A machine learning approach for predicting perihematomal edema expansion in patients with intracerebral hemorrhage

Chen, Yi-Hao; Qin, Chenchen; Chang, Jinyuan; Lyu, Yan; Zhang, Qinghua; Ye, Zeju; Li, Zhaojian; Tian, Fengxuan; Ma, Wenbin; Wei, Junji; Feng, Ming; Yao, Jianhua; Wang, Renzhi

doi:10.1007/s00330-022-09311-3

Cited by 7 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This study developed a novel multimodal interpretable artificial intelligence model for predicting the prognosis of brain hemorrhage. In comparison to previous relevant studies [ 49 – 51 ], this study innovatively proposes an interpretable machine learning radiomics framework, integrating three different semantic levels of image features for multimodal model training. This approach enriches data representation, aiding in enhancing both data characterization and model performance limits.…”

Section: Discussionmentioning

confidence: 99%

An interpretable artificial intelligence model based on CT for prognosis of intracerebral hemorrhage: a multicenter study

Zhang,

Yang,

Song

et al. 2024

BMC Med Imaging

View full text Add to dashboard Cite

Objectives To develop and validate a novel interpretable artificial intelligence (AI) model that integrates radiomic features, deep learning features, and imaging features at multiple semantic levels to predict the prognosis of intracerebral hemorrhage (ICH) patients at 6 months post-onset. Materials and methods Retrospectively enrolled 222 patients with ICH for Non-contrast Computed Tomography (NCCT) images and clinical data, who were divided into a training cohort (n = 186, medical center 1) and an external testing cohort (n = 36, medical center 2). Following image preprocessing, the entire hematoma region was segmented by two radiologists as the volume of interest (VOI). Pyradiomics algorithm library was utilized to extract 1762 radiomics features, while a deep convolutional neural network (EfficientnetV2-L) was employed to extract 1000 deep learning features. Additionally, radiologists evaluated imaging features. Based on the three different modalities of features mentioned above, the Random Forest (RF) model was trained, resulting in three models (Radiomics Model, Radiomics-Clinical Model, and DL-Radiomics-Clinical Model). The performance and clinical utility of the models were assessed using the Area Under the Receiver Operating Characteristic Curve (AUC), calibration curve, and Decision Curve Analysis (DCA), with AUC compared using the DeLong test. Furthermore, this study employs three methods, Shapley Additive Explanations (SHAP), Grad-CAM, and Guided Grad-CAM, to conduct a multidimensional interpretability analysis of model decisions. Results The Radiomics-Clinical Model and DL-Radiomics-Clinical Model exhibited relatively good predictive performance, with an AUC of 0.86 [95% Confidence Intervals (CI): 0.71, 0.95; P < 0.01] and 0.89 (95% CI: 0.74, 0.97; P < 0.01), respectively, in the external testing cohort. Conclusion The multimodal explainable AI model proposed in this study can accurately predict the prognosis of ICH. Interpretability methods such as SHAP, Grad-CAM, and Guided Grad-Cam partially address the interpretability limitations of AI models. Integrating multimodal imaging features can effectively improve the performance of the model. Clinical relevance statement Predicting the prognosis of patients with ICH is a key objective in emergency care. Accurate and efficient prognostic tools can effectively prevent, manage, and monitor adverse events in ICH patients, maximizing treatment outcomes.

show abstract

Section: Discussionmentioning

confidence: 99%

An interpretable artificial intelligence model based on CT for prognosis of intracerebral hemorrhage: a multicenter study

Zhang,

Yang,

Song

et al. 2024

BMC Med Imaging

View full text Add to dashboard Cite

show abstract

“…Combined with clinical and laboratory factors, ten features were able to predict the possibility of death after hemorrhagic transformation with the AUC of 0.85 (31). Other study also focused on the potential variables in CT to predict the expansion of perihematomal edema expansion for patients with intracranial hemorrhage with the combined AUC of 0.840 (32).…”

Section: Cerebrovascular Diseasementioning

confidence: 99%

A survey on common biostatistics tools in neuroscience: Machine learning and Bayesian modeling

Xue

2024

AETR

View full text Add to dashboard Cite

Machine learning was characterized by building models and finding correlations between data features, while logistic regression, decision trees, support vector machines (SVM), random forest (RF) and neural networks were recognized as common ML approaches. Bayesian modeling model uncertainty, which can estimate the features from the dataset directly instead of from sampling distribution. Their roles were extremely useful for the detection and progression for diseases in neuroscience. This review summarize different approaches in various diseases, hoping to introduce the potential roles of biostatistics tools in neuroscience.

show abstract

“…129,130 Radiomics, an evolving method for extracting quantitative features from images based on morphologic characteristics, has boosted predictive accuracy, especially when combined with CNN segmentation and ML clinical analysis (AUC: 0.95). [131][132][133] These advances suggest that ML can significantly enhance the rapid, automated identification of radiographic biomarkers to inform acute care and facilitate large-scale research.…”

Section: Intracerebral Hemorrhagementioning

confidence: 99%

Artificial Intelligence and Machine Learning Applications in Critically Ill Brain Injured Patients

Vitt,

Mainali

2024

Semin Neurol

View full text Add to dashboard Cite

The utilization of Artificial Intelligence (AI) and Machine Learning (ML) is paving the way for significant strides in patient diagnosis, treatment, and prognostication in neurocritical care. These technologies offer the potential to unravel complex patterns within vast datasets ranging from vast clinical data and EEG (electroencephalogram) readings to advanced cerebral imaging facilitating a more nuanced understanding of patient conditions. Despite their promise, the implementation of AI and ML faces substantial hurdles. Historical biases within training data, the challenge of interpreting multifaceted data streams, and the “black box” nature of ML algorithms present barriers to widespread clinical adoption. Moreover, ethical considerations around data privacy and the need for transparent, explainable models remain paramount to ensure trust and efficacy in clinical decision-making.This article reflects on the emergence of AI and ML as integral tools in neurocritical care, discussing their roles from the perspective of both their scientific promise and the associated challenges. We underscore the importance of extensive validation in diverse clinical settings to ensure the generalizability of ML models, particularly considering their potential to inform critical medical decisions such as withdrawal of life-sustaining therapies. Advancement in computational capabilities is essential for implementing ML in clinical settings, allowing for real-time analysis and decision support at the point of care. As AI and ML are poised to become commonplace in clinical practice, it is incumbent upon health care professionals to understand and oversee these technologies, ensuring they adhere to the highest safety standards and contribute to the realization of personalized medicine. This engagement will be pivotal in integrating AI and ML into patient care, optimizing outcomes in neurocritical care through informed and data-driven decision-making.

show abstract

A machine learning approach for predicting perihematomal edema expansion in patients with intracerebral hemorrhage

Cited by 7 publications

References 33 publications

An interpretable artificial intelligence model based on CT for prognosis of intracerebral hemorrhage: a multicenter study

An interpretable artificial intelligence model based on CT for prognosis of intracerebral hemorrhage: a multicenter study

A survey on common biostatistics tools in neuroscience: Machine learning and Bayesian modeling

Artificial Intelligence and Machine Learning Applications in Critically Ill Brain Injured Patients

Contact Info

Product

Resources

About