AUTHOR=Guo Kun , Zhu Bo , Li Rong , Xi Jing , Wang Qi , Chen KongBo , Shao Yuan , Liu Jiaqi , Cao Weili , Liu Zhiqin , Di Zhengli , Gu Naibing 

TITLE=Machine learning-based nomogram: integrating MRI radiomics and clinical indicators for prognostic assessment in acute ischemic stroke

JOURNAL=Frontiers in Neurology

VOLUME=Volume 15 - 2024

YEAR=2024

URL=https://www.frontiersin.org/journals/neurology/articles/10.3389/fneur.2024.1379031

DOI=10.3389/fneur.2024.1379031

ISSN=1664-2295

ABSTRACT=Acute Ischemic Stroke (AIS) continues to be a critical global health issue, significantly impacting mortality and morbidity rates. Efficiently predicting the prognosis of AIS is essential for guiding therapeutic decisions and improving patient outcomes. This study introduces a pioneering approach that combines a machine learning-derived radiomics signature from multi-parametric MRI scans with clinical factors to predict AIS prognosis accurately. By integrating advanced imaging features with pertinent clinical data, we have developed a nomogram that offers a novel tool for healthcare professionals to assess the potential outcomes of AIS patients more precisely.
Our research involved analyzing 506 patients diagnosed with AIS from two medical centers, with the patient cohort divided into training and validation groups. Through comprehensive logistic regression analysis, we identified several key clinical risk factors and, alongside 4682 radiomic features extracted from T1-weighted, T2-weighted, and diffusion-weighted imaging, constructed a predictive clinical-radiomics model. The efficacy of this model was rigorously evaluated, demonstrating its substantial accuracy in both training and validation cohorts.
This innovative clinical-radiomics model facilitates predicting AIS outcomes, underlining the transformative potential of integrating machine learning algorithms with radiomic and clinical data in stroke management. The nomogram developed through this study serves as a valuable tool for clinicians, enabling more personalized and effective treatment strategies. Ultimately, it aims to enhance the quality of care for AIS patients.