Descriptive Time Series Analysis for Downtime Prediction Using the Maintenance Data of a Medical Linear Accelerator

A medical linear accelerator (LINAC) delivers high-energy X-rays or electrons to the patient’s tumor. In this study, we categorized failures and predicted downtime leading discontinuous radiation treatment using a descriptive time series analysis of 20-year maintenance dataset LINAC. LINAC failure records for 359 instances was collected from 2001 2021. Next, performed institution-specific seasonal autoregressive integrated moving average (ARIMA) modeling analyze causes categories predict downtime. Furthermore, evaluated performance predictive model standard error metrics statistical methods. Our results show that will increase by 95 h/year after 2022 100 2023. The accumulated in 2029 is be maximum 2820 h. modeled ARIMA showed significance (p < 0.001) with residual σ2 (328.33 ± 9.4). addition, forecasting assessed mean absolute percentage (MAPE). parts where major occurred were multileaf collimator (25.2%), gantry couch motion part (15.4%), dosimetric (11.7%), computer console (10.0%). Using development specific our institution, reach up