Dose-report-driven body weight estimation in diagnostic CT using a practical machine learning framework.

In radiology practice, patient body weight is important for contrast media and radiopharmaceutical dosing, radiation dose management, and examination-related workflows, yet it is not consistently available in routine clinical settings. The purpose of this study was to investigate the feasibility of estimating adult body weight using diagnostic CT dose report metrics across CT systems. This retrospective single-center study included 2496 consecutive adults who underwent diagnostic CT on three scanners. Measured body weight served as the reference standard. LightGBM regression was evaluated in three settings: (1) a baseline model using dose report-derived patient size and exposure metrics, including water-equivalent diameter and sex; (2) an extended model additionally incorporating body region and CT system; and (3) scanner-wise cross-validation to assess cross-scanner generalizability. For settings 1 and 2, data were split into training, validation, and test sets (75%/15%/10%). On the independent test set, the baseline model achieved a mean absolute error of 3.07 kg, with 86.0% of examinations within ± 10% of reference weight. The extended model showed a slight improvement (mean absolute error, 2.83 kg; examinations within ± 10%, 88.8%). In scanner-wise cross-validation, mean absolute error ranged from 3.16 to 4.37 kg. Adult body weight can be estimated with practical accuracy using routinely available diagnostic CT dose-report information in a single-institution, multi-scanner setting.