Towards proactive palliative care in oncology: developing an explainable EHR-based machine learning model for mortality risk prediction.

BACKGROUND: Ex-ante identification of the last year in life facilitates a proactive palliative approach. Machine learning models trained on electronic health records (EHR) demonstrate promising performance in cancer prognostication. However, gaps in literature include incomplete reporting of model performance, inadequate alignment of model formulation with implementation use-case, and insufficient explainability hindering trust and adoption in clinical settings. Hence, we aim to develop an explainable machine learning EHR-based model that prompts palliative care processes by predicting for 365-day mortality risk among patients with advanced cancer within an outpatient setting. METHODS: Our cohort consisted of 5,926 adults diagnosed with Stage 3 or 4 solid organ cancer between July 1, 2017, and June 30, 2020 and receiving ambulatory cancer care within a tertiary center. The classification problem was modelled using Extreme Gradient Boosting (XGBoost) and aligned to our envisioned use-case: "Given a prediction point that corresponds to an outpatient cancer encounter, predict for mortality within 365-days from prediction point, using EHR data up to 365-days prior." The model was trained with 75% of the dataset (n = 39,416 outpatient encounters) and validated on a 25% hold-out dataset (n = 13,122 outpatient encounters). To explain model outputs, we used Shapley Additive Explanations (SHAP) values. Clinical characteristics, laboratory tests and treatment data were used to train the model. Performance was evaluated using area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC), while model calibration was assessed using the Brier score. RESULTS: In total, 17,149 of the 52,538 prediction points (32.6%) had a mortality event within the 365-day prediction window. The model demonstrated an AUROC of 0.861 (95% CI 0.856-0.867) and AUPRC of 0.771. The Brier score was 0.147, indicating slight overestimations of mortality risk. Explanatory diagrams utilizing SHAP values allowed visualization of feature impacts on predictions at both the global and individual levels. CONCLUSION: Our machine learning model demonstrated good discrimination and precision-recall in predicting 365-day mortality risk among individuals with advanced cancer. It has the potential to provide personalized mortality predictions and facilitate earlier integration of palliative care.

Wolf creek XVII part 4: Amplifying lay-rescuer response.

Introduction: Amplifying lay-rescuer response is a key priority to increase survival from out-of-hospital cardiac arrest (OHCA). We describe the current state of lay-rescuer response, how we envision the future, and the gaps, barriers, and research priorities that will amplify response to OHCA. Methods: 'Amplifying Lay-Rescuer Response' was one of six focus topics for the Wolf Creek XVII Conference held on June 14-17, 2023, in Ann Arbor, Michigan, USA. Conference invitees included international thought leaders and scientists in the field of cardiac arrest resuscitation from academia and industry. Participants submitted via online survey knowledge gaps, barriers to translation and research priorities for each focus topic. Expert panels used the survey results and their own perspectives and insights to create and present a preliminary unranked list for each category that was debated, revised and ranked by all attendees to identify the top 5 for each category. Results: The top five knowledge gaps as ranked by the panel, reflected a recognition of the need to better understand the psycho-social aspects of lay response. The top five barriers to translation reflected issues at the individual, community, societal, structural, and governmental levels. The top five research priorities were focused on understanding the social/psychological and emotional barriers to action, finding the most effective/cost-effective strategies to educate lay persons and implement community life-saving interventions, evaluation of new technological solutions and how to enhance the role of dispatch working with lay-rescuers. Conclusion: Future research in lay rescuer response should incorporate technology innovations, understand the "humanity" of the situation, leverage implementation science and systems thinking to save lives. This will require the field of resuscitation to engage with scholars outside our traditional ranks and to be open to new ways of thinking about old problems.

Three-year trends in out-of-hospital cardiac arrest across the world: Second report from the International Liaison Committee on Resuscitation (ILCOR).

BACKGROUND: The International Liaison Committee on Resuscitation (ILCOR) Research and Registries Working Group previously reported data on systems of care and outcomes of out-of-hospital cardiac arrest (OHCA) in 2015 from 16 national and regional registries. To describe the temporal trends with updated data on OHCA, we report the characteristics of OHCA from 2015 through 2017. METHODS: We invited national and regional population-based OHCA registries for voluntary participation and included emergency medical services (EMS)-treated OHCA. We collected descriptive summary data of core elements of the latest Utstein style recommendation during 2016 and 2017 at each registry. For registries that participated in the previous 2015 report, we also extracted the 2015 data. RESULTS: Eleven national registries in North America, Europe, Asia, and Oceania, and 4 regional registries in Europe were included in this report. Across registries, the estimated annual incidence of EMS-treated OHCA was 30.0-97.1 individuals per 100,000 population in 2015, 36.4-97.3 in 2016, and 40.8-100.2 in 2017. The provision of bystander cardiopulmonary resuscitation (CPR) varied from 37.2% to 79.0% in 2015, from 2.9% to 78.4% in 2016, and from 4.1% to 80.3% in 2017. Survival to hospital discharge or 30-day survival for EMS-treated OHCA ranged from 5.2% to 15.7% in 2015, from 6.2% to 15.8% in 2016, and from 4.6% to 16.4% in 2017. CONCLUSION: We observed an upward temporal trend in provision of bystander CPR in most registries. Although some registries showed favourable temporal trends in survival, less than half of registries in our study demonstrated such a trend.

Maximum expected survival rate model for public access defibrillator placement.

AIM: Mathematical optimization of automated external defibrillator (AED) placement has demonstrated potential to improve survival of out-of-hospital cardiac arrest (OHCA). Existing models mostly aim to improve accessibility based on coverage radius and do not account for detailed impact of delayed defibrillation on survival. We aimed to predict OHCA survival based on time to defibrillation and developed an AED placement model to directly maximize the expected survival rate. METHODS: We stratified OHCAs occurring in Singapore (2010-2017) based on time to defibrillation and developed a regression model to predict the Utstein survival rate. We then developed a novel AED placement model, the maximum expected survival rate (MESR) model. We compared the performance of MESR with a maximum coverage model developed for Canada that was shown to be generalizable to other settings (Denmark). The survival gain of MESR was assessed through 10-fold cross-validation for placement of 20 to 1000 new AEDs in Singapore. Statistical analysis was performed using χ2 and McNemar's tests. RESULTS: During the study period, 15,345 OHCAs occurred. The power-law approximation with R2 of 91.33% performed best among investigated models. It predicted a survival of 54.9% with defibrillation within the first two minutes after collapse that was reduced by more than 60% without defibrillation within the first 4 minutes. MESR outperformed the maximum coverage model with P-value < 0.05 (<0.0001 in 22 of 30 experiments). CONCLUSION: We developed a novel AED placement model based on the impact of time to defibrillation on OHCA outcomes. Mathematical optimization can improve OHCA survival.

Cardiac arrest and cardiopulmonary resuscitation outcome reports: update of the Utstein Resuscitation Registry Templates for Out-of-Hospital Cardiac Arrest: a statement for healthcare professionals from a task force of the International Liaison Committee on Resuscitation (American Heart Association, European Resuscitation Council, Australian and New Zealand Council on Resuscitation, Heart and Stroke Foundation of Canada, InterAmerican Heart Foundation, Resuscitation Council of Southern Africa, Resuscitation Council of Asia); and the American Heart Association Emergency Cardiovascular Care Committee and the Council on Cardiopulmonary, Critical Care, Perioperative and Resuscitation.

Utstein-style guidelines contribute to improved public health internationally by providing a structured framework with which to compare emergency medical services systems. Advances in resuscitation science, new insights into important predictors of outcome from out-of-hospital cardiac arrest, and lessons learned from methodological research prompted this review and update of the 2004 Utstein guidelines. Representatives of the International Liaison Committee on Resuscitation developed an updated Utstein reporting framework iteratively by meeting face to face, by teleconference, and by Web survey during 2012 through 2014. Herein are recommendations for reporting out-of-hospital cardiac arrest. Data elements were grouped by system factors, dispatch/recognition, patient variables, resuscitation/postresuscitation processes, and outcomes. Elements were classified as core or supplemental using a modified Delphi process primarily based on respondents' assessment of the evidence-based importance of capturing those elements, tempered by the challenges to collect them. New or modified elements reflected consensus on the need to account for emergency medical services system factors, increasing availability of automated external defibrillators, data collection processes, epidemiology trends, increasing use of dispatcher-assisted cardiopulmonary resuscitation, emerging field treatments, postresuscitation care, prognostication tools, and trends in organ recovery. A standard reporting template is recommended to promote standardized reporting. This template facilitates reporting of the bystander-witnessed, shockable rhythm as a measure of emergency medical services system efficacy and all emergency medical services system-treated arrests as a measure of system effectiveness. Several additional important subgroups are identified that enable an estimate of the specific contribution of rhythm and bystander actions that are key determinants of outcome.

Dispatcher-assisted bystander cardiopulmonary resuscitation in a metropolitan city: a before-after population-based study.

BACKGROUND: The goal of this study was to determine the effects of dispatcher-assisted bystander cardiopulmonary resuscitation (DA-CPR) on outcomes of out-of-hospital cardiac arrest (OHCA). METHODS: All EMS in a metropolitan city with a population of 10 million are dispatched by a single, centralized, and physician-supervised center. Data on patients with adult OHCA with cardiac etiology were collected from the dispatch center registry and from EMS run sheets and hospital medical record review from 2009 to 2011. A standardized DA-CPR protocol (aligned with the 2010 AHA guidelines) we implemented as an intervention in January 2011. The end points were survival to discharge, good neurological outcome, and bystander CPR rate. Multivariate logistic analysis was used to compare between intervention group (2011) and historical control group (2009-2010). RESULTS: Of 8.144 eligible patients, bystander CPR was performed for the patients in 5.7% (148/2600) of cases in 2009, 6.7% (190/2857) in 2010, and 12.4% (334/2686) in 2011 (p<0.001). The survival to discharge rates was 7.1% (2009), 7.1% (2010), and 9.4% (2011) (p=0.001). Good neurological outcomes occurred in 2.1% (2009), 2.0% (2010), and 3.6% (2011) of cases (p<0.001). The adjusted ORs (95% CIs) for survival to discharge compared with 2009 were 1.33 (1.07-1.66) in 2011 and 1.12 (0.89-1.41) in 2010. The adjusted ORs (95% CIs) for good neurological outcomes were 1.67 (1.13-2.45) in 2011 and 1.13 (0.74-1.72) in 2010. CONCLUSIONS: An EMS intervention using the DA-CPR protocol was associated with a significant increase in bystander CPR and an improved survival and neurologic outcome after OHCA.

Global health and emergency care: a resuscitation research agenda--part 1.

At the 2013 Academic Emergency Medicine global health consensus conference, a breakout session on a resuscitation research agenda was held. Two articles focusing on cardiac arrest and trauma resuscitation are the result of that discussion. This article describes the burden of disease and outcomes, issues in resuscitation research, and global trends in resuscitation research funding priorities. Globally, cardiovascular disease and trauma cause a high burden of disease that receives a disproportionately smaller research investment. International resuscitation research faces unique ethical challenges. It needs reliable baseline statistics regarding quality of care and outcomes; data linkages between providers; reliable and comparable national databases; and an effective, efficient, and sustainable resuscitation research infrastructure to advance the field. Research in resuscitation in low- and middle-income countries is needed to understand the epidemiology, infrastructure and systems context, level of training needed, and potential for cost-effective care to improve outcomes. Research is needed on low-cost models of population-based research, ways to disseminate information to the developing world, and finding the most cost-effective strategies to improve outcomes.

Cardiac arrest and resuscitation epidemiology in Singapore (CARE I study).

OBJECTIVES: To describe the epidemiology of out-of-hospital cardiac arrest (OHCA) in Singapore, the emergency medical services (EMS) response, and to identify possible areas for improvement. METHODS: This prospective observational study constitutes phase I of the Cardiac Arrest and Resuscitation Epidemiology (CARE) project. Included were all patients with nontraumatic OHCA conveyed by the national emergency ambulance service. Patient characteristics, cardiac arrest circumstances, EMS response, and outcomes were recorded according to the Utstein style. RESULTS: From October 1, 2001, to April 30, 2002, 548 patients were enrolled into the study. Mean (standard deviation [SD]) age was 62.2 (17.9) years, with a male predominance (65.6%). A total of 59.8% of collapses occurred at home, 35.3% of arrests were not witnessed, and bystander cardiopulmonary resuscitation was present for 20.6%. Mean (SD) time from collapse to call received by EMS was 10.6 (13.1) minutes. Mean (SD) EMS response time was 10.2 (4.3) minutes. Mean (SD) time from call to defibrillation was 16.7 (7.2) minutes. Mean (SD) on-scene time was 9.9 (4.5) minutes. First presenting rhythm at the scene was asystole in 54.5%, pulseless electrical activity 22.9%, ventricular fibrillation 19.6%, and ventricular tachycardia 0.4%. Of all cardiac arrests, 351 had resuscitation attempted and were of cardiac origin. Among these patients, 17.9% had return of spontaneous circulation, 8.5% survived to hospital admission, and 2.0% survived to discharge. CONCLUSION: CARE I establishes the baseline for the evaluation of incremental introduction of prehospital Advanced Cardiac Life Support interventions planned for future phases. Continuing efforts should be made to strengthen all chains of survival. This represents the most comprehensive OHCA study yet conducted in Singapore.