Use of ROC analysis and machine learning with an independent dose calculation system reduces number of physical dose measurements required for patient-specific quality assurance.

Hasse, K; Scholey, J; Ziemer, B P; Natsuaki, Y; Morin, O; Solberg, T D; Hirata, E; Valdes, G; Witztum, A

PURPOSE To assess the use of machine learning methods and Mobius 3D (M3D) dose calculation software to reduce the number of physical ion chamber (IC) dose measurements required for patient-specific quality assurance during COVID. METHODS AND MATERIALS In this study, 1464 inversely-planned treatments using Pinnacle or Raystation treatment planning software (TPS) were delivered using Elekta Versa HD, and Varian Truebeam and Truebeam STx linear accelerators between June 2018 and November 2019. For each plan, an independent dose calculation was performed using M3D and an absolute dose measurement was taken using a Pinpoint ion chamber inside the Mobius phantom. The point dose differences between the TPS and M3D calculation, and between TPS and IC measurement were calculated. Agreement between the TPS and IC was used to define the ground truth plan failure. In order to reduce the on-site personnel during the pandemic, two methods ROC analysis (n=1464) and machine learning (n=603) were used to identify patient plans that would require physical dose measurements. RESULTS In the ROC analysis, a pre-delivery M3D difference threshold of 3% identifies plans that fail an IC measurement at a 4% threshold with 100% sensitivity and 76.3% specificity. This indicates that fewer than 25% of plans would require a physical dose measurement. A threshold of 1% on a machine learning model is able to identify plans that fail an IC measurement at a 3% threshold with 100% sensitivity and 54.3% specificity, leading to fewer than 50% of plans that require a physical dose measurement. CONCLUSIONS It is possible to identify plans that are more likely to fail IC patient-specific quality assurance (QA) measurements prior to delivery. This possibly allows for a reduction of physical measurements taken, freeing up significant clinical resources and reducing the required amount of on-site personnel while maintaining patient safety.