Clinical Profile and Predictors of Outcome in Spontaneous Intracerebral Hemorrhage from a Tertiary Care Centre in South India

CT-based deep learning model for predicting hospital discharge outcome in spontaneous intracerebral hemorrhage

OBJECTIVES

To predict the functional outcome of patients with intracerebral hemorrhage (ICH) using deep learning models based on computed tomography (CT) images.

METHODS

A retrospective, bi-center study of ICH patients was conducted. Firstly, a custom 3D convolutional model was built for predicting the functional outcome of ICH patients based on CT scans from randomly selected ICH patients in H training dataset collected from H hospital. Secondly, clinical data and radiological features were collected at admission and the Extreme Gradient Boosting (XGBoost) algorithm was used to establish a second model, named the XGBoost model. Finally, the Convolution model and XGBoost model were fused to build the third "Fusion model." Favorable outcome was defined as modified Rankin Scale score of 0-3 at discharge. The prognostic predictive accuracy of the three models was evaluated using an H test dataset and an external Y dataset, and compared with the performance of ICH score and ICH grading scale (ICH-GS).

RESULTS

A total of 604 patients with ICH were included in this study, of which 450 patients were in the H training dataset, 50 patients in the H test dataset, and 104 patients in the Y dataset. In the Y dataset, the areas under the curve (AUCs) of the Convolution model, XGBoost model, and Fusion model were 0.829, 0.871, and 0.905, respectively. The Fusion model prognostic performance exceeded that of ICH score and ICH-GS (p = 0.043 and p = 0.045, respectively).

CONCLUSIONS

Deep learning models have good accuracy for predicting functional outcome of patients with spontaneous intracerebral hemorrhage.

CLINICAL RELEVANCE STATEMENT

The proposed deep learning Fusion model may assist clinicians in predicting functional outcome and developing treatment strategies, thereby improving the survival and quality of life of patients with spontaneous intracerebral hemorrhage.

KEY POINTS

• Integrating clinical presentations, CT images, and radiological features to establish deep learning model for functional outcome prediction of patients with intracerebral hemorrhage. • Deep learning applied to CT images provides great help in prognosing functional outcome of intracerebral hemorrhage patients. • The developed deep learning model performs better than clinical prognostic scores in predicting functional outcome of patients with intracerebral hemorrhage.

Important Factors to Expect the Outcome After Intracerebral Hemorrhage: An Observational Study From a University Hospital in Saudi Arabia

BACKGROUND

Intracerebral hemorrhage (ICH) has worse clinical outcomes than other stroke types. The risk factors contributing to ICH outcomes are not entirely understood, and published literature from Saudi Arabia on ICH outcomes is limited. Our goal was to study the specific clinical and imaging determinants of ICH outcomes.

METHODS

We retrospectively retrieved all patients with spontaneous ICH (SICH) from a prospective King Fahd Hospital University registry between 2017 and 2019. The clinical characteristics of ICH events and data on clinical outcomes (6 to 12 mo) were recorded. Groups of patients with a favorable modified Rankin Scale of 0 to 2 and nonfavorable outcomes of a modified Rankin Scale of 3 to 6 were investigated. The relationship between the clinical characteristics of the SICH event and its outcomes was assessed using linear and logistic regression analyses.

RESULTS

A total of 148 patients with a mean age of 60.3 years (±15.2) and a median follow-up of 9 months were included. Unfavorable outcomes were reported in 98 patients (66.2%). The ICH event variables associated with unfavorable outcomes were impaired renal function, Glasgow Coma Score <8, hematoma volume, hematoma expansion, and intraventricular extension (IVE).

CONCLUSIONS

Our study demonstrated important clinical and radiologic features in patients with ICH that may affect their clinical long-term functional outcomes. A larger multicenter study is required to validate our results and evaluate the methods to improve health care in patients with SICH.

Hydrocephalus is an independent factor affecting morbidity and mortality of ICH patients: Systematic review and meta-analysis

Background

Despite advances in our knowledge of the causes, preventions, and treatments of stroke, it continues to be a leading cause of death and disability. The most common type of stroke-related morbidity and mortality is intracerebral haemorrhage (ICH). Many prognostication scores include an intraventricular extension (IVH) after ICH because it affects mortality independently. Although it is a direct result of IVH and results in significant damage, hydrocephalus (HC) has never been taken into account when calculating prognostication scores. This study aimed to evaluate the significance of hydrocephalus on the outcomes of ICH patients by meta-analysis.

Methods

Studies that compared the rates of mortality and/or morbidity in patients with ICH, ICH with IVH (ICH ​+ ​IVH), and ICH with IVH and HC (ICH ​+ ​IVH ​+ ​HC) were identified. A meta-analysis was performed by using Mantel-Haezel Risk Ratio at 95% significance.

Results

This meta-analysis included thirteen studies. The findings indicate that ICH ​+ ​IVH ​+ ​HC has higher long-term (90-day) and short-term (30-day) mortality risks than ICH (4.26 and 2.30 higher risks, respectively) and ICH ​+ ​IVH (1.96 and 1.54 higher risks). Patients with ICH ​+ ​IVH ​+ ​HC have lower rates of short-term (3 months) and long-term (6 months) good functional outcomes than those with ICH (0.66 and 0.38 times) or ICH ​+ ​IVH (0.76 and 0.54 times). Confounding variables included vascular comorbidities, haemorrhage volume, midline shift, and an initial GCS score below 8.

Conclusion

Hydrocephalus causes a poorer prognosis in ICH patients. Thus, it is reasonable to suggest the inclusion of hydrocephalus in ICH prognostication scoring systems.

Spontaneous Intracerebral Hemorrhage in the Young: An Institutional Registry Analysis

Background

Spontaneous intracerebral hemorrhage (SICH) accounts for about 10-15% of all strokes. Generally, it is a disease of the elderly; worldwide, the incidence of SICH in the young is showing an increasing trend, especially in India and the Asian continent. An attempt is also made to analyze the presence of factors, which may predict the risk of SICH among young hypertensives.

Methods

A six-year retrospective review of patients aged below 50 years who presented with SICH was included in the study. Patients with bleeds secondary to an identifiable cause such as tumor, trauma, vascular malformations, and coagulopathy-induced bleeds were excluded from the study. The outcome was measured at 90 days using the modified ranking scale, and predictors of outcome (good outcome modified ranking score (mRS): 0-3; poor outcome mRS: 4-6) were analyzed.

Results

SICH in the young accounted for 28.4% of all intracerebral hemorrhage (ICH) patients admitted during the study period (344/1210). The mean age of our male-dominant (78.5%) cohort was 42.9 ± 6.24 years, and the median Glasgow coma score (GCS) on presentation was 11 (IQR: 8-14). A prior history of hypertension (HTN) was obtained in 51.2% (176), and left ventricular hypertrophy (LVH) was documented in 237 (68.9%) patients. The basal ganglia was the most common location of the bleed (62.2%). At 90 days, 200 patients (58.1%) had good outcome and 144 (41.9%) had poor outcome with an overall mortality of 75 (21.8%). Independent predictors of poor outcome were poor GCS, larger volume, and high serum creatinine values.

Conclusion

The incidence of SICH among the young accounts for nearly 30% of admitted ICH. Poor outcome and mortality are high with HTN being the single most important modifiable risk factor in the cohort.

Clinical and paraclinical predictors of early neurological deterioration and poor outcome in spontaneous intracerebral hemorrhage

Background

Spontaneous intracerebral hemorrhage (sICH) is the second most common form of stroke. It is a major cause of morbidity and mortality. Several clinical and radiological parameters are related to its poor outcome. The aim of this study is to elucidate the clinical, laboratory, and radiological factors associated with early neurological deterioration and poor outcome in patients with ICH.

Results

seventy patients diagnosed with sICH were evaluated within the first 72 h from the onset of symptoms by Clinical, radiological, and laboratory parameters. Patients were assessed for early neurological deterioration (END) during the hospital stay (up to 7 days from admission) using Glasgow coma scale (GSC), and the National Institutes of Health Stroke Scale (NIHSS), and within 3 months from stroke onset using modified Rankin scale (mRS). ICH score and Functional Outcome in Patients with Primary Intracerebral Hemorrhage (FUNC) Score were calculated for prognostication. 27.1% and 71.42% of patients had END and showed unfavorable outcome, respectively. Clinical indices, as NIHSS > 7 on admission and age > 51 years, radiological characteristics, as large hematoma size, leukoaraiosis, and mass effect detected on CT scan, as well as serum biomarkers; serum urea level > 50 mg/dL, high neutrophil:lymphocyte ratio on admission, high ALT and AST, as well as low total, LDL, and HDL cholesterol levels, all were significantly associated with poor outcome in the patients. Stepwise multivariate logistic regression analysis found the presence of aspiration to be an independent predictor of END, and the scores of NIHSS > 7 on admission, age > 51 years, and urea level > 50 mg/dL were independent predictors of poor outcome.

Conclusions

There are several predictors for END as well as poor outcome in ICH. Some are clinical, others are radiological and laboratory. Aspiration was an independent predictor of END during hospital stay (3-7 days) in patients with ICH, while older age, high NIHSS and urea level on admission were independent predictors of poor outcome.

Predictors of Early Mortality for Mechanically Ventilated Spontaneous Intracerebral Hemorrhage Patients

Introduction

Spontaneous intracerebral hemorrhage (sICH) carries a high mortality burden. Limited data are available on early mortality (EM) and sICH. This study attempted to identify the independent predictors of EM and analyze the mortality characteristics for mechanically ventilated patients with sICHs at a tertiary care hospital over a period of five years.

Methods

An Institutional Review Board (IRB)-approved and Health Insurance Portability and Accountability Act (HIPPA)-compliant retrospective analysis was performed on sICH patients admitted at the University of Mississippi Medical Center Neuroscience Intensive Care Unit between January 1, 2013, to December 31, 2017. Patients were divided into two cohorts: EM cohort (death within seven days of admission) versus survivor cohort (alive more than seven days after admission). Demographic, comorbidity, clinical, and radiographic data were collected for each patient. Outcomes were compared utilizing student t-test or Mann-Whitney U tests for continuous variables. Logistic regression analysis was performed to determine independent predictors of EM.

Results

A total of 204 mechanically ventilated patients with sICHs, with a mean age of 59.73 (SD ±14.30), mostly African American (137, 67%), were included in the study. The characteristics of the two cohorts were comparable except the EM cohort had a lower proportion of patients with hypertension and end-stage renal disease; lower median Glasgow Coma Score (GCS) on admission; lower proportion of surgical evacuation and external ventricular drain (EVD) placement; higher proportion of lobar hemorrhage, brainstem involvement, midline shift, hydrocephalus, intraventricular hemorrhage component, and right-sided intracerebral hemorrhage (ICH); higher median ICH score; and higher ICH volume compared to the survivor cohort.

Overall, the mortality of mechanically ventilated sICH patients in this institution was 53% (N=109), with 47% (N=96) not surviving beyond seven days.

Logistic regression analysis revealed that ICH volume and brainstem involvement increased the odds of EM, while a history of hypertension, surgical evacuation, and EVD placement decreased the odds of EM.

Conclusions

This study on mechanically ventilated sICH patients identified ICH volume and brainstem involvement as independent predictors of increased EM. History of hypertension, EVD placement, and surgical evacuation decreased its odds. Further studies should be conducted to explore potentially modifiable processes that can improve patient outcomes, most importantly EM, especially in this cohort of patients.

The Influence of Oxidative Stress on Neurological Outcomes in Spontaneous Intracerebral Hemorrhage

Spontaneous intracerebral hemorrhage (ICH) causes, besides the primary brain injury, a secondary brain injury (SBI), which is induced, amongst other things, by oxidative stress (OS) and inflammation, determining the patient's outcome. This study aims to assess the impact of OS in plasma and cerebrospinal fluid (CSF) on clinical outcomes in patients with ICH. A total of 19 ICH (volume > 30 cc) patients and 29 control patients were included. From day one until seven, blood and CSF samples were obtained, and ICH volume was calculated. OS markers, like malondialdehyde (MDA), superoxide dismutase (SOD), glutathione peroxidase (GSH-Px), glutathione-sulfhydryl (GSH), and the total antioxidant status (TAS) were measured. Clinical data on treatment and outcome were determined. Patients with mRS ≤ 4 showed significantly elevated SOD and GSH-Px levels in plasma compared to patients with poor CO (p = 0.004; p = 0.002). Initial increased TAS in plasma and increased MDA in CSF were linked to an unfavorable outcome after six months (p = 0.06, r = 0.45; p = 0.05, r = 0.44). A higher ICH volume was associated with a worse outcome at week six (p = 0.04, r = 0.47). OS plays a significant role in SBI. Larger ICHs, elevated MDA in CSF, and TAS in plasma were associated with a detrimental outcome, whereas higher plasma-SOD and -GSH-Px were associated with a favorable outcome.