View in EDS

Artificial intelligence-driven body composition analysis enhances chemotherapy toxicity prediction in colorectal cancer.

Saved in:
Bibliographic Details
Title: Artificial intelligence-driven body composition analysis enhances chemotherapy toxicity prediction in colorectal cancer.
Authors: Liu YZ; Department of Statistics, National Cheng Kung University, No. 1, University Road, East District, Tainan 701, Taiwan. Electronic address: r28121029@gs.ncku.edu.tw., Su PF; Department of Statistics, National Cheng Kung University, No. 1, University Road, East District, Tainan 701, Taiwan. Electronic address: pfsu@mail.ncku.edu.tw., Tai AS; Department of Statistics, National Cheng Kung University, No. 1, University Road, East District, Tainan 701, Taiwan. Electronic address: ashtai@gs.ncku.edu.tw., Shen MR; Department of Medicine, College of Medicine, National Cheng Kung University, No. 1, University Road, East District, Tainan 701, Taiwan; Department of Pharmacology, College of Medicine, National Cheng Kung University, No. 1, University Road, East District, Tainan 701, Taiwan. Electronic address: mrshen@mail.ncku.edu.tw., Tsai YS; Clinical Innovation and Research Center, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 138, Sheng Li Road, North District, Tainan 704, Taiwan; Department of Medical Imaging, National Cheng Kung University Hospital, College of Medicine, National Cheng Kung University, No. 138, Sheng Li Road, North District, Tainan 704, Taiwan. Electronic address: n506356@gmail.com.
Source: Clinical nutrition ESPEN [Clin Nutr ESPEN] 2025 Oct; Vol. 69, pp. 696-702. Date of Electronic Publication: 2025 Aug 11.
Publication Type: Evaluation Study; Journal Article
Language: English
Journal Info: Publisher: Elsevier Ltd Country of Publication: England NLM ID: 101654592 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 2405-4577 (Electronic) Linking ISSN: 24054577 NLM ISO Abbreviation: Clin Nutr ESPEN Subsets: MEDLINE
Imprint Name(s): Original Publication: [Oxford] : Elsevier Ltd., [2015]-
MeSH Terms: Colorectal Neoplasms*/diagnostic imaging , Colorectal Neoplasms*/drug therapy , Colorectal Neoplasms*/physiopathology , Drug-Related Side Effects and Adverse Reactions*/diagnosis , Drug-Related Side Effects and Adverse Reactions*/etiology , Drug-Related Side Effects and Adverse Reactions*/prevention & control , Body Composition*/drug effects , Antineoplastic Combined Chemotherapy Protocols*/administration & dosage , Antineoplastic Combined Chemotherapy Protocols*/adverse effects , Artificial Intelligence*, Retrospective Studies ; Mediation Analysis ; Lumbar Vertebrae/diagnostic imaging ; Tomography, X-Ray Computed ; Oxaliplatin/administration & dosage ; Oxaliplatin/adverse effects ; Antineoplastic Agents/administration & dosage ; Antineoplastic Agents/adverse effects ; Muscle, Skeletal/diagnostic imaging ; Adipose Tissue/diagnostic imaging ; Maximum Tolerated Dose ; Dose-Response Relationship, Drug ; Drug Tolerance ; Prediction Algorithms ; Predictive Value of Tests ; Clinical Decision-Making/methods ; Humans ; Male ; Female ; Middle Aged ; Aged
Abstract: Competing Interests: Declaration of competing interest The authors declare that they have no conflict of interest.
Background and Aims: Body surface area (BSA)-based chemotherapy dosing remains standard despite its limitations in predicting toxicity. Variations in body composition, particularly skeletal muscle and adipose tissue, influence drug metabolism and toxicity risk. This study aims to investigate the mediating role of body composition in the relationship between BSA-based dosing and dose-limiting toxicities (DLTs) in colorectal cancer patients receiving oxaliplatin-based chemotherapy.
Methods: We retrospectively analyzed 483 stage III colorectal cancer patients treated at National Cheng Kung University Hospital (2013-2021). An artificial intelligence (AI)-driven algorithm quantified skeletal muscle and adipose tissue compartments from lumbar 3 (L3) vertebral-level computed tomography (CT) scans. Mediation analysis evaluated body composition's role in chemotherapy-related toxicities.
Results: Among the cohort, 18.2 % (n = 88) experienced DLTs. While BSA alone was not significantly associated with DLTs (OR = 0.473, p = 0.376), increased intramuscular adipose tissue (IMAT) significantly predicted higher DLT risk (OR = 1.047, p = 0.038), whereas skeletal muscle area was protective. Mediation analysis confirmed that IMAT partially mediated the relationship between BSA and DLTs (indirect effect: 0.05, p = 0.040), highlighting adipose infiltration's role in chemotherapy toxicity.
Conclusion: BSA-based dosing inadequately accounts for interindividual variations in chemotherapy tolerance. AI-assisted body composition analysis provides a precision oncology framework for identifying high-risk patients and optimizing chemotherapy regimens. Prospective validation is warranted to integrate body composition into routine clinical decision-making.
(Copyright © 2025. Published by Elsevier Ltd.)
Contributed Indexing: Keywords: Artificial intelligence; Body composition; Body surface area; Chemotherapy dosing; Colorectal cancer; Dose-limiting toxicity
Substance Nomenclature: 04ZR38536J (Oxaliplatin)
0 (Antineoplastic Agents)
Entry Date(s): Date Created: 20250813 Date Completed: 20250923 Latest Revision: 20250923
Update Code: 20250923
DOI: 10.1016/j.clnesp.2025.08.013
PMID: 40803593
Database: MEDLINE
Description
Abstract:Competing Interests: Declaration of competing interest The authors declare that they have no conflict of interest.<br />Background and Aims: Body surface area (BSA)-based chemotherapy dosing remains standard despite its limitations in predicting toxicity. Variations in body composition, particularly skeletal muscle and adipose tissue, influence drug metabolism and toxicity risk. This study aims to investigate the mediating role of body composition in the relationship between BSA-based dosing and dose-limiting toxicities (DLTs) in colorectal cancer patients receiving oxaliplatin-based chemotherapy.<br />Methods: We retrospectively analyzed 483 stage III colorectal cancer patients treated at National Cheng Kung University Hospital (2013-2021). An artificial intelligence (AI)-driven algorithm quantified skeletal muscle and adipose tissue compartments from lumbar 3 (L3) vertebral-level computed tomography (CT) scans. Mediation analysis evaluated body composition's role in chemotherapy-related toxicities.<br />Results: Among the cohort, 18.2 % (n = 88) experienced DLTs. While BSA alone was not significantly associated with DLTs (OR = 0.473, p = 0.376), increased intramuscular adipose tissue (IMAT) significantly predicted higher DLT risk (OR = 1.047, p = 0.038), whereas skeletal muscle area was protective. Mediation analysis confirmed that IMAT partially mediated the relationship between BSA and DLTs (indirect effect: 0.05, p = 0.040), highlighting adipose infiltration's role in chemotherapy toxicity.<br />Conclusion: BSA-based dosing inadequately accounts for interindividual variations in chemotherapy tolerance. AI-assisted body composition analysis provides a precision oncology framework for identifying high-risk patients and optimizing chemotherapy regimens. Prospective validation is warranted to integrate body composition into routine clinical decision-making.<br /> (Copyright © 2025. Published by Elsevier Ltd.)
ISSN:2405-4577
DOI:10.1016/j.clnesp.2025.08.013