CT-based deep learning model for predicting hospital discharge outcome in spontaneous intracerebral hemorrhage

Zhao, Xianjing; Zhou, Bijing; Luo, Yong; Chen, Lei; Zhu, Lequn; Chang, Shixin; Fang, Xiangming; Yao, Zhenwei

doi:10.1007/s00330-023-10505-6

Cited by 5 publications

(2 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A study by Zhou et al developed and validated a clinical nomogram based on CT radiomic features for predicting the short-term prognosis of deep cerebral hemorrhage with AUC values of 0.80, 0.79, and 0.70 in the training set, test set, and validation set, respectively ( 31 ). Therefore, CT imaging features of HICH are also an important factor involved in the assessment of the functional prognosis of patients ( 32 – 34 ).…”

Section: Discussionmentioning

confidence: 99%

Predicting the 90-day prognosis of stereotactic brain hemorrhage patients by multiple machine learning using radiomic features combined with clinical features

Li,

Liang,

Dang

et al. 2024

Front. Surg.

View full text Add to dashboard Cite

Hypertensive Intracerebral Hemorrhage (HICH) is one of the most common types of cerebral hemorrhage with a high mortality and disability rate. Currently, preoperative non-contrast computed tomography (NCCT) scanning-guided stereotactic hematoma removal has achieved good results in treating HICH, but some patients still have poor prognoses. This study collected relevant clinical and radiomic data by retrospectively collecting and analyzing 432 patients who underwent stereotactic hematoma removal for HICH from January 2017 to December 2020 at the Liuzhou Workers Hospital. The prognosis of patients after 90 days was judged by the modified Rankin Scale (mRS) scale and divided into the good prognosis group (mRS ≤ 3) and the poor prognosis group (mRS > 3). The 268 patients were randomly divided into training and test sets in the ratio of 8:2, with 214 patients in the training set and 54 patients in the test set. The least absolute shrinkage and selection operator (Lasso) was used to screen radiomics features. They were combining clinical features and radiomic features to build a joint prediction model of the nomogram. The AUCs of the clinical model for predicting different prognoses of patients undergoing stereotactic HICH were 0.957 and 0.922 in the training and test sets, respectively, while the AUCs of the radiomics model were 0.932 and 0.770, respectively, and the AUCs of the combined prediction model for building a nomogram were 0.987 and 0.932, respectively. Compared with a single clinical or radiological model, the nomogram constructed by fusing clinical variables and radiomic features could better identify the prognosis of HICH patients undergoing stereotactic hematoma removal after 90 days.

show abstract

Section: Discussionmentioning

confidence: 99%

Predicting the 90-day prognosis of stereotactic brain hemorrhage patients by multiple machine learning using radiomic features combined with clinical features

Li,

Liang,

Dang

et al. 2024

Front. Surg.

View full text Add to dashboard Cite

show abstract

“…Deep learning algorithms can continuously adjust parameters to adapt to different scenarios and data structures. According to literature reports, the accuracy of deep learning models in predicting hematoma enlargement exceeds that of traditional clinical variable models and machine learning models ( Zhao et al, 2023 ). However, radiomics and deep learning are still in their early stages in this field, lacking real-world research, and some models may not perform well when applied to external data.…”

Section: Discussionmentioning

confidence: 99%

Research advances in predicting the expansion of hypertensive intracerebral hemorrhage based on CT images: an overview

Ai,

Zhang,

Feng

et al. 2024

PeerJ

View full text Add to dashboard Cite

Hematoma expansion (HE) is an important risk factor for death or poor prognosis in patients with hypertensive intracerebral hemorrhage (HICH). Accurately predicting the risk of HE in patients with HICH is of great clinical significance for timely intervention and improving patient prognosis. Many imaging signs reported in literatures showed the important clinical value for predicting HE. In recent years, the development of radiomics and artificial intelligence has provided new methods for HE prediction with high accuracy. Therefore, this article reviews the latest research progress in CT imaging, radiomics, and artificial intelligence of HE, in order to help identify high-risk patients for HE in clinical practice.

show abstract

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

Matsumoto,

Ishihara,

Matsuda

et al. 2024

JAHA

View full text Add to dashboard Cite

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.

show abstract

CT-based deep learning model for predicting hospital discharge outcome in spontaneous intracerebral hemorrhage

Cited by 5 publications

References 34 publications

Predicting the 90-day prognosis of stereotactic brain hemorrhage patients by multiple machine learning using radiomic features combined with clinical features

Predicting the 90-day prognosis of stereotactic brain hemorrhage patients by multiple machine learning using radiomic features combined with clinical features

Research advances in predicting the expansion of hypertensive intracerebral hemorrhage based on CT images: an overview

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

Contact Info

Product

Resources

About