Development and validation of the creatinine clearance predictor machine learning models in critically ill adults.

BACKGROUND: In critically ill patients, measured creatinine clearance (CrCl) is the most reliable method to evaluate glomerular filtration rate in routine clinical practice and may vary subsequently on a day-to-day basis. We developed and externally validated models to predict CrCl one day ahead and compared them with a reference reflecting current clinical practice. METHODS: A gradient boosting method (GBM) machine-learning algorithm was used to develop the models on data from 2825 patients from the EPaNIC multicenter randomized controlled trial database. We externally validated the models on 9576 patients from the University Hospitals Leuven, included in the M@tric database. Three models were developed: a "Core" model based on demographic, admission diagnosis, and daily laboratory results; a "Core + BGA" model adding blood gas analysis results; and a "Core + BGA + Monitoring" model also including high-resolution monitoring data. Model performance was evaluated against the actual CrCl by mean absolute error (MAE) and root-mean-square error (RMSE). RESULTS: All three developed models showed smaller prediction errors than the reference. Assuming the same CrCl of the day of prediction showed 20.6 (95% CI 20.3-20.9) ml/min MAE and 40.1 (95% CI 37.9-42.3) ml/min RMSE in the external validation cohort, while the developed model having the smallest RMSE (the Core + BGA + Monitoring model) had 18.1 (95% CI 17.9-18.3) ml/min MAE and 28.9 (95% CI 28-29.7) ml/min RMSE. CONCLUSIONS: Prediction models based on routinely collected clinical data in the ICU were able to accurately predict next-day CrCl. These models could be useful for hydrophilic drug dosage adjustment or stratification of patients at risk. TRIAL REGISTRATION: Not applicable.

Development and External Validation of a Machine Learning Model for the Early Prediction of Doses of Harmful Intracranial Pressure in Patients with Severe Traumatic Brain Injury.

Treatment and prevention of elevated intracranial pressure (ICP) is crucial in patients with severe traumatic brain injury (TBI). Elevated ICP is associated with secondary brain injury, and both intensity and duration of an episode of intracranial hypertension, often referred to as "ICP dose," are associated with worse outcomes. Prediction of such harmful episodes of ICP dose could allow for a more proactive and preventive management of TBI, with potential implications on patients' outcomes. The goal of this study was to develop and validate a machine-learning (ML) model to predict potentially harmful ICP doses in patients with severe TBI. The prediction target was defined based on previous studies and included a broad range of doses of elevated ICP that have been associated with poor long-term neurological outcomes. The ML models were used, with minute-by-minute ICP and mean arterial blood pressure signals as inputs. Harmful ICP episodes were predicted with a 30 min forewarning. Models were developed in a multi-center dataset of 290 adult patients with severe TBI and externally validated on 264 patients from the Collaborative European NeuroTrauma Effectiveness Research in Traumatic Brain Injury (CENTER-TBI) dataset. The external validation of the prediction model on the CENTER-TBI dataset demonstrated good discrimination and calibration (area under the curve: 0.94, accuracy: 0.89, precision: 0.87, sensitivity: 0.78, specificity: 0.94, calibration-in-the-large: 0.03, calibration slope: 0.93). The proposed prediction model provides accurate and timely predictions of harmful doses of ICP on the development and external validation dataset. A future interventional study is needed to assess whether early intervention on the basis of ICP dose predictions will result in improved outcomes.

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.

Data-driven ICU management: Using Big Data and algorithms to improve outcomes.

The digitalization of the Intensive Care Unit (ICU) led to an increasing amount of clinical data being collected at the bedside. The term "Big Data" can be used to refer to the analysis of these datasets that collect enormous amount of data of different origin and format. Complexity and variety define the value of Big Data. In fact, the retrospective analysis of these datasets allows to generate new knowledge, with consequent potential improvements in the clinical practice. Despite the promising start of Big Data analysis in medical research, which has seen a rising number of peer-reviewed articles, very limited applications have been used in ICU clinical practice. A close future effort should be done to validate the knowledge extracted from clinical Big Data and implement it in the clinic. In this article, we provide an introduction to Big Data in the ICU, from data collection and data analysis, to the main successful examples of prognostic, predictive and classification models based on ICU data. In addition, we focus on the main challenges that these models face to reach the bedside and effectively improve ICU care.

Prediction of short-term health outcomes in preterm neonates from heart-rate variability and blood pressure using boosted decision trees.

BACKGROUND AND OBJECTIVE: Efficient management of low blood pressure (BP) in preterm neonates remains challenging with considerable variability in clinical practice. There is currently no clear consensus on what constitutes a limit for low BP that is a risk to the preterm brain. It is argued that a personalised approach rather than a population based threshold is more appropriate. This work aims to assist healthcare professionals in assessing preterm wellbeing during episodes of low BP in order to decide when and whether hypotension treatment should be initiated. In particular, the study investigates the relationship between heart rate variability (HRV) and BP in preterm infants and its relevance to a short-term health outcome. METHODS: The study is performed on a large clinically collected dataset of 831 h from 23 preterm infants of less than 32 weeks gestational age. The statistical predictive power of common HRV features is first assessed with respect to the outcome. A decision support system, based on boosted decision trees (XGboost), was developed to continuously estimate the probability of neonatal morbidity based on the feature vector of HRV characteristics and the mean arterial blood pressure. RESULTS: It is shown that the predictive power of the extracted features improves when observed during episodes of hypotension. A single best HRV feature achieves an AUC of 0.87. Combining multiple HRV features extracted during hypotensive episodes with the classifier achieves an AUC of 0.97, using a leave-one-patient-out performance assessment. Finally it is shown that good performance can even be achieved using continuous HRV recordings, rather than only focusing on hypotensive events - this had the benefit of not requiring invasive BP monitoring. CONCLUSIONS: The work presents a promising step towards the use of multimodal data in providing objective decision support for the prediction of short-term outcome in preterm infants with hypotensive episodes.

Heart Rate Variability during Periods of Low Blood Pressure as a Predictor of Short-Term Outcome in Preterms.

Efficient management of low blood pressure (BP) in preterm neonates remains challenging with a considerable variability in clinical practice. The ability to assess preterm wellbeing during episodes of low BP will help to decide when and whether hypotension treatment should be initiated. This work aims to investigate the relationship between heart rate variability (HRV), BP and the short-term neurological outcome in preterm infants less than 32 weeks gestational age (GA). The predictive power of common HRV features with respect to the outcome is assessed and shown to improve when HRV is observed during episodes of low mean arterial pressure (MAP) - with a single best feature leading to an AUC of 0.87. Combining multiple features with a boosted decision tree classifier achieves an AUC of 0.97. The work presents a promising step towards the use of multimodal data in building an objective decision support tool for clinical prediction of short-term outcome in preterms who suffer episodes of low BP.