The Evaluation of Prognostic Scores in Spontaneous Intracerebral Hemorrhage in an Asian Population: A Retrospective Study

Prognostication of Outcomes in Spontaneous Intracerebral Hemorrhage: A Propensity Score-Matched Analysis with Support Vector Machine

OBJECTIVE

The role of surgery in spontaneous intracerebral hemorrhage (SICH) remains controversial. We aimed to use explainable machine learning (ML) combined with propensity-score matching to investigate the effects of surgery and identify subgroups of patients with SICH who may benefit from surgery in an interpretable fashion.

METHODS

We conducted a retrospective study of a cohort of 282 patients aged ≥21 years with SICH. ML models were developed to separately predict for surgery and surgical evacuation. SHapley Additive exPlanations (SHAP) values were calculated to interpret the predictions made by ML models. Propensity-score matching was performed to estimate the effect of surgery and surgical evacuation on 90-day poor functional outcomes (PFO).

RESULTS

Ninety-two patients (32.6%) underwent surgery, and 57 patients (20.2%) underwent surgical evacuation. A total of 177 patients (62.8%) had 90-day PFO. The support vector machine achieved a c-statistic of 0.915 when predicting 90-day PFO for patients who underwent surgery and a c-statistic of 0.981 for patients who underwent surgical evacuation. The SHAP scores for the top 5 features were Glasgow Coma Scale score (0.367), age (0.214), volume of hematoma (0.258), location of hematoma (0.195), and ventricular extension (0.164). Surgery, but not surgical evacuation of the hematoma, was significantly associated with improved mortality at 90-day follow-up (odds ratio, 0.26; 95% confidence interval, 0.10-0.67; P = 0.006).

CONCLUSIONS

Explainable ML approaches could elucidate how ML models predict outcomes in SICH and identify subgroups of patients who respond to surgery. Future research in SICH should focus on an explainable ML-based approach that can identify subgroups of patients who may benefit functionally from surgical intervention.

In-hospital outcomes of patients with spontaneous supratentorial intracerebral hemorrhage

Spontaneous intracerebral hemorrhage (ICH) in the brain parenchyma accounts for 16.1% of all stroke types in Taiwan. It is responsible for high morbidity and mortality in some underlying causes. The objective of this study is to discover the predicting factors focusing on in-hospital outcomes of patients with spontaneous supratentorial ICH. Between June 2014 and October 2018, there were a total of 159 patients with spontaneous supratentorial ICH ranging from 27 to 91 years old in our institution. Twenty-three patients died during hospitalization, whereas 59 patients had an extended length of stay of >30 days. The outcomes were measured by inpatient death, length of stay, and activity of daily living (ADL). Both univariate and multivariate binary logistic regression, as well as multivariate linear regression, were used for statistical analysis. Multivariate binary linear regression analysis showed the larger hematoma in initial computed tomography scan of >30 cm3 (odds ratio [OR] = 2.505, P = .013) and concurrent in-hospital infection (OR = 4.173, P = .037) were both statistically related to higher mortality. On the other hand, in-hospital infection (≥17.41 days, P = .000) and surgery (≥11.23 days, P = .001) were correlated with a longer length of stay. Lastly, drastically poor change of ADL (ΔADL <-30) was associated with larger initial ICH (>30 cc, OR = 2.915, P = .049), in-hospital concurrent infection (OR = 4.695, P = .01), and not receiving a rehabilitation training program (OR = 3.473, P = .04). The results of this study suggest that age, prothrombin, initial Glasgow Coma Scale, computed tomography image, location of the lesion, and surgery could predict the mortality and morbidity of the spontaneous ICH, which cannot be reversed at the time of occurrence. However, effective control of international normalized ratio level, careful prevention against infection, and the aid of rehabilitation programs might be important factors toward a decrease of inpatient mortality rate, the length of stay, and ADL recovery.

A Longitudinal Research on the Distribution and Prognosis of Intracerebral Hemorrhage During the COVID-19 Pandemic

Purpose

Globally, intracerebral hemorrhage (ICH) is a common cerebrovascular disease. At the beginning of 2020, due to the coronavirus disease 2019 (COVID-19) pandemic, the allocation of medical resources and the patient treatment and referrals were affected to varying degrees. We aimed to determine the characteristics and prognoses and associated factors of patients with ICH.

Patients and Methods

The baseline demographic characteristics and ICH outcomes were compared between patients diagnosed with ICH between January and June 2020 (the 2020 group) and between January and June 2019 (the 2019 group). COVID-19 positive patients were excluded from the study. A 30-day data from patients in the 2019 and 2020 groups were analyzed to create survival curves for these patients. We also used regression models to identify the significant determinants of poor outcomes [modified Rankin score (mRS): 3-6] and death.

Results

The number of patients diagnosed with ICH was slightly lower in the 2020 group (n = 707) than in the 2019 group (n = 719). During the lockdown period (February 2020), the admission rates for ICH decreased greatly by 35.1%. The distribution of the patients' domicile (P = 0.002) and the mRS (P < 0.001) differed significantly between the years. The survival curve revealed that the highest risk of death was in the acute stage (especially in the first 5 days) of ICH. At 30 days, mortality was 19.8% in February 2019 and 29.4% in February 2020 (P = 0.119). Multivariate analysis revealed age, baseline mRS, postoperative complications, massive brainstem hemorrhage, and creatinine as factors significantly associated with poor outcomes and death following ICH. Neurosurgery and massive supratentorial hemorrhage were only correlated with the risk of death.

Conclusion

During the lockdown period, the COVID-19 pandemic caused a decrease in the admission rates and severe conditions at admission due to strict traffic constraints for infection control. This led to high mortality and disability in patients with ICH. It is necessary to ensure an effective green channel and allocate adequate medical resources for patients to receive timely treatment and neurosurgery.

Machine Learning Models Prognosticate Functional Outcomes Better than Clinical Scores in Spontaneous Intracerebral Haemorrhage

OBJECTIVE

This study aims to develop and compare the use of deep neural networks (DNN) and support vector machines (SVM) to clinical prognostic scores for prognosticating 30-day mortality and 90-day poor functional outcome (PFO) in spontaneous intracerebral haemorrhage (SICH).

MATERIALS AND METHODS

We conducted a retrospective cohort study of 297 SICH patients between December 2014 and May 2016. Clinical data was collected from electronic medical records using standardized data collection forms. The machine learning workflow included imputation of missing data, dimensionality reduction, imbalanced-class correction, and evaluation using cross-validation and comparison of accuracy against clinical prognostic scores.

RESULTS

32 (11%) patients had 30-day mortality while 177 (63%) patients had 90-day PFO. For prognosticating 30-day mortality, the class-balanced accuracies for DNN (0.875; 95% CI 0.800-0.950; McNemar's p-value 1.000) and SVM (0.848; 95% CI 0.767-0.930; McNemar's p-value 0.791) were comparable to that of the original ICH score (0.833; 95% CI 0.748-0.918). The c-statistics for DNN (0.895; DeLong's p-value 0.715), and SVM (0.900; DeLong's p-value 0.619), though greater than that of the original ICH score (0.862), were not significantly different. For prognosticating 90-day PFO, the class-balanced accuracies for DNN (0.853; 95% CI 0.772-0.934; McNemar's p-value 0.003) and SVM (0.860; 95% CI 0.781-0.939; McNemar's p-value 0.004) were better than that of the ICH-Grading Scale (0.706; 95% CI 0.600-0.812). The c-statistic for SVM (0.883; DeLong's p-value 0.022) was significantly greater than that of the ICH-Grading Scale (0.778), while the c-statistic for DNN was 0.864 (DeLong's p-value 0.055).

CONCLUSION

We showed that the SVM model performs significantly better than clinical prognostic scores in predicting 90-day PFO in SICH.

Validation of the ICH score and ICH-GS in a Peruvian surgical cohort: a retrospective study

The intracerebral hemorrhage (ICH) score and the ICH-grading scale (ICH-GS) are mortality predictor tools developed predominantly in conservatively treated ICH cohorts. We aimed to compare and evaluate the external validity of both models in predicting mortality in patients with ICH undergoing surgical intervention. A retrospective review of all patients presenting with spontaneous ICH admitted to a Peruvian national hospital between January 2018 and March 2020 was conducted. We compared the area under the receiver operating characteristic curve (AUC) for the ICH score and ICH-GS for in-hospital, 30-day, and 6-month mortality prediction. The research protocol was approved by the Institutional Review Board. A total of 73 patients (median age 62 years, 56.2% males) were included in the study. The mean ICH and ICH-GS scores were 2.5 and 8.7, respectively. In-hospital, 30-day, and 6-month mortality were 37%, 27.4%, and 37%, respectively. The AUC for in-hospital, 30-day, and 6-month mortality was 0.69, 0.71, and 0.69, respectively, for the ICH score and 0.64, 0.65, and 0.68, respectively, for the ICH-GS score. In this study, the ICH score and ICH-GS had moderate discrimination capacities to predict in-hospital, 30-day, and 6-month mortality in surgically treated patients. Additional studies should assess whether surgical intervention affects the discrimination of these prognostic models in order to develop predictive scores based on specific populations.