Skip to content
DraconiticResearch
Search Sources API
201,642 studies31 sourcesUpdated 16 min ago
Peer-reviewedCC BYFrontiers in nutrition

Novel AI-derived muscle ultrasound biomarkers linking nutritional status and prognosis in cancer patients.

  • Juan José López-Gómez1,2,3
  • Lucía Estévez-Asensio1,2,3
  • Paloma Pérez-López1,2,3
  • Iván Rodríguez-Marín2
  • Noelia Martín-Gómez2
  • Olatz Izaola-Jauregui1,2,3
  • Ángela Cebriá4,5
  • Jaime González-Gutiérrez1,2,3
  • Rebeca Jiménez-Sahagún1,2,3
  • Puerto Bernoy-González1,2,3
  • Emilia Gómez-Hoyos1,2,3
  • Eduardo Jorge Godoy4,5
1 more authors
  • Daniel A De Luis-Román1,2,3
5 affiliations
  1. 1Servicio de Endocrinología y Nutrición, Hospital Clínico Universitario de Valladolid, Valladolid, Spain.
  2. 2Centro de Investigación en Endocrinología y Nutrición, Facultad de Medicina, Universidad de Valladolid, Valladolid, Spain.
  3. 3Health Research Institute of Valladolid (IBioVALL), Valladolid, Spain.
  4. 4DAWAKO Medtech S.L., Parc Cientific de la Universitat de Valencia, Paterna, Valencia, Spain.
  5. 5Técnicas Avanzadas de Desarrollo de Software Centrado en la Persona, Departamento de Informática, Universitat de Valencia, Burjassot, Valencia, Spain.
Read full textPDFDOICite

Abstract

Malnutrition and sarcopenia worsen prognosis in patients with cancer and require accessible diagnostic methods for assessing muscle quantity and quality. Artificial intelligence (AI)-assisted muscle ultrasound may improve the standardization and efficiency of body-composition assessment. This study evaluated the prognostic relevance of AI-assisted rectus femoris ultrasound biomarkers within a comprehensive nutritional assessment of patients with cancer. This prospective longitudinal observational cohort study included 389 patients with cancer, most of whom had tumors of digestive origin. Participants underwent longitudinal and transverse rectus femoris ultrasonography. Images were analyzed using PIIXMED™ MSK, which applies U-Net based anatomical segmentation followed by deterministic image-processing procedures. The evaluated variables included subcutaneous adipose tissue thickness (SAT), rectus femoris thickness (RFT) rectus femoris cross-sectional area (RFA), pennation angle, mean echo intensity, and the percentages of low- and medium-echogenicity pixels within the segmented region of interest, reported as the Muscle Index (Mi) and Fat Index (FATi), respectively. The muscle-area index was calculated as AreaMi = RFAxMi. The 389 participants had a mean age of 70.6 (10.8) years, 58.9% were men, and 53.7% (n = 206) were classified as geriatric oncology patients (≥70 years). Malnutrition was present in 75.3% of participants, confirmed sarcopenia in 18.8% and overall mortality during follow-up was 26.5%. In univariate log-rank survival analysis, reduced muscle-area index (MiArea<1.36 cm2; p = 0.014) and low muscle quality (Mi < 46%; p = 0.019) were the strongest univariate predictors of significantly shorter survival. In multivariate Cox proportional Hazards regression models adjusted for age, sex, digestive tumor location, and metastatic disease, larger rectus femoris area (RFA: HR = 0.77. 95%CI: 0.62-0.95; p < 0.05) and thickness (RFT: HR = 0.43, 95% CI: 0.19-0.99; p < 0.05) remained independent protective factors against mortality. Conversely, reduced muscle index (Mi < 47%: HR = 1.60, 95%CI: 1.05-2.06; p < 0.05) and the presence of myosteatosis (HR = 2.35, 95%CI: 1.19-4.62; p = 0.01) independently predicted an increased risk of mortality. In cancer patients, AI-assisted rectus femoris ultrasound variables effectively predict mortality. Greater muscle area and higher muscle index (Mi > 47%) indicate a favorable prognosis. Early ultrasound assessment detects structural alterations before overt deterioration, providing a crucial window for targeted nutritional interventions to preserve muscle integrity and prevent complications.

Related

  1. High-frequency ultrasound-derived imaging biomarkers in inflammatory skin diseases
    Claudia Gonzalez, Cesar Gonzalez, Carolina Palacio +4
    Frontiers in medicinePeer-reviewedCC BYFull textGeneral medicineEurope PMC
  2. Research on the use of bedside ultrasound to quickly evaluate neurological prognosis in patients with ROSC
    Kerong Wang, Guoliang Li, Xiuci Yang +5
    PLOS OnePeer-reviewedCC BY 4.0Full textPhysiologyPLOS
  3. A prospective cohort study of dietary intake and clinical-nutritional biomarkers in patients with periampullary malignancies undergoing pancreatoduodenectomy in Southeast Brazil.
    Marco Aurélio Ribeiro, José Sebastião Dos Santos, Gleici da Silva Castro Perdoná +1
    Supportive care in cancer : official journal of the Multinational Association of Supportive Care in CancerPeer-reviewedCC BYFull textGeneral medicineEurope PMC
  4. ATF4 and SLC7A11 as biomarkers predicting progression and prognosis in lung adenocarcinoma
    Yanjie Liu, Dongli Guo, Daojuan Li +1
    Frontiers in oncologyPeer-reviewedCC BYFull textOncologyEurope PMC
  5. Molecular biomarkers for diagnosis, prognosis, precision therapy, and immunotherapy in cholangiocarcinoma, cHCC-CCA, and HCC
    Jingguo Sun, Yingjie Lu, Lu Chang +4
    Hepatology communicationsPeer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{lopezgomez2026novel,
  title = {{Novel AI-derived muscle ultrasound biomarkers linking nutritional status and prognosis in cancer patients.}},
  author = {Juan José López-Gómez and Lucía Estévez-Asensio and Paloma Pérez-López and Iván Rodríguez-Marín and Noelia Martín-Gómez and Olatz Izaola-Jauregui and Ángela Cebriá and Jaime González-Gutiérrez and Rebeca Jiménez-Sahagún and Puerto Bernoy-González and Emilia Gómez-Hoyos and Eduardo Jorge Godoy and Daniel A De Luis-Román},
  journal = {Frontiers in nutrition},
  year = {2026},
  month = oct,
  doi = {10.3389/fnut.2026.1961328},
  url = {https://europepmc.org/article/MED/42953640},
  note = {CC BY},
}
RIS
TY  - JOUR
TI  - Novel AI-derived muscle ultrasound biomarkers linking nutritional status and prognosis in cancer patients.
AU  - Juan José López-Gómez
AU  - Lucía Estévez-Asensio
AU  - Paloma Pérez-López
AU  - Iván Rodríguez-Marín
AU  - Noelia Martín-Gómez
AU  - Olatz Izaola-Jauregui
AU  - Ángela Cebriá
AU  - Jaime González-Gutiérrez
AU  - Rebeca Jiménez-Sahagún
AU  - Puerto Bernoy-González
AU  - Emilia Gómez-Hoyos
AU  - Eduardo Jorge Godoy
AU  - Daniel A De Luis-Román
PY  - 2026
DA  - 2026/10/14
JO  - Frontiers in nutrition
DO  - 10.3389/fnut.2026.1961328
UR  - https://europepmc.org/article/MED/42953640
AB  - Malnutrition and sarcopenia worsen prognosis in patients with cancer and require accessible diagnostic methods for assessing muscle quantity and quality. Artificial intelligence (AI)-assisted muscle ultrasound may improve the standardization and efficiency of body-composition assessment. This study evaluated the prognostic relevance of AI-assisted rectus femoris ultrasound biomarkers within a comprehensive nutritional assessment of patients with cancer. This prospective longitudinal observational cohort study included 389 patients with cancer, most of whom had tumors of digestive origin. Participants underwent longitudinal and transverse rectus femoris ultrasonography. Images were analyzed using PIIXMED™ MSK, which applies U-Net based anatomical segmentation followed by deterministic image-processing procedures. The evaluated variables included subcutaneous adipose tissue thickness (SAT), rectus femoris thickness (RFT) rectus femoris cross-sectional area (RFA), pennation angle, mean echo intensity, and the percentages of low- and medium-echogenicity pixels within the segmented region of interest, reported as the Muscle Index (Mi) and Fat Index (FATi), respectively. The muscle-area index was calculated as AreaMi = RFAxMi. The 389 participants had a mean age of 70.6 (10.8) years, 58.9% were men, and 53.7% (n = 206) were classified as geriatric oncology patients (≥70 years). Malnutrition was present in 75.3% of participants, confirmed sarcopenia in 18.8% and overall mortality during follow-up was 26.5%. In univariate log-rank survival analysis, reduced muscle-area index (MiArea<1.36 cm2; p = 0.014) and low muscle quality (Mi < 46%; p = 0.019) were the strongest univariate predictors of significantly shorter survival. In multivariate Cox proportional Hazards regression models adjusted for age, sex, digestive tumor location, and metastatic disease, larger rectus femoris area (RFA: HR = 0.77. 95%CI: 0.62-0.95; p < 0.05) and thickness (RFT: HR = 0.43, 95% CI: 0.19-0.99; p < 0.05) remained independent protective factors against mortality. Conversely, reduced muscle index (Mi < 47%: HR = 1.60, 95%CI: 1.05-2.06; p < 0.05) and the presence of myosteatosis (HR = 2.35, 95%CI: 1.19-4.62; p = 0.01) independently predicted an increased risk of mortality. In cancer patients, AI-assisted rectus femoris ultrasound variables effectively predict mortality. Greater muscle area and higher muscle index (Mi > 47%) indicate a favorable prognosis. Early ultrasound assessment detects structural alterations before overt deterioration, providing a crucial window for targeted nutritional interventions to preserve muscle integrity and prevent complications.
SN  - 2296-861X
ER  -