Abstract
Predictions of patient outcomes after a given therapy are fundamental to medical practice. We employ a machine learning approach towards predicting the outcomes after stereotactic radiosurgery for cerebral arteriovenous malformations (AVMs). Using three prospective databases, a machine learning approach of feature engineering and model optimization was implemented to create the most accurate predictor of AVM outcomes. Existing prognostic systems were scored for purposes of comparison. The final predictor was secondarily validated on an independent site’s dataset not utilized for initial construction. Out of 1,810 patients, 1,674 to 1,291 patients depending upon time threshold, with 23 features were included for analysis and divided into training and validation sets. The best predictor had an average area under the curve (AUC) of 0.71 compared to existing clinical systems of 0.63 across all time points. On the heldout dataset, the predictor had an accuracy of around 0.74 at across all time thresholds with a specificity and sensitivity of 62% and 85% respectively. This machine learning approach was able to provide the best possible predictions of AVM radiosurgery outcomes of any method to date, identify a novel radiobiological feature (3D surface dose), and demonstrate a paradigm for further development of prognostic tools in medical care.
Highlights
Predicting the outcome of a specific patient treated with a particular therapy is fundamental to medical practice
Of the 1,810 patients, a varying number were excluded for incomplete baseline data or failure to achieve the endpoint by a given time threshold leaving 1,291–1,674 patients at each time threshold with complete 23 feature profiles which were graded utilizing current prognostic models for arteriovenous malformations (AVMs) radiosurgery outcomes (RBAS, Virginia Radiosurgery AVM Scale (VRAS), SM) (Fig. 1, Table 1)
Of the patients considered as having been obliterated, 76.8% were confirmed with cerebral angiography, while 23% were noted on magnetic resonance imaging (MRI) only
Summary
Predicting the outcome of a specific patient treated with a particular therapy is fundamental to medical practice. In the case of cerebral arteriovenous malformations (AVMs), several scoring systems have been developed to augment clinician experience in predicting individual patient outcomes after treatment with radiosurgery, a type of highly focused radiation therapy[1,2,3,4,5,6,7,8]. Machine learning is an interdisciplinary field combining computer science and mathematics to develop models with the intent of delivering maximal predictive accuracy[17] Combining these new analytical tools with modern clinical databases and registries promises an entirely new approach towards conducting medical research and, ideally, developing ways to predict individual outcomes and the risk to benefit profiles from specific therapies[18]. Our aims are to (1) apply a machine learning approach towards predicting individual patient outcomes after AVM radiosurgery and (2) analyze the predictive capability of existing grading systems for AVM patients treated with radiosurgery
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.