โก Quick Summary
This study developed multiple machine learning models to predict the risk of early intracranial aneurysm (IA) rupture, utilizing data from 989 patients. The models demonstrated promising performance, with the random forest (RF) model achieving an AUC of 0.839 in the test set, indicating its potential for clinical application.
๐ Key Details
- ๐ Dataset: 989 patients diagnosed with IA
- ๐งฉ Features used: Clinical characteristics, blood indicators, IA morphological parameters
- โ๏ธ Technologies: Random Forest (RF), Support Vector Machine (SVM), Artificial Neural Network (ANN)
- ๐ Performance: RF AUC: 0.839, SVM AUC: 0.806, ANN AUC: 0.860
๐ Key Takeaways
- ๐ Predictive models can significantly aid in assessing IA stability.
- ๐ Age, white blood cell count (WBC), and uric acid (UA) were identified as critical predictors of IA stability.
- ๐ค Machine learning methods like RF, SVM, and ANN show varying degrees of effectiveness.
- ๐ฅ The study included both stable (561) and unstable (428) IA patients.
- ๐ The RF model outperformed others in both training and test sets.
- ๐ Conducted at Central Hospital of Dalian University of Technology from 2010 to 2022.
- ๐ฌ Clinical implications suggest improved risk assessment for IA patients.
๐ Background
Intracranial aneurysms (IAs) pose a significant risk of rupture, leading to severe neurological complications. Traditional methods of assessing IA stability often lack precision, highlighting the need for innovative approaches. The integration of artificial intelligence in medical diagnostics offers a promising avenue for enhancing predictive accuracy and patient outcomes.
๐๏ธ Study
This study, conducted at the Central Hospital of Dalian University of Technology, aimed to develop predictive models for IA stability using data collected from January 2010 to June 2022. Researchers gathered comprehensive information on clinical characteristics, blood indicators, and IA morphological parameters from 989 patients diagnosed with IA through CT angiography.
๐ Results
The results indicated that the random forest model achieved the highest performance metrics, with sensitivity ranging from 71.9% to 78.8% and an AUC of 0.809 in the test set. The support vector machine and artificial neural network models also showed respectable performance, but with lower AUC values of 0.806 and 0.860, respectively. Notably, age, WBC, and UA were identified as significant factors influencing IA stability.
๐ Impact and Implications
The findings from this study have substantial implications for clinical practice. By leveraging machine learning algorithms, healthcare professionals can enhance their ability to predict IA rupture risk, leading to timely interventions and improved patient management. This research underscores the transformative potential of AI in neurosurgery and vascular medicine, paving the way for more personalized treatment strategies.
๐ฎ Conclusion
This study highlights the effectiveness of machine learning in developing predictive models for intracranial aneurysm stability. The promising results, particularly from the random forest model, suggest that AI can play a crucial role in clinical decision-making. Continued research in this area is essential to refine these models and integrate them into routine clinical practice, ultimately improving patient outcomes.
๐ฌ Your comments
What are your thoughts on the application of artificial intelligence in predicting intracranial aneurysm stability? We invite you to share your insights and engage in a discussion! ๐ฌ Leave your comments below or connect with us on social media:
Artificial intelligence applied to development of predictive stability model for intracranial aneurysms.
Abstract
BACKGROUND: We aimed to develop multiple machine learning models to predict the risk of early intracranial aneurysms (IAs) rupture, evaluate and compare the performance of predictive models.
METHODS: Information related to patients diagnosed with IA by CT angiography and clinicians in Central hospital of Dalian University of Technology from January 2010 to June 2022 was collected, including clinical characteristics, blood indicators and IA morphological parameters. IA with rupture or maximum growthโโฅโ0.5ย mm within 1ย month of first diagnosis was considered unstable. The relevant factors affecting IA stability were screened and predictive models were developed based on the above three levels, including random forest (RF), support vector machine (SVM), and artificial neural network (ANN). Sensitivity, specificity, accuracy and area under curve (AUC) value were used to evaluate the predictive models.
RESULTS: A total of 989 IA patients were included in the study, including 561 stable patients and 428 unstable patients. For RF models, the training set showed that sensitivity, specificity, accuracy and the AUC values were 72.8-83.7%, 76.9-86.9%, 75.1-84.1% and 0.748 (0.719-0.778)-0.839 (0.814-0.864), respectively; after test set validation, the results were 71.9-78.8%, 75.0-84.0%, 73.6-81.1% and 0.734 (0.688-0.781)-0.809 (0.768-0.850), respectively. For SVM models, the training set were 66.0-80.2%, 76.5-85.5%, 71.7-82.3%, 0.712 (0.682-0.743)-0.913 (0.884-0.924), respectively; the test set were 44.2-78.3%, 63.4-84.4%, 57.9-80.9%, 0.699 (0.651-0.747)-0.806 (0.765-0.848), respectively. For ANN models, the training set were 66.8-83.0%, 75.3-82.3%, 71.6-82.1%, 0.783 (0.757-0.808)-0.897 (0.879-0.914); the test set were 63.1-76.3%, 65.5-84.0%, 64.4-80.6%, 0.680 (0.593-0.694)-0.860 (0.821-0.899). The results of variable importance showed that age, white blood cell count (WBC) and uric acid (UA) played an important role in predicting the stability of IA.
CONCLUSIONS: The predictive stability models of IA based on three artificial intelligence methods shows good clinical application. Age, WBC and UA played an important role in predicting the IA stability, and were potentially important predictors.
Author: [‘Tao J’, ‘Wei W’, ‘Song M’, ‘Hu M’, ‘Zhao H’, ‘Li S’, ‘Shi H’, ‘Jia L’, ‘Zhang C’, ‘Dong X’, ‘Chen X’]
Journal: Eur J Med Res
Citation: Tao J, et al. Artificial intelligence applied to development of predictive stability model for intracranial aneurysms. Artificial intelligence applied to development of predictive stability model for intracranial aneurysms. 2024; 29:505. doi: 10.1186/s40001-024-02101-1