Predictive nomogram for unfavorable outcome of spontaneous intracerebral hemorrhage

Background and purpose Introduction The goal of this study was to retrospectively identify potential risk factors, especially surgical timing, for poor prognosis of ICH. Methods Medical records of ICH cases who had undergone surgery between January 2014 and January 2021 were reviewed. The modified Rankin Scale score (MRS) were assigned to ICH subjects at 6 months after attack. The relationships of surgical timing with the risk of unfavorable outcome were identified using the interaction and stratified analyses, generalized additive and logistic regression model. Depending on the results of logistic regression, a nomogram was established and evaluated using a receiver operating characteristic curve analysis, plotted decision curve and calibration curve. Results Finally, 53 and 144 cases were enrolled into the favorable and unfavorable outcome group respectively. The cases who underwent surgery at >12h and <36h in the favorable outcome group were more than that in the unfavorable outcome group (p<0.001). When the time to operation room (TOR) was less than 21h, the negative association between TOR and unfavorable outcome was observed in the smoothing spline (OR=0.8, p < 0.001). We developed a nomogram including SBP, GCS, midline shift, hematoma volume and TOR for predicting the unfavorable outcome. The AUC, accuracy, specificity, and sensitivity of nomogram were 0.90, 0.87, 0.72, 0.93 respectively. Conclusions The patients who underwent surgery at >12h and <36h were more likely to get favorable outcome. The nomogram including SBP, GCS, midline shift, hematoma volume and TOR was reliable for predicting ICH outcome.