Automated Cerebral Hemorrhage Detection Using RAPID.

BACKGROUND AND PURPOSE: Intracranial hemorrhage (ICH) is an important event that is diagnosed on head NCCT. Increased NCCT utilization in busy hospitals may limit timely identification of ICH. RAPID ICH is an automated hybrid 2D-3D convolutional neural network application designed to detect ICH that may allow for expedited ICH diagnosis. We determined the accuracy of RAPID ICH for ICH detection and ICH volumetric quantification on NCCT. MATERIALS AND METHODS: NCCT scans were evaluated for ICH by RAPID ICH. Consensus detection of ICH by 3 neuroradiology experts was used as the criterion standard for RAPID ICH comparison. ICH volume was also automatically determined by RAPID ICH in patients with intraparenchymal or intraventricular hemorrhage and compared with manually segmented ICH volumes by a single neuroradiology expert. ICH detection accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and positive and negative likelihood ratios by RAPID ICH were determined. RESULTS: We included 308 studies. RAPID ICH correctly identified 151/158 ICH cases and 143/150 ICH-negative cases, which resulted in high sensitivity (0.956, CI: 0.911-0.978), specificity (0.953, CI: 0.907-0.977), positive predictive value (0.956, CI: 0.911-0.978), and negative predictive value (0.953, CI: 0.907-0.977) for ICH detection. The positive likelihood ratio (20.479, CI 9.928-42.245) and negative likelihood ratio (0.046, CI 0.023-0.096) for ICH detection were similarly favorable. RAPID ICH volumetric quantification for intraparenchymal and intraventricular hemorrhages strongly correlated with expert manual segmentation (correlation coefficient r = 0.983); the median absolute error was 3 mL. CONCLUSIONS: RAPID ICH is highly accurate in the detection of ICH and in the volumetric quantification of intraparenchymal and intraventricular hemorrhages.

Outcome prediction in mechanically ventilated neurologic patients by junior neurointensivists.

OBJECTIVE: Physician prediction of outcome in critically ill neurologic patients impacts treatment decisions and goals of care. In this observational study, we prospectively compared predictions by neurointensivists to patient outcomes at 6 months. METHODS: Consecutive neurologic patients requiring mechanical ventilation for 72 hours or more were enrolled. The attending neurointensivist was asked to predict 6-month 1) functional outcome (modified Rankin scale [mRS]), 2) quality of life (QOL), and 3) whether supportive care should be withdrawn. Six-month functional outcome was determined by telephone interviews and dichotomized to good (mRS 0-3) and poor outcome (mRS 4-6). RESULTS: Of 187 eligible patients, 144 were enrolled. Neurointensivists correctly predicted 6-month functional outcome in 80% (95% confidence interval [CI], 72%-86%) of patients. Accuracy for a predicted good outcome was 63% (95% CI, 50%-74%) and for poor outcome 94% (95% CI, 85%-98%). Excluding patients who had life support withdrawn, accuracy for good outcome was 73% (95% CI, 60%-84%) and for poor outcome 87% (95% CI, 74%-94%). Accuracy for exact agreement between neurointensivists' mRS predictions and actual 6-month mRS was only 43% (95% CI, 35%-52%). Predicted accuracy for QOL was 58% (95% CI, 39%-74%) for good/excellent and 67% (95% CI, 46%-83%) for poor/fair. Of 27 patients for whom withdrawal of care was recommended, 1 patient survived in a vegetative state. CONCLUSIONS: Prediction of long-term functional outcomes in critically ill neurologic patients is challenging. Our neurointensivists were more accurate in predicting poor outcome than good outcome in patients requiring mechanical ventilation >or=72 hours.