHA 90 s goal, 73 additional lives may be saved; if all cases are recognized within the AHA 60 s goal, 25 additional lives may be saved.

Conclusions

The AHA policy statement serves as a benchmark for all emergency medical dispatch centres (EMDC). Additional effort is needed at Swedish EMDC to achieve AHA goals for DA-CPR. Our study suggests that if EMDC further optimize handling of OHCA calls in accordance with AHA goals, many more lives may be saved.

Responding to Cardiac Arrest in the Community in the Digital Age

Sudden cardiac arrest (SCA) is a common event, affecting almost 400,000 individuals annually in North America. Initiation of cardiopulmonary resuscitation (CPR) and early defibrillation using an automated external defibrillator (AED) are critical for survival, yet many bystanders are reluctant to intervene. Digital technologies, including mobile devices, social media and crowdsourcing may help play a role to improve survival from SCA. In this article we review the current digital tools and strategies available to increase rates of bystander recognition of SCA, prompt immediate activation of Emergency Medical Services (EMS), initiate high quality CPR and to locate, retrieve and operate AEDs. Smartphones can help to both educate and connect bystanders with EMS dispatchers, through text messaging or video-calling, to encourage the initiation of CPR and retrieval of the closest AED. Wearable devices and household smartspeakers could play a future role in continuous vital signs monitoring in individuals at-risk of lethal arrhythmias and send an alert to either chosen contacts or EMS. Machine learning algorithms and mathematical modeling may aid EMS dispatchers with better recognition of SCA as well as policymakers with where to best place AEDs for optimal accessibility. There are challenges with the use of digital tech, including the need for government regulation and issues with data ownership, accessibility and interoperability. Future research will include smart cities, e-linkages, new technologies and using social media for mass education. Together or in combination, these emerging digital technologies may represent the next leap forward in SCA survival.