Asunto(s)

RESUMEN

INTRODUCTION: The proportion of very elderly patients in the intensive care unit (ICU) is expected to rise. Furthermore, patients are likely more prone to suffer a cardiac arrest (CA) event within the ICU. The occurrence of intensive care unit cardiac arrest (ICU-CA) is associated with high mortality. To date, the incidence of ICU-CA and its clinical impact on outcome in the very old (≥ 90 years) patients treated is unknown. METHODS: Retrospective analysis of all consecutive critically ill patients ≥ 90 years admitted to the ICU of a tertiary care university hospital in Hamburg (Germany). All patients suffering ICU-CA were included and CA characteristics and functional outcome was assessed. Clinical course and outcome were assessed and compared between the subgroups of patients with and without ICU-CA. RESULTS: 1,108 critically ill patients aged ≥ 90 years were admitted during the study period. The median age was 92.3 (91.0-94.2) years and 67% (n = 747) were female. 2% (n = 25) of this cohort suffered ICU-CA after a median duration 0.5 (0.2-3.2) days of ICU admission. The presumed cause of ICU-CA was cardiac in 64% (n = 16). The median resuscitation time was 10 (2-15) minutes and the initial rhythm was shockable in 20% (n = 5). Return of spontaneous circulation (ROSC) could be achieved in 68% (n = 17). The cause of ICU admission was primarily medical in the total cohort (ICU-CA: 48% vs. No ICU-CA: 34%, p = 0.13), surgical - planned (ICU-CA: 32% vs. No ICU-CA: 37%, p = 0.61) and surgical - unplanned/emergency (ICU-CA: 43% vs. No ICU-CA: 28%, p = 0.34). The median Charlson Comorbidity Index (CCI) was 2 (1-3) points for patients with ICU-CA and 1 (0-2) for patients without ICU-CA (p = 0.54). Patients with ICU-CA had a higher disease severity according to SAPS II (ICU-CA: 54 vs. No ICU-CA: 36 points, p < 0.001). Patients with ICU-CA had a higher rate of mechanically ventilation (ICU-CA: 64% vs. No ICU-CA: 34%, p < 0.01) and required vasopressor therapy more often (ICU-CA: 88% vs. No ICU-CA: 41%, p < 0.001). The ICU and in-hospital mortality was 88% (n = 22) and 100% (n = 25) in patients with ICU-CA compared to 17% (n = 179) and 28% (n = 306) in patients without ICU-CA. The mortality rate for patients with ICU-CA was observed to be 88% (n = 22) in the ICU and 100% (n = 25) in-hospital. In contrast, patients without ICU-CA had an in-ICU mortality rate of 17% (n = 179) and an in-hospital mortality rate of 28% (n = 306) (both p < 0.001). CONCLUSION: The occurrence of ICU-CA in very elderly patients is rare but associated with high mortality. Providing CPR in this cohort did not lead to long-term survival at our centre. Very elderly patients admitted to the ICU likely benefit from supportive care only and should probably not be resuscitated due to poor chance of survival and ethical considerations. Providing personalized assurances that care will remain appropriate and in accordance with the patient's and family's wishes can optimise compassionate care while avoiding futile life-sustaining interventions.

Asunto(s)

RESUMEN

This study aimed to evaluate the readability, reliability, and quality of responses by 4 selected artificial intelligence (AI)-based large language model (LLM) chatbots to questions related to cardiopulmonary resuscitation (CPR). This was a cross-sectional study. Responses to the 100 most frequently asked questions about CPR by 4 selected chatbots (ChatGPT-3.5 [Open AI], Google Bard [Google AI], Google Gemini [Google AI], and Perplexity [Perplexity AI]) were analyzed for readability, reliability, and quality. The chatbots were asked the following question: "What are the 100 most frequently asked questions about cardio pulmonary resuscitation?" in English. Each of the 100 queries derived from the responses was individually posed to the 4 chatbots. The 400 responses or patient education materials (PEM) from the chatbots were assessed for quality and reliability using the modified DISCERN Questionnaire, Journal of the American Medical Association and Global Quality Score. Readability assessment utilized 2 different calculators, which computed readability scores independently using metrics such as Flesch Reading Ease Score, Flesch-Kincaid Grade Level, Simple Measure of Gobbledygook, Gunning Fog Readability and Automated Readability Index. Analyzed 100 responses from each of the 4 chatbots. When the readability values of the median results obtained from Calculators 1 and 2 were compared with the 6th-grade reading level, there was a highly significant difference between the groups (P < .001). Compared to all formulas, the readability level of the responses was above 6th grade. It can be seen that the order of readability from easy to difficult is Bard, Perplexity, Gemini, and ChatGPT-3.5. The readability of the text content provided by all 4 chatbots was found to be above the 6th-grade level. We believe that enhancing the quality, reliability, and readability of PEMs will lead to easier understanding by readers and more accurate performance of CPR. So, patients who receive bystander CPR may experience an increased likelihood of survival.

Asunto(s)

RESUMEN

BACKGROUND: Out-of-hospital cardiac arrest (OHCA) survival in the UK remains overall poor with fewer than 10% of patients surviving to hospital discharge. Extracorporeal cardiopulmonary resuscitation (ECPR) is a developing therapy option that can improve survival in select patients if treatment begins within an hour. Clinicians' perspectives are a pivotal consideration to the development of effective systems for OHCA ECPR, but they have been infrequently explored. This study investigates clinicians' views on the barriers and facilitators to establishing effective systems to facilitate transport of OHCA patients for in-hospital ECPR. METHODS: In January 2023, Thames Valley Air Ambulance (TVAA) and Harefield Hospital developed an ECPR partnership pathway for conveyance of OHCA patients for in-hospital ECPR. The authors of this study conducted a survey of clinicians across both services looking to identify clear barriers and positive contributors to the effective implementation of the programme. The survey included questions about technical and non-technical barriers and facilitators, with free-text responses analysed thematically. RESULTS: Responses were received from 14 pre-hospital TVAA critical care and 9 in-hospital clinicians' representative of various roles and experiences. Data analysis revealed 10 key themes and 19 subthemes. The interconnected themes, identified by pre-hospital TVAA critical care clinicians as important barriers or facilitators in this ECPR system included educational programmes; collectiveness in effort and culture; teamwork; inter-service communication; concurrent activity; and clarity of procedures. Themes from in-hospital clinicians' responses were distilled into key considerations focusing on learning and marginal gains, standardising and simplifying protocols, training and simulation; and nurturing effective teams. CONCLUSION: This study identified several clear themes and subthemes from clinical experience that should be considered when developing and modelling an ECPR system for OHCA. These insights may inform future development of ECPR programmes for OHCA in other centres. Key recommendations identified include prioritising education and training (including regular simulations), standardising a 'pitstop style' handover process, establishing clear roles during the cannulation process and developing standardised protocols and selection criteria. This study also provides insight into the feasibility of using pre-hospital critical care teams for intra-arrest patient retrieval in the pre-hospital arena.

Asunto(s)

RESUMEN

IMPORTANCE: The relationship between post-hospital arrival factors and out-of-hospital cardiac arrest (OHCA) outcomes remains unclear. OBJECTIVES: This study assessed the impact of post-hospital arrival factors on OHCA outcomes during the COVID-19 pandemic using a prediction model. DESIGN, SETTING, AND PARTICIPANTS: In this cohort study, data from the All-Japan Utstein Registry, a nationwide population-based database, between 2015 and 2021 were used. A total of 541,781 patients older than 18 years old who experienced OHCA of cardiac origin were included. MAIN OUTCOMES AND MEASURES: The primary exposure was trends in COVID-19 cases. The study compared the predicted proportion of favorable neurologic outcomes 1 month after resuscitation with the actual outcomes. Neurologic outcomes were categorized based on the Cerebral Performance Category score (1, good cerebral function; 2, moderate cerebral function). RESULTS: The prediction model, which had an area under the curve of 0.96, closely matched actual outcomes in 2019. However, a significant discrepancy emerged after the pandemic began in 2020, where outcomes continued to deteriorate as the virus spread, exacerbated by both pre- and post-hospital arrival factors. CONCLUSIONS AND RELEVANCE: Post-hospital arrival factors were as important as pre-hospital factors in adversely affecting the prognosis of patients following OHCA during the COVID-19 pandemic. The results suggest that the overall response of the healthcare system needs to be improved during infectious disease outbreaks to improve outcomes.

Asunto(s)

Asunto(s)

Asunto(s)

RESUMEN

Importance: Ventricular fibrillation (VF) or pulseless ventricular tachycardia (pVT) are the most treatable causes of out-of-hospital cardiac arrest (OHCA). Yet, it remains unknown if defibrillator pad position, placement in the anterior-posterior (AP) or anterior-lateral (AL) locations, impacts patient outcomes in VF or pVT OHCA. Objective: To determine the association between initial defibrillator pad placement position and OHCA outcomes for patients presenting with VF or pVT. Design, Setting, and Participants: This prospective cohort study included patients with OHCA and VF or pVT treated by a single North American emergency medical services (EMS) agency from July 1, 2019, through June 30, 2023. The study included patients with OHCA treated by a large suburban fire-based EMS agency that covers a population of 550 000. Consecutive patients with an initial EMS-assessed rhythm of VF or pVT receiving EMS defibrillation were included. Pediatric patients (younger than 18 years), interfacility transfers, arrests of obvious traumatic etiology, and patients with preexisting do-not-resuscitate status were excluded. Exposure: AP or AL pad placement. Main Outcomes and Measures: Return of spontaneous circulation (ROSC) at any time with secondary outcomes of pulses present at emergency department (ED) arrival, survival to hospital admission, survival to hospital discharge, and functional survival at hospital discharge (cerebral performance category score of 2 or less). Measures included adjusted odds ratios (aOR), multivariable logistic regressions, and Fine-Gray competing risks regression. Results: A total of 255 patients with OHCA were included (median [IQR] age, 66 [55-74] years; 63 females [24.7%]), with initial pad positioning documented as either AP (158 patients [62.0%]; median [IQR] age, 65 [54-74] years; 37 females [23.4%]) or AL (97 patients [38.0%]; median [IQR] age, 66 [57-74] years; 26 females [26.8%]). Patients with AP placement had higher adjusted odds ratio (aOR) of ROSC at any time (aOR, 2.64 [95% CI, 1.50-4.65]), but not significantly different odds of pulses present at ED arrival (1.34 [95% CI, 0.78-2.30]), survival to hospital admission (1.41 [0.82-2.43]), survival to hospital discharge (1.55 [95% CI, 0.83-2.90]), or functional survival at hospital discharge (1.86 [95% CI, 0.98-3.51]). Competing risk analysis found significantly greater cumulative incidence of ROSC among those at risk with initial AP placement compared with AL (subdistribution hazard ratio, 1.81 [95% CI, 1.23-2.67]; P = .003). Conclusions and Relevance: In this cohort study of patients with OHCA and VF or pVT, AP defibrillator pad placement was associated with higher ROSC compared with AL placement.

Asunto(s)

RESUMEN

BACKGROUND: Pneumothorax may occur as a complication of cardiopulmonary resuscitation (CPR) and could pose a potentially life-threatening condition. In this study we sought to investigate the incidence of pneumothorax following CPR for out-of-hospital cardiac arrest (OHCA), identify possible risk factors, and elucidate its association with outcomes. METHODS: This study was a retrospective data analysis of patients hospitalized following CPR for OHCA. We included cases from 1st March 2014 to 31st December 2021 which were attended by teams of the physician staffed ambulance based at the University Medical Centre Graz, Austria. Chest imaging after CPR was reviewed to assess whether pneumothorax was present or not. Logistic regression analysis was performed to identify factors for the development of pneumothorax relevant and to assess its association with outcomes [survival to hospital discharge and cerebral performance category (CPC)]. RESULTS: Pneumothorax following CPR was found in 26 out of 237 included cases (11.0%). History of obstructive lung disease was significantly associated with presence of pneumothorax after CPR. This subgroup of patients (n = 61) showed a pneumothorax rate of 23.0%. Pneumothorax was not identified as a relevant factor to predict survival to hospital discharge or favourable neurological outcome (CPC1 + 2). CONCLUSIONS: Pneumothorax may be present in greater than one in ten patients hospitalized after CPR for OHCA. Pre-existent obstructive pulmonary disease seems to be a relevant risk factor for development of post-CPR pneumothorax. CLINICALTRIALS: gov ID: NCT06182007 (retrospectively registered). TRIAL REGISTRATION: NCT06182007 (retrospectively registered).

Asunto(s)

RESUMEN

BACKGROUND: Limited research has analyzed the association between diastolic blood pressure (DBP) and survival after pediatric cardiopulmonary resuscitation (CPR). This study aimed to explore the association between post-resuscitation diastolic blood pressure and survival in pediatric patients who underwent CPR. METHOD: This retrospective single-center study included pediatric patients admitted to the pediatric intensive care unit of Asan Medical Center between January 2016 to November 2022. Patients undergoing extracorporeal CPR and those with unavailable data were excluded. The primary endpoint was survival to ICU discharge. RESULTS: A total of 106 patients were included, with 67 (63.2%) achieving survival to ICU discharge. Multivariate logistic regression analysis identified DBP within 1 h after ROSC as the sole significant variable (p = 0.002, aOR, 1.043; 95% CI, 1.016-1.070). Additionally, DBP within 1 h demonstrated an area under the ROC curve of 0.7 (0.592-0.809) for survival to ICU discharge, along with mean blood pressure within the same timeframe. CONCLUSION: Our study highlights the importance of DBP within 1-hour post-ROSC as a significant prognostic factor for survival to ICU discharge. However, further validation through further prospective large-scale studies is warranted to confirm the appropriate post-resuscitation DBP of pediatric patients.

Asunto(s)

RESUMEN

BACKGROUND: Thoracic computed tomography scans (CT) are used by several study groups to investigate the circulatory structures (heart and vessels) located behind the pressure point for chest compressions. Yet, it remains unclear how the positioning of these structures is influenced by factors such as intubation, the respiratory cycle and arm positioning. METHODS: We retrospectively analyzed data of adult patients with in- or out-of-hospital cardiac arrest who underwent thoracic CT imaging within one year before or up to six months after arrest. A region of interest (ROI) behind the pressure point was defined. The largest structure within this region was defined as "leading circulatory structure", which was the primary outcome. Airway status (intubated versus spontaneous breathing), respiratory cycle (inspiration, expiration, resting expiratory position), and arm position (up over the head versus down beside the trunk) served as covariates in an ordinal regression model. RESULTS: Among 500 initially screened patients, 411 (82.2 %) were included in the analysis. There was a significant association between the arm position and the leading circulatory structure behind the pressure point. However, no association was found with airway status or respiratory cycle. The most frequently identified leading circulatory structure was the left atrium (arms up: 41.8 %, down: 50.7 %), followed by the ascending aorta (up: 23.8 % vs. down: 16.7 %). The left ventricle was the leading structure in only one case (0.2 %, arms down). CONCLUSION: This study shows that arm position is significantly associated with the leading circulatory structure behind the pressure point for chest compressions in cardiac arrest.

Asunto(s)

RESUMEN

PURPOSE: Out-of-hospital cardiac arrest (OHCA) survivors face significant risks of complications and death from hypoxic-ischemic brain injury leading to withdrawal of life-sustaining treatment (WLST). Accurate multimodal neuroprognostication, including automated pupillometry, is essential to avoid inappropriate WLST. However, inconsistent study results hinder standardized threshold recommendations. We aimed to validate proposed pupillometry thresholds with no false predictions of unfavorable outcomes in comatose OHCA survivors. METHODS: In the multi-center BOX-trial, quantitative measurements of automated pupillometry (quantitatively assessed pupillary light reflex [qPLR] and Neurological Pupil index [NPi]) were obtained at admission (0 h) and after 24, 48, and 72 h in comatose patients resuscitated from OHCA. We aimed to validate qPLR < 4% and NPi ≤ 2, predicting unfavorable neurological conditions defined as Cerebral Performance Category 3-5 at follow-up. Combined with 48-h neuron-specific enolase (NSE) > 60 µg/L, pupillometry was evaluated for multimodal neuroprognostication in comatose patients with Glasgow Motor Score (M) ≤ 3 at ≥ 72 h. RESULTS: From March 2017 to December 2021, we consecutively enrolled 710 OHCA survivors (mean age: 63 ± 14 years; 82% males), and 266 (37%) patients had unfavorable neurological outcomes. An NPi ≤ 2 predicted outcome with 0% false-positive rate (FPR) at all time points (0-72 h), and qPLR < 4% at 24-72 h. In patients with M ≤ 3 at ≥ 72 h, pupillometry thresholds significantly increased the sensitivity of NSE, from 42% (35-51%) to 55% (47-63%) for qPLR and 50% (42-58%) for NPi, maintaining 0% (0-0%) FPR. CONCLUSION: Quantitative pupillometry thresholds predict unfavorable neurological outcomes in comatose OHCA survivors and increase the sensitivity of NSE in a multimodal approach at ≥ 72 h.

Asunto(s)

Asunto(s)

Asunto(s)

RESUMEN

Out-of-hospital cardiac arrest (OHCA) is associated with very poor outcomes. Extracorporeal cardiopulmonary resuscitation (eCPR) for selected patients is a potential therapeutic option for refractory cardiac arrest. However, randomised controlled studies applying eCPR after refractory OHCA have demonstrated conflicting results regarding survival and good functional neurological outcomes. eCPR is an invasive, labour-intensive, and expensive therapeutic approach with associated side-effects. A rapid monitoring device would be valuable in facilitating selection of appropriate patients for this expensive and complex treatment. To this end, rapid diagnosis of hyperfibrinolysis, or premature clot dissolution, diagnosed by viscoelastic testing might represent a feasible option. Hyperfibrinolysis is an evolutionary response to low or no-flow states. Studies in trauma patients demonstrate a high mortality rate in those with established hyperfibrinolysis upon emergency room admission. Similar findings have now been reported for the first time in OHCA patients. Hyperfibrinolysis upon admission diagnosed by rotational thromboelastometry was strongly associated with mortality and poor neurological outcomes in a small cohort of patients treated with extracorporeal membrane oxygenation.

Asunto(s)

RESUMEN

IMPORTANCE: In-hospital cardiac arrest (IHCA) is a significant public health burden. Rates of return of spontaneous circulation (ROSC) have been improving, but the best way to care for patients after the initial resuscitation remains poorly understood, and improvements in survival to discharge are stagnant. Existing North American cardiac arrest databases lack comprehensive data on the postresuscitation period, and we do not know current post-IHCA practice patterns. To address this gap, we developed the Discover IHCA study, which will thoroughly evaluate current post-IHCA care practices across a diverse cohort. OBJECTIVES: Our study collects granular data on post-IHCA treatment practices, focusing on temperature control and prognostication, with the objective of describing variation in current post-IHCA practices. DESIGN, SETTING, AND PARTICIPANTS: This is a multicenter, prospectively collected, observational cohort study of patients who have suffered IHCA and have been successfully resuscitated (achieved ROSC). There are 24 enrolling hospital systems (23 in the United States) with 69 individuals enrolling in hospitals (39 in the United States). We developed a standardized data dictionary, and data collection began in October 2023, with a projected 1000 total enrollments. Discover IHCA is endorsed by the Society of Critical Care Medicine. MAIN OUTCOMES AND MEASURES: The study collects data on patient characteristics, including prearrest frailty, arrest characteristics, and detailed information on postarrest practices and outcomes. Data collection on post-IHCA practice was structured around current American Heart Association and European Resuscitation Council guidelines. Among other data elements, the study captures postarrest temperature control interventions and postarrest prognostication methods. RESULTS: The majority of participating hospital systems are large, academic, tertiary care centers serving urban populations. The analysis will evaluate variations in practice and their association with mortality and neurologic function. CONCLUSIONS AND RELEVANCE: We expect this study, Discover IHCA, to identify variability in practice and outcomes following IHCA and be a vital resource for future investigations into best practices for managing patients after IHCA.

Asunto(s)

RESUMEN

INTRODUCTION: Timely arrival of emergency medical services (EMS) is pivotal for effective prehospital care, and efforts by EMS leaders and policymakers to reduce response times, especially in cardiac arrests responsible for 70%-80% of coronary heart disease-related deaths, underscore the global urgency. With approximately 55 out-of-hospital cardiac arrests per 100 000 people annually, survival rates hinge on timely cardiopulmonary resuscitation, emphasising its initiation within a 4-6 min window. Trauma, causing 6 million deaths and nearly 40 million injuries a year, further underscores the need for prompt prehospital care. Acknowledging these challenges, health systems have incorporated community first responder (CFR) models, where trained community members provide initial aid, aiming to bridge the crucial gap until professional help arrives. This scoping review intends to explore the experiences of various countries with CFR models, including their conceptual and theoretical frameworks, recognising CFR as a critical solution for reducing response times in prehospital emergency care. METHODS AND ANALYSIS: Arksey and O'Malley's approach will be followed in this scoping review. Our protocol was drafted using the Preferred Reporting Items for Systematic Reviews and Meta-Analyses Protocols extension for Scoping Reviews. The study objective is to comprehensively understand and map current knowledge about CFR model characteristics and identify effective components and indicators. The review will encompass available articles indexed in PubMed, Scopus and Web of Science without restrictions on date of publication. Additional searches will explore grey literature on Google Scholar and reliable websites in the field of EMS. Articles published in languages other than English and those inaccessible in full text will not be considered for inclusion. ETHICS AND DISSEMINATION: Since the study data are accessible from publicly accessible secondary sources, no ethical approval is necessary. Peer-reviewed publications will be used to report the study findings.

Asunto(s)

RESUMEN

BACKGROUND: Established protocols for implementing high-quality targeted temperature management (TTM) provide guidance concerning the cooling rate, duration of maintenance, and rewarming speed. However, whether compliant to TTM protocols results in improved survival and better neurological recovery has not been examined. METHODS: A retrospective cohort study enrolled 1141 survivors of non-traumatic adult cardiac arrest with a pre-arrest cerebral performance category (CPC) score of 1-2 from 2015 to 2020 at a tertiary medical center. Of the survivors, 330 patients who underwent TTM were further included. Patients with spontaneous hypothermia (<35 °C) (n = 107) and expired during the TTM (n = 21) were excluded. A total of 202 patients were thus enrolled. One hundred and ten patients underwent TTM that completely complied with the protocol (protocol-complaint group), but 92 patients deviated in some manner from the protocol (protocol non-compliant group). RESULTS: Fifty patients (50%) and 46 patients (50%) in the protocol-compliant and non-compliant groups, respectively, did not survive to hospital discharge. In the protocol-compliant group, 42 patients (38.2%) had favorable neurological recovery, compared with 32 patients (34.8%) in the protocol non-compliant group. After adjusting for age, initial shockable rhythm, witnessed collapse, and cardiopulmonary resuscitation duration, protocol non-compliant was associated with the poor neurological outcomes (aOR 2.44, 95% CI = 1.13-5.25), but not with in-hospital mortality (aOR 1.31, 95% CI = 0.70-2.47). The most common reason for noncompliance was a prolonged duration reaching the target temperature (n = 33, 58.7%). The number of phases of non-compliant was not significantly associated with in-hospital mortality or poor neurological recovery. CONCLUSION: Among cardiac arrest survivors undergoing TTM, those who did not receive TTM that in compliance with the protocol were more likely to experience poor neurological recovery than those whose TTM fully complied with the protocols. The most frequently identified deviation was a prolonged duration to reaching the target temperature.

Asunto(s)

RESUMEN

BACKGROUND: We aimed to estimate the effect of extracorporeal cardiopulmonary resuscitation (ECPR) on neurological outcome and mortality, when compared to conventional cardiopulmonary resuscitation (CCPR), using an individual patient data meta-analysis (IPDMA). METHODS: A systematic literature search was performed up to the 20th of October 2022 in the PubMed, EMBASE and CENTRAL databases. For observational studies with unmatched populations, a propensity score including age, location of arrest and initial rhythm was used to match ECPR and CCPR patients in a 1:1 ratio. The primary and secondary outcomes were unfavorable neurological outcome (Cerebral Performance Category of 3-5) and mortality, respectively, which were both collected at different time-points. RESULTS: Data from 17 studies, including 2064 matched cardiac arrest (CA) patients (1031 ECPR and 1033 CCPR cases) were included. In comparison to CCPR, ECPR was associated with a decreased odds of unfavorable neurological outcome (847, 82.2% vs. 897, 86.8% - OR 0.68 [95%CI 0.53-0.87]; p = 0.002) and death (803, 77.9% vs. 860, 83.3% - OR 0.68 [95%CI 0.54-0.86]; p = 0.001). These results were consistent across most of the prespecified subgroups. Moreover, the odds of both unfavorable neurological outcome and mortality were significantly influenced by initial rhythm, cause of arrest and combinations of lactate levels on admission and duration of resuscitation. CONCLUSIONS: This IPDMA showed that ECPR was associated with significantly lower rates of unfavorable neurological outcome and mortality in refractory CA. The overall effect could be influenced by CA characteristics and the severity of the initial injury.

Asunto(s)

RESUMEN

Out-of-hospital cardiac arrest (OHCA) is a critical condition with low survival rates. In patients with a return of spontaneous circulation, brain injury is a leading cause of death. In this study, we propose an interpretable machine learning approach for predicting neurologic outcome after OHCA, using information available at the time of hospital admission. METHODS: The study population were 55 615 OHCA cases registered in the Swedish Cardiopulmonary Resuscitation Registry between 2010 and 2020. The dataset was split to training and validation sets (for model development) and test set (for evaluation of the final model). We used an XGBoost algorithm with stratified, repeated 10-fold cross-validation along with Optuna framework for hyperparameters tuning. The final model was trained on 10 features selected based on the importance scores and evaluated on the test set in terms of discrimination, calibration and bias-variance tradeoff. We used SHapley Additive exPlanations to address the 'black-box' model and align with eXplainable artificial intelligence. RESULTS: The final model achieved: area under the receiver operating characteristic value 0.964 (95% confidence interval (CI) [0.960-0.968]), sensitivity 0.606 (95% CI [0.573-0.634]), specificity 0.975 (95% CI [0.972-0.978]), positive predictive value (PPV) 0.664 (95% CI [0.625-0.696]), negative predictive value (NPV) 0.969 (95% CI [0.966-0.972]), macro F1 0.803 (95% CI [0.788-0.816]), and showed a very good calibration. SHAP features with the highest impact on the model's output were:'ROSC on arrival to hospital', 'Initial rhythm asystole' and 'Conscious on arrival to hospital'. CONCLUSIONS: The XGBoost machine learning model with 10 features available at the time of hospital admission showed good performance for predicting neurologic outcome after OHCA, with no apparent signs of overfitting.

Asunto(s)