Practical machine learning estimates body weight from CT dose reports

A machine learning model using routine CT dose report metrics estimated adult body weight with a mean absolute error of 2.83 kg; 88.8% of exams were within 10% of measured weight. Findings from single-center, 2496-patient study.

• Retrospective single-center study of 2496 adults used LightGBM regression on dose-report metrics from three CT scanners.
• Extended model achieved MAE 2.83 kg with 88.8% of estimates within ±10% of measured weight; scanner-wise cross-validation MAE ranged 3.16–4.37 kg.
• Single-institution design limits generalizability; external validation is needed.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.