Department of Radiology, Body Imaging Service, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
Department of Radiology, Interventional Radiology Service, Memorial Sloan Kettering Cancer Center, New York, NY, USA.
J Digit Imaging. 2022 Feb;35(1):1-8. doi: 10.1007/s10278-021-00532-4. Epub 2021 Nov 9.
The aim of the study was to evaluate the performance of the Prophet forecasting procedure, part of the Facebook open-source Artificial Intelligence portfolio, for forecasting variations in radiological examination volumes. Daily CT and MRI examination volumes from our institution were extracted from the radiology information system (RIS) database. Data from January 1, 2015, to December 31, 2019, was used for training the Prophet algorithm, and data from January 2020 was used for validation. Algorithm performance was then evaluated prospectively in February and August 2020. Total error and mean error per day were evaluated, and computational time was logged using different Markov chain Monte Carlo (MCMC) samples. Data from 610,570 examinations were used for training; the majority were CTs (82.3%). During retrospective testing, prediction error was reduced from 19 to < 1 per day in CT (total 589 to 17) and from 5 to < 1 per day (total 144 to 27) in MRI by fine-tuning the Prophet procedure. Prospective prediction error in February was 11 per day in CT (9934 predicted, 9667 actual) and 1 per day in MRI (2484 predicted, 2457 actual) and was significantly better than manual weekly predictions (p = 0.001). Inference with MCMC added no substantial improvements while vastly increasing computational time. Prophet accurately models weekly, seasonal, and overall trends paving the way for optimal resource allocation for radiology exam acquisition and interpretation.
这项研究的目的是评估 Prophet 预测程序的性能，该程序是 Facebook 开源人工智能组合的一部分，用于预测放射学检查量的变化。我们机构的每日 CT 和 MRI 检查量从放射信息系统 (RIS) 数据库中提取。2015 年 1 月 1 日至 2019 年 12 月 31 日的数据用于训练 Prophet 算法，2020 年 1 月的数据用于验证。然后在 2020 年 2 月和 8 月前瞻性评估算法性能。评估了每日总误差和平均误差，并使用不同的马尔可夫链蒙特卡罗 (MCMC) 样本记录计算时间。使用 610,570 次检查的数据进行培训；其中大部分是 CT（82.3%）。在回顾性测试中，通过微调 Prophet 程序，CT 的预测误差从每天 19 次减少到每天 <1 次（总 589 次减少到 17 次），MRI 的预测误差从每天 5 次减少到每天 <1 次（总 144 次减少到 27 次）。2 月的前瞻性预测误差在 CT 为每天 11 次（预测 9934 次，实际 9667 次），MRI 为每天 1 次（预测 2484 次，实际 2457 次），明显优于手动每周预测（p = 0.001）。使用 MCMC 进行推断并没有显著提高，而大大增加了计算时间。Prophet 准确地建模了每周、季节性和总体趋势，为放射科检查获取和解释的资源优化分配铺平了道路。
