Machine Learning-Based Detection of Bladder Cancer by Urine cfDNA Fragmentation Hotspots that Capture Cancer-Associated Molecular Features
Clinical Chemistry · 02.12.2024 · 70 (12) · 1463-1473
DOI: 10.1093/clinchem/hvae156 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clinical Chemistry, online erschienen am 21.10.2024. Verfasst von Xiang-Yu Meng und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, Zhongnan Hospital of Wuhan University, Wuhan, China. Hauptthemen laut MEDLINE: Urinary Bladder Neoplasms, Machine Learning. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 42 Literaturangaben. Gefördert von: Innovation Fund for Medical Sciences, Zhongnan Hospital of Wuhan University, National Natural Science Foundation of China.
Abstract (Originalsprache)
Background cfDNA fragmentomics-based liquid biopsy is a potential option for noninvasive bladder cancer (BLCA) detection that remains an unmet clinical need.
Methods
We assessed the diagnostic performance of cfDNA hotspot-driven machine-learning models in a cohort of 55 BLCA patients, 51 subjects with benign conditions, and 11 healthy volunteers. We further performed functional bioinformatics analysis for biological understanding and interpretation of the tool’s diagnostic capability.
Results
Urinary cfDNA hotspots-based machine-learning model enabled effective BLCA detection, achieving high performance (area under curve 0.96) and an 87% sensitivity at 100% specificity. It outperformed models using other cfDNA-derived features. In stage-stratified analysis, the sensitivity at 100% specificity of the urine hotspots-based model was 71% and 92% for early (low-grade Ta and T1) and advanced (high-grade T1 and muscle-invasive) disease, respectively. Biologically, cfDNA hotspots effectively retrieved regulatory elements and were correlated with the cell of origin. Urine cfDNA hotspots specifically captured BLCA-related molecular features, including key functional pathways, chromosome loci associated with BLCA risk as identified in genome-wide association studies, or presenting frequent somatic alterations in BLCA tumors, and the transcription factor regulatory landscape.
Conclusions
Our findings support the applicability of urine cfDNA fragmentation hotspots for noninvasive BLCA diagnosis, as well as for future translational study regarding its molecular pathology and heterogeneity.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Urology, Zhongnan Hospital of Wuhan University, Wuhan, China.
- Hubei Provincial Clinical Medical Research Center for Nephropathy, Hubei Minzu University, Enshi, China.
- Hubei Key Laboratory of Agricultural Bioinformatics, College of Informatics, Huazhong Agricultural University, Wuhan, China.
- Department of Laboratory Medicine, Zhongnan Hospital of Wuhan University, Wuhan, China.
- Center for Single-cell Omics and Tumor Liquid Biopsy, Zhongnan Hospital of Wuhan University, Wuhan, China.
- Department of Urology, Beijing Friendship Hospital, Capital Medical University, Beijing, China.
ORCID-Profile: Xiang-Yu Meng, Xiong-Hui Zhou, Hong-Yu Zhang
Förderung
- Innovation Fund for Medical Sciences
- Zhongnan Hospital of Wuhan University
- National Natural Science Foundation of China
- Beijing Hospitals Authority' Youth Program
- Natural Science Foundation of Hubei Province of China
- Fundamental Research Funds for the Central Universities
- Beijing Hospitals Authority’ Youth Program
Zitieren
APA
Meng, X. Y., Zhou, X. H., Li, S., Shi, M. J., Li, X. H., Yang, B. Y., Liu, M., Yi, K. Z., Wang, Y. Z., Zhang, H. Y., Song, J., Wang, F. B., & Wang, X. H. (2024). Machine Learning-Based Detection of Bladder Cancer by Urine cfDNA Fragmentation Hotspots that Capture Cancer-Associated Molecular Features. Clinical Chemistry, 70(12), 1463-1473. https://doi.org/10.1093/clinchem/hvae156
Vancouver
Meng XY, Zhou XH, Li S, Shi MJ, Li XH, Yang BY, et al. Machine Learning-Based Detection of Bladder Cancer by Urine cfDNA Fragmentation Hotspots that Capture Cancer-Associated Molecular Features. Clinical Chemistry. 2024;70(12):1463-1473. doi:10.1093/clinchem/hvae156
BibTeX
@article{Meng2024,
author = {Meng, Xiang-Yu and Zhou, Xiong-Hui and Li, Shuo and Shi, Ming-Jun and Li, Xuan-Hao and Yang, Bo-Yu and Liu, Min and Yi, Ke-Zhen and Wang, Yun-Ze and Zhang, Hong-Yu and Song, Jian and Wang, Fu-Bing and Wang, Xing-Huan},
title = {Machine Learning-Based Detection of Bladder Cancer by Urine cfDNA Fragmentation Hotspots that Capture Cancer-Associated Molecular Features},
journal = {Clinical Chemistry},
year = {2024},
volume = {70},
number = {12},
pages = {1463--1473},
doi = {10.1093/clinchem/hvae156}
}
EUVIMED