Predicting Recurrent Hypertensive Intracerebral Hemorrhage: Derivation and Validation of a Risk-Scoring Model Based on Clinical Characteristics

Early decompressive surgery improves long-term prognosis in patients with intracerebral hemorrhage

BACKGROUND

Multiple studies have shown that early decompressive surgery in patients with intracerebral hemorrhage can effectively limit hematoma expansion, reduce perihematomal edema, and improve prognosis. However, these studies are limited by small sample sizes and short follow-up times.

OBJECTIVE

To analyze the effect of early decompressive surgery on the long-term prognosis of patients with cerebral hemorrhage and identify the influencing factors for poor prognosis.

METHODS

A retrospective analysis of 78 patients with cerebral hemorrhage admitted between January 2020 and December 2022 was conducted. Patients were divided into early and delayed surgery groups for comparison of outcomes such as mortality rate, modified Rankin Scale score, and Short Form-36 scores. Additionally, factors influencing long-term prognosis were analyzed through logistic regression based on significant differences observed between groups.

RESULTS

The early decompressive surgery group showed superior outcomes with lower mortality rates, modified Rankin Scale (mRS) scores, hematoma expansion rates, and perihematomal edema volumes compared to the delayed surgery group (P< 0.05). Additionally, age, preoperative Glasgow Coma Scale (GCS) score, preoperative hematoma volume, and a history of hypertension or diabetes were identified as independent prognostic factors for patients with cerebral hemorrhage, with odds ratios (ORs) greater than 1.

CONCLUSIONS

Early decompressive surgery can improve the long-term prognosis and quality of life of patients with cerebral hemorrhage, reduce mortality rates, and decrease hematoma expansion and perihematomal edema. Older patients, those with higher preoperative hematoma volume and GCS score, and those with coexisting hypertension and diabetes should be given special attention to decrease the occurrence of adverse prognosis.

Retrospective analysis of prognostic factors in HICH patients after neuroendoscopic hematoma evacuation

The objective of this study is to investigate key prognostic factors of clinical data and prognostic factors in patients with hypertensive intracerebral hemorrhage (HICH) who have undergone neuroendoscopic hematoma evacuation, specifically focusing on those with a hemorrhage volume of 20-40 mL, to identify the determinants influencing their prognosis. In this study, a total of 113 patients were ultimately included in the analysis. Variables such as age, preoperative Glasgow Coma Scale (GCS) scores, and hemorrhage locations were assessed. LASSO logistic regression was employed to select pertinent variables, which were then incorporated into a multivariate logistic regression model. The model's performance was evaluated using ROC and calibration curves, along with clinical utility curves, and the recovery times of patients were analyzed using Kaplan-Meier curves, complemented by COX regression analysis. These three variables-Age (OR: 0.811; 95% CI 0.711-0.925), GCS score (OR: 25.923; 95% CI 4.108-163.598), and ICH location (OR: 7.345; 95% CI 1.811-29.783)-are strong predictors of intracerebral hemorrhage prognosis. Among the patients analyzed, 85.84% experienced a favorable prognosis. Younger age, higher preoperative GCS scores, and hemorrhages located in the basal ganglia and cerebral lobes were associated with better outcomes (mRS score of 0-3) . The nomogram, validated by an ROC curve analysis yielding an AUC of 0.9417 and the Hosmer-Lemeshow test, demonstrated accurate predictive and calibration capabilities for postoperative prognosis in patients with hypertensive intracerebral hemorrhage. Kaplan-Meier intervals and COX regression analysis indicated that age is a significant factor affecting the recovery time of these patients. Age, GCS score, and ICH location are significant prognostic factors for patients undergoing neuroendoscopic hematoma evacuation following hypertensive intracerebral hemorrhage, with age being a particularly important determinant of recovery time. Younger age, higher GCS scores, and lobar hemorrhage are associated with better prognosis.

Predicting the recurrence of spontaneous intracerebral hemorrhage using a machine learning model

Background

Recurrence can worsen conditions and increase mortality in ICH patients. Predicting the recurrence risk and preventing or treating these patients is a rational strategy to improve outcomes potentially. A machine learning model with improved performance is necessary to predict recurrence.

Methods

We collected data from ICH patients in two hospitals for our retrospective training cohort and prospective testing cohort. The outcome was the recurrence within one year. We constructed logistic regression, support vector machine (SVM), decision trees, Voting Classifier, random forest, and XGBoost models for prediction.

Results

The model included age, NIHSS score at discharge, hematoma volume at admission and discharge, PLT, AST, and CRP levels at admission, use of hypotensive drugs and history of stroke. In internal validation, logistic regression demonstrated an AUC of 0.89 and precision of 0.81, SVM showed an AUC of 0.93 and precision of 0.90, the random forest achieved an AUC of 0.95 and precision of 0.93, and XGBoost scored an AUC of 0.95 and precision of 0.92. In external validation, logistic regression achieved an AUC of 0.81 and precision of 0.79, SVM obtained an AUC of 0.87 and precision of 0.76, the random forest reached an AUC of 0.92 and precision of 0.86, and XGBoost recorded an AUC of 0.93 and precision of 0.91.

Conclusion

The machine learning models performed better in predicting ICH recurrence than traditional statistical models. The XGBoost model demonstrated the best comprehensive performance for predicting ICH recurrence in the external testing cohort.

Predicting postoperative rehemorrhage in hypertensive intracerebral hemorrhage using noncontrast CT radiomics and clinical data with an interpretable machine learning approach

In hypertensive intracerebral hemorrhage (HICH) patients, while emergency surgeries effectively reduce intracranial pressure and hematoma volume, their significant risk of causing postoperative rehemorrhage necessitates early detection and management to improve patient prognosis. This study sought to develop and validate machine learning (ML) models leveraging clinical data and noncontrast CT radiomics to pinpoint patients at risk of postoperative rehemorrhage, equipping clinicians with an early detection tool for prompt intervention. The study conducted a retrospective analysis on 609 HICH patients, dividing them into training and external verification cohorts. These patients were categorized into groups with and without postoperative rehemorrhage. Radiomics features from noncontrast CT images were extracted, standardized, and employed to create several ML models. These models underwent internal validation using both radiomics and clinical data, with the best model's feature significance assessed via the Shapley additive explanations (SHAP) method, then externally validated. In the study of 609 patients, postoperative rehemorrhage rates were similar in the training (18.8%, 80/426) and external verification (17.5%, 32/183) cohorts. Six significant noncontrast CT radiomics features were identified, with the support vector machine (SVM) model outperforming others in both internal and external validations. SHAP analysis highlighted five critical predictors of postoperative rehemorrhage risk, encompassing three radiomics features from noncontrast CT and two clinical data indicators. This study highlights the effectiveness of an SVM model combining radiomics features from noncontrast CT and clinical parameters in predicting postoperative rehemorrhage among HICH patients. This approach enables timely and effective interventions, thereby improving patient outcomes.

Serum vascular endothelial growth factor and cortisol expression to predict prognosis of patients with hypertensive cerebral hemorrhage

BACKGROUND

Cerebral hemorrhage is a common and severe complication of hypertension in middle-aged and elderly men.

AIM

To investigate the correlation between vascular endothelial growth factor (VEGF) and cortisol (Cor) and the prognosis of patients with hypertensive cerebral hemorrhage.

METHODS

A hundred patients with hypertensive intracerebral hemorrhage were enrolled from January 2020 to December 2022 and assigned to the hypertensive intracerebral hemorrhage group. Another 100 healthy people who were examined at our hospital during the same period were selected and assigned to the healthy group. Peripheral venous blood was collected, and serum Cor and VGEF levels were measured through enzyme linked immunosorbent assay.

RESULTS

A statistically significant difference in serum Cor and VGEF levels was observed among patients with varying degrees of neurological impairment (P < 0.05). Serum Cor and VGEF levels were significantly higher in the severe group than in the mild-to-moderate group. Cor and VEGF levels were significantly higher in patients with poor prognoses than in those with good prognoses. Multiple logistic regression analysis revealed that serum Cor and VGEF levels were independent factors affecting hypertensive intracerebral hemorrhage (P < 0.05).

CONCLUSION

Cor and VGEF are associated with the occurrence and development of hypertensive cerebral hemorrhage and are significantly associated with neurological impairment and prognosis of patients.

Constructing and Validating a Nomogram for Survival in Patients without Hypertension in Hypertensive Intracerebral Hemorrhage-Related Locations

OBJECTIVE

We aimed to evaluate the risk factors for patients, who had hypertensive intracerebral hemorrhage (ICH)-specific location hemorrhage without hypertensive history, to elucidate a novel and detailed understanding.

METHODS

We conducted a retrospective review to identify patients diagnosed with hemorrhage in hypertensive ICH-specific locations without hypertensive history between January 2011 and December 2019 from West China Hospital. A least absolute shrinkage and selector operation (LASSO) algorithm was used to select the optimal prognostic factors, and then we performed a multivariable logistic analysis. To verify the accuracy of the nomogram in predicting patient outcome, we used Harrell's statistics, area under the curve, and a calibration as well as decision curves.

RESULTS

The LASSO method, at a tenfold cross-validation for 7-day mortality, 90-day mortality, and 90-day morbidity, was applied to construct the prognosis-predicting models. Both a higher Glasgow Coma Scale (GCS) score at admission and larger hematoma volume ≥13.64 mL were independently associated with better survival at 7 days and 90 days in multivariate analysis. Lactic dehydrogenase >250 IU/L and neutrophilic granulocyte/lymphocyte ratio in 1 increase were significantly associated with poor outcome at 90 days. Only one factor (GCS score at 7 days) influencing 90-day morbidity remained in a LASSO model.

CONCLUSIONS

In this study, the GCS score, hematoma volume, and other laboratory factors (Lactic dehydrogenase and neutrophilic granulocyte/lymphocyte ratio) were related to survival. Our current findings of the specific location ICH need to be proven by a large randomized controlled trial study.

Value of inflammatory mediator profiles and procalcitonin in predicting postoperative infection in patients with hypertensive cerebral hemorrhage

BACKGROUND

Hypertensive cerebral hemorrhage (HICH) is a common clinical cerebrovascular disease and one of the most serious complications of hypertension. Early warning of the occurrence of infection during treatment and timely anti-infective treatment are of great significance for the early prevention and treatment of postoperative infection in patients with HICH. Changes in the levels of inflammatory mediators, which are closely related to the occurrence and development of postoperative infection, and procalcitonin (PCT), which is a sensitive indicator for diagnosing bacterial infections, are widely used in clinical practice.

AIM

To explore the application value of inflammatory mediator profiles and PCT in predicting postoperative infection in patients with HICH.

METHODS

A total of 271 patients who underwent HICH surgery at our hospital between March 2019 and March 2021 were selected and divided into the infection (n = 80) and non-infection (n = 191) groups according to whether postoperative infection occurred. The postoperative infection status and etiological characteristics of the infective pathogens in the infection group were analyzed. Changes in inflammatory mediator profile indices and PCT levels were compared between the two groups, pre- and postoperatively.

RESULTS

A total of 109 strains of pathogenic bacteria were detected in the infection group, including 67 strains (61.47%) of gram-negative bacteria, 32 strains (29.36%) of gram-positive bacteria, and 10 strains (9.17%) of fungi. The main infection site of the patients in the infection group was the respiratory system (63.75%). Preoperative interleukin (IL)-4, IL-6, IL-10, tumor necrosis factor-α, interferon-γ, and PCT levels were higher in the infection group than in the non-infection group (P < 0.05), and there were no significant differences in the IL-2 Levels between the two groups (P > 0.05). The inflammatory mediator profile indices and PCT levels were higher in the two groups of patients on the first postoperative day than preoperatively (P < 0.05), and were higher than those in the non-infection group (P < 0.05). Logistic regression analysis showed that preoperative IL-6 and PCT levels correlated with postoperative infection (P < 0.05). Operating characteristic curve analysis results showed that the area under the curve (AUC) values of preoperative IL-6 and PCT levels in predicting postoperative infection in patients with HICH were 0.755 and 0.824, respectively. The AUC value of joint detection was 0.866, which was significantly higher than that of the single index (P < 0.05).

CONCLUSION

Preoperative IL-6 and PCT levels are correlated with postoperative infection in patients with HICH. Their detection is clinically significant for early identification of patients at high risk for postoperative infection.

Repeated intracerebral hemorrhage after craniotomy for a distal middle cerebral artery aneurysm: A case report

RATIONALE

Distal middle cerebral artery aneurysms are very rare in the clinic, and craniotomy clipping is the better treatment after diagnosis. However, patients can also have repeated acute intracerebral hemorrhage after craniotomy for aneurysm, which has not been previously reported.

PATIENT CONCERNS

A 24-year-old male patient was admitted to our hospital with headache, nausea, and vomiting. He was well before, had no family history of cerebrovascular disease or hypertension, and had no history of trauma.

DIAGNOSES

Computer tomography and digital subtraction angiography of the brain revealed intracranial hematoma and an aneurysm located at the M4 segment of the left middle cerebral artery.

INTERVENTIONS

The patient underwent 2 surgeries to treat the aneurysm, followed by 2 operations for acute cerebral hemorrhage.

OUTCOMES

Despite repeated surgical treatments, the patient had a poor prognosis and eventually died of respiratory and circulatory failure after repeated brain bleeding.

LESSONS

Briefly, it is of great importance to consider the risk factors of cerebral hemorrhage, and provide individualized treatment and psychological counseling for patients with intracerebral hemorrhage.

Analysis of clinical distribution and drug resistance of klebsiella pneumoniae pulmonary infection in patients with hypertensive intra cerebral hemorrhage after minimally invasive surgery

Objectives:

To investigate the clinical distribution and drug resistance of Klebsiella pneumoniae pulmonary infection in patients with hypertensive intracerebral hemorrhage after minimally invasive surgery.

Methods:

A total of 658 patients with hypertensive intracerebral hemorrhage who underwent minimally invasive surgery admitted to the intensive care unit (ICU) and the Department of Neurology of Affiliated Hospital of Hebei University from January 2015 to January 2020 were enrolled and divided into two groups: the observation group and the control group. Three hundred and thirty-three cases with postoperative pulmonary infection were included into the observation group, and 325 cases without postoperative pulmonary infection were divided into the control group. The intubation time, neurological deficiency score and Glasgow coma scale (GCS) of the two groups were analyzed and compared. Automatic microbial identification system was utilized to isolate bacteria from patients in the observation group, identify Klebsiella pneumoniae, and analyze Klebsiella pneumoniae infection, clinical department distribution, and age distribution. The Kirby-Bauer method was adopted to carry out the drug susceptibility test of Klebsiella pneumoniae infection.

Results:

The intubation time and neurological deficiency score of patients with hypertensive cerebral hemorrhage in the observation group were significantly higher than those in the control group (p<0.05), while the GCS score was significantly lower than that in the control group (p<0.05). A total of 403 strains of pathogenic bacteria were isolated from 325 patients in the observation group, of which 52 strains of Klebsiella pneumoniae were detected in 52 patients with postoperative pulmonary infection, accounting for 12.90%. The detection rates of Klebsiella pneumoniae in ICU and neurology department were 53.85% and 46.15%, respectively. Klebsiella pneumoniae had the highest detection rate (40.38%) in people aged 70 years and above. Moreover, fifty-two strains of Klebsiella pneumoniae showed low drug resistance rate (<20%) to cefoperazone/sulbactam, piperacillin/tazobactam, cefoxitin, imipenem, meropenem, amikacin, ciprofloxacin, and levofloxacin.

Conclusion:

For patients with hypertensive cerebral hemorrhage who have pulmonary infection after minimally invasive surgery, risk factors causing infection should be identified in time, their Klebsiella pneumoniae infection should be correctly monitored, and antibiotics should be taken rationally to effectively promote the elimination of brain edema in patients and protect the cranial nerve function of patients.

Blood Pressure Model Based on Hybrid Feature Convolution Neural Network in Promoting Rehabilitation of Patients with Hypertensive Intracerebral Hemorrhage

Objective

Accurate prediction of the rise of blood pressure is essential for the hypertensive intracerebral hemorrhage. This study uses the hybrid feature convolution neural network to establish the blood pressure model instead of the traditional method of pulse waves.

Methods

The pulse waves of 100 patients were collected, and the pulse wave was decomposed into three bell wave compound forms to obtain the accurate pulse wave propagation time. Then, the mixed feature convolution neural network model ABP-net was proposed, which combined the pulse wave propagation time characteristics with the pulse wave waveform characteristics automatically extracted by one-dimensional convolution to predict the arterial blood pressure. Finally, according to the prediction results, 20 patients were treated before the high blood pressure appeared (model group), and another 20 patients with a daily fixed treatment scheme were selected as the control group.

Results

In 80 training sets, compared with linear regression and the random forest method, the hybrid feature convolution neural network has higher accuracy in predicting blood pressure. In 20 test sets, the blood pressure error was eliminated within 5 mmHg. The total effective rate in the model group and the control group was 95.0% and 85.0%, respectively (P = 0.035). After treatment, the scores of self-care ability of daily life and limb motor function in the model group were higher than those in the control group (P < 0.05). There were 8 cases (13.6%) in the model group and 17 cases (28.3%) in the control group due to the recurrence of cerebrovascular accident (P = 0.043).

Conclusion

Drug treatment guided by a blood pressure model based on a hybrid feature convolution neural network for patients with hypertensive cerebral hemorrhage can significantly and smoothly reduce blood pressure, promote the health recovery, and reduce the occurrence of cerebrovascular accidents.

Construction of a nomogram to reveal the prognostic benefit of spontaneous intracranial hemorrhage among Chinese adults: a population-based study

BACKGROUND AND PURPOSE

We aimed to build a nomogram, based on patients with spontaneous intracerebral hemorrhage (SICH), to predict the probability of mortality and morbidity at 7 days and 90 days, respectively.

METHODS

We performed a retrospective study, with patients at less than 6 h from ictus admitted to the department of neurosurgery in a single institute, from January 2011 to December 2018. A total of 1036 patients with SICH were included, 486 patients (46.9%) were 47-66 years old at diagnosis, and 711 patients (68.6%) were male. The least absolute shrinkage and section operator method was performed to identify the key adverse factors predicting the outcomes in patients with SICH, and multivariate logistic regression analysis was built on these variables, and then the results were visualized by a nomogram. The discrimination of the prognostic models was measured and compared by means of Harrell's concordance index (C-index), calibration curve, area under the curve (AUC), and decision curve analysis (DCA).

RESULTS

Multivariate logistic regression analysis revealed that factors affecting 7-day mortality, including the following: age, therapy, Glasgow Coma Scale (GCS) admission, location, ventricle involved, hematoma volume, white blood cell (WBC), uric acid (UA), and L-lactic dehydrogenase (LDH); and factors affecting 90-day mortality, including temperature, therapy, GCS admission, ventricle involved, WBC, international normalized ratio, UA, LDH, and systolic blood pressure. The C-index for the 7-day mortality and 90-day mortality prediction nomogram was 0.9239 (95% CI = 0.9061-0.9416) and 0.9241 (95% CI = 0.9064-0.9418), respectively. The AUC of 7-day mortality was 92.4, as is true of 90-day mortality. The calibration curve and DCA indicated that nomograms in our study had a good prediction ability. For 90-day morbidity, age, marital status, and GCS at 7-day remained statistically significant in multivariate analysis. The C-index for the prediction nomogram was 0.6898 (95% CI = 0.6511-0.7285), and the calibration curve, AUC as well as DCA curve indicated that the nomogram for the prediction of good outcome demonstrated good agreement in this cohort.

CONCLUSIONS

Nomograms in this study revealed many novel prognostic demographic and laboratory factors, and the individualized quantitative risk estimation by this model would be more practical for treatment management and patient counseling.

The risk factors for the postoperative pulmonary infection in patients with hypertensive cerebral hemorrhage: A retrospective analysis

ABSTRACT

The risk factors for the pulmonary infections after hypertensive cerebral hemorrhage remains unclear. We aimed to investigate the potential risk factors for the postoperative pulmonary infection in patients with hypertensive cerebral hemorrhage.Patients with hypertensive cerebral hemorrhage undergone surgery from January 2018 to December 2019 were included. Related personal and medical information were collected. Univariate and multivariate logistic regression analyses were performed to identify the potential risk factors for the postoperative pulmonary infection.A total of 264 patients were included, and the incidence of pulmonary infection for patients with hypertensive cerebral hemorrhage after surgery was 19.70%. Escherichia coli is the most common bacteria of pulmonary infection. Multivariate regression analysis revealed that the preoperative hypoalbuminemia (OR2.89, 1.67∼4.78), tracheotomy (OR5.31, 1.24∼11.79), diabetes (OR4.92, 1.32∼9.80), preoperative GCS (OR5.66, 2.84∼11.21), and the duration of mechanical ventilation (OR2.78, 2.32∼3.61) were the independent risk factors for the pulmonary infection in patients with hypertensive cerebral hemorrhage (all P < .05).Patients with hypertensive intracerebral hemorrhage after surgery have a higher risk of postoperative pulmonary infections, and there are many related risk factors, which should be taken seriously in clinical practice.

Prognostic Significance of Homocysteine Level on Neurological Outcome in Brain Arteriovenous Malformations

Objective

We aimed to investigate the serum homocysteine (Hcy) level in patients with brain arteriovenous malformation (bAVM) and their impact on neurological outcome during hospitalization.

Method

We retrospectively reviewed patients diagnosed with bAVMs in Beijing Tiantan Hospital from January 2019 to August 2020. Patients were divided into two groups according to the mRS (modified Rankin Scale) score at discharge. Clinical and laboratory characteristics were compared. Logistic regression analyses were performed to identify the potential risk factors for short-term neurological outcome.

Results

A total of 175 bAVM patients were enrolled in the study, including 139 patients with favorable outcome (mRS ≤ 2) and 36 patients with unfavorable outcome (mRS > 2). Hyperhomocysteinemia was identified in 32.6% of cases (n = 57). Serum Hcy level was related to seizure manifestation (P = 0.034) and short-term neurological outcome (P = 0.027). Logistic regression analysis showed that serum glucose (OR 1.897, 95% CI 1.115-3.229; P = 0.018) and Hcy level (OR 0.838, 95% CI 0.720-0.976; P = 0.023) were significantly associated with short-term disability.

Conclusion

Our results indicated that the lower serum Hcy level is strongly associated with in-hospital unfavorable outcome. Further prospective studies of Hcy natural history and managements in bAVMs are required, which would be valuable for evaluating the disease-modifying efficacy of oral nutritional supplements in bAVM patients.