Clinical decision support of radiotherapy treatment planning: A data-driven machine learning strategy for patient-specific dosimetric decision making.
Gilmer Valdes, Charles B Simone, Josephine Chen, Alexander Lin, Sue S Yom, Adam J Pattison, Colin M Carpenter, Timothy D Solberg
Author Information
Gilmer Valdes: Department of Radiation Oncology, University of California, San Francisco, United States. Electronic address: gilmer.valdes@ucsf.edu.
Charles B Simone: University of Maryland Medical Center, Baltimore, United States.
Josephine Chen: Department of Radiation Oncology, University of California, San Francisco, United States.
Alexander Lin: Department of Radiation Oncology, University of Pennsylvania, Philadelphia, United States.
Sue S Yom: Department of Radiation Oncology, University of California, San Francisco, United States; Department of Otolaryngology-Head and Neck Surgery, San Francisco, United States.
Adam J Pattison: Siris Medical, Redwood City, United States.
Colin M Carpenter: Siris Medical, Redwood City, United States.
Timothy D Solberg: Department of Radiation Oncology, University of California, San Francisco, United States.
BACKGROUND AND PURPOSE: Clinical decision support systems are a growing class of tools with the potential to impact healthcare. This study investigates the construction of a decision support system through which clinicians can efficiently identify which previously approved historical treatment plans are achievable for a new patient to aid in selection of therapy. MATERIAL AND METHODS: Treatment data were collected for early-stage lung and postoperative oropharyngeal cancers treated using photon (lung and head and neck) and proton (head and neck) radiotherapy. Machine-learning classifiers were constructed using patient-specific feature-sets and a library of historical plans. Model accuracy was analyzed using learning curves, and historical treatment plan matching was investigated. RESULTS: Learning curves demonstrate that for these datasets, approximately 45, 60, and 30 patients are needed for a sufficiently accurate classification model for radiotherapy for early-stage lung, postoperative oropharyngeal photon, and postoperative oropharyngeal proton, respectively. The resulting classification model provides a database of previously approved treatment plans that are achievable for a new patient. An exemplary case, highlighting tradeoffs between the heart and chest wall dose while holding target dose constant in two historical plans is provided. CONCLUSIONS: We report on the first artificial-intelligence based clinical decision support system that connects patients to past discrete treatment plans in radiation oncology and demonstrate for the first time how this tool can enable clinicians to use past decisions to help inform current assessments. Clinicians can be informed of dose tradeoffs between critical structures early in the treatment process, enabling more time spent on finding the optimal course of treatment for individual patients.
