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

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 < 0.01). The prognostic accuracy remained excellent from day 1 to day 3 with an AUROC at approximately 95% when adding research-grade biomarkers. The models which included NSE after 72 h and NFL on any of the three days had a low risk of false-positive predictions while retaining a low number of false-negative predictions. CONCLUSIONS: In 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.

Artificial neural networks improve early outcome prediction and risk classification in out-of-hospital cardiac arrest patients admitted to intensive care.

BACKGROUND: Pre-hospital circumstances, cardiac arrest characteristics, comorbidities and clinical status on admission are strongly associated with outcome after out-of-hospital cardiac arrest (OHCA). Early prediction of outcome may inform prognosis, tailor therapy and help in interpreting the intervention effect in heterogenous clinical trials. This study aimed to create a model for early prediction of outcome by artificial neural networks (ANN) and use this model to investigate intervention effects on classes of illness severity in cardiac arrest patients treated with targeted temperature management (TTM). METHODS: Using the cohort of the TTM trial, we performed a post hoc analysis of 932 unconscious patients from 36 centres with OHCA of a presumed cardiac cause. The patient outcome was the functional outcome, including survival at 180 days follow-up using a dichotomised Cerebral Performance Category (CPC) scale with good functional outcome defined as CPC 1-2 and poor functional outcome defined as CPC 3-5. Outcome prediction and severity class assignment were performed using a supervised machine learning model based on ANN. RESULTS: The outcome was predicted with an area under the receiver operating characteristic curve (AUC) of 0.891 using 54 clinical variables available on admission to hospital, categorised as background, pre-hospital and admission data. Corresponding models using background, pre-hospital or admission variables separately had inferior prediction performance. When comparing the ANN model with a logistic regression-based model on the same cohort, the ANN model performed significantly better (p = 0.029). A simplified ANN model showed promising performance with an AUC above 0.852 when using three variables only: age, time to ROSC and first monitored rhythm. The ANN-stratified analyses showed similar intervention effect of TTM to 33 °C or 36 °C in predefined classes with different risk of a poor outcome. CONCLUSION: A supervised machine learning model using ANN predicted neurological recovery, including survival excellently, and outperformed a conventional model based on logistic regression. Among the data available at the time of hospitalisation, factors related to the pre-hospital setting carried most information. ANN may be used to stratify a heterogenous trial population in risk classes and help determine intervention effects across subgroups.

Functional outcomes associated with varying levels of targeted temperature management after out-of-hospital cardiac arrest - An INTCAR2 registry analysis.

INTRODUCTION: Targeted temperature management (TTM) after out-of-hospital cardiac arrest (OHCA) has been recommended in international guidelines since 2005. The TTM-trial published in 2013 showed no difference in survival or neurological outcome for patients randomised to 33 °C or 36 °C, and many hospitals have changed practice. The optimal utilization of TTM is still debated. This study aimed to analyse if a difference in temperature goal was associated with outcome in an unselected international registry population. METHODS: This is a retrospective observational study based on a prospective registry - the International Cardiac Arrest Registry 2. Patients were categorized as receiving TTM in the lower range at 32-34 °C (TTM-low) or at 35-37 °C (TTM-high). Primary outcome was good functional status defined as cerebral performance category (CPC) of 1-2 at hospital discharge and secondary outcome was adverse events related to TTM. A logistic regression model was created to evaluate the independent effect of temperature by correcting for clinical and demographic factors associated with outcome. RESULTS: Of 1710 patients included, 1242 (72,6%) received TTM-low and 468 (27,4%) TTM-high. In patients receiving TTM-low, 31.3% survived with good outcome compared to 28.8% in the TTM-high group. There was no significant association between temperature and outcome (p = 0.352). In analyses adjusted for baseline differences the OR for a good outcome with TTM-low was 1.27, 95% CI (0.94-1.73). Haemodynamic instability leading to discontinuation of TTM was more common in TTM-low. CONCLUSIONS: No significant difference in functional outcome at hospital discharge was found in patients receiving lower- versus higher targeted temperature management.

Target Temperature Management after out-of-hospital cardiac arrest--a randomized, parallel-group, assessor-blinded clinical trial--rationale and design.

BACKGROUND: Experimental animal studies and previous randomized trials suggest an improvement in mortality and neurologic function with induced hypothermia after cardiac arrest. International guidelines advocate the use of a target temperature management of 32°C to 34°C for 12 to 24 hours after resuscitation from out-of-hospital cardiac arrest. A systematic review indicates that the evidence for recommending this intervention is inconclusive, and the GRADE level of evidence is low. Previous trials were small, with high risk of bias, evaluated select populations, and did not treat hyperthermia in the control groups. The optimal target temperature management strategy is not known. METHODS: The TTM trial is an investigator-initiated, international, randomized, parallel-group, and assessor-blinded clinical trial designed to enroll at least 850 adult, unconscious patients resuscitated after out-of-hospital cardiac arrest of a presumed cardiac cause. The patients will be randomized to a target temperature management of either 33°C or 36°C after return of spontaneous circulation. In both groups, the intervention will last 36 hours. The primary outcome is all-cause mortality at maximal follow-up. The main secondary outcomes are the composite outcome of all-cause mortality and poor neurologic function (cerebral performance categories 3 and 4) at hospital discharge and at 180 days, cognitive status and quality of life at 180 days, assessment of safety and harm. DISCUSSION: The TTM trial will investigate potential benefit and harm of 2 target temperature strategies, both avoiding hyperthermia in a large proportion of the out-of-hospital cardiac arrest population.

Intimal thickness of the coronary arteries in low-birthweight infants.

BACKGROUND: Intimal thickening is considered to be an early manifestation of developing atherosclerosis in healthy young adults and children. Low birthweight correlates with increased incidence of cardiovascular diseases. AIM: To test the hypothesis that low birthweight is associated with relatively thickened intima at birth. METHODS: The coronary arteries of 175 children were screened from serial cross-sections for maximal intimal thickening and measured morphometrically. The area of intima and media and the length of internal elastic lamina were measured. The intimal to medial area ratio and calculated thicknesses of intima were used in statistical comparisons. Only children who died within 30 d after birth (n=111) were included. RESULTS: There was a significant positive correlation between intimal thickness and birthweight in low-birthweight children (p<0.006). Neither the relative thickness of the intima nor the ratio of intimal to medial area increased with increasing growth restriction. The sum of the thicknesses of arterial media and intima had a significant positive correlation with birthweight in these infants. CONCLUSION: Intimal thickness present at birth in small-for-date children does not seem to be an aetiological factor for the increased risk of coronary heart disease later in life.

TUNEL: a useful screening method in sudden cardiac death.

The primary objective of this study was to investigate if detection of apoptosis in the heart can be used to diagnose early myocardial ischaemia. The material consisted of myocardial tissue from autopsy cases: 10 cases with occlusive, thrombotic coronary artery disease and acute myocardial infarction, 10 cases of sudden cardiac death without coronary artery disease (CAD) and 8 controls without cardiovascular disease and with known causes of death. Necrotic changes in the myocardium were detected with hematoxylin-erythrosin-saffron, Mallory's PTAH stain and with antibodies against complement 9. Apoptotic nuclei were visualised with two different kits using the terminal deoxynucleotidyl transferase-mediated desoxyuridinetriphosphate nick end-labeling (TUNEL) method on histological sections. In the patients with CAD, early myocardial infarction was found in one defined area of the ventricular wall; apoptotic myocyte nuclei were observed not in the necrotic lesions, but evenly spread usually without a gradient, all over the myocardium with a mean number per high power field of 29% (range 3-56%) of the total number of myocyte nuclei. In the sudden cardiac deaths without CAD, necrosis was scarce and distributed both focally and irregularly in both the left and right ventricular walls. With few exceptions, the percentage of apoptotic myocyte nuclei exceeded 20% in all sections (mean 24%, range 0-68%). No difference was seen between patients with CAD and those without CAD (p > 0.05). With the TUNEL method, positively stained nuclei were seen very early and extensively all over the myocardium. It is not certain that they represent true apoptosis induced by ischemia, but TUNEL appears to be a useful screening method in cases where sudden cardiac death is suspected.