Skip to content
DraconiticResearch
Search Sources API
194,161 studies31 sourcesUpdated 50 min ago
Peer-reviewedCC BY 4.0Frontiers in Oncology

NGAL and traditional biomarkers in cervical cancer: a comparative evaluation using random forest

  • Behar Raci1,2
  • Snezana Stojkovska2
  • Gezim Hodolli1
  • Violeta Klisarovska3
  • Goran Dimitrov4
  • Arta Kameri Jusufi1
  • Hekuran Sejdiu1
  • Burim Sermaxhaj5
  • Diellor Rizaj6
  • Ilir Kurtishi1
  • Mentor Kurshumliu7
7 affiliations
  1. 1Clinic of Oncology, University Clinical Center of Kosovo
  2. 2University Clinic for Infectious Diseases & Febrile Conditions, Faculty of Medicine
  3. 3University Clinic of Radiotherapy and Oncology, Faculty of Medicine
  4. 4University Clinic of Gynecology and Obstetrics, Faculty of Medicine
  5. 5Clinic for Radio-Oncology, Stadtspital Triemli
  6. 6UBT College
  7. 7College of Medical Sciences Heimerer
Read full textPDFDOICite

Abstract

Introduction: Tumor stage and biological aggressiveness have a significant impact on the prognosis of cervical cancer, which is still a serious global health concern.

Methods: This work assesses an exploratory, leakage-free Random Forest model and describes longitudinal NGAL and traditional biomarker patterns in 100 individuals with cervical cancer. Since there was no independent radiologic, pathological, or defined response endpoint in the database, the machine-learning result was specifically characterized as an NGAL-decrease phenotype (post-treatment NGAL < pre-treatment NGAL), not clinical treatment response. All NGAL-derived variables and all post-treatment variables were removed from the predictor set in order to prevent target leakage.

Results: The mean accuracy using stratified 5-fold cross validation was 43.0% (SD 7.6%) and the mean balanced accuracy was 42.1%, suggesting that there was no discriminative performance that was useful. Greater histological grades and more advanced broad-stage groups had descriptively greater NGAL concentrations.

Discussion: These results do not prove clinical predictive usefulness; rather, they are hypothesis-generating.

Related

  1. Dose- and time-resolved immune states in cervical cancer radiotherapy: dynamic multimodal biomarkers for adaptive immunoradiotherapy
    Chengjian Xiao, Feilong Tian, Minli Kang +1
    Frontiers in ImmunologyPeer-reviewedCC BY 4.0Full textOncologyCrossref
  2. Comparative Evaluation of Concurrent Carboplatin-Paclitaxel Versus Cisplatin-Etoposide Chemoradiotherapy in Unresectable Non-small Cell Lung Cancer: A Prospective Randomized Study
    Yamini Kumar, Bala Venkat Subramanian, G V Deepthi +2
    CureusPeer-reviewedCC BYFull textGeneral medicineEurope PMC
  3. Application of a Quantitative POCT-FIT Based on Near-Infrared Fluorescence Immunochromatography in Population-Based Colorectal Cancer Screening: A Comparative Evaluation with a Centralized Testing System
    Fang-Chao Zhu, Yu-Lin Ku, Jie Pan +2
    Diagnostics (Basel, Switzerland)Peer-reviewedCC BYFull textGeneral medicineEurope PMC
  4. Cross-cultural adaptation and comparative psychometric evaluation of four patient-reported outcome measures for breast cancer-related lymphedema: measurement properties and clinical discrimination
    Yue Zhou, Yun Li, Qi Zhang +11
    Gland SurgeryPeer-reviewedCC BY-NC-NDFull textGeneral medicineEurope PMC
  5. Cancer-associated stroke: a comparative analysis of thrombus composition, resistance to lysis, and plasma biomarkers
    Capucine Habay, Benoît Ho-Tin-Noé, Mialitiana Solo Nomenjanahary +7
    Research and Practice in Thrombosis and HaemostasisPeer-reviewedCC BY-NC-ND 4.0Full textEpidemiology & public healthHAL

Cite

BibTeXRIS
BibTeX
@article{raci2026ngal,
  title = {{NGAL and traditional biomarkers in cervical cancer: a comparative evaluation using random forest}},
  author = {Behar Raci and Snezana Stojkovska and Gezim Hodolli and Violeta Klisarovska and Goran Dimitrov and Arta Kameri Jusufi and Hekuran Sejdiu and Burim Sermaxhaj and Diellor Rizaj and Ilir Kurtishi and Mentor Kurshumliu},
  journal = {Frontiers in Oncology},
  year = {2026},
  month = oct,
  doi = {10.3389/fonc.2026.1933456},
  url = {https://www.frontiersin.org/articles/10.3389/fonc.2026.1933456/full},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - NGAL and traditional biomarkers in cervical cancer: a comparative evaluation using random forest
AU  - Behar Raci
AU  - Snezana Stojkovska
AU  - Gezim Hodolli
AU  - Violeta Klisarovska
AU  - Goran Dimitrov
AU  - Arta Kameri Jusufi
AU  - Hekuran Sejdiu
AU  - Burim Sermaxhaj
AU  - Diellor Rizaj
AU  - Ilir Kurtishi
AU  - Mentor Kurshumliu
PY  - 2026
DA  - 2026/10/20
JO  - Frontiers in Oncology
DO  - 10.3389/fonc.2026.1933456
UR  - https://www.frontiersin.org/articles/10.3389/fonc.2026.1933456/full
AB  - Introduction: Tumor stage and biological aggressiveness have a significant impact on the prognosis of cervical cancer, which is still a serious global health concern.  Methods: This work assesses an exploratory, leakage-free Random Forest model and describes longitudinal NGAL and traditional biomarker patterns in 100 individuals with cervical cancer. Since there was no independent radiologic, pathological, or defined response endpoint in the database, the machine-learning result was specifically characterized as an NGAL-decrease phenotype (post-treatment NGAL < pre-treatment NGAL), not clinical treatment response. All NGAL-derived variables and all post-treatment variables were removed from the predictor set in order to prevent target leakage.  Results: The mean accuracy using stratified 5-fold cross validation was 43.0% (SD 7.6%) and the mean balanced accuracy was 42.1%, suggesting that there was no discriminative performance that was useful. Greater histological grades and more advanced broad-stage groups had descriptively greater NGAL concentrations.  Discussion: These results do not prove clinical predictive usefulness; rather, they are hypothesis-generating.
SN  - 2234-943X
ER  -