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.

Background: Neuron-specific enolase (NSE) has traditionally been used as a biomarker to predict neurologic outcomes after cardiac arrest. This study aimed to evaluate the utility of NSE in predicting neurologic outcomes in patients undergoing extracorporeal cardiopulmonary resuscitation (ECPR). Methods: This observational cohort study included 47 consecutive adult ECPR patients (median age, 59.0 years; 74.5% males) treated between January 2018 and December 2021 at a tertiary extracorporeal life support center. The primary outcome was a poor neurologic outcome, defined as a Cerebral Performance Category score of 3-5 at hospital discharge. Results: Twelve (25.5%) patients had abnormal findings on computed tomography of the brain. A poor neurologic outcome was demonstrated in 22 (46.8%) patients. The NSE level at 72 h after ECPR showed the best prediction power for a poor neurologic outcome compared with NSE at 24 and 48 h. A cutoff value exceeding 61.9 μg/L for NSE at 72 h yielded an area under the curve (AUC) of 0.791 for predicting poor neurologic outcomes and exceeding 62.1 μg/L with an AUC of 0.838 for 30-day mortality. Conclusions: NSE levels at 72 h after ECPR appear to be a reliable biomarker for predicting poor neurologic outcomes and 30-day mortality in ECPR patients.

The likelihood of neurological recovery after out-of-hospital cardiac arrest (OHCA) may be influenced by advanced age. This study aims to evaluate the impact of advanced age on neurological recovery in elderly OHCA survivors treated with targeted temperature management (TTM). This retrospective observational study, using a nationwide population-based OHCA registry, was conducted from January 2016 to December 2020. Non-traumatic elderly (≥ 65 years) comatose OHCA survivors treated with TTM were categorized according to age (65-69, 70-74, 75-79, and ≥ 80 years). Among 23,336 admitted OHCA patients, 3,398 were treated with TTM. Excluding 2,033 non-elderly patients, 1,365 were analyzed. Among the four groups, the rate of good neurological outcomes decreased by advanced age (24.2%, 16.1%, 11.4%, and 5.9%, respectively), which was also observed after subgroup analysis based on the initial shockable (40.6%, 31.5%, 28.6%, and 14.9%, respectively) and non-shockable rhythm (10.6%, 7.2%, 4.1%, and 3.4%, respectively). Multivariate analysis showed the adjusted odds ratio (aOR) for good neurological outcome decreased as age increased (65-69: reference, 70-74: aOR 0.70, 75-79: aOR 0.49, and ≥ 80 years: aOR 0.25). The optimal age cutoffs for good outcomes in elderly OHCA survivors with shockable and non-shockable rhythm were 77 and 72 years, respectively. The neurologic recovery rate in OHCA survivors treated with TTM gradually decreased with increasing age. However, even patients aged ≥ 80 years with shockable rhythm had a good neurologic outcome of 14.9% compared with patients aged 65-69 years with non-shockable rhythm (10.6%).

In this two-center prospective cohort study of children on ECMO, we assessed a panel of plasma brain injury biomarkers using exploratory factor analysis (EFA) to evaluate their interplay and association with outcomes. Biomarker concentrations were measured daily for the first 3 days of ECMO support in 95 participants. Unfavorable composite outcome was defined as in-hospital mortality or discharge Pediatric Cerebral Performance Category > 2 with decline ≥ 1 point from baseline. EFA grouped 11 biomarkers into three factors. Factor 1 comprised markers of cellular brain injury (NSE, BDNF, GFAP, S100β, MCP1, VILIP-1, neurogranin); Factor 2 comprised markers related to vascular processes (vWF, PDGFRβ, NPTX1); and Factor 3 comprised the BDNF/MMP-9 cellular pathway. Multivariable logistic models demonstrated that higher Factor 1 and 2 scores were associated with higher odds of unfavorable outcome (adjusted OR 2.88 [1.61, 5.66] and 1.89 [1.12, 3.43], respectively). Conversely, higher Factor 3 scores were associated with lower odds of unfavorable outcome (adjusted OR 0.54 [0.31, 0.88]), which is biologically plausible given the role of BDNF in neuroplasticity. Application of EFA on plasma brain injury biomarkers in children on ECMO yielded grouping of biomarkers into three factors that were significantly associated with unfavorable outcome, suggesting future potential as prognostic instruments.

Traumatic brain injury (TBI) is a leading cause of morbidity and mortality in children. Head computed tomography (CT) is frequently utilized for evaluating trauma-related characteristics, selecting treatment options, and monitoring complications in the early stages. This study assessed the relationship between cranial CT findings and early and late neurological outcomes in pediatric TBI patients admitted to the pediatric intensive care unit (PICU). The study included children aged 1 month to 18 years who were admitted to the PICU due to TBI between 2014 and 2020. Sociodemographic data, clinical characteristics, and cranial CT findings were analyzed. Patients were categorized based on their Glasgow Coma Scale (GCS) score. Of the 129 patients, 83 (64%) were male, and 46 (36%) were female, with a mean age of 6.8 years. Falls (n = 51, 39.5%) and in-vehicle traffic accidents (n = 35, 27.1%) were the most common trauma types observed. Normal brain imaging findings were found in 62.7% of the patients, while 37.3% exhibited intracranial pathology. Hemorrhage was the most frequent CT finding. Severe TBI (n = 26, p = 0.032) and mortality (n = 9, p = 0.017) were more prevalent in traffic accidents. The overall mortality rate in the study population was 10.1%. In children with TBI, cranial CT imaging serves as an essential initial method for patients with neurological manifestations. Particularly, a GCS score of ≤ 8, multiple hemorrhages, diffuse cerebral edema, and intraventricular bleeding are associated with sequelae and mortality.

Delayed hypothermia, initiated after hospital arrival, several hours after cardiac arrest with 8-10 hours to reach the target temperature, is likely to have limited impact on overall survival. However, the effect of ultrafast hypothermia, i.e., delivered intra-arrest or immediately after return of spontaneous circulation (ROSC), on functional neurologic outcome after out-of-hospital cardiac arrest (OHCA) is unclear. In two prior trials, prehospital trans-nasal evaporative intra-arrest cooling was safe, feasible and reduced time to target temperature compared to delayed cooling. Both studies showed trends towards improved neurologic recovery in patients with shockable rhythms. The aim of the PRINCESS2-study is to assess whether cooling, initiated either intra-arrest or immediately after ROSC, followed by in-hospital hypothermia, significantly increases survival with complete neurologic recovery as compared to standard normothermia care, in OHCA patients with shockable rhythms.
In this investigator-initiated, randomized, controlled trial, the emergency medical services (EMS) will randomize patients at the scene of cardiac arrest to either trans-nasal cooling within 20 minutes from EMS arrival with subsequent hypothermia at 33°C for 24 hours after hospital admission (intervention), or to standard of care with no prehospital or in-hospital cooling (control). Fever (>37,7°C) will be avoided for the first 72 hours in both groups. All patients will receive post resuscitation care and withdrawal of life support procedures according to current guidelines. Primary outcome is survival with complete neurologic recovery at 90 days, defined as modified Rankin scale (mRS) 0-1. Key secondary outcomes include survival to hospital discharge, survival at 90 days and mRS 0-3 at 90 days. In total, 1022 patients are required to detect an absolute difference of 9% (from 45 to 54%) in survival with neurologic recovery (80% power and one-sided α=0,025, β=0,2) and assuming 2,5% lost to follow-up. Recruitment starts in Q1 2024 and we expect maximum enrolment to be achieved during Q4 2024 at 20-25 European and US sites.
This trial will assess the impact of ultrafast hypothermia applied on the scene of cardiac arrest, as compared to normothermia, on 90-day survival with complete neurologic recovery in OHCA patients with initial shockable rhythm.
NCT06025123.

The diagnosis of corpus callosum anomalies by prenatal ultrasound has improved over the last decade because of improved imaging techniques, scanning skills, and the routine implementation of transvaginal neurosonography.
Our aim was to investigate all cases of incomplete agenesis of the corpus callosum and to report the sonographic characteristics, the associated anomalies, and the perinatal outcomes.
We performed a retrospective analysis of cases from January 2007 to December 2017 with corpus callosum anomalies, either referred for a second opinion or derived from the prenatal ultrasound screening program in a single tertiary referral center. Cases with complete agenesis were excluded from the analysis. Standardized investigation included a detailed fetal ultrasound including neurosonogram, fetal karyotyping (standard karyotype or array comparative genomic hybridization) and fetal magnetic resonance imaging. The pregnancy outcome was collected, and pathologic investigation in case of termination of the pregnancy or fetal or neonatal loss was compared with the prenatal findings. The pregnancy and fetal or neonatal outcomes were reported. The neurologic assessment was conducted by a pediatric neurologist using the Bayley Scales of Infant Development-II and the standardized Child Development Inventory when the Bayley investigation was unavailable.
Corpus callosum anomalies were diagnosed in 148 cases during the study period, 62 (41.9%) of which were excluded because of complete agenesis, and 86 fetuses had partial agenesis (58.1%). In 20 cases, partial agenesis (23.2%) was isolated, whereas 66 (76.7%) presented with different malformations among which 29 cases (43.9%) were only central nervous system lesions, 21 cases (31.8%) were non-central nervous system lesions, and 16 cases (24.3%) had a combination of central nervous system and non-central nervous system lesions. The mean gestational age at diagnosis for isolated and non-isolated cases was comparable (24.29 [standard deviation, 5.05] weeks and 24.71 [standard deviation, 5.35] weeks, respectively). Of the 86 pregnancies with partial agenesis, 46 patients opted for termination of the pregnancy. Neurologic follow-up data were available for 35 children. The overall neurologic outcome was normal in 21 of 35 children (60%); 3 of 35 (8.6%) showed mild impairment and 6 of 35 (17.1%) showed moderate impairment. The remaining 5 of 35 (14.3%) had severe impairment. The median duration of follow-up for the isolated form was 45.6 months (range, 36-52 months) and 73.3 months (range, 2-138 months) for the nonisolated form.
Partial corpus callosum agenesis should be accurately investigated by neurosonography and fetal magnetic resonance imaging to describe its morphology and the associated anomalies. Genetic anomalies are frequently present in nonisolated cases. Efforts must be taken to improve ultrasound diagnosis of partial agenesis and to confirm its isolated nature to enhance parental counseling. Although 60% of children with prenatal diagnosis of isolated agenesis have a favorable prognosis later in life, they often have mild to severe disabilities including speech disorders at school age and behavior and motor deficit disorders that can emerge at a later age.

Background Neurologic events during primary stay in heart transplant (HTx) recipients may be associated with reduced outcome and survival, which we aim to explore with the current study. Methods and Results We screened and included all patients undergoing HTx in our center between September 2010 and December 2022 (n=268) and checked for the occurrence of neurologic events within their index stay. Neurologic events were defined as ischemic stroke, hemorrhage, hypoxic ischemic injury, or acute symptomatic neurologic dysfunction without central nervous system injury. The cohort was then divided into recipients with (n=33) and without (n=235) neurologic events after HTx. Using a multivariable Cox regression model, the association of neurologic events after HTx and survival was assessed. Recipients with neurologic events displayed a longer intensive care unit stay (30 versus 16 days; P=0.009), longer mechanical ventilation (192 versus 48 hours; P<0.001), and higher need for blood transfusion, and need for hemodialysis after HTx was substantially higher (81% versus 55%; P=0.01). Resternotomy (36% versus 26%; P=0.05) and mechanical life support (extracorporeal life support) after HTx (46% versus 24%; P=0.02) were also significantly higher in patients with neurologic events. Covariable-adjusted multivariable Cox regression analysis revealed a significant independent association of neurologic events and increased 30-day (hazard ratio [HR], 2.5 [95% CI, 1.0-6.0]; P=0.049), 1-year (HR, 2.2 [95% CI, 1.1-4.3]; P=0.019), and overall (HR, 2.5 [95% CI, 1.5-4.2]; P<0.001) mortality after HTx and reduced Kaplan-Meier survival up to 5 years after HTx (P<0.001). Conclusions Neurologic events after HTx were strongly and independently associated with worse postoperative outcome and reduced survival up to 5 years after HTx.

(1) Background: Post-cardiac arrest syndrome (PCAS) is a type of global ischemic reperfusion injury that occurs after the return of spontaneous circulation (ROSC). The procalcitonin to albumin ratio (PAR) has been studied as an independent prognostic factor of various diseases. There are no previous studies of PAR in patients with PCAS. We assessed if PAR is more effective than procalcitonin (PCT) in predicting prognosis for patients with PCAS. (2) Methods: This retrospective cohort study included a total of 187 patients with PCAS after non-traumatic out-of-hospital cardiac arrest (OHCA) between January 2016 and December 2020. Multivariate logistic regression analysis was conducted to assess the association between PAR and PCAS prognosis. The predictive performance of PAR was compared with PCT via the receiver-operating characteristic (ROC) analysis and DeLong test.; (3) Results: PAR at 24 and 48 h after hospital admission were independently associated with one-month neurological outcome (OR: 1.167, 95% CI: 1.023-1.330; OR: 1.077, 95% CI: 1.012-1.146, p < 0.05). By ROC analysis, PAR showed better performance over PCT at 48 h after admission in predicting one-month CPC (0.763 vs. 0.772, p = 0.010). (4) Conclusions: Our findings suggest that PAR at 48 h after admission is more effective in predicting a one-month neurological outcome than PCT at 48 h after admission in patients with PCAS after OHCA.

UNASSIGNED: Hyperperfusion therapy, mean arterial blood pressure (MAP) > 85 mmHg, is a recommended treatment of blunt traumatic spinal cord injury (SCI). We hypothesized the first 24 h of MAP augmentation would be most influential on neurological outcomes.
UNASSIGNED: This retrospective study from a level 1 urban trauma center dating 1/2017 to 12/2019 included all blunt traumatic spinal cord injured patients receiving hyperperfusion therapy. Patients were grouped as \"No improvement\" vs \"Improvement\" measured by change in American Spinal Injury Association (ASIA) score during their hospitalization. MAP values for the first 12, first 24 and last 72 h were compared between the two groups; P < 0.05 was significant.
UNASSIGNED: After exclusions, 96 patients underwent hyperperfusion therapy for blunt traumatic SCI, 82 in the No Improvement and 14 in the Improvement group. Groups had similar treatment durations (95.6 and 96.7 h, P = 0.66) and ISS (20.5 and 23, P = 0.45). The area under the curve, calculation, to account for time less than goal and MAP difference from goal, in the No Improvement group was significantly higher (lower and more time below MAP goal) compared to the Improvement group for the first 12 h (40.3 v. 26.1 P = 0.03) with similar findings in the subsequent 12 h of treatment (13-24 h; 62.2 vs 43, P = 0.09). There was no difference between the groups in the subsequent 72 h (25-96 h; 156.4 vs 136.6, P = 0.57).
UNASSIGNED: Hyperperfusion to the spinal cord in the first 12 h correlated significantly with improved neurological outcome in SCI patients.