Using Machine Learning to Spot Metabolic Markers for Cancer Risk

JJohn September 4, 2023 11:33 AM

A new study from the University of South Australia (UniSA) leveraged machine learning to identify metabolic biomarkers that could predict cancer risk. The research utilized data from the UK Biobank, highlighting 84 features potentially signaling an increased risk of cancer.

Applying Machine Learning to Biobank Data

The research, conducted by UniSA in collaboration with the University of Adelaide, used machine learning techniques to analyze data from 459,169 participants in the UK Biobank. The AI model applied in the study not only helped identify 84 features that could indicate an increased cancer risk but also highlighted several biomarkers related to chronic kidney or liver disease.

Unveiling Biomarkers of Cancer and Chronic Diseases

One of the significant findings was that over 40% of the identified features were biomarkers. These biological molecules can signal health or unhealthy conditions based on their status. Several of these biomarkers were found to be jointly linked to the risk of cancer and kidney or liver disease, providing a new avenue for exploring the underlying pathogenic mechanisms of these diseases and their potential connections with cancer.

Dr. Amanda Lumsden, one of the researchers involved in the study, pointed out that high levels of urinary microalbumin, a serum protein necessary for tissue growth and healing, emerged as a significant predictor of cancer risk. Other indicators of poor kidney performance, such as high blood levels of cystatin C, high urinary creatinine, and overall lower total serum protein, were also found to be linked to cancer risk.

Another key finding of the study was the relationship between greater red cell distribution width (RDW), which represents the variation in the size of red blood cells, and increased cancer risk. Discrepancies in the size of red blood cells can signify higher inflammation and poorer renal function, both of which the study found to correlate with a higher risk of cancer.

Inflammation and Liver Stress as Cancer Risk Factors

The study also discovered connections between high levels of C-reactive protein (an indicator of systemic inflammation) and high levels of the enzyme gamma glutamyl transferase (GGT, a liver stress-related biomarker), and increased cancer risk. These findings underline the significance of systemic inflammation and liver stress in predicting cancer risk.

More articles

Also read

Here are some interesting articles on other sites from our network.