Improving the prediction of chemotherapy dose-limiting toxicity in colon cancer patients using an AI-CT-based 3D body composition of the entire L1-L5 lumbar spine

Ke Cao; Josephine Yeung; Matthew Y K Wei; Cheuk Shan Choi; Margaret Lee; Lincoln J Lim; Yasser Arafat; Paul N Baird; Justin M C Yeung

doi:10.1007/s00520-024-09108-8

Improving the prediction of chemotherapy dose-limiting toxicity in colon cancer patients using an AI-CT-based 3D body composition of the entire L1-L5 lumbar spine

Support Care Cancer. 2024 Dec 21;33(1):45. doi: 10.1007/s00520-024-09108-8.

Authors

Ke Cao¹, Josephine Yeung¹, Matthew Y K Wei^{1

2}, Cheuk Shan Choi¹, Margaret Lee³, Lincoln J Lim^{1

4}, Yasser Arafat^{1

2}, Paul N Baird^#⁵, Justin M C Yeung^#^{6

7}

Affiliations

¹ Department of Surgery, Western Precinct, University of Melbourne, Melbourne, Australia.
² Department of Colorectal Surgery, Western Health, Melbourne, Australia.
³ Department of Oncology, Western Health, Melbourne, Australia.
⁴ Department of Radiology, Western Health, Melbourne, Australia.
⁵ Department of Surgery, University of Melbourne, Melbourne, Australia.
⁶ Department of Surgery, Western Precinct, University of Melbourne, Melbourne, Australia. [email protected].
⁷ Department of Colorectal Surgery, Western Health, Melbourne, Australia. [email protected].

^# Contributed equally.

PMID: 39707027
DOI: 10.1007/s00520-024-09108-8

Abstract

Purpose: Chemotherapy dose-limiting toxicities (DLT) pose a significant challenge in successful colon cancer treatment. Body composition analysis may enable tailored interventions thereby supporting the mitigation of chemotherapy toxic effects. This study aimed to evaluate and compare the effectiveness of using three-dimensional (3D) CT body composition measures from the entire lumbar spine levels (L1-L5) versus a single vertebral level (L3), the current gold standard, in predicting chemotherapy DLT in colon cancer patients.

Methods: Retrospective analysis of 184 non-metastatic colon cancer patients receiving adjuvant chemotherapy was performed. DLT was defined as any occurrence of dose reduction or discontinuation due to chemotherapy toxicity. Using artificial intelligence (AI) auto-segmentation, 3D body composition measurements were obtained from patients' L1-L5 levels on CT imaging. The effectiveness of patients' 3D L3 body composition measurement and incorporating data from the entire L1-L5 (including L3) region in predicting DLT was examined.

Results: Of the 184 patients, 112 (60.9%) experienced DLT. Neuropathy was the most common toxicity (49/112, 43.8%) followed by diarrhea (35.7%) and nausea/vomiting (33%). Patients with DLT had lower muscle volume at all lumbar levels compared to those without. The machine learning model incorporating L1-L5 data and patient clinical data achieved high predictive performance (AUC = 0.75, accuracy = 0.75), outperforming the prediction using single L3 level (AUC = 0.65, accuracy = 0.65).

Conclusion: Evaluating a patient's body composition allowed prediction of chemotherapy toxicities for colon cancer. Incorporating fully automated body composition analysis of CT slices from the entire lumbar region offers promising performance in early identification of high-risk individuals, with the ultimate aim of improving patient's quality of life.

Keywords: 3D body composition; Artificial intelligence; Cancer care; Chemotherapy toxicity.

MeSH terms

Adult
Aged
Aged, 80 and over
Antineoplastic Agents / administration & dosage
Antineoplastic Agents / adverse effects
Artificial Intelligence*
Body Composition* / drug effects
Chemotherapy, Adjuvant / adverse effects
Chemotherapy, Adjuvant / methods
Colonic Neoplasms* / drug therapy
Colonic Neoplasms* / pathology
Dose-Response Relationship, Drug
Female
Humans
Imaging, Three-Dimensional / methods
Lumbar Vertebrae*
Male
Middle Aged
Retrospective Studies
Tomography, X-Ray Computed* / methods

Substances

Antineoplastic Agents