Dataset Information

Predicting neurological outcome after out-of-hospital cardiac arrest with cumulative information; development and internal validation of an artificial neural network algorithm.

ABSTRACT:

Background

Prognostication of neurological outcome in patients who remain comatose after cardiac arrest resuscitation is complex. Clinical variables, as well as biomarkers of brain injury, cardiac injury, and systemic inflammation, all yield some prognostic value. We hypothesised that cumulative information obtained during the first three days of intensive care could produce a reliable model for predicting neurological outcome following out-of-hospital cardiac arrest (OHCA) using artificial neural network (ANN) with and without biomarkers.

Methods

We performed a post hoc analysis of 932 patients from the Target Temperature Management trial. We focused on comatose patients at 24, 48, and 72 h post-cardiac arrest and excluded patients who were awake or deceased at these time points. 80% of the patients were allocated for model development (training set) and 20% for internal validation (test set). To investigate the prognostic potential of different levels of biomarkers (clinically available and research-grade), patients' background information, and intensive care observation and treatment, we created three models for each time point: (1) clinical variables, (2) adding clinically accessible biomarkers, e.g., neuron-specific enolase (NSE) and (3) adding research-grade biomarkers, e.g., neurofilament light (NFL). Patient outcome was the dichotomised Cerebral Performance Category (CPC) at six months; a good outcome was defined as CPC 1-2 whilst a poor outcome was defined as CPC 3-5. The area under the receiver operating characteristic curve (AUROC) was calculated for all test sets.

Results

AUROC remained below 90% when using only clinical variables throughout the first three days in the ICU. Adding clinically accessible biomarkers such as NSE, AUROC increased from 82 to 94% (p?ConclusionsIn this exploratory study, ANNs provided good to excellent prognostic accuracy in predicting neurological outcome in comatose patients post OHCA. The models which included NSE after 72 h and NFL on all days showed promising prognostic performance.

SUBMITTER: Andersson P

PROVIDER: S-EPMC7905905 | biostudies-literature | 2021 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Predicting neurological outcome after out-of-hospital cardiac arrest with cumulative information; development and internal validation of an artificial neural network algorithm.

Andersson Peder P Johnsson Jesper J Björnsson Ola O Cronberg Tobias T Hassager Christian C Zetterberg Henrik H Stammet Pascal P Undén Johan J Kjaergaard Jesper J Friberg Hans H Blennow Kaj K Lilja Gisela G Wise Matt P MP Dankiewicz Josef J Nielsen Niklas N Frigyesi Attila A

Critical care (London, England) 20210225 1

<h4>Background</h4>Prognostication of neurological outcome in patients who remain comatose after cardiac arrest resuscitation is complex. Clinical variables, as well as biomarkers of brain injury, cardiac injury, and systemic inflammation, all yield some prognostic value. We hypothesised that cumulative information obtained during the first three days of intensive care could produce a reliable model for predicting neurological outcome following out-of-hospital cardiac arrest (OHCA) using artific ...[more]

PMID: 33632280

Similar Datasets

Project description:Background In-hospital cardiac arrest is a major burden in health care. Although several track-and-trigger systems are used to predict cardiac arrest, they often have unsatisfactory performances. We hypothesized that a deep-learning-based artificial intelligence algorithm (DLA) could effectively predict cardiac arrest using electrocardiography (ECG). We developed and validated a DLA for predicting cardiac arrest using ECG. Methods We conducted a retrospective study that included 47,505 ECGs of 25,672 adult patients admitted to two hospitals, who underwent at least one ECG from October 2016 to September 2019. The endpoint was occurrence of cardiac arrest within 24?h from ECG. Using subgroup analyses in patients who were initially classified as non-event, we confirmed the delayed occurrence of cardiac arrest and unexpected intensive care unit transfer over 14?days. Results We used 32,294 ECGs of 10,461 patients and 4483 ECGs of 4483 patients from a hospital were used as development and internal validation data, respectively. Additionally, 10,728 ECGs of 10,728 patients from another hospital were used as external validation data, which confirmed the robustness of the developed DLA. During internal and external validation, the areas under the receiver operating characteristic curves of the DLA in predicting cardiac arrest within 24?h were 0.913 and 0.948, respectively. The high risk group of the DLA showed a significantly higher hazard for delayed cardiac arrest (5.74% vs. 0.33%, P?<?0.001) and unexpected intensive care unit transfer (4.23% vs. 0.82%, P?<?0.001). A sensitivity map of the DLA displayed the ECG regions used to predict cardiac arrest, with the DLA focused most on the QRS complex. Conclusions Our DLA successfully predicted cardiac arrest using diverse formats of ECG. The results indicate that cardiac arrest could be screened and predicted not only with a conventional 12-lead ECG, but also with a single-lead ECG using a wearable device that employs our DLA.

Project description:Fibroblast growth factor (FGF) 21 is a marker associated with mitochondrial and cellular stress. Cardiac arrest causes mitochondrial stress, and we tested if FGF 21 would reflect the severity of hypoxia-reperfusion injury after cardiac arrest. We measured serum concentrations of FGF 21 in 112 patients on ICU admission and 24, 48 and 72 h after out-of-hospital cardiac arrest with shockable initial rhythm included in the COMACARE study (NCT02698917). All patients received targeted temperature management for 24 h. We defined 6-month cerebral performance category 1-2 as good and 3-5 as poor neurological outcome. We used samples from 40 non-critically ill emergency room patients as controls. We assessed group differences with the Mann Whitney U test and temporal differences with linear modeling with restricted maximum likelihood estimation. We used multivariate logistic regression to assess the independent predictive value of FGF 21 concentration for neurologic outcome. The median (inter-quartile range, IQR) FGF 21 concentration was 0.25 (0.094-0.91) ng/ml in controls, 0.79 (0.37-1.6) ng/ml in patients at ICU admission (P < 0.001 compared to controls) and peaked at 48 h [1.2 (0.46-2.5) ng/ml]. We found no association between arterial blood oxygen partial pressure and FGF 21 concentrations. We observed with linear modeling an effect of sample timepoint (F 5.6, P < 0.01), poor neurological outcome (F 6.1, P = 0.01), and their interaction (F 3.0, P = 0.03), on FGF 21 concentration. In multivariate logistic regression analysis, adjusting for relevant clinical covariates, higher average FGF 21 concentration during the first 72 h was independently associated with poor neurological outcome (odds ratio 1.60, 95% confidence interval 1.10-2.32). We conclude that post cardiac arrest patients experience cellular and mitochondrial stress, reflected as a systemic FGF 21 response. This response is higher with a more severe hypoxic injury but it is not exacerbated by hyperoxia.

Project description:BACKGROUND:The prognosis in refractory out-of-hospital cardiac arrest (OHCA) with ongoing cardiopulmonary resuscitation (CPR) at hospital arrival is often considered dismal. The use of extracorporeal cardiopulmonary resuscitation (eCPR) for perfusion enhancement during resuscitation has shown variable results. We aimed to investigate outcome in refractory OHCA patients managed conservatively without use of eCPR. METHODS:We included consecutive OHCA patients with refractory arrest or prehospital return of spontaneous circulation (ROSC) in the Copenhagen area in 2002-2011. RESULTS:A total of 3992 OHCA patients with resuscitation attempts were included; in 2599, treatment was terminated prehospital, and 1393 (35%) were brought to the hospital either with ROSC (n?=?1285, 92%) or with refractory OHCA (n?=?108, 8%). Of patients brought in with refractory OHCA, 56 (52%) achieved ROSC in the emergency department. There were no differences between patients with refractory OHCA or prehospital ROSC with regard to age, sex, comorbidities, or etiology of OHCA. Time to emergency medical services (EMS) arrival was similar, whereas time to ROSC (when ROSC was achieved) was longer in refractory OHCA patients (EMS, 6 (5-9] vs. 7 [5-10] min, p?=?0.8; ROSC, 15 [9-22] vs. 27 [20-41] min, p?<?0.001). Independent factors associated with transport with refractory OHCA instead of prehospital termination of therapy were OHCA in public (OR, 3.6 [95% CI, 2.2-5.8]; p?<?0.001), witnessed OHCA (OR, 3.7 [2.0-7.1]; p?<?0.001), shockable rhythm (OR, 3.0 [1.9-4.7]; p?<?0.001), younger age (OR, 1.2 [1.1-1.2]; p?<?0.001), and later calendar year (OR, 1.4 [1.2-1.6]; p?<?0.001). Thirty-day survival was 20% in patients with refractory OHCA compared with 42% in patients with prehospital ROSC (p?<?0.001). Four of 28 refractory OHCA patients with duration of resuscitation >?60 min achieved ROSC. No difference in favorable neurological outcome in patients surviving to discharge was found (prehospital ROSC 84% vs. refractory OHCA 86%; p?=?0.7). CONCLUSIONS:Survival after refractory OHCA with ongoing CPR at hospital arrival was significantly lower than among patients with prehospital ROSC. Despite a lower survival, the majority of survivors with both refractory OHCA and prehospital ROSC were discharged with a similar degree of favorable neurological outcome, indicating that continued efforts in spite of refractory OHCA are not in vain and may still lead to favorable outcome even without eCPR.

Dataset Information

Predicting neurological outcome after out-of-hospital cardiac arrest with cumulative information; development and internal validation of an artificial neural network algorithm.

Background

Methods

Results

Publications

Predicting neurological outcome after out-of-hospital cardiac arrest with cumulative information; development and internal validation of an artificial neural network algorithm.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets