By Jane Kirby

Copyright independent

A new artificial intelligence (AI) tool could estimate a patient’s risk of more than 1,000 diseases in a single assessment, according to research.

Experts have developed and tested the model using anonymised patient record data to help predict what might happen to people over the next decade and beyond.

The team behind the research hope the new model will be available to doctors within five to 10 years to help guide decisions around prevention, diagnosis and treatment.

The tool assesses the probability of whether – and when – people may develop diseases such as cancer, diabetes, cardiovascular disease, respiratory disease and numerous disorders.

It processes “medical events” in people’s history, such as when illnesses were diagnosed, together with lifestyle factors such as whether people were obese, smoked or drank alcohol, plus their age and sex. It learned to forecast disease risk from the order in which such events happened and how much time had passed between them.

The tool was better at offering predictions for conditions with clear and consistent progression patterns, such as certain types of cancer, heart attacks, and septicaemia, blood poisoning.

It was less reliable for conditions that may be variable, such as mental health problems or pregnancy-related complications.

Ewan Birney, interim executive director of the European Molecular Biology Laboratory (EMBL), who worked on the research, said: “The future – and this is five to 10 years away – is when clinicians are enhanced and supported by these sophisticated AI tools.

“You walk into the doctor’s surgery and the clinician is very used to using these tools, and they are able to say: ‘Here’s four major risks that are in your future and here’s two things you could do to really change that.’

“I suspect everyone will be told to lose weight and if you smoke, you will be told to stop smoking – and that will be in your data, so that advice isn’t going to change remarkably – but for some diseases, I think there will be some very specific things. That’s the future we want to create.”

He said the advantage of the new AI model over existing tools – such as the Qrisk way of calculating a person’s risk of developing a heart attack or stroke over the next decade – was “we can do all diseases at once and over a long time period. That is the thing that single disease models can’t do.”

The team hope doctors will be able to identify high-risk patients early, while having population-level data to hand could help NHS or public health leaders plan better and allocate resources where they are needed.

The researchers said health risks are expressed as rates over time, similar to forecasting a 70 per cent chance of rain.

Generally, forecasts over a shorter period of time had higher accuracy than longer-range ones.

Writing in the journal Nature, the team said: “Delphi-2M predicts the rates of more than 1,000 diseases, conditional on each individual’s past disease history, with accuracy comparable to that of existing single-disease models.

“Delphi-2M’s generative nature also enables sampling of synthetic future health trajectories, providing meaningful estimates of potential disease burden for up to 20 years…”

The model was custom-built and trained on anonymised patient data from 400,000 people from the UK Biobank.

Researchers also successfully tested the model using data from 1.9 million patients in the Danish National Patient Registry.

Moritz Gerstung, head of the division of AI in oncology at the German Cancer Research Centre, who worked on the study, said: “This is the beginning of a new way to understand human health and disease progression.

“Generative models such as ours could one day help personalise care and anticipate healthcare needs at scale.

“By learning from large populations, these models offer a powerful lens into how diseases unfold, and could eventually support earlier, more tailored interventions.”