AI study finds that gut gases could point to colon cancer

Researchers at Xi’an Jiaotong-Liverpool University’s School of Science have identified telltale gases in tiny stool samples that could aid the early detection of colorectal cancer, one of the most common cancers worldwide.

Existing screening methods for the disease, such as genetic testing and faecal occult blood tests, can produce false-positive results.

However, scientists in the Department of Chemistry and Materials Science have conducted an AI-assisted study that identified 80 volatile organic compounds (VOCs) as potential biomarkers related to gut health.

The team, led by PhD candidate Weiyu Xiao and Dr Qiuchen Dong, used GC-MS – an analytical technique that combines gas chromatography for separating complex mixtures of VOCs with mass spectrometry for identifying and quantifying them – to examine faecal samples from 37 colorectal cancer patients, 44 patients with precancerous growths, and 55 healthy donors.

Results showed clear differences in the levels of certain gases among the three groups. After entering the data into machine-learning models, the scientists were able to accurately predict the gut health of unknown samples.

Figure 1. (A) and (B) The predictions of PCA algorithm for three groups and supervised machine learning models are based on fecal isopropanol gas concentration detected by ZnO/IrO_x-based gas sensor and fecal p-cresol analyzed by GC-MS. (C) The predictions of the K-means algorithm for three groups. (D) Supervised machine learning models are based on fecal isopropanol gas concentration detected by ZnO/IrO_x-based gas sensor and fecal p-cresol, 2-methylbutanoic acid and 3-methylbutanoic acid analyzed by GC-MS.

Figure 2. (A) Electrodeposited 40 min ZnO including current curves toward different feal isopropanol gas released from human feces with condition of CRC patients, polyps and healthy donors at 40  and the humidity of RH 15 %. (B) The quantitative analysis of fecal isopropanol gas. (C) Box plot and distribution of fecal isopropanol gas from three groups detected by ZnO-based gas sensor. (D) PCA algorithm for three groups based on fecal isopropanol gas concentration detected by ZnO-based gas sensor and fecal p-cresol analyzed by GC-MS.

Researchers say the evidence suggests isopropanol and para-cresol are the most promising VOCs for the early detection of colorectal cancer, while 2-methylbutanoic acid and 3-methylbutanoic acid could help fine-tune the prediction model due to their varying abundance in the test subjects.

In addition to discovering biomarkers, the study, which was conducted in partnership with the First Affiliated Hospital of Soochow University, has also led to the development of two types of gas sensors and two Chinese patent applications.

One sensor is based on pure zinc oxide, while the other uses a p-n heterojunction – an interface formed between two different semiconductor materials – made from zinc oxide and iridium oxide nanomaterials. These were microfabricated using photolithography and deposited onto specially designed concentric interdigitated electrodes. Electrodeposition and heat treatments were used to achieve stable crystalline structures that enhance the oxidation of isopropanol, improving performance.

In December 2025, the research was published in two peer-reviewed journals: Sensors and Actuators B: Chemical; and Sensors and Actuators Reports.

Editor:Patricia Pieterse