Machine learning-enhanced gas sensor technology identifies ovarian and endometrial cancer of all stages through plasma volatile organic compound patterns
Abstract
Background: Ovarian cancer presents with non-specific symptoms that make early diagnosis challenging and the prognosis poor. Ovarian and endometrial cancers exhibit similar genomic mutations and biomarker profiles. Endogenous volatile organic compounds (VOCs) are products of metabolic activity. In cancer, metabolites increase due to tumour necrosis, leading to cancer-specific VOC patterns. The aim of this study was to evaluate VOC analyses in plasma as diagnostic tests for early diagnosis of ovarian and endometrial cancer.
Methods: Preoperative plasma from 133 women with ovarian cancer (stages I-IV or borderline ovarian tumors) and 41 women with endometrial cancer (stages I-IV) was compared to 115 healthy controls with highly sensitive gas sensors. Data analyses were performed using feature extraction from 32 gas sensors per sample. 85 features were extracted from each signal (including statistical, time-domain, and frequency-domain features), and training and test datasets were formed. The features underwent an iterative redundancy removal process for stepwise optimization of models. Model robustness was assessed using a train/test split scheme with unique datasets, leading to a model optimized for diagnostic performance. By implementing sequential binary classification boosting-based models, it was possible to determine not only the presence or not of cancer, but also to distinguish between ovarian- and endometrial cancer, and the stage of the cancer.
Findings: The VOC…
Read the paper
Related studies
- Quantum dots: synthesis, bioapplications, and toxicity
- A Guide to In Silico Drug Design
- Quantum Computing for Healthcare: A Review
- Automated in Silico Design of Homogeneous Catalysts
- Identification of Novel 3-Hydroxy-pyran-4-One Derivatives as Potent HIV-1 Integrase Inhibitors Using in silico Structure-Based Combinatorial Library Design Approach
- In silico structural elucidation of RNA-dependent RNA polymerase towards the identification of potential Crimean-Congo Hemorrhagic Fever Virus inhibitors
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.