Computer programme predicts early signs of painful rheumatoid arthritis

Researchers in US Mayo Clinic identify blood biomarkers that indicate chronic disease

Researchers in the US have developed a computer programme to predict if a patient is predisposed to crippling rheumatoid arthritis. AP

Researchers in the US have developed a computer programme to predict if a patient is predisposed to crippling rheumatoid arthritis.

It is the latest step in predictive medicine that could encourage patients to take preventive measures before symptoms appear.

Scientists at the Mayo Clinic’s Centre of Individualised Medicine and Division of Rheumatology used a machine-learning algorithm to analyse blood markers for the disease.

The algorithm looked at biochemical metabolites produced by the body’s natural metabolism.

In biochemistry, a metabolite is an intermediate or end product of metabolism.

"Having fast, reliable and scalable measures for predicting the clinical course of disease activity is an important, unmet need for patients with rheumatoid arthritis,'' said Jaeyun Sung, a computational biologist at the centre.

“The study sheds light on why symptoms differ significantly among rheumatoid arthritis patients, which in turn makes it so difficult to treat.

"We turned to the blood because it could potentially provide a treasure-trove of novel biomarkers for assessing not only disease activity but also clinical subgroups, risk factors and predictors of treatment response that complement current standard laboratory tests.”

Biomarker refers to a broad range of measures that capture what is happening in a cell or organism. It is used by medics to assess the presence or progress of disease or the effects of treatment.

The research took place at Mayo Clinic’s centre in Rochester, Minnesota from where virtual consultations take place with patients at Sheikh Shakhbout Medical City in Abu Dhabi.

Plasma samples were extracted from 128 patients diagnosed with rheumatoid arthritis to identify metabolites commonly related to their condition.

The debilitating disease affects around 20 per cent of the UAE population and 1.3 million in the US.

It usually appears as joint pain in the wrists and ankles and can be inflammatory and degenerative causing a deteriorating range of movement in hands and feet.

Researchers identified which of the biomarkers detected were related to worse symptoms in patients.

"The blood provides a great window into understanding disease, especially in cases where biopsies of inflamed tissue are not easily accessible,” Dr Sung said.

"We found that metabolites in the blood were different between patients with higher and lower disease activity.

”So basically, this implies that depending on the disease activity of a patient's rheumatoid arthritis — whether they're in remission or on the other end of the spectrum, possibly suffering from much pain — they have different biochemicals floating around in their blood.

“Some were molecules you don't want much of in your body but some were those you want to be kept with. This observation led us to wonder whether biochemical blood profiles predict a patient's disease activity score."

By identifying similar biomarkers, doctors could identify which patients were most likely to suffer more severely from the condition.

Treatment and preventive measures could then be offered at an earlier stage to ease or delay the onset of symptoms in other patients.

Doctors said the findings provided direction for the potential future development of lab tests and digital diagnostics to further enable precision medicine for those with rheumatoid arthritis.

Dr John Davis, a clinical rheumatologist in Mayo Clinic's Division of rheumatology, said a patient's rheumatoid arthritis disease activity was not notable through symptoms alone.

"Our study highlights the importance of investigating which biochemical functions are altered during the onset and progression of the disease," he said.

"To this end, metabolomics platforms can present unique opportunities for discovering novel biomarkers.

"Metabolomics can screen for nearly 1,000 metabolites, which is way too many to keep track of. By narrowing down this list into a panel of 51 metabolites, we obtained reasonable prediction to predict quantitative disease activity."