Search

Purpose: The emerging online adaptive radiation therapy (OART) treatment strategy based on cone beam computed tomography allows for real-time replanning according to a patient's current anatomy. However, implementing this procedure requires a new approach across the patient's care path and monitoring of the “black box” adaptation process. This study identifies high-risk failure modes (FMs) associated with AI-driven OART and proposes an interdisciplinary workflow to mitigate potential medical errors from highly automated processes, enhance treatment efficiency, and reduce the burden on clinicians. Methods and Materials: An interdisciplinary working group was formed to identify safety concerns in each process step using failure mode and effects analysis (FMEA). Based on the FMEA results, the team designed standardized procedures and safety checklists to prevent errors and ensure successful task completion. The Risk Priority Numbers (RPNs) for the top twenty FMs were calculated before and after implementing the proposed workflow to evaluate its effectiveness. Three hundred seventy-four adaptive sessions across 5 treatment sites were performed, and each session was evaluated for treatment safety and FMEA assessment. Results: The OART workflow has 4 components, each with 4, 8, 13, and 4 sequentially executed tasks and safety checklists. Site-specific template preparation, which includes disease-specific physician directives and Intelligent Optimization Engine template testing, is one of the new procedures introduced. The interdisciplinary workflow significantly reduced the RPNs of the high-risk FMs, with an average decrease of 110 (maximum reduction of 305.5 and minimum reduction of 27.4). Conclusions: This study underscores the importance of addressing high-risk FMs associated with AI-driven OART and emphasizes the significance of safety measures in its implementation. By proposing a structured interdisciplinary workflow and integrated checklists, the study provides valuable insights into ensuring the safe and efficient delivery of OART while facilitating its effective integration into clinical practice.

Purpose: Hippocampal volume (HV) is an established predicting factor for neurocognitive function (NCF) in neurodegenerative disease. Whether the same phenomenon exists with hippocampal-avoidant whole brain radiation therapy is not known; therefore, we assessed the association of baseline HV with NCF among patients enrolled on RTOG 0933. Methods and Materials: Hippocampal volume and total brain volume were calculated from the radiation therapy plan. Hippocampal volume was correlated with baseline and 4-month NCF scores (Hopkins Verbal Learning Test–Revised [HVLT-R] Total Recall [TR], Immediate Recognition, and Delayed Recall [DR]) using Pearson correlation. Deterioration in NCF was defined per the primary endpoint of RTOG 0933(mean 4-month relative decline in HVLT-R DR). Comparisons between patients with deteriorated and nondeteriorated NCF were made using the Wilcoxon test. Results: Forty-two patients were evaluable. The median age was 56.5 years (range, 28-83 years), and 81% had a class II recursive partitioning analysis. The median total, right, and left HVs were 5.4 cm3 (range, 1.9-7.4 cm3), 2.8 cm3 (range, 0.9-4.0 cm3), and 2.7 cm3 (range, 1.0-3.7 cm3), respectively. The median total brain volume was 1343 cm3 (range, 1120.5-1738.8 cm3). For all measures of corrected HV, increasing HV was associated with higher baseline HVLT-R TR and DR scores (ρ: range, 0.35-0.40; P-value range, .009-.024) and 4-month TR and DR scores (ρ: range, 0.29-0.40; P-value range, .009-.04), with the exception of right HV and 4-month DR scores (ρ: 0.29; P = .059). There was no significant association between HV and NCF change between baseline and 4 months. Fourteen patients (33.3%) developed NCF deterioration per the primary endpoint of RTOG 0933. There was no significant difference in HV between patients with deteriorated and nondeteriorated NCF, although in all instances, patients with deteriorated NCF had numerically lower HV. Conclusions: Larger HV was positively associated with improved performance on baseline and 4-month HVLT-R TR and DR scores in patients with brain metastases undergoing hippocampal-avoidant whole brain radiation therapy but was not associated with a change in NCF.

Purpose: NRG Oncology's RTOG 0933 demonstrated benefits to memory preservation after hippocampal avoidant whole-brain radiation therapy (HA-WBRT), the avoidance of radiation dose to the hippocampus (using intensity modulated radiation planning and delivery techniques) during WBRT, supporting the hypothesis of hippocampal radiosensitivity and associated memory specificity. However, some patients demonstrated cognitive decline, suggesting mechanisms outside hippocampal radiosensitivity play a role. White matter injury (WMI) has been implicated in radiation therapy–induced neurocognitive decline. This secondary analysis explored the relationship between pretreatment WMI and memory after HA-WBRT. Methods and Materials: Volumetric analysis of metastatic disease burden and disease-unrelated WMI was conducted on the pretreatment magnetic resonance image. Correlational analyses were performed examining the relationship between pretreatment WMI and Hopkins Verbal Learning Test-Revised (HVLT-R) outcomes at baseline and 4 months after HA-WBRT. Results: In the study, 113 patients received HA-WBRT. Of 113 patients, 33 underwent pretreatment and 4-month posttreatment HVLT testing and pretreatment postcontrast volumetric T1 and axial T2/fluid-attenuated inversion recovery magnetic resonance imaging. Correlation was found between larger volumes of pretreatment WMI and decline in HVLT-R recognition (r = 0.54, P