Clinically Applicable Machine Learning Approach to Predict Intracerebral Hematoma Expansion

 You don't know predictions are TOTALLY FUCKING USELESS to getting survivors recovered? You're fired!

Clinically Applicable Machine Learning Approach to Predict Intracerebral Hematoma Expansion

Shogo Watanabe, PhD https://orcid.org/0009-0000-5053-8405, 

Nice Ren, MD, PhD https://orcid.org/0000-0003-4702-2760, 

Yukihiro Imaoka, MD, PhD https://orcid.org/0000-0002-7054-2708, 

Kento Morita, PhD https://orcid.org/0000-0002-7171-8197, 

Syoji Kobashi, PhD https://orcid.org/0000-0003-3659-4114, 

Nobutaka Mukae, MD, PhD https://orcid.org/0000-0003-1990-1485, 

Koichi Arimura, MD, PhD https://orcid.org/0000-0003-2455-9506, 

Kunihiro Nishimura, MD, PhD https://orcid.org/0000-0002-0639-0949, and 

Koji Iihara, MD, PhD https://orcid.org/0000-0002-7852-220X kiihara@ncvc.go.jp J‐ASPECT study collaboratorsAuthor Info & Affiliations

 Journal of the American Heart Association

 New online https://doi.org/10.1161/JAHA.125.042387 

Abstract

Background

Hematoma expansion (HE) is a significant risk factor for poor prognosis in patients with intracerebral hemorrhage (ICH). Accurately predicting HE is crucial for determining optimal treatment strategies.

Methods

This study enrolled 452 patients with ICH from 10 hospitals. To predict HE, 28 clinical variables available on patient arrival (including medical history, ICH location, and ICH volume) and 1142 radiomics features extracted from noncontrast computed tomography images of the ICH regions were used. Clinical variables and radiomics features were selected using gradient boosting and the least absolute shrinkage and selection operator. Three HE prediction models were built on clinical variables alone, radiomics features alone, and a third combining both. The models were compared using 5‐fold cross‐validation, and the mean area under the receiver operating characteristic curve was calculated for each. Additionally, the important features of HE prediction in the combined model were explored.

Results

The combined model demonstrated the highest performance for predicting HE with a 5‐fold mean area under the receiver operating characteristic curve of 0.77±0.05, compared with 0.70±0.06 for the clinical variables alone and 0.73±0.04 for the radiomics features alone. Permutation feature importance analysis suggested that anticoagulant treatment was the most predictive of HE.

Conclusions

A predictive model for HE was developed using the medical history, clinical features available on the patient’s arrival, imaging, and radiomics features extracted from computed tomography images. This prediction model will assist non–stroke care(NOT RECOVERY!) specialists in making treatment decisions for ICH in emergency settings.

Article Commentary: “Association of Biomarkers With Intracerebral Hematoma Expansion and Arterial Thromboembolic Events in Patients With Acute Intracranial Hemorrhage”

 

Associations DO NOTHING FOR RECOVERY! Because you don't have recovery protocols mapped to the problems found. Can't anyone in stroke think at all?

Oops, I'm not playing by the polite rules of Dale Carnegie,  'How to Win Friends and Influence People'. 

Telling stroke medical persons they know nothing about stroke is a no-no even if it is true. 

Politeness will never solve anything in stroke. Yes, I'm a bomb thrower and proud of it. Someday a stroke 'leader' will try to ream me out for making them look bad by being truthful, I look forward to that day.

Send me personal hate mail on this: oc1dean@gmail.com. I'll print your complete statement with your name(If you can't stand by your name don't bother replying anonymously) and my response in my blog. Or are you afraid to engage with my stroke-addled mind? No excuses are allowed! You're medically trained; it should be simple to precisely state EXACTLY WHY you aren't working on 100% recovery protocols with NO EXCUSES!

Article Commentary: “Association of Biomarkers With Intracerebral Hematoma Expansion and Arterial Thromboembolic Events in Patients With Acute Intracranial Hemorrhage”

• Shravan Sivakumar, MD, @sshravanMD

Eikelboom JW, Sharma M, Xu L, Bamberg K, Beyer-Westendorf J, Falkenberg C, Ladenvall P, Narayan R, Penland RC, Verhamme P, Shoamanesh A. Association of Biomarkers With Intracerebral Hematoma Expansion and Arterial Thromboembolic Events in Patients With Acute Intracranial Hemorrhage: The ANNEXA-I Biomarker Substudy. Stroke. 2025.

Despite advances in acute hemorrhagic stroke care, hematoma expansion (HE) remains a major contributor to early neurological deterioration and poor outcomes in patients with intracerebral hemorrhage (ICH) associated with the use of anti-Xa inhibitors. The ANNEXA-I trial, initially aimed at assessing andexanet alfa for reversing factor Xa inhibitor–associated bleeding, provided a valuable platform to explore the underlying pathophysiological mechanisms — especially those driving hematoma expansion and thromboembolic events, which remain poorly understood. In this biomarker substudy, researchers explored the association between circulating biomarkers and both hematoma expansion and arterial thromboembolic events, aiming to provide additional insights into the mechanism of action of andexanet alfa.

Patients with ICH during treatment with a Factor Xa inhibitor were eligible for inclusion in the original ANNEXA-I trial if they underwent baseline brain imaging within 12 hours of symptom onset and had a hematoma volume of ≤60 mL with HE defined as increase in volume of ≥12.5 mL or ≥35% within 12 hours. The authors further modified criteria to include hematoma volume of 0.5 to 60 mL and with a maximum National Institutes of Health Stroke Scale score of 35 who underwent brain imaging within 6 hours of symptom onset. Hemorrhages needed to be confirmed on neuroimaging within 2 hours before randomization, and the last dose of Factor Xa inhibitor had to be taken within 15 hours of randomization. Patients with GCS <7, plan for surgery <12 hours and history of thromboembolic events in prior 2 weeks were excluded. Arterial thromboembolic events included ischemic stroke, myocardial infarction and systemic embolism occurring within 30 days. Analysis was restricted to patients taking apixaban or rivaroxaban, and to availability of anti-Factor Xa activity or endogenous thrombin potential (ETP) data.

438 subjects with anti-Xa activity and 328 with ETP levels met criteria. In patients with apixaban- or rivaroxaban-associated ICH, the mean age was 79.1 years. Baseline characteristics were similar in the anti-Factor Xa and ETP populations and were well balanced by randomized treatment group. The results showed large reduction between baseline and 1 hour in anti-Factor Xa activity (median difference at 1 hour being andexanet 98.3 ng/mL and for usual care 10.9 ng/mL (between group difference, P<0.001) and a large increase in ETP (andexanet 753.1 nmol/L-min and for usual care 126.6 nmol/L-min (between group difference, P<0.001), but by 12 hours, the contrast between randomized treatment in ETP was no longer evident. Reduction in anti-Factor Xa activity between baseline and 1 hour independently predicted reduced risk of hematoma expansion (per 100 ng/mL: OR, 0.69 [95% CI, 0.53–0.92]; P=0.010). While increase in ETP between baseline and 1 hour independently predicted reduced risk of hematoma expansion (per 100 nmol/L-min: OR, 0.94 [95% CI, 0.90–0.99]; P=0.019). After adjustment for age, baseline biomarker level, prior MI, and high-dose andexanet eligibility, change in ETP from baseline to 1 hour independently predicted arterial thromboembolic events, whereas neither change in anti-Xa from baseline to 1 hour nor change in ETP from baseline to 12 hours was significantly associated with arterial thromboembolic events during 30 days of follow-up.

These results suggest an immediate treatment effect of anti-Xa agents that is limited to the first few hours of treatment. The authors further demonstrated that that change between baseline and 1 hour in ETP was independently associated with increased arterial thromboembolic events. Given most of the hematoma expansion is expected to occur within the first few hours of onset of symptoms, this is further supported by the biomarker findings of enhanced benefit with early and specific anticoagulant reversal to prevent hematoma expansion. Prothrombin complex concentrates that can enhance hemostatic by increasing ETP are recommended in the absence of specific reversal agents, and given their use in usual care, the finding of only a minimal increase in ETP at 1 hour in the usual care arm and lack of association between the change between baseline and 12 hours in ETP and risk of hematoma expansion further supports use of specific anti-Xa agents. Furthermore, biomarker analyses from the ANNEXA-4 cohort study have demonstrated that andexanet is associated with reduced tissue factor pathway inhibitor activity, which may contribute to the early increase in ETP, which is a well-documented risk factor for thromboembolism which is supported by the current study findings.

Strengths of the study include the analysis performed as part of a randomized control trial allowing for causal association between biomarker change and hematoma expansion. Their limitations include lack of statistical power as reflected by the wide CIs and that not all patients in the usual care arm received a prothrombin complex concentrate. However, changes in anti-FXa and ETP were similar in sensitivity analyses that excluded patients who did not receive a prothrombin complex concentrate. The next step would include integrating biomarker data with imaging and clinical variables, alongside mechanistic studies to uncover causal pathways, which could pave the way for biomarker-guided therapeutic trials. Picture this: A patient with ICH arrives in the ED, gets a CT and a rapid biomarker panel, and within minutes, a combined score predicts high risk for hematoma expansion. The team immediately starts hemostatic therapy and tailors anticoagulation timing, preventing both expansion and clotting complications. This is the promise of integrating biomarkers, imaging, and clinical data — turning ICH care into precise, proactive treatment.

ARISE I Consensus Statement on the Management of Chronic Subdural Hematoma

 But you didn't write up any protocols on what to do in this situation. SO EVERYTHING YOU DID WAS FUCKING USELESS! Are you finally going to solve stroke AFTER  you are the 1 in 4 per WHO that has a stroke?

Just a thought: that might be too late, depending on where the stroke hits you!

Survivors really don't want things 'managed'; Cures are what they want. Don't you ever talk to survivors!

ARISE I Consensus Statement on the Management of Chronic Subdural Hematoma

Peter Kan,

David Fiorella,

Guilherme Dabus,

Edgar A. Samaniego,

Giuseppe Lanzino,

Adnan H. Siddiqui,

Huanwen Chen,

Alexander A. Khalessi,

Vitor Mendes Pereira,

Johanna T. Fifi,

Mark D. Bain,

… See all authors

Originally published22 Apr 2024https://doi.org/10.1161/STROKEAHA.123.044129Stroke. 2024;55:1438–1448

Abstract

ARISE (Aneurysm/AVM/cSDH Roundtable Discussion With Industry and Stroke Experts) organized a one-and-a-half day meeting and workshop and brought together representatives from academia, industry, and government to discuss the most promising approaches to improve outcomes for patients with chronic subdural hematoma (cSDH). The emerging role of middle meningeal artery embolization in clinical practice and the design of current and potential future trials were the primary focuses of discussion. Existing evidence for imaging, indications, agents, and techniques was reviewed, and areas of priority for study and key questions surrounding the development of new and existing treatments for cSDH were identified. Multiple randomized, controlled trials have met their primary efficacy end points, providing high-level evidence that middle meningeal artery embolization is a potent adjunctive therapy to the standard (surgical and nonsurgical) management of neurologically stable cSDH patients in terms of reducing rates of disease recurrence. Pooled data analyses following the formal conclusion and publication of these trials will form a robust foundation upon which guidelines can be strengthened for cSDH treatment modalities and optimal patient selection, as well as delineate future lines of investigation.

Footnotes

The opinions expressed in this article are not necessarily those of the editors or of the American Heart Association.

For Sources of Funding and Disclosures, see page 1446.

Correspondence to: Peter T. Kan, MD, Department of Neurosurgery, The University of Texas Medical Branch, 1005 Harborside Dr, 5th floor, Galveston, TX 77550. Email ptkan@utmb.edu

Predictors of severe intracerebral hemorrhage expansion

 Predicting problems does absolutely nothing unless you have created a solution to prevent the problem! I don't see that here, so useless research!

Predictors of severe intracerebral hemorrhage expansion

Andrea Morotti https://orcid.org/0000-0002-6558-1155 andrea.morotti@unibs.it, Qi Li https://orcid.org/0000-0002-9144-148X, […], and Andrea Zini+14View all authors and affiliations

OnlineFirst

https://doi.org/10.1177/23969873241247436

• 
  

• • Abstract
  • Introduction
  • Methods
  • Results
  • Discussion
  • Conclusion
  • Informed consent
  • Ethical approval
  • Declaration of conflicting interest
  • Funding
  • ORCID iDs
  • Footnote
  • References
  • Supplementary Material
• PDF / ePub
• • Cite article
  • Share options
  • Information, rights and permissions
  • Metrics and citations
  • Figures and tables

Abstract

Background:

Severe hematoma expansion (sHE) has the strongest impact on intracerebral hemorrhage (ICH) outcome. We investigated the predictors of sHE.

Methods:

Retrospective analysis of ICH patients admitted at nine sites in Italy, Germany, China, and Canada. The following imaging features were analyzed: non-contrast CT (NCCT) hypodensities, heterogeneous density, blend sign, irregular shape, and CT angiography (CTA) spot sign. The outcome of interest was sHE, defined as volume increase >66% and/or >12.5 from baseline to follow-up NCCT. Predictors of sHE were explored with logistic regression.

Results:

A total of 1472 patients were included (median age 73, 56.6% males) of whom 223 (15.2%) had sHE. Age (odds ratio (OR) per year, 95% confidence interval (CI), 1.02 (1.01–1.04)), Anticoagulant treatment (OR 3.00, 95% CI 2.09–4.31), Glasgow Coma Scale (OR 0.93, 95% CI 0.89–0.98), time from onset/last known well to imaging, (OR per h 0.96, 95% CI 0.93–0.99), and baseline ICH volume, (OR per mL 1.02, 95% CI 1.02–1.03) were independently associated with sHE. Ultra-early hematoma growth (baseline volume/baseline imaging time) was also a predictor of sHE (OR per mL/h 1.01, 95% CI 1.00–1.02). All NCCT and CTA imaging markers were also predictors of sHE. Amongst imaging features NCCT hypodensities had the highest sensitivity (0.79) whereas the CTA spot sign had the highest positive predictive value (0.51).

Conclusions:

sHE is common in the natural history of ICH and can be predicted with few clinical and imaging variables. These findings might inform clinical practice and future trials targeting active bleeding in ICH.

Graphical abstract

Introduction

Intracerebral hemorrhage (ICH) is one of the deadliest types of stroke, with high short term mortality and severe neurological sequelae in the majority of survivors.¹ Hematoma expansion (HE) is a potentially preventable determinant(Useless statement without the EXACT PROTOCOL THAT WILL PREVENT THIS EXPANSION!) of poor outcome and represents therefore a compelling therapeutic target.² However, the HE-outcome relationship is not linear, and only severe HE (sHE), defined as hematoma volume increase >66% and/or >12.5 mL, has a significant prognostic impact.³ Previous studies and prediction models focused on the more commonly used definition of HE (volume increase >33% and or >6 mL), whereas predictors of sHE remain poorly characterized.⁴ We aimed to describe the clinical and imaging variables associated with sHE.

 

More at link.

Association Between Hematoma Volume and Risk of Subsequent Ischemic Stroke: A MISTIE III and ATACH-2 Analysis

Telling us of a problem with no suggested solution doesn't help stroke survivors one bit! What will your competent? doctor do to prevent this problem from happening?

Association Between Hematoma Volume and Risk of Subsequent Ischemic Stroke: A MISTIE III and ATACH-2 Analysis

William Harris,

Jed H. Kaiser,

Vanessa Liao,

Radhika Avadhani,

Costantino Iadecola,

Guido J. Falcone,

Kevin N. Sheth,

Adnan I. Qureshi,

Joshua N. Goldstein,

Issam A. Awad,

Daniel F. Hanley,

… See all authors

Originally published1 Feb 2024https://doi.org/10.1161/STROKEAHA.123.045859Stroke. 2024;0

Abstract

BACKGROUND:

Nontraumatic intracerebral hemorrhage (ICH) is independently associated with a long-term increased risk of major arterial ischemic events. While the relationship between ICH location and ischemic risk has been studied, whether hematoma volume influences this risk is poorly understood.

METHODS:

We pooled individual patient data from the MISTIE III (Minimally Invasive Surgery Plus Alteplase for Intracerebral Hemorrhage Evacuation Phase 3) and the ATACH-2 (Antihypertensive Treatment of Acute Cerebral Hemorrhage-2) trials. The exposure was hematoma volume, treated as a continuous measure in the primary analysis, and dichotomized by the median in the secondary analyses. The outcome was a symptomatic, clinically overt ischemic stroke, adjudicated centrally within each trial. We evaluated the association between hematoma volume and the risk of an ischemic stroke using Cox regression analyses after adjustment for demographics, vascular comorbidities, and ICH characteristics.

RESULTS:

Of 1470 patients with ICH, the mean age was 61.7 (SD, 12.8) years, and 574 (38.3%) were female. The median hematoma volume was 17.3 mL (interquartile range, 7.2–35.7). During a median follow-up of 107 days (interquartile range, 91–140), a total of 30 ischemic strokes occurred, of which 22 were in patients with a median ICH volume of ≥17.3 mL and a cumulative incidence of 4.6% (95% CI, 3.1–7.1). Among patients with a median ICH volume <17.3 mL, there were 8 ischemic strokes with a cumulative incidence of 3.1% (95% CI, 1.7–6.0). In primary analyses using adjusted Cox regression models, ICH volume was associated with an increased risk of ischemic stroke (hazard ratio, 1.02 per mL increase [95% CI, 1.01–1.04]). In secondary analyses, ICH volume of ≥17.3 mL was associated with an increased risk of ischemic stroke (hazard ratio, 2.5 [95% CI, 1.1–7.2]), compared with those with an ICH volume <17.3 mL.

CONCLUSIONS:

In a heterogeneous cohort of patients with ICH, initial hematoma volume was associated with a heightened short-term risk of ischemic stroke.

• Download figure
• Download PowerPoint

EXPRESS: The coronal plane maximum diameter of deep intracerebral hemorrhage predicts functional outcome more accurately than hematoma volume

Completely and totally fucking useless for survivors. Survivors want you to reduce the hematoma volume. GET THERE! Predictions like this have no value for survivors.

EXPRESS: The coronal plane maximum diameter of deep intracerebral hemorrhage predicts functional outcome more accurately than hematoma volume

 

Show all authors

Stefan Philipp Haider, Adnan Qureshi, Abhi Jain, , , , , , , , , , , , , , , ...

First Published September 27, 2021 Research Article Find in PubMed 

https://doi.org/10.1177/17474930211050749

Article information

Abstract

Background: 

Among prognostic imaging variables, the hematoma volume on admission CT has long been considered the strongest predictor of outcome and mortality in intracerebral hemorrhage (ICH).

Aims:  

To examine whether different features of hematoma shape are associated with functional outcome in deep ICH.

Methods: 

We analyzed 790 patients from the ATACH-2 trial, and 14 shape features were quantified. We calculated Spearman’s Rho to assess the correlation between shape features and 3-month modified Rankin scale (mRS) score, and the ROC-AUC to quantify the association between shape features and poor outcome defined as mRS>2 as well as mRS>3.

Results: 

Among 14 shape features, the maximum ICH diameter in the coronal plane was the strongest predictor of functional outcome, with a maximum coronal diameter >~3.5 cm indicating higher 3-month mRS scores. The maximum coronal diameter versus hematoma volume yielded a Rho of 0.40 vs 0.35 (p=0.006), an AUC[mRS>2] of 0.71 vs 0.68 (p=0.004), and an AUC[mRS>3] of 0.71 vs 0.69 (p=0.029). In multiple regression analysis adjusted for known outcome predictors, the maximum coronal diameter was independently associated with 3-month mRS (p<0.001).

Conclusions:  

A coronal-plane maximum diameter measurement offers greater prognostic value in deep ICH than hematoma volume. This simple shape metric may expedite assessment of admission head CTs, offer a potential biomarker for hematoma size eligibility criteria in clinical trials and may substitute volume in prognostic ICH scoring systems.

Keywords

CT, hematoma, intracerebral hemorrhage, outcome, shape feature, volume

Access Options

Hemostatic Therapies For Acute Spontaneous Intracerebral Hemorrhage

I didn't understand but hopefully your doctors have a protocol to account for this.
https://www.ahajournals.org/doi/10.1161/STROKEAHA.118.022071?platform=hootsuite

Zhe Kang Law

,

Rustam Al-Shahi Salman

,

Philip M. Bath

,

Thorsten Steiner

and

Nikola Sprigg

Originally published5 Jul 2018Stroke. 2018;49:e271-e272

Outcome after spontaneous intracerebral hemorrhage (ICH) is worsened by hematoma growth, which occurs in up to one third of patients within 24 hours of onset. Early hemostatic therapy might improve outcome by limiting hematoma growth.

Objectives

This updated review aimed to examine the efficacy and safety of individual classes of hemostatic therapies in adults with acute spontaneous ICH, according to the type of antithrombotic drug taken immediately before ICH onset (ie, anticoagulant, antiplatelet, or none).¹

Methods

Search Methods

We searched the Cochrane Stroke Trials Register, MEDLINE, EMBASE, reference list of articles, and international trial registers up to November 2017.

Selection Criteria

We included randomized controlled trials (RCTs) of any hemostatic intervention for acute spontaneous ICH, compared with placebo, open control, or an active comparator, reporting relevant clinical outcomes.

Data Collection and Analysis

Two authors independently extracted data, assessed risk of bias, and contacted corresponding authors of eligible RCTs for specific data if they were not provided in the published report of an RCT.

Main Results

We included 12 RCTs involving 1732 participants. There were 7 RCTs of clotting factors versus placebo/control (1480 participants), 3 RCTs of antifibrinolytic drugs versus placebo/control (57 participants), 1 RCT of platelet transfusion versus control (190 participants) and 1 RCT of clotting factors versus fresh frozen plasma (5 participants). We could not include 2 eligible RCTs of clotting factors versus fresh frozen plasma because they presented aggregate data for ICH and other types of intracranial hemorrhage. In 1 RCT of platelet transfusion versus control for antiplatelet-related ICH, there was a significant increase in death or dependence (modified Rankin Scale score 4–6) at day 90 (70/97 versus 52/93; risk ratio 1.29; 95% confidence interval 1.04–1.61). There were no significant differences in death or dependency at day 90 for clotting factors versus placebo/control (risk ratio 0.87; 95% confidence interval 0.70–1.07; Figure) and antifibrinolytic drugs versus placebo/control (risk ratio 1.25; 95% confidence interval 0.57–2.75) for acute spontaneous ICH. There was no significant difference in death at day 90 for clotting factors versus fresh frozen plasma for anticoagulant-related ICH (risk ratio 0.27; 95% confidence interval 0.02–3.74).

One Versus Double Burr Holes for Treating Chronic Subdural Hematoma Meta-Analysis

For you patients that need part of your skull removed, would you rather have one or two holes in your head? Although I doubt you will have any say as your doctor does this.
http://cjns.metapress.com/content/1030477136x207l6/?id=1030477136X207L6

Abstract

Objective and Design: There is controversy among neurosurgeons regarding whether double burr hole craniostomy (DBHC) is better than single burr hole craniostomy (SBHC) in the treatment of chronic subdural hematoma (CSH), in terms of having a lower revision rate. In order to compare the revision rates after SBHC versus DBHC, we performed a meta-analysis of the available studies in the literature. Materials and Methods: Multiple electronic health databases were searched to identify all the studies published between 1966 and December 2010 that compared SBHC and DBHC. Data were processed in Review Manager 5.0.18. Effect sizes were expressed in pooled odds ratio (OR) estimates, and due to heterogeneity between studies we used random effect of the inverse variance weighted method to perform the meta-analysis. Results: Five observational retrospective cohort studies were identified: four published studies and one unpublished, describing the outcomes of 355 DBHC and 358 SBHC to evacuate 713 CSH in 631 patients. Meta-analysis showed that there was no significant difference in the revision rates between double burr hole craniostomy and single burr hole craniostomy when performed to evacuate CSH. Pooled odds ratio for all the studies was 0.62 (95% confidence interval 0.26 - 1.46). Conclusions: The results of this meta-analysis suggest that SBHC is as good as DBHC in evacuating chronic subdural hematoma and is not associated with a higher revision rate compared to DBHC.