收藏切换
Prognostic prediction model for patients with low-grade gliomas based on multi-omics data
收藏切换
PDF
Yi-rong LIU1, Yue REN1, Yang QIN1, Shu-qi WU1, Jin-fang ZHAO1, 2, Tian-e LUO1, 2
Modern Preventive Medicine | 2024, 51(14) : 2669 - 2674
Less
收藏切换
Modern Preventive Medicine | 2024, 51(14): 2669-2674
Clinical Medicine and Prevention
Prognostic prediction model for patients with low-grade gliomas based on multi-omics data
Full
Yi-rong LIU1, Yue REN1, Yang QIN1, Shu-qi WU1, Jin-fang ZHAO1, 2, Tian-e LUO1, 2
Affiliations
  • Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, Shanxi 030001, China
Published: 2024-07-25 doi: 10.20043/j.cnki.MPM.202404262
Outline
收藏切换
Objective

To explore the application of integrated clustering methods in identifying low-grade glioma subtypes and prognostic prediction.

Methods

A comprehensive clustering algorithm (MOVICS), which pools ten clustering algorithms, was used to integrate the multi-omics data of LGG patients downloaded from TCGA to obtain cluster subtypes; prognostic factors of LGG were analyzed by multifactorial Cox regression. A random forest classification prediction model was constructed using mRNA data to evaluate the classification performance and externally validated with the CGGA dataset.

Results

LGG patients were clustered into two subtypes, and the difference in survival between the two groups was statistically significant (χ2=54.410, P<0.001). The results of multifactorial Cox regression analysis showed that age (HR=1.053,95%CI: 1.037-1.069), cancer grade (HR=2.733,95%CI: 1.836-4.069) and cluster typing (HR=3.210,95%CI: 2.216-4.650) were all prognostic factors for LGG, and the results of Nomogram plots, calibration curves and ROC curves indicated good predictive performance of the model. The average prediction accuracy of the ten-fold cross-validated RF model was 87.81%, and the C-indexes of the training set, the internal validation set, and the two external validation sets were 0.717, 0.721, 0.574, and 0.572, and the Brier scores were 0.044, 0.066, 0.179, and 0.128, and the differences in the survival of the two external validation datasets were all statistically significance (P<0.05).

Conclusion

The comprehensive clustering method can effectively identify LGG subtypes, which are prognostic factors for LGG patients, and has been validated in an external dataset, CGGA, which can provide an important theoretical basis for clinical personalized treatment of LGG.

Multi-omics clustering  /  Low-grade glioma  /  Prognosis prediction  /  Random forest
Yi-rong LIU, Yue REN, Yang QIN, Shu-qi WU, Jin-fang ZHAO, Tian-e LUO. Prognostic prediction model for patients with low-grade gliomas based on multi-omics data[J]. Modern Preventive Medicine, 2024 , 51 (14) : 2669 -2674 . DOI: 10.20043/j.cnki.MPM.202404262
Year 2024 volume 51 Issue 14
PDF
47
23
Cite this Article
BibTeX
Article Info
doi: 10.20043/j.cnki.MPM.202404262
  • Receive Date:2024-04-16
  • Online Date:2026-03-18
  • Published:2024-07-25
Article Data
Affiliations
History
  • Received:2024-04-16
Funding
Affiliations
    Department of Health Statistics, School of Public Health, Shanxi Medical University, Taiyuan, Shanxi 030001, China
References
Share
https://castjournals.cast.org.cn/joweb/xdyfyx/EN/10.20043/j.cnki.MPM.202404262
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT