Association of Dose of Intracranial Hypertension with Outcome in Subarachnoid Hemorrhage.

BACKGROUND: In patients with aneurysmal subarachnoid hemorrhage (aSAH) the burden of intracranial pressure (ICP) and its contribution to outcomes remains unclear. In this multicenter study, the independent association between intensity and duration, or "dose," of episodes of intracranial hypertension and 12-month neurological outcomes was investigated. METHODS: This was a retrospective analysis of multicenter prospectively collected data of 98 adult patients with aSAH amendable to treatment. Patients were admitted to the intensive care unit of two European centers (Medical University of Innsbruck [Austria] and San Gerardo University Hospital of Monza [Italy]) from 2009 to 2013. The dose of intracranial hypertension was visualized. The obtained visualizations allowed us to investigate the association between intensity and duration of episodes of intracranial hypertension and the 12-month neurological outcomes of the patients, assessed with the Glasgow Outcome Score. The independent association between the cumulative dose of intracranial hypertension and outcome for each patient was investigated by using multivariable logistic regression models corrected for age, occurrence of delayed cerebral ischemia, and the Glasgow Coma Scale score at admission. RESULTS: The combination of duration and intensity defined the tolerance to intracranial hypertension for the two cohorts of patients. A semiexponential transition divided ICP doses that were associated with better outcomes (in blue) with ICP doses associated with worse outcomes (in red). In addition, in both cohorts, an independent association was found between the cumulative time that the patient experienced ICP doses in the red area and long-term neurological outcomes. The ICP pressure-time burden was a stronger predictor of outcomes than the cumulative time spent by the patients with an ICP greater than 20 mmHg. CONCLUSIONS: In two cohorts of patients with aSAH, an association between duration and intensity of episodes of elevated ICP and 12-month neurological outcomes could be demonstrated and was visualized in a color-coded plot.

Postoperative Cerebral Oxygen Saturation in Children After Congenital Cardiac Surgery and Long-Term Total Intelligence Quotient: A Prospective Observational Study.

OBJECTIVES: During the early postoperative period, children with congenital heart disease can suffer from inadequate cerebral perfusion, with possible long-term neurocognitive consequences. Cerebral tissue oxygen saturation can be monitored noninvasively with near-infrared spectroscopy. In this prospective study, we hypothesized that reduced cerebral tissue oxygen saturation and increased intensity and duration of desaturation (defined as cerebral tissue oxygen saturation < 65%) during the early postoperative period, independently increase the probability of reduced total intelligence quotient, 2 years after admission to a PICU. DESIGN: Single-center, prospective study, performed between 2012 and 2015. SETTING: The PICU of the University Hospitals Leuven, Belgium. PATIENTS: The study included pediatric patients after surgery for congenital heart disease admitted to the PICU. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Postoperative cerebral perfusion was characterized with the mean cerebral tissue oxygen saturation and dose of desaturation of the first 12 and 24 hours of cerebral tissue oxygen saturation monitoring. The independent association of postoperative mean cerebral tissue oxygen saturation and dose of desaturation with total intelligence quotient at 2-year follow-up was evaluated with a Bayesian linear regression model adjusted for known confounders. According to a noninformative prior, reduced mean cerebral tissue oxygen saturation during the first 12 hours of monitoring results in a loss of intelligence quotient points at 2 years, with a 90% probability (posterior ß estimates [80% credible interval], 0.23 [0.04-0.41]). Similarly, increased dose of cerebral tissue oxygen saturation desaturation would result in a loss of intelligence quotient points at 2 years with a 90% probability (posterior ß estimates [80% credible interval], -0.009 [-0.016 to -0.001]). CONCLUSIONS: Increased dose of cerebral tissue oxygen saturation desaturation and reduced mean cerebral tissue oxygen saturation during the early postoperative period independently increase the probability of having a lower total intelligence quotient, 2 years after PICU admission.

Development and External Validation of an Online Clinical Prediction Model for Augmented Renal Clearance in Adult Mixed Critically Ill Patients: The Augmented Renal Clearance Predictor.

OBJECTIVES: Augmented renal clearance might lead to subtherapeutic plasma levels of drugs with predominant renal clearance. Early identification of augmented renal clearance remains challenging for the ICU physician. We developed and validated our augmented renal clearance predictor, a clinical prediction model for augmented renal clearance on the next day during ICU stay, and made it available via an online calculator. We compared its predictive performance with that of two existing models for augmented renal clearance. DESIGN: Multicenter retrospective registry-based cohort study. SETTING: Three Belgian tertiary care academic hospitals. PATIENTS: Adult medical, surgical, and cardiac surgery ICU patients. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Development of the prediction model was based on clinical information available during ICU stay. Out of 33,258 ICU days, we found augmented renal clearance on 19.6% of all ICU days in the development cohort. We retained six clinical variables in our augmented renal clearance predictor: day from ICU admission, age, sex, serum creatinine, trauma, and cardiac surgery. We assessed performance by measuring discrimination, calibration, and net benefit. We externally validated the final model in a single-center population (n = 10,259 ICU days). External validation confirmed good performance with an area under the curve of 0.88 (95% CI 0.87-0.88) and a sensitivity and specificity of 84.1 (95% CI 82.5-85.7) and 76.3 (95% CI 75.4-77.2) at the default threshold probability of 0.2, respectively. CONCLUSIONS: Augmented renal clearance on the next day can be predicted with good performance during ICU stay, using routinely collected clinical information that is readily available at bedside. Our augmented renal clearance predictor is available at www.arcpredictor.com.

Clinical prediction models for acute kidney injury. / Modelos de predição clínica para lesão renal aguda na unidade de terapia intensiva: uma revisão sistemática.

OBJECTIVE: To report on the currently available prediction models for the development of acute kidney injury in heterogeneous adult intensive care units. METHODS: A systematic review of clinical prediction models for acute kidney injury in adult intensive care unit populations was carried out. PubMed® was searched for publications reporting on the development of a novel prediction model, validation of an established model, or impact of an existing prediction model for early acute kidney injury diagnosis in intensive care units. RESULTS: We screened 583 potentially relevant articles. Among the 32 remaining articles in the first selection, only 5 met the inclusion criteria. The nonstandardized adaptations that were made to define baseline serum creatinine when the preadmission value was missing led to heterogeneous definitions of the outcome. Commonly included predictors were sepsis, age, and serum creatinine level. The final models included between 5 and 19 risk factors. The areas under the Receiver Operating Characteristic curves to predict acute kidney injury development in the internal validation cohorts ranged from 0.78 to 0.88. Only two studies were externally validated. CONCLUSION: Clinical prediction models for acute kidney injury can help in applying more timely preventive interventions to the right patients. However, in intensive care unit populations, few models have been externally validated. In addition, heterogeneous definitions for acute kidney injury and evaluation criteria and the lack of impact analysis hamper a thorough comparison of existing models. Future research is needed to validate the established models and to analyze their clinical impact before they can be applied in clinical practice.

Modelos de predição clínica para lesão renal aguda na unidade de terapia intensiva: uma revisão sistemática / Clinical prediction models for acute kidney injury

RESUMO Objetivo: Relatar os modelos atualmente disponíveis de predição para o desenvolvimento de lesão renal aguda em unidades de terapia para adultos heterogêneas. Métodos: Foi realizada revisão sistemática dos modelos de predição de lesão renal aguda em unidades de terapia intensiva para pacientes adultos. Fizemos busca na base PubMed® quanto a publicações que relatassem desenvolvimento de um novo modelo de predição, validação de um modelo estabelecido, ou impacto de um modelo de predição existente para diagnóstico precoce de lesão renal aguda em unidades de terapia intensiva. Resultados: Triamos 583 artigos potencialmente relevantes. Dentre os 32 artigos que restaram após a primeira seleção, apenas 5 cumpriram os critérios para inclusão. As adaptações não padronizadas feitas para definir o valor inicial de creatinina sérica, quando o valor desse exame antes da admissão estava faltando, levaram a definições heterogêneas do resultado. Preditores comumente incluídos foram sepse, idade e nível de creatinina sérica. Os modelos finais incluíram entre 5 e 19 fatores de risco. As áreas sob a curva Característica de Operação do Receptor para predição do desenvolvimento de lesão renal aguda nas coortes de validação interna variaram entre 0,78 e 0,88. Apenas dois estudos tiveram validação externa. Conclusão: Os modelos de predição clínica de lesão renal aguda podem ajudar na aplicação em tempo apropriado de intervenções preventivas para os pacientes adequados. Contudo, poucos modelos foram externamente validados para as populações da unidade de terapia intensiva. Além disto, definições heterogêneas para lesão renal aguda e critérios de avaliação, e a falta de análise do impacto comprometem uma comparação abrangente dos modelos existentes. São necessárias novas pesquisas para validar os modelos estabelecidos e analisar seu impacto clínico, antes que estes possam ser aplicados na prática clínica.

ABSTRACT Objective: To report on the currently available prediction models for the development of acute kidney injury in heterogeneous adult intensive care units. Methods: A systematic review of clinical prediction models for acute kidney injury in adult intensive care unit populations was carried out. PubMed® was searched for publications reporting on the development of a novel prediction model, validation of an established model, or impact of an existing prediction model for early acute kidney injury diagnosis in intensive care units. Results: We screened 583 potentially relevant articles. Among the 32 remaining articles in the first selection, only 5 met the inclusion criteria. The nonstandardized adaptations that were made to define baseline serum creatinine when the preadmission value was missing led to heterogeneous definitions of the outcome. Commonly included predictors were sepsis, age, and serum creatinine level. The final models included between 5 and 19 risk factors. The areas under the Receiver Operating Characteristic curves to predict acute kidney injury development in the internal validation cohorts ranged from 0.78 to 0.88. Only two studies were externally validated. Conclusion: Clinical prediction models for acute kidney injury can help in applying more timely preventive interventions to the right patients. However, in intensive care unit populations, few models have been externally validated. In addition, heterogeneous definitions for acute kidney injury and evaluation criteria and the lack of impact analysis hamper a thorough comparison of existing models. Future research is needed to validate the established models and to analyze their clinical impact before they can be applied in clinical practice.

Machine learning versus physicians' prediction of acute kidney injury in critically ill adults: a prospective evaluation of the AKIpredictor.

BACKGROUND: Early diagnosis of acute kidney injury (AKI) is a major challenge in the intensive care unit (ICU). The AKIpredictor is a set of machine-learning-based prediction models for AKI using routinely collected patient information, and accessible online. In order to evaluate its clinical value, the AKIpredictor was compared to physicians' predictions. METHODS: Prospective observational study in five ICUs of a tertiary academic center. Critically ill adults without end-stage renal disease or AKI upon admission were considered for enrollment. Using structured questionnaires, physicians were asked upon admission, on the first morning, and after 24 h to predict the development of AKI stages 2 or 3 (AKI-23) during the first week of ICU stay. Discrimination, calibration, and net benefit of physicians' predictions were compared against the ones by the AKIpredictor. RESULTS: Two hundred fifty-two patients were included, 30 (12%) developed AKI-23. In the cohort of patients with predictions by physicians and AKIpredictor, the performance of physicians and AKIpredictor were respectively upon ICU admission, area under the receiver operating characteristic curve (AUROC) 0.80 [0.69-0.92] versus 0.75 [0.62-0.88] (n = 120, P = 0.25) with net benefit in ranges 0-26% versus 0-74%; on the first morning, AUROC 0.94 [0.89-0.98] versus 0.89 [0.82-0.97] (n = 187, P = 0.27) with main net benefit in ranges 0-10% versus 0-48%; after 24 h, AUROC 0.95 [0.89-1.00] versus 0.89 [0.79-0.99] (n = 89, P = 0.09) with main net benefit in ranges 0-67% versus 0-50%. CONCLUSIONS: The machine-learning-based AKIpredictor achieved similar discriminative performance as physicians for prediction of AKI-23, and higher net benefit overall, because physicians overestimated the risk of AKI. This suggests an added value of the systematic risk stratification by the AKIpredictor to physicians' predictions, in particular to select high-risk patients or reduce false positives in studies evaluating new and potentially harmful therapies. Due to the low event rate, future studies are needed to validate these findings. TRIAL REGISTRATION: ClinicalTrials.gov, NCT03574896 registration date: July 2nd, 2018.

Near-Infrared-Based Cerebral Oximetry for Prediction of Severe Acute Kidney Injury in Critically Ill Children After Cardiac Surgery.

Cerebral oximetry by near-infrared spectroscopy is used frequently in critically ill children but guidelines on its use for decision making in the PICU are lacking. We investigated cerebral near-infrared spectroscopy oximetry in its ability to predict severe acute kidney injury after pediatric cardiac surgery and assessed its additional predictive value to routinely collected data. DESIGN: Prospective observational study. The cerebral oximeter was blinded to clinicians. SETTING: Twelve-bed tertiary PICU, University Hospitals Leuven, Belgium, between October 2012 and November 2015. PATIENTS: Critically ill children with congenital heart disease, younger than 12 years old, were monitored with cerebral near-infrared spectroscopy oximetry from PICU admission until they were successfully weaned off mechanical ventilation. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: The primary outcome was prediction of severe acute kidney injury 6 hours before its occurrence during the first week of intensive care. Near-infrared spectroscopy-derived predictors and routinely collected clinical data were compared and combined to assess added predictive value. Of the 156 children included in the analysis, 55 (35%) developed severe acute kidney injury. The most discriminant near-infrared spectroscopy-derived predictor was near-infrared spectroscopy variability (area under the receiver operating characteristic curve, 0.68; 95% CI, 0.67-0.68), but was outperformed by a clinical model including baseline serum creatinine, cyanotic cardiopathy pre-surgery, blood pressure, and heart frequency (area under the receiver operating characteristic curve, 0.75; 95% CI, 0.75-0.75; p < 0.001). Combining clinical and near-infrared spectroscopy information improved model performance (area under the receiver operating characteristic curve, 0.79; 95% CI, 0.79-0.80; p < 0.001). CONCLUSIONS: After pediatric cardiac surgery, near-infrared spectroscopy variability combined with clinical information improved discrimination for acute kidney injury. Future studies are required to identify whether supplementary, timely clinical interventions at the bedside, based on near-infrared spectroscopy variability analysis, could improve outcome.

Performance of Pediatric Mortality Prediction Scores for PICU Mortality and 90-Day Mortality.

OBJECTIVES: The use of mortality prediction scores in clinical trials in the PICU is essential for comparing patient groups. Because of the decline in PICU mortality over the last decades, leading to a shift toward later deaths, recent trials use 90-day mortality as primary outcome for estimating mortality and survival more accurately. This study assessed and compared the performance of two frequently used PICU mortality prediction scores for prediction of PICU and 90-day mortality. DESIGN: This secondary analysis of the randomized controlled Early versus Late Parenteral Nutrition in the Pediatric Intensive Care Unit trial compared the discrimination (area under the receiver operating characteristic curve) and calibration of the Pediatric Index of Mortality 3 and the Pediatric Risk of Mortality III scores for prediction of PICU and 90-day mortality. SETTING: Three participating PICUs within academic hospitals in Belgium, the Netherlands, and Canada. PATIENTS: One-thousand four-hundred twenty-eight critically ill patients 0-17 years old. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Although Pediatric Index of Mortality 3 only includes information available at the time of PICU admission, thus before any intervention in the PICU, it showed good discrimination (area under the receiver operating characteristic curve, 0.894; 95% CI, 0.892-0.896) and good calibration (no deviation from the diagonal, p = 0.58) for PICU mortality. Pediatric Risk of Mortality III, which involves the worst values for the evaluated variables during the first 24 hours of PICU stay, was statistically more discriminant (area under the receiver operating characteristic curve, 0.920; 95% CI, 0.918-0.921; p = 0.04) but poor in calibration (significant deviation from the diagonal; p = 0.04). Pediatric Index of Mortality 3 and Pediatric Risk of Mortality III discriminated equally well between 90-day mortality and survival (area under the receiver operating characteristic curve, 0.867; 95% CI, 0.866-0.869 and area under the receiver operating characteristic curve, 0.882; 95% CI, 0.880-0.884, respectively, p = 0.77), but Pediatric Risk of Mortality III was not well calibrated (p = 0.04), unlike Pediatric Index of Mortality 3 (p = 0.34). CONCLUSIONS: Pediatric Index of Mortality 3 performed better in calibration for predicting PICU and 90-day mortality than Pediatric Risk of Mortality III and is not influenced by intervention or PICU quality of care. Therefore, Pediatric Index of Mortality 3 seems a better choice for use in clinical trials with 90-day mortality as primary outcome.

Visualizing Cerebrovascular Autoregulation Insults and Their Association with Outcome in Adult and Paediatric Traumatic Brain Injury.

OBJECTIVE: The aim of this study is to assess visually the impact of duration and intensity of cerebrovascular autoregulation insults on 6-month neurological outcome in severe traumatic brain injury. MATERIAL AND METHODS: Retrospective analysis of prospectively collected minute-by-minute intracranial pressure (ICP) and mean arterial blood pressure data of 259 adult and 99 paediatric traumatic brain injury (TBI) patients from multiple European centres. The relationship of the 6-month Glasgow Outcome Scale with cerebrovascular autoregulation insults (defined as the low-frequency autoregulation index above a certain threshold during a certain time) was visualized in a colour-coded plot. The analysis was performed separately for autoregulation insults occurring with cerebral perfusion pressure (CPP) below 50 mmHg, with ICP above 25 mmHg and for the subset of adult patients that did not undergo decompressive craniectomy. RESULTS: The colour-coded plots showed a time-intensity-dependent association with outcome for cerebrovascular autoregulation insults in adult and paediatric TBI patients. Insults with a low-frequency autoregulation index above 0.2 were associated with worse outcomes and below -0.6 with better outcomes, with and approximately exponentially decreasing transition curve between the two intensity thresholds. All insults were associated with worse outcomes when CPP was below 50 mmHg or ICP was above 25 mmHg. CONCLUSIONS: The colour-coded plots indicate that cerebrovascular autoregulation is disturbed in a dynamic manner, such that duration and intensity play a role in the determination of a zone associated with better neurological outcome.

Near-Infrared Cerebral Oximetry to Predict Outcome After Pediatric Cardiac Surgery: A Prospective Observational Study.

OBJECTIVES: To assess whether near-infrared cerebral tissue oxygen saturation, measured with the FORESIGHT cerebral oximeter (CAS Medical Systems, Branford, CT) predicts PICU length of stay, duration of invasive mechanical ventilation, and mortality in critically ill children after pediatric cardiac surgery. DESIGN: Single-center prospective, observational study. SETTING: Twelve-bed PICU of a tertiary academic hospital. PATIENTS: Critically ill children and infants with congenital heart disease, younger than 12 years old, admitted to the PICU between October 2012 and November 2015. Children were monitored with the FORESIGHT cerebral oximeter from PICU admission until they were weaned off mechanical ventilation. Clinicians were blinded to cerebral tissue oxygen saturation data. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: Primary outcome was the predictive value of the first 24 hours of postoperative cerebral tissue oxygen saturation for duration of PICU stay (median [95% CI], 4 d [3-8 d]) and duration of mechanical ventilation (median [95% CI], 111.3 hr (69.3-190.4 hr]). We calculated predictors on the first 24 hours of cerebral tissue oxygen saturation monitoring. The association of each individual cerebral tissue oxygen saturation predictor and of a combination of predictors were assessed using univariable and multivariable bootstrap analyses, adjusting for age, weight, gender, Pediatric Index of Mortality 2, Risk Adjustment in Congenital Heart Surgery 1, cyanotic heart defect, and time prior to cerebral tissue oxygen saturation monitoring. The most important risk factors associated with worst outcomes were an increased SD of a smoothed cerebral tissue oxygen saturation signal and an elevated cerebral tissue oxygen saturation desaturation score. CONCLUSIONS: Increased SD of a smoothed cerebral tissue oxygen saturation signal and increased depth and duration of desaturation below the 50% saturation threshold were associated with longer PICU and hospital stays and with longer duration of mechanical ventilation after pediatric cardiac surgery.

Generalisability of a Virtual Trials Method for Glycaemic Control in Intensive Care.

BACKGROUND: Elevated blood glucose (BG) concentrations (Hyperglycaemia) are a common complication in critically ill patients. Insulin therapy is commonly used to treat hyperglycaemia, but metabolic variability often results in poor BG control and low BG (hypoglycaemia). OBJECTIVE: This paper presents a model-based virtual trial method for glycaemic control protocol design, and evaluates its generalisability across different populations. METHODS: Model-based insulin sensitivity (SI) was used to create virtual patients from clinical data from three different ICUs in New Zealand, Hungary, and Belgium. Glycaemic results from simulation of virtual patients under their original protocol (self-simulation) and protocols from other units (cross simulation) were compared. RESULTS: Differences were found between the three cohorts in median SI and inter-patient variability in SI. However, hour-to-hour intra-patient variability in SI was found to be consistent between cohorts. Self and cross-simulation results were found to have overall similarity and consistency, though results may differ in the first 24-48 h due to different cohort starting BG and underlying SI. CONCLUSIONS AND SIGNIFICANCE: Virtual patients and the virtual trial method were found to be generalisable across different ICUs. This virtual trial method is useful for in silico protocol design and testing, given an understanding of the underlying assumptions and limitations of this method.

AKIpredictor, an online prognostic calculator for acute kidney injury in adult critically ill patients: development, validation and comparison to serum neutrophil gelatinase-associated lipocalin.

PURPOSE: Early diagnosis of acute kidney injury (AKI) remains a major challenge. We developed and validated AKI prediction models in adult ICU patients and made these models available via an online prognostic calculator. We compared predictive performance against serum neutrophil gelatinase-associated lipocalin (NGAL) levels at ICU admission. METHODS: Analysis of the large multicenter EPaNIC database. Model development (n = 2123) and validation (n = 2367) were based on clinical information available (1) before and (2) upon ICU admission, (3) after 1 day in ICU and (4) including additional monitoring data from the first 24 h. The primary outcome was a comparison of the predictive performance between models and NGAL for the development of any AKI (AKI-123) and AKI stages 2 or 3 (AKI-23) during the first week of ICU stay. RESULTS: Validation cohort prevalence was 29% for AKI-123 and 15% for AKI-23. The AKI-123 model before ICU admission included age, baseline serum creatinine, diabetes and type of admission (medical/surgical, emergency/planned) and had an AUC of 0.75 (95% CI 0.75-0.75). The AKI-23 model additionally included height and weight (AUC 0.77 (95% CI 0.77-0.77)). Performance consistently improved with progressive data availability to AUCs of 0.82 (95% CI 0.82-0.82) for AKI-123 and 0.84 (95% CI 0.83-0.84) for AKI-23 after 24 h. NGAL was less discriminant with AUCs of 0.74 (95% CI 0.74-0.74) for AKI-123 and 0.79 (95% CI 0.79-0.79) for AKI-23. CONCLUSIONS: AKI can be predicted early with models that only use routinely collected clinical information and outperform NGAL measured at ICU admission. The AKI-123 models are available at http://akipredictor.com/ . Trial registration Clinical Trials.gov NCT00512122.

Informatics in neurocritical care: new ideas for Big Data.

PURPOSE OF REVIEW: Big data is the new hype in business and healthcare. Data storage and processing has become cheap, fast, and easy. Business analysts and scientists are trying to design methods to mine these data for hidden knowledge. Neurocritical care is a field that typically produces large amounts of patient-related data, and these data are increasingly being digitized and stored. This review will try to look beyond the hype, and focus on possible applications in neurointensive care amenable to Big Data research that can potentially improve patient care. RECENT FINDINGS: The first challenge in Big Data research will be the development of large, multicenter, and high-quality databases. These databases could be used to further investigate recent findings from mathematical models, developed in smaller datasets. Randomized clinical trials and Big Data research are complementary. Big Data research might be used to identify subgroups of patients that could benefit most from a certain intervention, or can be an alternative in areas where randomized clinical trials are not possible. SUMMARY: The processing and the analysis of the large amount of patient-related information stored in clinical databases is beyond normal human cognitive ability. Big Data research applications have the potential to discover new medical knowledge, and improve care in the neurointensive care unit.