As we know, AI has taken the lead in almost every field. AI is everywhere, whether we talk about media, healthcare, financial institutions, or the education sector. Many companies are trying to incorporate AI into their daily routine. A novel study from the University of South Australia has discovered a range of metabolic biomarkers that could help identify cancer risks. According to the study, 84 indicators using machine learning to analyze data from 459,169 UK Biobank users could signal an increased cancer risk. Several markers also identified chronic liver or renal disease, highlighting the significance of examining the underlying pathogenic mechanisms of these mechanisms to look for any links to cancer.
Cancer is a significant health problem worldwide. Its critical early detection and management are essential for patients to recover quickly. Therefore, the early identification and treatment of liver cancer can benefit from using biomarkers. However, identifying and using biomarkers to minimize cancer risk might be difficult. Artificial intelligence is a valuable tool for research and potential clinical application since it has promised to detect and use biomarkers in managing liver cancer.
The study on how AI helps identify cancer risks, mainly named the Hypothesis-free discovery of novel cancer predictors using machine learning, was made by UniSA researchers Dr. Iqbal Madakkatel, Dr. Amanda Lumsden, Dr. Anwar Mulugeta, and Professor Elina Hyppönen, with University of Adelaide’s Professor Ian Olver.
According to Dr. Iqbal Madakkatel, Researcher, UniSA, “We conducted a hypothesis-free analysis using artificial intelligence and statistical approaches to identify cancer risk factors among more than 2800 features. More than 40% of the features the model identified were biomarkers – biological molecules that signal health or unhealthy conditions depending on their status – and several of these were jointly linked to cancer risk and kidney or liver disease.”
In addition, Dr. Amada Lumsden states that this study gives a broad spectrum of mechanisms that may contribute to cancer risks. “Similarly, other indicators of poor kidney performance such as high blood levels of cystatin C, high urinary creatinine (a waste product filtered by your kidneys), and overall lower total serum protein were also linked to cancer risk.”
She also highlighted the point that, “We also identified that greater red cell distribution width (RDW) – or the variation in size of your red blood cells – is associated with increased risk of cancer.” Her team also identified, “Normally, your red blood cells should be about the same size, and when there are discrepancies, it can correlate with higher inflammation and poorer renal function. As this study shows, there is also a higher cancer risk.”
Moreover, the study also highlights that high levels of C-reactive protein, an indicator of systematic inflammation, are interrelated to increased cancer risk. This is because of the high enzyme gamma-glutamyl transferase (GGT)- a liver stress-related biomarker. According to Chief investigator Professor Elina Hyppönen, Centre Director of the Australian Centre for Precision Health at UniSA, the intensity and power of this study lies in machine learning as machine learning has taken the lead in almost every way.
According to Prof Hyppönen, “Using artificial intelligence, our model has shown that it can incorporate and cross-reference thousands of features and identify relevant risk predictors that may otherwise remain hidden.” In addition, he also stated, “It is interesting that while our model incorporated information on thousands of features, including clinical, behavioral, and social factors, so many were biomarkers, which reflect the metabolic state before cancer diagnoses.”
The team of researchers also stated, “While further studies are needed to confirm causality and clinical relevance, this research suggests that with relatively simple blood tests, it may be possible to gain information about our future cancer risk. This is important as it allows us to act early when it may still be possible to prevent the disease.”