Related Experiment Video
Updated: Jul 3, 2026
Segmentation and Linear Measurement for Body Composition Analysis using Slice-O-Matic and Horos
Published on: March 21, 2021
Development of an automated, imaging-based preoperative screening model for early identification of malnutrition in
Background:
Clinical malnutrition affects one in five abdominal surgery patients and increases postoperative complications and mortality. Current screening occurs after admission, closing the window for preoperative nutritional intervention. No objective, scalable preoperative screening tool exists.
Objective:
To determine whether automated volumetric CT-based body composition analysis improves preoperative identification of surgical patients at risk for clinical malnutrition compared to clinical variables or single-slice imaging alone.
Methods:
Retrospective cohort study of adults undergoing elective abdominal surgery at a quaternary academic medical center (2018-2021) with a preoperative CT scan within 90 days and complete nutrition assessment. Clinical malnutrition was diagnosed by a registered dietitian using ASPEN/AND criteria. Three sex-stratified Elastic Net models were compared: (1) base clinical variables; (2) base plus L3 single-slice skeletal muscle index and attenuation; and (3) base plus comprehensive 3D volumetric quantification of five muscle groups and two fat depots. Discrimination (AUROC), calibration (Brier score), and clinical utility (decision curve analysis) were assessed via 10-fold cross-validation.
Results:
Among 1,143 patients (52.4% female; mean age 60.5 years), 231 (20.2%) were diagnosed with malnutrition. Malnourished patients had significantly higher complication rates (36.4% vs. 15.4%, p <0.001) and prolonged length of stay (45.9% vs. 16.4%, p <0.001). Critically, 27.2% of malnourished patients were not flagged as at-risk by the standard Malnutrition Screening Tool. The volumetric model (Model 3) achieved the highest discrimination (males: AUROC 0.808; females: 0.794) and best calibration (males: Brier 0.129; females: 0.124), significantly outperforming both the base model (males: p =0.004; females: p <0.001) and L3 model (males: p =0.019; females: p <0.001). L3 features modestly improved discrimination but paradoxically worsened calibration - an effect corrected by volumetric features. Sex-specific risk profiles differed markedly, with ASA classification dominating female models and demographic factors dominating male models.
Conclusions:
Automated volumetric CT body composition analysis significantly improves preoperative malnutrition risk identification, with sex-stratified models revealing distinct risk profiles. Leveraging imaging already obtained for surgical planning, this approach opens a preoperative window for nutritional intervention that current practice fails to utilize.
