Feature Analysis of Predictors Affecting the Nidus Obliteration of Linear Accelerator-Based Radiosurgery for Arteriovenous Malformations Using Explainable Predictive Modeling
Source abstract
Abstract
This study aimed to evaluate prognostic factors associated with nidus obliteration following stereotactic radiosurgery (SRS) for cerebral arteriovenous malformations. From January 2001 to January 2018, 119 patients who underwent SRS with AVM were studied to analyze major prognostic factors (age, prescription dose (Gy), volume (mm3), nidus size (cm), and Spetzler–Martin (SM) grade) for nidus obliteration. A random forest and tree explainer was used to construct a predictive model of nidus obliteration. The prognostic factors affecting nidus obliteration from most to least important were age, nidus size, volume, total prescription dose, and SM grade, using a predictive model. In a specific case for nidus size (1.5 cm), total dose (23 Gy), and SM grade (2), the result showed a high obliteration score of 0.75 with the actual obliteration period of 6 months spent; the mean AUC was 0.90 in K-fold cross validation. The predictive model identified the main contributing factors associated with a prognostic of nidus obliteration from linear accelerator-based SRS for cerebral AVM. It was confirmed that the results, including the prognostic factors, are potentially useful for outcome prediction for patient and treatment.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Vascular Malformations Diagnosis and Treatment · Intracranial Aneurysms: Treatment and Complications · Meningioma and schwannoma management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Neurosurgery, Neuroscience and Radiosurgery Hybrid Research Center, Inje University Ilsan Paik Hospital, College of Medicine, Goyang 10380, Republic of Korea
Funding
2018 Inje University
References (44)
Show source-provided references
1. Stereotactic radiosurgery for arteriovenous malformations of the brain10.3171/jns.1991.75.4.0512 ↗
2. Stereotaxic radiosurgery for cerebral arteriovenous malformations
3. Stereotactic radiosurgery for brain arteriovenous malformations: Evaluation of obliteration and review of associated predictors10.1016/j.jstrokecerebrovasdis.2020.104863 ↗
4. The natural history and predictive features of hemorrhage from brain arteriovenous malformations10.1161/STROKEAHA.108.524678 ↗
5. Risk of endovascular treatment of brain arteriovenous malformations10.1161/01.STR.0000020123.80940.B2 ↗
6. Features predictive of brain arteriovenous malformation hemorrhage: Extrapolation to a physiologic model10.1161/STROKEAHA.114.005170 ↗
7. Predictors of hemorrhage in patients with untreated brain arteriovenous malformation10.1212/01.wnl.0000210524.68507.87 ↗
8. Factors associated with successful arteriovenous malformation radiosurgery10.1097/00006123-199806000-00020 ↗
9. Stereotactic radiosurgery for brainstem arteriovenous malformations: Factors affecting outcome10.3171/jns.2004.100.3.0407 ↗
10. Analysis of factors predictive of success or complications in arteriovenous malformation radiosurgery10.1227/01.NEU.0000043692.51385.91 ↗
11. Radiosurgery for cerebral arteriovenous malformations in elderly patients: Effect of advanced age on outcomes after intervention10.1016/j.wneu.2015.05.012 ↗
12. Clinical outcomes of stereotactic radiosurgery for cerebral arteriovenous malformations in pediatric patients: Systematic review and meta-analysis10.1093/neuros/nyz146 ↗
13. Analysis of nidus obliteration rates after gamma knife surgery for arteriovenous malformations based on long-term follow-up data: The University of Tokyo experience10.3171/jns.2004.101.1.0018 ↗
14. Using a machine learning approach to predict outcomes after radiosurgery for cerebral arteriovenous malformations10.1038/srep21161 ↗
15. A machine learning model predicts the outcome of SRS for residual arteriovenous malformations after partial embolization: A real-world clinical obstacle10.1016/j.wneu.2022.03.007 ↗
16. Machine learning for predicting hemorrhage in pediatric patients with brain arteriovenous malformation10.3171/2022.4.PEDS21470 ↗
17. A survey on explainable artificial intelligence (xai): Toward medical xai10.1109/TNNLS.2020.3027314 ↗
18. Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI10.1016/j.inffus.2019.12.012 ↗
19. XAI—Explainable artificial intelligence10.1126/scirobotics.aay7120 ↗
20. Prediction of AVM obliteration after stereotactic radiotherapy using radiobiological modelling10.1088/0031-9155/47/14/308 ↗
21. Comparative analysis of arteriovenous malformation grading scales in predicting outcomes after stereotactic radiosurgery10.3171/2015.11.JNS151300 ↗
22. Angiographic features help predict outcome after stereotactic radiosurgery for the treatment of pediatric arteriovenous malformations10.1007/s00381-013-2231-4 ↗
23. Machine learning and neurosurgical outcome prediction: A systematic review10.1016/j.wneu.2017.09.149 ↗
24. Interpretation of machine learning models using shapley values: Application to compound potency and multi-target activity predictions10.1007/s10822-020-00314-0 ↗
25. Random forests10.1023/A:1010933404324 ↗
26. Assessment and comparison of prognostic classification schemes for survival data10.1002/(SICI)1097-0258(19990915/30)18:17/18<2529::AID-SIM274>3.0.CO;2-5 ↗
27. Stereotactic radiosurgery at a low marginal dose for the treatment of pediatric arteriovenous malformations: Obliteration, complications, and functional outcomes10.3171/2014.3.PEDS13381 ↗
28. Risk for hemorrhage during the 2-year latency period following gamma knife radiosurgery for arteriovenous malformations10.1016/S0360-3016(00)01432-2 ↗
29. Stereotactic radiosurgery for Spetzler-Martin Grade III arteriovenous malformations: An international multicenter study10.3171/2016.1.JNS152564 ↗
30. Machine learning in medicine10.1056/NEJMra1814259 ↗
31. A critical review for developing accurate and dynamic predictive models using machine learning methods in medicine and health care10.1007/s10916-017-0715-6 ↗
32. Machine learning in medicine: A practical introduction
33. Machine learning: Supervised methods10.1038/nmeth.4551 ↗
34. Machine learning, practically speaking10.1038/s41592-019-0432-9 ↗
35. Big data, machine learning, and artificial intelligence: A field guide for neurosurgeons
36. A systematic review on machine learning in neurosurgery: The future of decision-making in patient care
37. Machine learning applications to clinical decision support in neurosurgery: An artificial intelligence augmented systematic review10.1007/s10143-019-01163-8 ↗
38. Machine learning in neurosurgery: A global survey10.1007/s00701-020-04532-1 ↗
39. Radiosurgery for arteriovenous malformations in children10.3171/ped.2006.104.6.388 ↗
40. Radiosurgery for cerebral AVMs in children and adolescents: The neurobehavioral outcome10.3171/jns.1997.86.2.0207 ↗
41. Stereotactic radiosurgery in children and adolescents10.1159/000120530 ↗
42. Dynamic conformal arc radiosurgery for arteriovenous malformations: Outcome and influence of clinical and dosimetrical data10.1016/j.radonc.2017.03.013 ↗
43. Stereotactic radiosurgery for brain metastases: Analysis of outcome and risk of brain radionecrosis10.1186/1748-717X-6-48 ↗
44. Deep learning: A review for the radiation oncologist10.3389/fonc.2019.00977 ↗