Machine Learning-Based Perihematomal Tissue Features to Predict Clinical Outcome after Spontaneous Intracerebral Hemorrhage

A nomogram incorporating CT-based peri-hematoma radiomics features to predict functional outcome in patients with intracerebral hemorrhage

OBJECTIVE

To evaluate the ability of non-contrast computed tomography based peri-hematoma and intra-hematoma radiomic features to predict the 90-day poor functional outcome for spontaneous intracerebral hemorrhage (sICH) and to present an effective clinically relevant machine learning system to assist in prognosis prediction.

MATERIALS AND METHODS

We retrospectively analyzed the data of 691 patients diagnosed with sICH at two medical centers. Fifteen radiomic features from the intra- and peri-hematoma regions were extracted and selected to build six radiomics models. The clinical-semantic model and nomogram model were constructed to compare prediction abilities. The areas under the curve (AUC) and decision curve analysis were used to evaluate discriminative performance.

RESULTS

Combining radiomics of the intra-hematoma with peri-hematoma regions significantly improved the AUC to 0.843 compared with radiomics of the intra-hematoma region (AUC = 0.780, P ＜ 0.001) in the test set. A similar trend was observed in the external validation cohort (AUC, 0.769 vs. 0.793, P = 0.709). The nomogram, which integrates clinical-semantic signatures with intra-hematoma and peri-hematoma radiomics signatures, accurately predicted a 90-day poor functional outcome in both the test and external validation sets (AUC 0.879 and 0.901, respectively).

CONCLUSION

The nomogram constructed using clinical-semantic signatures and combined intra-hematoma and peri-hematoma radiomics signatures showed the potential to precisely predict 90-day poor functional outcomes for sICH.

Prediction of prognosis in patients with cerebral contusions based on machine learning

Traumatic brain injury (TBI) is a global issue and a major cause of patient mortality, and cerebral contusions (CCs) is a common primary TBI. The haemorrhagic progression of a contusion (HPC) poses a significant risk to patients' lives, and effectively predicting changes in haematoma volume is an urgent clinical challenge that needs to be addressed. As a branch of artificial intelligence, machine learning (ML) can proficiently handle a wide range of complex data and identify connections between data for tasks such as prediction and decision making. We collected data from 673 CCs patients who were hospitalized in the neurosurgery department of The First Affiliated Hospital of Wannan Medical College (Yijishan Hospital of Wannan Medical College) from September 2019 to September 2022. Selecting three popular machine learning algorithms, Decision Tree (DT), Random Forest (RF), and Multilayer Perceptron (MLP) to predict hematoma. Machine learning algorithms were run on the Python 3.9 platform. The model was evaluated for sensitivity, specificity, F1 score, accuracy, receiver operating characteristic (ROC) curves, and the area under the receiver operating characteristic curve (AUC). Using sensitivity as the evaluation metric, the best model is DT model. The DT model included the initial haematoma volume, GCS score, Fib level, blood sugar level, multiple CCs, Male, PT, blood sodium level and PLT count. The evaluation indicators of the DT model were as follows: sensitivity = 0.9545 (0.857, 1.0), specificity = 0.9803 (0.9602, 0.9952), F1 score = 0.8936 (0.7742, 0.9778), accuracy = 0.9778 (0.9556, 0.9956), and AUC-ROC = 0.9674 (0.9143, 0.9975). The DT model is the machine learning algorithm most closely aligned with the research objectives, allowing for the scientific and effective prediction of hematoma changes.

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.

Predicting Outcome of Patients With Cerebral Hemorrhage Using a Computed Tomography-Based Interpretable Radiomics Model: A Multicenter Study

OBJECTIVE

The aim of this study was to develop and validate an interpretable and highly generalizable multimodal radiomics model for predicting the prognosis of patients with cerebral hemorrhage.

METHODS

This retrospective study involved 237 patients with cerebral hemorrhage from 3 medical centers, of which a training cohort of 186 patients (medical center 1) was selected and 51 patients from medical center 2 and medical center 3 were used as an external testing cohort. A total of 1762 radiomics features were extracted from nonenhanced computed tomography using Pyradiomics, and the relevant macroscopic imaging features and clinical factors were evaluated by 2 experienced radiologists. A radiomics model was established based on radiomics features using the random forest algorithm, and a radiomics-clinical model was further trained by combining radiomics features, clinical factors, and macroscopic imaging features. The performance of the models was evaluated using area under the curve (AUC), sensitivity, specificity, and calibration curves. Additionally, a novel SHAP (SHAPley Additive exPlanations) method was used to provide quantitative interpretability analysis for the optimal model.

RESULTS

The radiomics-clinical model demonstrated superior predictive performance overall, with an AUC of 0.88 (95% confidence interval, 0.76-0.95; P < 0.01). Compared with the radiomics model (AUC, 0.85; 95% confidence interval, 0.72-0.94; P < 0.01), there was a 0.03 improvement in AUC. Furthermore, SHAP analysis revealed that the fusion features, rad score and clinical rad score, made significant contributions to the model's decision-making process.

CONCLUSION

Both proposed prognostic models for cerebral hemorrhage demonstrated high predictive levels, and the addition of macroscopic imaging features effectively improved the prognostic ability of the radiomics-clinical model. The radiomics-clinical model provides a higher level of predictive performance and model decision-making basis for the risk prognosis of cerebral hemorrhage.

Based on hematoma and perihematomal tissue NCCT imaging radiomics predicts early clinical outcome of conservatively treated spontaneous cerebral hemorrhage

Spontaneous intracerebral hemorrhage (ICH) is a very serious kind of stroke. If the outcome of patients can be accurately assessed at the early stage of disease occurrence, it will be of great significance to the patients and clinical treatment. The present study was conducted to investigate whether non-contrast computer tomography (NCCT) models of hematoma and perihematomal tissues could improve the accuracy of short-term prognosis prediction in ICH patients with conservative treatment. In this retrospective analysis, a total of 166 ICH patients with conservative treatment during hospitalization were included. Patients were randomized into a training group (N = 132) and a validation group (N = 34) in a ratio of 8:2, and the functional outcome at 90 days after clinical treatment was assessed by the modified Rankin Scale (mRS). Radiomic features of hematoma and perihematomal tissues of 5 mm, 10 mm, 15 mm were extracted from NCCT images. Clinical factors were analyzed by univariate and multivariate logistic regression to identify independent predictive factors. In the validation group, the mean area under the ROC curve (AUC) of the hematoma was 0.830, the AUC of the perihematomal tissue within 5 mm, 10 mm, 15 mm was 0.792, 0.826, 0.774, respectively, and the AUC of the combined model of hematoma and perihematomal tissue within 10 mm was 0.795. The clinical-radiomics nomogram consisting of five independent predictors and radiomics score (Rad-score) of the hematoma model were used to assess 90-day functional outcome in ICH patients with conservative treatment. Our findings found that the hematoma model had better discriminative efficacy in evaluating the early prognosis of conservatively managed ICH patients. The visual clinical-radiomics nomogram provided a more intuitive individualized risk assessment for 90-day functional outcome in ICH patients with conservative treatment. The hematoma could remain the primary therapeutic target for conservatively managed ICH patients, emphasizing the need for future clinical focus on the biological significance of the hematoma itself.

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

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.

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

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.

A Radiomics Model Based on CT Images Combined with Multiple Machine Learning Models to Predict the Prognosis of Spontaneous Intracerebral Hemorrhage

OBJECTIVE

We aimed to construct 3 predictive models, including a clinical model, a radiomics model, and a combined model, to forecast the discharge prognosis of patients with intracerebral hemorrhage on admission.

METHODS

A retrospective study was conducted, involving a total of 161 patients with intracerebral hemorrhage (ICH). At a ratio of 7:3, 115 of these patients were assigned to the training cohort, and 46 of these patients were assigned to the validation cohort. To produce the radionics signature and pick the features to use in its construction, the least absolute shrinkage and selection operator (LASSO) regression was applied. Five machine models were applied, and the optimal model was chosen to construct the radionics model. A clinical model was constructed using univariate and stepwise analysis to identify independent risk variables for poor outcomes at discharge. A predictive combined model nomogram was generated by integrating the clinical model and radiomics model. The performance of the nomogram was assessed in the training cohort and validated in the validation cohort. Analyses of the receiver operating characteristic curve (ROC), the calibration curve, and the decision curve were performed to assess the performance of the combined model.

RESULTS

This study encompassed a cohort of 161 individuals diagnosed with intracerebral hemorrhage (ICH), consisting of 110 males and 51 females. Utilizing the modified Rankin Scale (mRS) at discharge, the analysis revealed that 89 patients (55.3%) had a good prognosis, while 72 patients (44.7%) had a poor prognosis. Only 8 out of 1130 radiomics features were selected and used in conjunction with the LR algorithm to develop the radiomics model. Sex, IVH, GCS score, and ICH volume were determined to be independent predictors of poor outcomes at the time of discharge. The AUC values of the combined model, radiomics model, and clinical model were 0.8583, 0.8364, and 0.7579 in the training cohort, and 0.9153, 0.8692, and 0.7114 in the validation cohort, respectively. The combined model nomogram exhibited good calibration and clinical benefit in both the training and validation cohorts. The decision curve analysis (DCA) displays that the combined model obtained the highest net benefit compared to the radiomics model and clinics model in the training cohort.

CONCLUSIONS

The combined model demonstrates reliability and efficacy in predicting the discharge prognosis of ICH, enabling physicians to perform individualized risk assessments, and make optimal choices about patients with ICH.