Prognostic models for intracerebral hemorrhage: systematic review and meta-analysis

Computational modeling of basal ganglia hemorrhage morphology improves functional outcome prognostication after minimally invasive surgical evacuation

INTRODUCTION

Anatomic factors that predict outcomes following basal ganglia intracranial hemorrhage (bgICH) evacuation are poorly understood. Given the compact neuroanatomic organization of the basal ganglia, we hypothesized that bgICH spatial representation could predict postoperative functional outcomes.

METHODS

Patients undergoing minimally invasive surgical bgICH evacuation between 2013 and 2024 at one center were retrospectively reviewed. bgICH volumes were segmented and stereotactically localized using anatomic landmarks. Heat maps that identified bgICH spatial representation across functional outcome states were generated. Differential bgICH volume overlap with each heat map was calculated after subtracting out that patient's contribution to the map. Area under the receiver operating characteristic curve (AUC) was used to evaluate the diagnostic accuracy of differential volume overlap for poor functional outcome (modified Rankin Scale score of 4-6 within 1 year of surgery) and compared with that of the intracranial hemorrhage (ICH) score with a z test.

RESULTS

Forty-five patients were included (62% men, 7% Caucasian, median age 53 years). Thirty-two patients (71%) had poor functional outcome (median follow-up 4.1 months), which was associated with increased age (P=0.032), bgICH volume (P=0.005), intraventricular hemorrhage severity (P=0.032), National Institutes of Health Stroke Scale (P=0.006), and differential volume overlap (P<0.001). Anatomically, poor outcome was associated with bgICH extension into the anterior limb of the internal capsule (P=0.004), caudate (P=0.042), and temporal lobe (P=0.006). The AUC for differential volume overlap was 0.87 (95% CI: 0.76-0.97), which was higher than chance alone (P<0.001), but statistically similar to that (0.82 (0.71-0.97)) of the ICH score (P=0.545).

CONCLUSION

Stereotactic bgICH localization enabled functional outcome prognostication in patients undergoing minimally invasive surgical evacuation.

Machine Learning-Based Prediction for In-Hospital Mortality After Acute Intracerebral Hemorrhage Using Real-World Clinical and Image Data

BACKGROUND

Machine learning (ML) techniques are widely employed across various domains to achieve accurate predictions. This study assessed the effectiveness of ML in predicting early mortality risk among patients with acute intracerebral hemorrhage (ICH) in real-world settings.

METHODS AND RESULTS

ML-based models were developed to predict in-hospital mortality in 527 patients with ICH using raw brain imaging data from brain computed tomography and clinical data. The models' performances were evaluated using the area under the receiver operating characteristic curves and calibration plots, comparing them with traditional risk scores such as the ICH score and ICH grading scale. Kaplan-Meier curves were used to examine the post-ICH survival rates, stratified by ML-based risk assessment. The net benefit of ML-based models was evaluated using decision curve analysis. The area under the receiver operating characteristic curves were 0.91 (95% CI, 0.86-0.95) for the ICH score, 0.93 (95% CI, 0.89-0.97) for the ICH grading scale, 0.83 (95% CI, 0.71-0.91) for the ML-based model fitted with raw image data only, and 0.87 (95% CI, 0.76-0.93) for the ML-based model fitted using clinical data without specialist expertise. The area under the receiver operating characteristic curve increased significantly to 0.97 (95% CI, 0.94-0.99) when the ML model was fitted using clinical and image data assessed by specialists. All ML-based models demonstrated good calibration, and the survival rates showed significant differences between risk groups. Decision curve analysis indicated the highest net benefit when utilizing the findings assessed by specialists.

CONCLUSIONS

ML-based prediction models exhibit satisfactory performance in predicting post-ICH in-hospital mortality when utilizing raw imaging data or nonspecialist input. Nevertheless, incorporating specialist expertise notably improves performance.

Incorporating platelet-to-white blood cell ratio into survival prediction models for intracerebral hemorrhage: a nomogram approach

Background

Predicting long-term survival in intensive care unit patients with intracerebral hemorrhage (ICH) is crucial. This study aimed to develop a platelet-to-white blood cell ratio (PWR) incorporated nomogram for long-term survival prediction.

Methods

A retrospective analysis was conducted on 1,728 ICH patients in the MIMIC-IV 2.2 database. The independent prognostic value of PWR for 1-year mortality was assessed. A nomogram was developed using LASSO and Cox regression to predict 1-year survival, incorporating PWR and other factors. The performance of the nomogram was evaluated through calibration curves, area under the curve, Delong test, net reclassification index, integrated discrimination improvement, and decision curve analysis.

Results

The nomogram, which included age, weight, Glasgow Coma Scale (GCS) score, mechanical ventilation, glucose, red blood cell (RBC) count, blood urea nitrogen (BUN), and PWR, showed good predictive performance for 1-year survival. The C-index was 0.736 (95% CI = 0.716-0.756) for the training set and 0.766 (95% CI = 0.735-0.797) for the testing set. Higher age and ventilation increased mortality risk, while higher weight, GCS score, RBC count, and PWR decreased risk. The nomogram outperformed conventional scores.

Conclusions

A nomogram incorporating PWR as a prognostic factor accurately predicts long-term survival in ICH patients. However, validation in large-scale multicenter studies and further exploration of biomarkers are needed.

How much of the variance in functional outcome related to intracerebral hemorrhage volume is already apparent in neurological status at admission?

BACKGROUND

Hematoma volume is a major pathophysiological hallmark of acute intracerebral hemorrhage (ICH). We investigated how the variance in functional outcome induced by the ICH volume is explained by neurological deficits at admission using a mediation model.

METHODS

Patients with acute ICH treated in three tertiary stroke centers between January 2010 and April 2019 were retrospectively analyzed. Mediation analysis was performed to investigate the effect of ICH volume (0.8 ml (5% quantile) versus 130.6 ml (95% quantile)) on the risk of unfavorable functional outcome at discharge defined as modified Rankin Score (mRS) ≥ 3 with mediation through National Institutes of Health Stroke Scale (NIHSS) at admission. Multivariable regression was conducted to identify factors related to neurological improvement and deterioration.

RESULTS

Three hundred thirty-eight patients were analyzed. One hundred twenty-one patients (36%) achieved mRS ≤ 3 at discharge. Mediation analysis showed that NIHSS on admission explained 30% [13%; 58%] of the ICH volume-induced variance in functional outcome at smaller ICH volume levels, and 14% [4%; 46%] at larger ICH volume levels. Higher ICH volume at admission and brainstem or intraventricular location of ICH were associated with neurological deterioration, while younger age, normotension, lower ICH volumes, and lobar location of ICH were predictors for neurological improvement.

CONCLUSION

NIHSS at admission reflects 14% of the functional outcome at discharge for larger hematoma volumes and 30% for smaller hematoma volumes. These results underscore the importance of effects not reflected in NIHSS admission for the outcome of ICH patients such as secondary brain injury and early rehabilitation.

The National Institutes of Health Stroke Scale is comparable to the ICH score in predicting outcomes in spontaneous acute intracerebral hemorrhage

Background

Validating the National Institutes of Health NIH Stroke Scale (NIHSS) as a tool to assess deficit severity and prognosis in patients with acute intracerebral hemorrhage would harmonize the assessment of intracerebral hemorrhage (ICH) and acute ischemic stroke (AIS) patients, enable clinical use of a readily implementable and non-imaging dependent prognostic tool, and improve monitoring of ICH care quality in administrative datasets.

Methods

Among randomized trial ICH patients, the relation between NIHSS scores early after Emergency Department arrival and 3-month outcomes of dependency or death (modified Rankin Scale, mRS 3-6) and case fatality was examined. NIHSS predictive performance was compared to a current standard prognostic scale, the intracerebral hemorrhage score (ICH score).

Results

Among the 384 patients, the mean age was 65 (±13), with 66% being male. The median NIHSS score was 16 (interquartile range (IQR) 9-25), the mean initial hematoma volume was 29 mL (±38), and the ICH score median was 1 (IQR 0-2). At 3 months, the mRS had a median of 4 (IQR 2-6), with dependency or death occurring in 70% and case fatality in 26%. The NIHSS and ICH scores were strongly correlated (r = 0.73), and each was strongly correlated with the 90-day mRS (NIHSS, r = 0.61; ICH score, r = 0.62). The NIHSS performed comparably to the ICH score in predicting both dependency or death (c = 0.80 vs. 0.80, p = 0.83) and case fatality (c = 0.78 vs. 0.80, p = 0.29). At threshold values, the NIHSS predicted dependency or death with 74.1% accuracy (NIHSS 17.5) and case fatality with 75.0% accuracy (NIHSS 18.5).

Conclusion

The NIHSS forecasts 3-month functional and case fatality outcomes with accuracy comparable to the ICH Score. Widely documented in routine clinical care and administrative data, the NIHSS can serve as a valuable measure for clinical prognostication, therapy development, and case-mix risk adjustment in ICH patients.Clinical trial registrationClinicaltrials.gov, NCT00059332.

Prognostic biomarkers of intracerebral hemorrhage identified using targeted proteomics and machine learning algorithms

Early prognostication of patient outcomes in intracerebral hemorrhage (ICH) is critical for patient care. We aim to investigate protein biomarkers' role in prognosticating outcomes in ICH patients. We assessed 22 protein biomarkers using targeted proteomics in serum samples obtained from the ICH patient dataset (N = 150). We defined poor outcomes as modified Rankin scale score of 3-6. We incorporated clinical variables and protein biomarkers in regression models and random forest-based machine learning algorithms to predict poor outcomes and mortality. We report Odds Ratio (OR) or Hazard Ratio (HR) with 95% Confidence Interval (CI). We used five-fold cross-validation and bootstrapping for internal validation of prediction models. We included 149 patients for 90-day and 144 patients with ICH for 180-day outcome analyses. In multivariable logistic regression, UCH-L1 (adjusted OR 9.23; 95%CI 2.41-35.33), alpha-2-macroglobulin (aOR 5.57; 95%CI 1.26-24.59), and Serpin-A11 (aOR 9.33; 95%CI 1.09-79.94) were independent predictors of 90-day poor outcome; MMP-2 (aOR 6.32; 95%CI 1.82-21.90) was independent predictor of 180-day poor outcome. In multivariable Cox regression models, IGFBP-3 (aHR 2.08; 95%CI 1.24-3.48) predicted 90-day and MMP-9 (aOR 1.98; 95%CI 1.19-3.32) predicted 180-day mortality. Machine learning identified additional predictors, including haptoglobin for poor outcomes and UCH-L1, APO-C1, and MMP-2 for mortality prediction. Overall, random forest models outperformed regression models for predicting 180-day poor outcomes (AUC 0.89), and 90-day (AUC 0.81) and 180-day mortality (AUC 0.81). Serum biomarkers independently predicted short-term poor outcomes and mortality after ICH. Further research utilizing a multi-omics platform and temporal profiling is needed to explore additional biomarkers and refine predictive models for ICH prognosis.

Outcome Trajectories after Intracerebral Hemorrhage

Spontaneous intracerebral hemorrhage (ICH) is the most morbid of all stroke types with a high early mortality and significant early disability burden. Traditionally, outcome assessments after ICH have mirrored those of acute ischemic stroke, with 3 months post-ICH being considered a standard time point in most clinical trials, observational studies, and clinical practice. At this time point, the majority of ICH survivors remain with moderate to severe functional disability. However, emerging data suggest that recovery after ICH occurs over a more protracted course and requires longer periods of follow-up, with more than 40% of ICH survivors with initial severe disability improving to partial or complete functional independence over 1 year. Multiple other domains of recovery impact ICH survivors including cognition, mood, and health-related quality of life, all of which remain under studied in ICH. To further complicate the picture, the most important driver of mortality after ICH is early withdrawal of life-sustaining therapies, before initiation of treatment and evaluating effects of prolonged supportive care, influenced by early pessimistic prognostication based on baseline severity factors and prognostication biases. Thus, our understanding of the true natural history of ICH recovery remains limited. This review summarizes the existing literature on outcome trajectories in functional and nonfunctional domains, describes limitations in current prognostication practices, and highlights areas of uncertainty that warrant further research.

Establishing reliable selection criteria for performing fibrinolytic therapy in patients with intracerebral haemorrhage based on prognostic tools

OBJECTIVES

Minimally invasive surgery combined with fibrinolytic therapy is a promising treatment option for patients with intracerebral haemorrhage (ICH), but a meticulous patient selection is required, because not every patient benefits from it. The ICH score facilitates a reliable patient selection for fibrinolytic therapy except for ICH-4. This study evaluated whether an additional use of other prognostic tools can overcome this limitation.

MATERIALS AND METHODS

A consecutive ICH patient cohort treated with fibrinolytic therapy between 2010 and 2020 was retrospectively analysed. The following prognostic tools were calculated: APACHE II, ICH-GS, ICH-FUNC, and ICH score. The discrimination power of every score was determined by ROC-analysis. Primary outcome parameters regarding the benefit of fibrinolytic therapy were the in-hospital mortality and a poor outcome defined as modified Rankin scale (mRS) > 4.

RESULTS

A total of 280 patients with a median age of 72 years were included. The mortality rates according to the ICH score were ICH-0 = 0 % (0/0), ICH-1 = 0 % (0/22), ICH-2 = 7.1 % (5/70), ICH-3 = 17.3 % (19/110), ICH-4 = 67.2 % (45/67), ICH-5 = 100 % (11/11). The APACHE II showed the best discrimination power for in-hospital mortality (AUC = 0.87, p < 0.0001) and for poor outcome (AUC = 0.79, p < 0.0001). In the subgroup with ICH-4, APACHE II with a cut-off of 24.5 showed a good discriminating power for in-hospital mortality (AUC = 0.83, p < 0.001) and for poor outcome (AUC = 0.87, p < 0.001).

CONCLUSIONS

An additional application of APACHE II score increases the discriminating power of ICH score 4 enabling a more precise appraisal of in-hospital mortality and of functional outcome, which could support the patient selection for fibrinolytic therapy.

Guidelines for Neuroprognostication in Critically Ill Adults with Intracerebral Hemorrhage

BACKGROUND

The objective of this document is to provide recommendations on the formal reliability of major clinical predictors often associated with intracerebral hemorrhage (ICH) neuroprognostication.

METHODS

A narrative systematic review was completed using the Grading of Recommendations Assessment, Development, and Evaluation methodology and the Population, Intervention, Comparator, Outcome, Timing, Setting questions. Predictors, which included both individual clinical variables and prediction models, were selected based on clinical relevance and attention in the literature. Following construction of the evidence profile and summary of findings, recommendations were based on Grading of Recommendations Assessment, Development, and Evaluation criteria. Good practice statements addressed essential principles of neuroprognostication that could not be framed in the Population, Intervention, Comparator, Outcome, Timing, Setting format.

RESULTS

Six candidate clinical variables and two clinical grading scales (the original ICH score and maximally treated ICH score) were selected for recommendation creation. A total of 347 articles out of 10,751 articles screened met our eligibility criteria. Consensus statements of good practice included deferring neuroprognostication-aside from the most clinically devastated patients-for at least the first 48-72 h of intensive care unit admission; understanding what outcomes would have been most valued by the patient; and counseling of patients and surrogates whose ultimate neurological recovery may occur over a variable period of time. Although many clinical variables and grading scales are associated with ICH poor outcome, no clinical variable alone or sole clinical grading scale was suggested by the panel as currently being reliable by itself for use in counseling patients with ICH and their surrogates, regarding functional outcome at 3 months and beyond or 30-day mortality.

CONCLUSIONS

These guidelines provide recommendations on the formal reliability of predictors of poor outcome in the context of counseling patients with ICH and surrogates and suggest broad principles of neuroprognostication. Clinicians formulating their judgments of prognosis for patients with ICH should avoid anchoring bias based solely on any one clinical variable or published clinical grading scale.

Integrative transcriptomic and network pharmacology analysis reveals the neuroprotective role of BYHWD through enhancing autophagy by inhibiting Ctsb in intracerebral hemorrhage mice

BACKGROUND

In this study, we aimed to combine transcriptomic and network pharmacology to explore the crucial mRNAs and specific regulatory molecules of Buyang Huanwu Decoction (BYHWD) in intracerebral hemorrhage (ICH) treatment.

METHODS

C57BL/6 mice were randomly divided into three groups: sham, ICH, and BYHWD. BYHWD (43.29 g/kg) was administered once a day for 7 days. An equal volume of double-distilled water was used as a control. Behavioural and histopathological experiments were conducted to confirm the neuroprotective effects of BYHWD. Brain tissues were collected for transcriptomic detection. Bioinformatics analysis were performed to illustrate the target gene functions. Network pharmacology was used to predict potential targets for BYHWD. Next, transcriptomic assays were combined with network pharmacology to identify the potential differentially expressed mRNAs. Immunofluorescence staining, real-time polymerase chain reaction, western blotting, and transmission electron microscopy were performed to elucidate the underlying mechanisms.

RESULTS

BYHWD intervention in ICH reduced neurological deficits. Network pharmacology analysis identified 203 potential therapeutic targets for ICH, whereas transcriptomic assay revealed 109 differentially expressed mRNAs post-ICH. Among these, cathepsin B, ATP binding cassette subfamily B member 1, toll-like receptor 4, chemokine (C-C motif) ligand 12, and baculoviral IAP repeat-containing 5 were identified as potential target mRNAs through the integration of transcriptomics and network pharmacology approaches. Bioinformatics analysis suggested that the beneficial effects of BYHWD in ICH may be associated with apoptosis, animal autophagy signal pathways, and PI3K-Akt and mTOR biological processes. Furthermore, BYHWD intervention decreased Ctsb expression levels and increased autophagy levels in ICH.

CONCLUSIONS

Animal experiments in combination with bioinformatics analysis confirmed that BYHWD plays a neuroprotective role in ICH by regulating Ctsb to enhance autophagy.

Clinical narratives as a predictor for prognosticating functional outcomes after intracerebral hemorrhage

BACKGROUND

Intracerebral hemorrhage (ICH) is a devastating stroke type that causes high mortality rates and severe disability among survivors. Many prognostic models are available for prognosticating patients with ICH. This study aimed to investigate whether clinical narratives can improve the performance for predicting functional outcomes after ICH.

METHODS

This study used data from the hospital stroke registry and electronic health records. The study population (n = 1363) was randomly divided into a training set (75%, n = 1023) and a holdout test set (25%, n = 340). Five risk scores for ICH were used as baseline prognostic models. Using natural language processing (NLP), text-based markers were generated from the clinical narratives of the training set through machine learning (ML) and deep learning (DL) approaches. The primary outcome was a poor functional outcome (modified Rankin Scale score of 3 to 6) at hospital discharge. The predictive performance was compared between the baseline models and models enhanced by incorporating the text-based markers using the holdout test set.

RESULTS

The enhanced prognostic models outperformed the baseline models, regardless of whether ML or DL approaches were used. The areas under the receiver operating characteristic curve (AUCs) of the baseline models were between 0.760 and 0.892. Adding the text-based marker to the baseline models significantly increased the model discrimination, with AUCs ranging from 0.861 to 0.914. The net reclassification improvement and integrated discrimination improvement indices also showed significant improvements.

CONCLUSIONS

Using NLP to extract textual information from clinical narratives could improve the predictive performance of all baseline prognostic models for ICH.

Development and validation of a random forest model to predict functional outcome in patients with intracerebral hemorrhage

OBJECTIVE

To develop and validate a machine learning (ML)-based model to predict functional outcome in Chinese patients with intracerebral hemorrhage (ICH).

METHODS

This retrospective cohort study enrolled patients with ICH between November 2017 and November 2020. The follow-up period ended in February 2021. The study population was divided into training and testing sets with a ratio of 7:3. All variables were included in the least absolute shrinkage and selection operator (LASSO) regression for feature selection. The selected variables were incorporated into the random forest algorithm to construct the prediction model. The predictive performance of the model was evaluated via the area under the curve (AUC), accuracy, sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and calibration curve.

RESULTS

A total of 412 ICH patients were included, with 288 in the training set, and 124 in the testing set. Twelve attributes were selected: neurological deterioration, Glasgow Coma Scale (GCS) score at 24 h, baseline GCS score, time from onset to the emergency room, blood glucose, diastolic blood pressure (DBP) change in 24 h, hematoma volume change in 24 h, systemic immune-inflammatory index (SII), systolic blood pressure (SBP) change in 24 h, serum creatinine, serum sodium, and age. In the testing set, the accuracy, AUC, sensitivity, specificity, PPV, and NPV of the model were 0.895, 0.964, 0.872, 0.906, 0.810, and 0.939, respectively. The calibration curves showed a good calibration capability of the model.

CONCLUSION

This developed random forest model performed well in predicting 3-month poor functional outcome for Chinese ICH patients.

Prognostic Neuroimaging Biomarkers in Acute Vascular Brain Injury and Traumatic Brain Injury

Prognostic imaging biomarkers after acute brain injury inform treatment decisions, track the progression of intracranial injury, and can be used in shared decision-making processes with families. Herein, key established biomarkers and prognostic scoring systems are surveyed in the literature, and their applications in clinical practice and clinical trials are discussed. Biomarkers in acute ischemic stroke include computed tomography (CT) hypodensity scoring, diffusion-weighted lesion volume, and core infarct size on perfusion imaging. Intracerebral hemorrhage biomarkers include hemorrhage volume, expansion, and location. Aneurysmal subarachnoid biomarkers include hemorrhage grading, presence of diffusion-restricting lesions, and acute hydrocephalus. Traumatic brain injury CT scoring systems, contusion expansion, and diffuse axonal injury grading are reviewed. Emerging biomarkers including white matter disease scoring, diffusion tensor imaging, and the automated calculation of scoring systems and volumetrics are discussed.

Increased serum fibroblast growth factor 21 levels are associated with adverse clinical outcomes after intracerebral hemorrhage

Introduction

Intracerebral hemorrhage (ICH) is the most prevalent cause of death. We sought to explore whether serum Fibroblast growth factor 21 (FGF21) is of substantial benefit in predicting poor prognosis in ICH patient.

Methods

A prospective, multicenter cohort analysis of serum FGF21 levels in 418 ICH patients was carried out. At three months following ICH start, the primary endpoint was death or major disability, whereas the secondary endpoint was death. We investigated the association between serum FGF21 and clinical outcomes. We added FGF21 to the existing rating scale to assess whether it enhanced the prediction ability of the original model. Effectiveness was determined by calculating the C-statistic, net reclassification index (NRI), absolute integrated discrimination improvement (IDI) index.

Results

Among 418 enrolled patients, 217 (51.9%) of the all subjects had death or significant disability. Compared with patients in the lowest quartile group, those in the first quartile group had higher risk of the primary outcome (Odds ratio, 2.73 [95%CI,1.42-5.26, p < 0.05]) and second outcome (Hazard ratio, 4.28 [95%CI,1.61-11.42, p < 0.001]). The integration of FGF21 into many current ICH scales improved the discrimination and calibration quality for the integrated discrimination index's prediction of main and secondary findings (all p < 0.05).

Conclusion

Elevated serum FGF21 is associated with increased risks of adverse clinical outcomes at 3 months in ICH patients, suggesting FGF21 may be a valuable prognostic factor.

Early mobilisation is associated with lower subacute blood pressure and variability in ICH: A retrospective cohort study✰

BACKGROUND

Very early rehabilitation after stroke appears to worsen outcome, particularly in intracerebral haemorrhage (ICH). Plausible mechanisms include increased mean blood pressure (BP) and BP variability.

AIMS

To test associations between early mobilisation, subacute BP and survival, in observational data of ICH patients during routine clinical care.

METHODS

We collected demographic, clinical and imaging data from 1372 consecutive spontaneous ICH patients admitted between 2 June 2013 and 28 September 2018. Time to first mobilisation (defined as walking, standing, or sitting out-of-bed) was extracted from electronic records. We evaluated associations between early mobilisation (within 24 h of onset) and both subacute BP and death by 30 days using multifactorial linear and logistic regression analyses respectively.

RESULTS

Mobilisation at 24 h was not associated with increased odds of death by 30 days when adjusting for key prognostic factors (OR 0.4, 95% CI 0.2 to 1.1, p = 0.07). Mobilisation at 24 h was independently associated with both lower mean systolic BP (-4.5 mmHg, 95% CI -7.5 to -1.5 mmHg, p = 0.003) and lower diastolic BP variability (-1.3 mmHg, 95% CI -2.4 to -0.2 mg, p = 0.02) during the first 72 h after admission.

CONCLUSIONS

Adjusted analysis in this observational dataset did not find an association between early mobilisation and death by 30 days. We found early mobilisation at 24 h to be independently associated with lower mean systolic BP and lower diastolic BP variability over 72 h. Further work is needed to establish mechanisms for the possible detrimental effect of early mobilisation in ICH.

Prediction of poor outcome in stroke patients using radiomics analysis of intraparenchymal and intraventricular hemorrhage and clinical factors

PURPOSE

To build three prognostic models using radiomics analysis of the hemorrhagic lesions, clinical variables, and their combination, to predict the outcome of stroke patients with spontaneous intracerebral hemorrhage (sICH).

MATERIALS AND METHODS

Eighty-three sICH patients were included. Among them, 40 patients (48.2%) had poor prognosis with modified Rankin scale (mRS) of 5 and 6 at discharge, and the prognostic model was built to differentiate mRS ≤ 4 vs. 5 + 6. The region of interest (ROI) of intraparenchymal hemorrhage (IPH) and intraventricular hemorrhage (IVH) were separately segmented. Features were extracted using PyRadiomics, and the support vector machine was applied to select features and build radiomics models based on IPH and IPH + IVH. The clinical models were built using multivariate logistic regression, and then the radiomics scores were combined with clinical variables to build the combined model.

RESULTS

When using IPH, the AUC for radiomics, clinical, and combined model was 0.78, 0.82, and 0.87, respectively. When using IPH + IVH, the AUC was increased to 0.80, 0.84, and 0.90, respectively. The combined model had a significantly improved AUC compared to the radiomics by DeLong test. A clinical prognostic model based on the ICH score of 0-1 only achieved AUC of 0.71.

CONCLUSIONS

The combined model using the radiomics score derived from IPH + IVH and the clinical factors could achieve a high accuracy in prediction of sICH patients with poor outcome, which may be used to assist in making the decision about the optimal care.

A nomogram predictive model for long-term survival in spontaneous intracerebral hemorrhage patients without cerebral herniation at admission

Stratification of spontaneous intracerebral hemorrhage (sICH) patients without cerebral herniation at admission, to determine the subgroups may be suffered from poor outcomes or benefit from surgery, is important for following treatment decision. The aim of this study was to establish and verify a de novo nomogram predictive model for long-term survival in sICH patients without cerebral herniation at admission. This study recruited sICH patients from our prospectively maintained ICH patient database (RIS-MIS-ICH, ClinicalTrials.gov Identifier: NCT03862729) between January 2015 and October 2019. All eligible patients were randomly classified into a training cohort and a validation cohort according to the ratio of 7:3. The baseline variables and long-term survival outcomes were collected. And the long-term survival information of all the enrolled sICH patients, including the occurrence of death and overall survival. Follow-up time was defined as the time from the onset to death of the patient or the last clinical visit. The nomogram predictive model was established based on the independent risk factors at admission for long-term survival after hemorrhage. The concordance index (C-index) and ROC curve were used to evaluate the accuracy of the predictive model. Discrimination and calibration were used to validate the nomogram in both the training cohort and the validation cohort. A total of 692 eligible sICH patients were enrolled. During the average follow-up time of 41.77 ± 0.85 months, a total of 178 (25.7%) patients died. The Cox Proportional Hazard Models showed that age (HR 1.055, 95% CI 1.038-1.071, P < 0.001), Glasgow Coma Scale (GCS) at admission (HR 2.496, 95% CI 2.014-3.093, P < 0.001) and hydrocephalus caused by intraventricular hemorrhage (IVH) (HR 1.955, 95% CI 1.362-2.806, P < 0.001) were independent risk factors. The C index of the admission model was 0.76 and 0.78 in the training cohort and validation cohort, respectively. In the ROC analysis, the AUC was 0.80 (95% CI 0.75-0.85) in the training cohort and was 0.80 (95% CI 0.72-0.88) in the validation cohort. SICH patients with admission nomogram scores greater than 87.75 were at high risk of short survival time. For sICH patients without cerebral herniation at admission, our de novo nomogram model based on age, GCS and hydrocephalus on CT may be useful to stratify the long-term survival outcomes and provide suggestions for treatment decision-making.

Artificial intelligence and its impact on the domains of universal health coverage, health emergencies and health promotion: An overview of systematic reviews

BACKGROUND

Artificial intelligence is fueling a new revolution in medicine and in the healthcare sector. Despite the growing evidence on the benefits of artificial intelligence there are several aspects that limit the measure of its impact in people's health. It is necessary to assess the current status on the application of AI towards the improvement of people's health in the domains defined by WHO's Thirteenth General Programme of Work (GPW13) and the European Programme of Work (EPW), to inform about trends, gaps, opportunities, and challenges.

OBJECTIVE

To perform a systematic overview of systematic reviews on the application of artificial intelligence in the people's health domains as defined in the GPW13 and provide a comprehensive and updated map on the application specialties of artificial intelligence in terms of methodologies, algorithms, data sources, outcomes, predictors, performance, and methodological quality.

METHODS

A systematic search in MEDLINE, EMBASE, Cochrane and IEEEXplore was conducted between January 2015 and June 2021 to collect systematic reviews using a combination of keywords related to the domains of universal health coverage, health emergencies protection, and better health and wellbeing as defined by the WHO's PGW13 and EPW. Eligibility criteria was based on methodological quality and the inclusion of practical implementation of artificial intelligence. Records were classified and labeled using ICD-11 categories into the domains of the GPW13. Descriptors related to the area of implementation, type of modeling, data entities, outcomes and implementation on care delivery were extracted using a structured form and methodological aspects of the included reviews studies was assessed using the AMSTAR checklist.

RESULTS

The search strategy resulted in the screening of 815 systematic reviews from which 203 were assessed for eligibility and 129 were included in the review. The most predominant domain for artificial intelligence applications was Universal Health Coverage (N = 98) followed by Health Emergencies (N = 16) and Better Health and Wellbeing (N = 15). Neoplasms area on Universal Health Coverage was the disease area featuring most of the applications (21.7 %, N = 28). The reviews featured analytics primarily over both public and private data sources (67.44 %, N = 87). The most used type of data was medical imaging (31.8 %, N = 41) and predictors based on regions of interest and clinical data. The most prominent subdomain of Artificial Intelligence was Machine Learning (43.4 %, N = 56), in which Support Vector Machine method was predominant (20.9 %, N = 27). Regarding the purpose, the application of Artificial Intelligence I is focused on the prediction of the diseases (36.4 %, N = 47). With respect to the validation, more than a half of the reviews (54.3 %, N = 70) did not report a validation procedure and, whenever available, the main performance indicator was the accuracy (28.7 %, N = 37). According to the methodological quality assessment, a third of the reviews (34.9 %, N = 45) implemented methods for analysis the risk of bias and the overall AMSTAR score below was 5 (4.01 ± 1.93) on all the included systematic reviews.

CONCLUSION

Artificial intelligence is being used for disease modelling, diagnose, classification and prediction in the three domains of GPW13. However, the evidence is often limited to laboratory and the level of adoption is largely unbalanced between ICD-11 categoriesand diseases. Data availability is a determinant factor on the developmental stage of artificial intelligence applications. Most of the reviewed studies show a poor methodological quality and are at high risk of bias, which limits the reproducibility of the results and the reliability of translating these applications to real clinical scenarios. The analyzed papers show results only in laboratory and testing scenarios and not in clinical trials nor case studies, limiting the supporting evidence to transfer artificial intelligence to actual care delivery.

Prognostic value of glycemic gap in patients with spontaneous intracerebral hemorrhage

BACKGROUND

Glycemic gap (GG), as a novel biomarker showing the acute glycemic change after the onset of acute illness, has been found to be associated with adverse outcomes in many diseases. This study aimed to explore the prognostic value of GG on long-term outcomes of spontaneous intracerebral hemorrhage (sICH).

METHODS

The current study included 528 patients from a multi-center, prospective, consecutive, observational cohort study. Poor clinical outcome was defined as the modified Rankin Scale ≥ 3. GG was calculated using admission blood glucose minus hemoglobin A1c-derived average blood glucose. Logistic regression analyses were performed to determine the association between GG and poor clinical outcomes at 30-day, 90-day and 1-year.

RESULTS

GG was significantly associated with poor clinical outcomes at 30-day, 90-day, and 1-year (P < 0.05 for all models), where patients with higher GG were more likely to have poor clinical outcome. Restricted cubic splines revealed a positive association between GG and poor clinical outcome. In addition, patients with higher GG were more likely to have a higher 1-year mortality rate. The addition of GG to the intracerebral hemorrhage score improved the discrimination and calibration properties for the prediction of poor clinical outcome.

CONCLUSIONS

GG was independently associated with poor outcomes and may be a valuable prognostic factor in patients with sICH.

Identification and Validation of a Novel Nomogram Predicting 7-day Death in Patients with Intracerebral Hemorrhage

Background:

Intracerebral hemorrhage (ICH) is a serious brain condition with high mortality and disability rates. In recent decades, several risk factors related to death risk have been identified, with several models predicting mortality, but rarely used and accepted in daily clinical practice.

Aims:

To establish and validate a predictive nomogram of spontaneous ICH death that can be used to predict patient death within 7 days.

Study Design:

Cohort study.

Methods:

A cohort of 449 patients with ICH, diagnosed clinically from January 2015 to December 2017, were identified as the model training cohort. Univariate analysis and least absolute contraction and selection operator (Lasso) regression were used to determine the most powerful predictors of patients with ICH. Discrimination, calibration, and clinical applicability were used to assess the function of the new nomogram. In external validation, we also evaluated the nomogram in another 148 subjects (validation cohort) examined between January and December 2018.

Results:

We observed no significant differences in patient baseline characteristics in the training and validation cohorts, including sex, age, Glasgow coma scale (GCS) score, and one-week mortality rates. The model included three predictive variables from univariate and multivariate analysis, including GCS scores, hematoma volume, and brainstem hemorrhage (BSH). Internal validation revealed that the nomogram had a good discrimination, the area under the receiver operating characteristic curve (AUC) was 0.935, and calibration was good (U = -0.004, P = 0.801). Similarly, this nomogram also showed good differentiation ability (AUC = 0.925) and good accuracy (U = -0.007, P = 0.241) in the validation cohort data. Decision curve analysis indicated that the new prediction model was helpful.

Conclusion:

At the early stages of the condition, our prediction model accurately predicts the death of patients with ICH.

Hyperacute prediction of functional outcome in spontaneous intracerebral haemorrhage: systematic review and meta-analysis

Purpose

To describe the association between factors routinely available in hyperacute care of spontaneous intracerebral haemorrhage (ICH) patients and functional outcome.

Methods

We searched Medline, Embase and CINAHL in February 2020 for original studies reporting associations between markers available within six hours of arrival in hospital and modified Rankin Scale (mRS) at least 6 weeks post-ICH. A random-effects meta-analysis was performed where three or more studies were included.

Findings

Thirty studies were included describing 40 markers. Ten markers underwent meta-analysis and age (OR = 1.06; 95%CI = 1.05 to 1.06; p < 0.001), pre-morbid dependence (mRS, OR = 1.73; 95%CI = 1.52 to 1.96; p < 0.001), level of consciousness (Glasgow Coma Scale, OR = 0.82; 95%CI = 0.76 to 0.88; p < 0.001), stroke severity (National Institutes of Health Stroke Scale, OR=1.19; 95%CI = 1.13 to 1.25; p < 0.001), haematoma volume (OR = 1.12; 95%CI=1.07 to 1.16; p < 0.001), intraventricular haemorrhage (OR = 2.05; 95%CI = 1.68 to 2.51; p < 0.001) and deep (vs. lobar) location (OR = 2.64; 95%CI = 1.65 to 4.24; p < 0.001) were predictive of outcome but systolic blood pressure, CT hypodensities and infratentorial location were not. Of the remaining markers, sex, medical history (diabetes, hypertension, prior stroke), prior statin, prior antiplatelet, admission blood results (glucose, cholesterol, estimated glomerular filtration rate) and other imaging features (midline shift, spot sign, sedimentation level, irregular haematoma shape, ultraearly haematoma growth, Graeb score and onset to CT time) were associated with outcome.

Conclusion

Multiple demographic, pre-morbid, clinical, imaging and laboratory factors should all be considered when prognosticating in hyperacute ICH. Incorporating these in to accurate and precise models will help to ensure appropriate levels of care for individual patients.

Machine Learning-Based Approaches for Prediction of Patients’ Functional Outcome and Mortality after Spontaneous Intracerebral Hemorrhage

Spontaneous intracerebral hemorrhage (SICH) has been common in China with high morbidity and mortality rates. This study aims to develop a machine learning (ML)-based predictive model for the 90-day evaluation after SICH. We retrospectively reviewed 751 patients with SICH diagnosis and analyzed clinical, radiographic, and laboratory data. A modified Rankin scale (mRS) of 0–2 was defined as a favorable functional outcome, while an mRS of 3–6 was defined as an unfavorable functional outcome. We evaluated 90-day functional outcome and mortality to develop six ML-based predictive models and compared their efficacy with a traditional risk stratification scale, the intracerebral hemorrhage (ICH) score. The predictive performance was evaluated by the areas under the receiver operating characteristic curves (AUC). A total of 553 patients (73.6%) reached the functional outcome at the 3rd month, with the 90-day mortality rate of 10.2%. Logistic regression (LR) and logistic regression CV (LRCV) showed the best predictive performance for functional outcome (AUC = 0.890 and 0.887, respectively), and category boosting presented the best predictive performance for the mortality (AUC = 0.841). Therefore, ML might be of potential assistance in the prediction of the prognosis of SICH.

Location-Specific Radiomics Score: Novel Imaging Marker for Predicting Poor Outcome of Deep and Lobar Spontaneous Intracerebral Hemorrhage

Objective: To derive and validate a location-specific radiomics score (Rad-score) based on noncontrast computed tomography for predicting poor deep and lobar spontaneous intracerebral hemorrhage (SICH) outcome.

Methods: In total, 494 SICH patients from multiple centers were retrospectively reviewed. Poor outcome was considered mRS 3–6 at 6 months. The Rad-score was derived using optimal radiomics features. The optimal location-specific Rad-score cut-offs for poor deep and lobar SICH outcomes were identified using receiver operating characteristic curve analysis. Univariable and multivariable analyses were used to determine independent poor outcome predictors. The combined models for deep and lobar SICH were constructed using independent predictors of poor outcomes, including dichotomized Rad-score in the derivation cohort, which was validated in the validation cohort.

Results: Of 494 SICH patients, 392 (79%) had deep SICH, and 373 (76%) had poor outcomes. The Glasgow Coma Scale score, haematoma enlargement, haematoma location, haematoma volume and Rad-score were independent predictors of poor outcomes (all P < 0.05). Cut-offs of Rad-score, 82.90 (AUC = 0.794) in deep SICH and 80.77 (AUC = 0.823) in lobar SICH, were identified for predicting poor outcomes. For deep SICH, the AUCs of the combined model were 0.856 and 0.831 in the derivation and validation cohorts, respectively. For lobar SICH, the combined model AUCs were 0.866 and 0.843 in the derivation and validation cohorts, respectively.

Conclusion: Location-specific Rad-scores and combined models can identify subjects at high risk of poor deep and lobar SICH outcomes, which could improve clinical trial design by screening target patients.

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.

Methodological quality of multivariate prognostic models for intracranial haemorrhages in intensive care units: a systematic review

OBJECTIVES

Patients with severe spontaneous intracranial haemorrhages, managed in intensive care units, face ethical issues regarding the difficulty of anticipating their recovery. Prognostic tools help clinicians in counselling patients and relatives and guide therapeutic decisions. We aimed to methodologically assess prognostic tools for functional outcomes in severe spontaneous intracranial haemorrhages.

DATA SOURCES

Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses recommendations, we conducted a systematic review querying Medline, Embase, Web of Science, and the Cochrane in January 2020.

STUDY SELECTION

We included development or validation of multivariate prognostic models for severe intracerebral or subarachnoid haemorrhage.

DATA EXTRACTION

We evaluated the articles following the CHecklist for critical Appraisal and data extraction for systematic Reviews of prediction Modelling Studies and Transparent Reporting of multivariable prediction model for Individual Prognosis Or Diagnosis statements to assess the tools' methodological reporting.

RESULTS

Of the 6149 references retrieved, we identified 85 articles eligible. We discarded 43 articles due to the absence of prognostic performance or predictor selection. Among the 42 articles included, 22 did not validate models, 6 developed and validated models and 14 only externally validated models. When adding 11 articles comparing developed models to existing ones, 25 articles externally validated models. We identified methodological pitfalls, notably the lack of adequate validations or insufficient performance levels. We finally retained three scores predicting mortality and unfavourable outcomes: the IntraCerebral Haemorrhages (ICH) score and the max-ICH score for intracerebral haemorrhages, the SubArachnoid Haemorrhage International Trialists score for subarachnoid haemorrhages.

CONCLUSIONS

Although prognostic studies on intracranial haemorrhages abound in the literature, they lack methodological robustness or show incomplete reporting. Rather than developing new scores, future authors should focus on externally validating and updating existing scores with large and recent cohorts.

Effect of Tongfu Xingshen capsule on the endogenous neural stem cells of experimental rats with intracerebral hemorrhage

Intracerebral hemorrhage (ICH) can stimulate neural regeneration, promoting tissue repair and recovery of nerve function. Tongfu Xingshen capsule (TXC) is a Chinese medicinal formula used to treat ICH and has been shown to protect brain tissue and improve nerve function in clinical studies. However, the effect of TXC on endogenous neural stem cells (NSCs) remains elusive. To explore the mechanisms underlying TXC action, a rat model of ICH was established. The effects of TXC on the proliferation and differentiation of NSCs were assessed in the subventricular zone (SVZ). TXC significantly improved nerve function defects, decreased brain water content and restored blood‑brain barrier integrity. Additionally, BrdU labeling showed that both high and low doses of TXC significantly increased the proportion of actively cycling NSCs positive for Nestin and glial fibrillary acidic protein, but did not affect the proliferation rates of NeuN‑positive neurons. Finally, TXC also upregulated the mRNA levels of brain‑derived neurotrophic factor and its receptor, TrκB, in affected brain tissues. Taken together, TXC accelerated neural repair and functional recovery after brain injury by potentially enhancing the proliferation and differentiation of endogenous NSCs into astroglial cells in the SVZ area.

Head-to-head comparison of prognostic models of spontaneous intracerebral hemorrhage: tools for personalized care and clinical trial in ICH

To systematically compare 27 ICH models with regard to mortality and functional outcome at 1-month, 3-month and 1-year after ICH. The validation cohort was derived from the Beijing Registration of Intracerebral Hemorrhage. Poor functional outcome was defined as modified Rankin Scale score (mRS) ≥3 at 1-month, 3-month and 1-year after ICH, respectively. The area under the receiver operating characteristic curve (AUROC) and Hosmer-Lemeshow goodness-of-fit test were used to assess model discrimination and calibration. A total number of 1575 patients were included. The mean age was 57.2 ± 14.3 and 67.2% were male. The median NIHSS score on admission was 11 (IQR: 3-21). For predicting mortality at 3-month after ICH, AUROC of 27 ICH models ranged from 0.604 to 0.856. In pairwise comparison, the ICH-FOS (0.856, 95%CI = 0.835-0.878, P < 0.001) showed statistically better discrimination than other models for mortality at 3-month after ICH (all P < 0.05). For predicting poor functional outcome (mRS≥3) at 3-month after ICH, AUROC of 27 ICH models ranged from 0.602 to 0.880. In pairwise comparison with other prediction models, the ICH-FOS was superior in predicting poor functional outcome at 3-month after ICH (all P < 0.001). The ICH-FOS showed the largest Cox and Snell R-square. Similar results were verified for mortality and poor functional outcome at 1-month and 1-year after ICH. Several risk models are externally validated to be effective for risk stratification and outcome prediction after ICH, especially the ICH-FOS, which would be useful tools for personalized care and clinical trial in ICH.

Variation in medical management and neurosurgical treatment of patients with supratentorial spontaneous intracerebral haemorrhage

Introduction

The role of surgery in spontaneous intracerebral haemorrhage (sICH) remains controversial. This leads to variation in the percentage of patients who are treated with surgery between countries.

Patients and methods

We sent an online survey to all neurosurgeons (n = 140) and to a sample of neurologists (n = 378) in Dutch hospitals, with questions on management in supratentorial sICH in general, and on treatment in six patients, to explore current variation in medical and neurosurgical management. We assessed patient and haemorrhage characteristics influencing treatment decisions.

Results

Twenty-nine (21%) neurosurgeons and 92 (24%) neurologists responded. Prior to surgery, neurosurgeons would more frequently administer platelet-transfusion in patients on clopidogrel (64% versus 13%; p = 0.000) or acetylsalicylic acid (61% versus 11%; p = 0.000) than neurologists. In the cases, neurosurgeons and neurologists were similar in their choice for surgery as initial treatment (24% and 31%; p = 0.12), however variation existed amongst physicians in specific cases. Neurosurgeons preferred craniotomy with haematoma evacuation (74%) above minimally-invasive techniques (5%). Age, Glasgow Coma Scale score and ICH location were important factors influencing decisions on treatment for neurosurgeons and neurologists. 69% of neurosurgeons and 80% of neurologists would randomise patients in a trial evaluating the effect of minimally-invasive surgery on functional outcome.

Discussion

Our results reflect the lack of evidence about the right treatment strategy in patients with sICH.

Conclusion

New high quality evidence is needed to guide treatment decisions for patients with ICH. The willingness to randomise patients into a clinical trial on minimally-invasive surgery, contributes to the feasibility of such studies in the future.

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.

Prognostication after intracerebral hemorrhage: a review

Background

Approximately half of patients with spontaneous intracerebral hemorrhage (ICH) die within 1 year. Prognostication in this context is of great importance, to guide goals of care discussions, clinical decision-making, and risk stratification. However, available prognostic scores are hardly used in clinical practice. The purpose of this review article is to identify existing outcome prediction scores for spontaneous intracerebral hemorrhage (ICH) discuss their shortcomings, and to suggest how to create and validate more useful scores.

Main text

Through a literature review this article identifies existing ICH outcome prediction models. Using the Essen-ICH-score as an example, we demonstrate a complete score validation including discrimination, calibration and net benefit calculations. Score performance is illustrated in the Erlangen UKER-ICH-cohort (NCT03183167). We identified 19 prediction scores, half of which used mortality as endpoint, the remainder used disability, typically the dichotomized modified Rankin score assessed at variable time points after the index ICH. Complete score validation by our criteria was only available for the max-ICH score. Our validation of the Essen-ICH-score regarding prediction of unfavorable outcome showed good discrimination (area under the curve 0.87), fair calibration (calibration intercept 1.0, slope 0.84), and an overall net benefit of using the score as a decision tool. We discuss methodological pitfalls of prediction scores, e.g. the withdrawal of care (WOC) bias, physiological predictor variables that are often neglected by authors of clinical scores, and incomplete score validation. Future scores need to integrate new predictor variables, patient-reported outcome measures, and reduce the WOC bias. Validation needs to be standardized and thorough. Lastly, we discuss the integration of current ICH scoring systems in clinical practice with the awareness of their shortcomings.

Conclusion

Presently available prognostic scores for ICH do not fulfill essential quality standards. Novel prognostic scores need to be developed to inform the design of research studies and improve clinical care in patients with ICH.

Supplementary Information

The online version contains supplementary material available at 10.1186/s42466-021-00120-5.

Cerebral Small Vessel Disease Load Predicts Functional Outcome and Stroke Recurrence After Intracerebral Hemorrhage: A Median Follow-Up of 5 Years

Background: Uncertainty exists over the long-term prognostic significance of cerebral small vessel disease (CSVD) in primary intracerebral hemorrhage (ICH).

Methods: We performed a longitudinal analysis of CSVD and clinical outcomes in consecutive patients with primary ICH who had MRI. Baseline CSVD load (including white matter hyperintensities [WMH], cerebral microbleeds [CMBs], lacunes, and enlarged perivascular spaces [EPVS]) was evaluated. The cumulative CSVD score was calculated by combining the presence of each CSVD marker (range 0–4). We followed participants for poor functional outcome [modified Rankin scale [mRS] ≥ 4], stroke recurrence, and time-varying survival during a median follow-up of 4.9 [interquartile range [IQR] 3.1–6.0] years. Parsimonious and fuller multivariable logistic regression analysis and Cox-regression analysis were performed to estimate the association of CSVD markers, individually and collectively, with each outcome.

Results: A total of 153 patients were included in the analyses. CMBs ≥ 10 [adjusted OR [adOR] 3.252, 95% CI 1.181–8.956, p = 0.023] and periventricular WMH (PWMH) (adOR 2.053, 95% CI 1.220–3.456, p = 0.007) were significantly associated with poor functional outcome. PWMH (adOR 2.908, 95% CI 1.230–6.878, p = 0.015) and lobar CMB severity (adOR 1.811, 95% CI 1.039–3.157, p = 0.036) were associated with stroke recurrence. The cumulative CSVD score was associated with poor functional outcome (adOR 1.460, 95% CI 1.017–2.096) and stroke recurrence (adOR 2.258, 95% CI 1.080–4.723). Death occurred in 36.1% (13/36) of patients with CMBs ≥ 10 compared with 18.8% (22/117) in those with CMB < 10 (adjusted HR 2.669, 95% CI 1.248–5.707, p = 0.011). In addition, the cumulative CSVD score ≥ 2 was associated with a decreased survival rate (adjusted HR 3.140, 95% CI 1.066–9.250, p = 0.038).

Conclusions: Severe PWMH, CMB, or cumulative CSVD burden exert important influences on the long-term outcome of ICH.

Exploration of Multiparameter Hematoma 3D Image Analysis for Predicting Outcome After Intracerebral Hemorrhage

BACKGROUND

Rapid diagnosis and proper management of intracerebral hemorrhage (ICH) play a crucial role in the outcome. Prediction of the outcome with a high degree of accuracy based on admission data including imaging information can potentially influence clinical decision-making practice.

METHODS

We conducted a retrospective multicenter study of consecutive ICH patients admitted between 2012-2017. Medical history, admission data, and initial head computed tomography (CT) scan were collected. CT scans were semiautomatically segmented for hematoma volume, hematoma density histograms, and sphericity index (SI). Discharge unfavorable outcomes were defined as death or severe disability (modified Rankin Scores 4-6). We compared (1) hematoma volume alone; (2) multiparameter imaging data including hematoma volume, location, density heterogeneity, SI, and midline shift; and (3) multiparameter imaging data with clinical information available on admission for ICH outcome prediction. Multivariate analysis and predictive modeling were used to determine the significance of hematoma characteristics on the outcome.

RESULTS

We included 430 subjects in this analysis. Models using automated hematoma segmentation showed incremental predictive accuracies for in-hospital mortality using hematoma volume only: area under the curve (AUC): 0.85 [0.76-0.93], multiparameter imaging data (hematoma volume, location, CT density, SI, and midline shift): AUC: 0.91 [0.86-0.97], and multiparameter imaging data plus clinical information on admission (Glasgow Coma Scale (GCS) score and age): AUC: 0.94 [0.89-0.99]. Similarly, severe disability predictive accuracy varied from AUC: 0.84 [0.76-0.93] for volume-only model to AUC: 0.88 [0.80-0.95] for imaging data models and AUC: 0.92 [0.86-0.98] for imaging plus clinical predictors.

CONCLUSIONS

Multiparameter models combining imaging and admission clinical data show high accuracy for predicting discharge unfavorable outcome after ICH.

Imaging-Based Outcome Prediction of Acute Intracerebral Hemorrhage

We hypothesized that imaging-only-based machine learning algorithms can analyze non-enhanced CT scans of patients with acute intracerebral hemorrhage (ICH). This retrospective multicenter cohort study analyzed 520 non-enhanced CT scans and clinical data of patients with acute spontaneous ICH. Clinical outcome at hospital discharge was dichotomized into good outcome and poor outcome using different modified Rankin Scale (mRS) cut-off values. Predictive performance of a random forest machine learning approach based on filter- and texture-derived high-end image features was evaluated for differentiation of functional outcome at mRS 2, 3, and 4. Prediction of survival (mRS ≤ 5) was compared to results of the ICH Score. All models were tuned, validated, and tested in a nested 5-fold cross-validation approach. Receiver-operating-characteristic area under the curve (ROC AUC) of the machine learning classifier using image features only was 0.80 (95% CI [0.77; 0.82]) for predicting mRS ≤ 2, 0.80 (95% CI [0.78; 0.81]) for mRS ≤ 3, and 0.79 (95% CI [0.77; 0.80]) for mRS ≤ 4. Trained on survival prediction (mRS ≤ 5), the classifier reached an AUC of 0.80 (95% CI [0.78; 0.82]) which was equivalent to results of the ICH Score. If combined, the integrated model showed a significantly higher AUC of 0.84 (95% CI [0.83; 0.86], P value <0.05). Accordingly, sensitivities were significantly higher at Youden Index maximum cut-offs (77% vs. 74% sensitivity at 76% specificity, P value <0.05). Machine learning–based evaluation of quantitative high-end image features provided the same discriminatory power in predicting functional outcome as multidimensional clinical scoring systems. The integration of conventional scores and image features had synergistic effects with a statistically significant increase in AUC.

Comparison of Multivariable Logistic Regression and Other Machine Learning Algorithms for Prognostic Prediction Studies in Pregnancy Care: Systematic Review and Meta-Analysis

BACKGROUND

Predictions in pregnancy care are complex because of interactions among multiple factors. Hence, pregnancy outcomes are not easily predicted by a single predictor using only one algorithm or modeling method.

OBJECTIVE

This study aims to review and compare the predictive performances between logistic regression (LR) and other machine learning algorithms for developing or validating a multivariable prognostic prediction model for pregnancy care to inform clinicians' decision making.

METHODS

Research articles from MEDLINE, Scopus, Web of Science, and Google Scholar were reviewed following several guidelines for a prognostic prediction study, including a risk of bias (ROB) assessment. We report the results based on the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Studies were primarily framed as PICOTS (population, index, comparator, outcomes, timing, and setting): Population: men or women in procreative management, pregnant women, and fetuses or newborns; Index: multivariable prognostic prediction models using non-LR algorithms for risk classification to inform clinicians' decision making; Comparator: the models applying an LR; Outcomes: pregnancy-related outcomes of procreation or pregnancy outcomes for pregnant women and fetuses or newborns; Timing: pre-, inter-, and peripregnancy periods (predictors), at the pregnancy, delivery, and either puerperal or neonatal period (outcome), and either short- or long-term prognoses (time interval); and Setting: primary care or hospital. The results were synthesized by reporting study characteristics and ROBs and by random effects modeling of the difference of the logit area under the receiver operating characteristic curve of each non-LR model compared with the LR model for the same pregnancy outcomes. We also reported between-study heterogeneity by using τ2 and I2.

RESULTS

Of the 2093 records, we included 142 studies for the systematic review and 62 studies for a meta-analysis. Most prediction models used LR (92/142, 64.8%) and artificial neural networks (20/142, 14.1%) among non-LR algorithms. Only 16.9% (24/142) of studies had a low ROB. A total of 2 non-LR algorithms from low ROB studies significantly outperformed LR. The first algorithm was a random forest for preterm delivery (logit AUROC 2.51, 95% CI 1.49-3.53; I2=86%; τ2=0.77) and pre-eclampsia (logit AUROC 1.2, 95% CI 0.72-1.67; I2=75%; τ2=0.09). The second algorithm was gradient boosting for cesarean section (logit AUROC 2.26, 95% CI 1.39-3.13; I2=75%; τ2=0.43) and gestational diabetes (logit AUROC 1.03, 95% CI 0.69-1.37; I2=83%; τ2=0.07).

CONCLUSIONS

Prediction models with the best performances across studies were not necessarily those that used LR but also used random forest and gradient boosting that also performed well. We recommend a reanalysis of existing LR models for several pregnancy outcomes by comparing them with those algorithms that apply standard guidelines.

TRIAL REGISTRATION

PROSPERO (International Prospective Register of Systematic Reviews) CRD42019136106; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=136106.

Development and usability testing of Understanding Stroke, a tailored life-sustaining treatment decision support tool for stroke surrogate decision makers

BACKGROUND

Surrogate decision makers of stroke patients are often unprepared to make critical decisions on life-sustaining treatments. We describe the development process and key features for the Understanding Stroke web-based decision support tool.

METHODS

We used multiple strategies to develop a patient-centered, tailored decision aid. We began by forming a Patient and Family Advisory Council to provide continuous input to our multidisciplinary team on the development of the tool. Additionally, focus groups consisting of nurses, therapists, social workers, physicians, stroke survivors, and family members reviewed key elements of the tool, including prognostic information, graphical displays, and values clarification exercise. To design the values clarification exercise, we asked focus groups to provide feedback on a list of important activities of daily living. An ordinal prognostic model was developed for ischemic stroke and intracerebral hemorrhage using data taken from the Virtual International Stroke Trials Archive Plus, and incorporated into the tool.

RESULTS

Focus group participants recommended making numeric prognostic information optional due to possible emotional distress. Pie charts were generally favored by participants for graphical presentation of prognostic information, though a horizontal stacked bar chart was also added due to its prevalence in stroke literature. Plain language descriptions of the modified Rankin Scale were created to accompany the prognostic information. A values clarification exercise was developed consisting of a list of 13 situations that may make an individual consider comfort measures only. The final version of the web based tool (which can be viewed on tablets) included the following sections: general introduction to stroke, outcomes (prognostic information and recovery), in-hospital and life-sustaining treatments, decision making and values clarification, post-hospital care, tips for talking to the health care team, and a summary report. Preliminary usability testing received generally favorable feedback.

CONCLUSION

We developed Understanding Stroke, a tailored decision support tool for surrogate decision makers of stroke patients. The tool was well received and will be formally pilot tested in a group of stroke surrogate decision makers.

TRIAL REGISTRATION

ClinicalTrials.gov ( NCT03427645 ).

Intracranial hypertension in patients with aneurysmal subarachnoid hemorrhage: a systematic review and meta-analysis

Aneurysmal subarachnoid hemorrhage (aSAH) is a devastating and life-threatening condition with high mortality and morbidity. Even though there is an association with intracranial pressure (ICP) raise and aSAH, there is a lack of recommendations regarding the indications for ICP monitoring in patients with aSAH. Defining what patients are at a higher risk to develop intracranial hypertension and its role in the functional outcome and mortality in patients with aSAH will be the purpose of the following systematic review and meta-analysis. The primary endpoint is to determine the prevalence and impact on mortality of ICP in patients with aSAH. Secondary endpoints aim to describe the variables related to the development of ICP and the relationship between traumatic and aneurysmal etiology of intracranial hypertension. PubMed, Embase, Central Cochrane Registry of Controlled Trials, and research meeting abstracts were searched up to August 2019 for studies that performed ICP monitoring, assessed the prevalence of intracranial hypertension and the mortality, in adults. Newcastle Ottawa scale (NOS) was used to assess study quality. The statistical analysis was performed using the Mantel-Haenszel methodology for the prevalence and mortality of intracranial hypertension for reasons with a randomized effect analysis model. Heterogeneity was assessed by I². A total of 110 bibliographic citations were identified, 20 were considered potentially eligible, and after a review of the full text, 12 studies were considered eligible and 5 met the inclusion criteria for this review. One study obtained 7 points in the NOS, another obtained 6 points, and the rest obtained 5 points. Five studies were chosen for the final analysis, involving 793 patients. The rate of intracranial hypertension secondary to aSAH was 70.69% (95% CI 56.79-82.84%) showing high heterogeneity (I² = 92.48%, p = < 0.0001). The results of the meta-analysis of mortality rate associated with intracranial hypertension after aSAH found a total of four studies, which involved 385 patients. The mortality rate was 30.3% (95% CI: 14.79-48.57%). Heterogeneity was statistically significant (I² = 90.36%; p value for heterogeneity < 0.001). We found that in several studies, they reported that a high degree of clinical severity scale (Hunt and Hess or WNFS) and tomographic (Fisher) were significantly correlated with the increase in ICP above 20 mmHg (P < 0.05). The interpretation of the results could be underestimated for the design heterogeneity of the included studies. New protocols establishing the indications for ICP monitoring in aSAH are needed. Given the high heterogeneity of the studies included, we cannot provide clinical recommendations regarding this issue.

Use of the Bispectral Index to Predict Recovery of Consciousness in Patients with Spontaneous Intracerebral Hemorrhage After Surgical Hematoma Evacuation: A Prospective Cohort Study

Background

Our study aimed to test the predictive value of the bispectral index (BIS) for the post-operational consciousness recovery in patients undergone hematoma evacuation due to spontaneous intracerebral hemorrhage (ICH).

Material/Methods

In this prospective cohort study, we enrolled adult spontaneous ICH patients after surgical hematoma evacuation who did not recover consciousness on the first postoperative day. After patient enrollment, the BIS was continuously monitored for 12 hours, and the motor response on the Glasgow Coma Scale (GCS-M) was evaluated. The patients were followed up for 30 days and divided into a consciousness recovery group and a nonrecovery group. Receiver operating characteristic curve analysis was performed to investigate the predictive values of the BIS, GCS-M and ICH score on the consciousness recovery. The area under the curve (AUC) and 95% confidence interval (95%CI) were calculated. During the 12-hour monitoring period, the peak BIS value after GCS-M stimulation was used for ROC analysis.

Results

Of the 55 enrolled patients, 19 patients recovered consciousness, and 36 patients did not. The BIS value of the consciousness recovery group was significantly higher than that of the nonrecovery group (P<0.001). For consciousness recovery prediction, the AUC (95%CI) of the BIS values after external stimulation was 0.97 (0.91–1.00), which was superior to the GCS-M (0.75 [0.59–0.91]) and ICH score (0.57 [0.41–0.73]).

Conclusions

Our study demonstrates that BIS might be a potential tool for predicting the consciousness recovery in ICH patients undergone surgical hematoma evacuation.