News
Breakthrough for AI dementia diagnosis tool
Researchers at the University of Cambridge have developed an artificially-intelligent tool capable of predicting in four cases out of five whether people with early signs of dementia will remain stable or develop Alzheimer’s disease.
The team say this new approach could reduce the need for invasive and costly diagnostic tests while improving treatment outcomes early when interventions such as lifestyle changes or new medicines may have a chance to work best.
Professor Zoe Kourtzi from the Department of Psychology at the University of Cambridge is the study’s senior author.
The researcher said: “We’ve created a tool which, despite using only data from cognitive tests and MRI scans, is much more sensitive than current approaches at predicting whether someone will progress from mild symptoms to Alzheimer’s – and if so, whether this progress will be fast or slow.
“This has the potential to significantly improve patient wellbeing, showing us which people need closest care, while removing the anxiety for those patients we predict will remain stable.
“At a time of intense pressure on healthcare resources, this will also help remove the need for unnecessary invasive and costly diagnostic tests.”
Early detection of dementia is crucial as this is when treatments are likely to be most effective, yet early diagnosis and prognosis may not be accurate without the use of invasive or expensive tests such as positron emission tomography (PET) scans or lumbar puncture, which are not available in allmemory clinics.
As a result, up to a third of patients may be misdiagnosed and others diagnosed too late for treatment to be effective.
In the new study, researchers developed a machine learning model able to predict whether and how fast an individual with mild memory and thinking problems will progress to developing Alzheimer’s disease. In research, they show that it is more accurate than current clinical diagnostic tools.
To build their model, the researchers used routinely-collected, non-invasive, and low-cost patient data – cognitive tests and structural MRI scans showing grey matter atrophy – from over 400 individuals who were part of a research cohort in the USA.
They then tested the model using real-world patient data from a further 600 participants from the US cohort and – importantly – longitudinal data from 900 people from memory clinics in the UK and Singapore.
The algorithm was able to distinguish between people with stable mild cognitive impairment and those who progressed to Alzheimer’s disease within a three-year period.
It was able to correctly identify individuals who went on to develop Alzheimer’s in 82 per cent of cases and correctly identify those who didn’t in 81 per cent of cases from cognitive tests and an MRI scan alone.
The algorithm was around three times more accurate at predicting the progression to Alzheimer’sthan the current standard of care; that is, standard clinical markers (such as grey matter atrophy or cognitive scores) or clinical diagnosis.
This shows that the model could significantly reduce misdiagnosis.
The model also allowed the researchers to stratify people with Alzheimer’s disease using data from each person’s first visit at the memory clinic into three groups: those whose symptoms would remain stable (around 50 per cent of participants), those who would progress to Alzheimer’s slowly (around 35 per cent) and those who would progress more rapidly (the remaining 15 per cent).
These predictions were validated when looking at follow-up data over six years.
This is important as it could help identify those people at an early enough stage that they may benefit from new treatments, while also identifying those people who need close monitoring as their condition is likely to deteriorate rapidly.
Importantly, those 50 per cent of people who have symptoms such as memory loss but remain stable, would be better directed to a different clinical pathway as their symptoms may be due to other causes rather than dementia, such as anxiety or depression.
While the researchers tested the algorithm on data from a research cohort, it was validated using independent data that included almost 900 individuals who attended memory clinics in the UK and Singapore.
The researchers say this shows it should be applicable in a real-world patient, clinical setting.
Dr Ben Underwood is Honorary Consultant Psychiatrist at CPFT and assistant professor at the Department of Psychiatry, University of Cambridge.
He said: “Memory problems are common as we get older.
“In clinic I see how uncertainty about whether these might be the first signs of dementia can cause a lot of worry for people and their families, as well as being frustrating for doctors who would much prefer to give definitive answers.
“The fact that we might be able to reduce this uncertainty with information we already have is exciting and is likely to become even more important as new treatments emerge.”
The team now hope to extend their model to other forms of dementia, such as vascular dementia and frontotemporal dementia, and using different types of data, such as markers from blood tests.
Gut-friendly foods such as kimchi and kombucha may carry hidden risks for heart health when eaten in excess, the British Heart Foundation (BHF) has warned.
The charity said foods marketed as prebiotic, probiotic or otherwise good for the gut can support the microbiome, but some may also be high in salt or sugar, which can raise the risk of cardiovascular disease.
Products highlighted by the British Heart Foundation included kimchi, kombucha, fruit yoghurts, smoothies and sauerkraut. It said there is no harm in including them as part of a healthy diet, but advised people to check labels for added salt and sugar and eat them in moderation.
Tracy Parker, the charity’s nutrition lead, said: “We encourage everyone to choose foods that can keep their gut microbiome healthy. The benefits are clear, and we are continuing to improve our understanding of how a gut-friendly diet may help our hearts.
“A lot of these products can contain high levels of salt or sugar though, so it is important to be aware of the potential drawbacks.
“By ensuring you check package labels for added salt and sugars, and eat each in moderation, you can make sure the risks do not outweigh the benefits for your heart health.”
Fermented foods such as kimchi and sauerkraut are rich in probiotics, the healthy bacteria produced during fermentation that can help support a diverse and healthy gut microbiome.
However, both are traditionally made using a lot of salt, which can raise blood pressure if eaten frequently or in large quantities. High blood pressure is known to increase the risk of heart attack and stroke.
Kombucha, a fermented tea, also contains probiotics and can be a healthier alternative to fizzy drinks, but many commercial and shop-bought versions contain added sugar.
Eating too much sugar can lead to weight gain, which can increase the risk of heart attack, stroke and other cardiovascular disease.
Fruit yoghurts can contain probiotic live bacteria cultures, but may also be high in sugar and have fewer live cultures than plain versions.
The charity said plain yoghurt with live and active cultures on the label can be a lower-sugar option, with whole fruit added at home for sweetness.
Smoothies made with whole fruits provide prebiotic fibre, which feeds beneficial gut bacteria and supports digestive health.
They can also provide vitamins and antioxidants, especially when made with a variety of plant-based ingredients.
But blending breaks down the structure of fruit, releasing free sugars that behave like added sugars in the body and can cause faster rises in blood sugar levels.
Regularly consuming too much sugar can lead to weight gain, which can increase the risk of developing type 2 diabetes, heart disease and kidney disease.
The charity said only one 150ml serving of any smoothie counts towards five-a-day, and suggested adding nuts or seeds for extra protein and fibre to help keep blood sugar levels more stable.
The BHF also noted that some shop-bought sauerkraut is pasteurised, which removes most of the live bacteria.
It advised checking the label, eating small portions and choosing unpasteurised products for those seeking the probiotic benefits.
The charity said beneficial gut bacteria produce short-chain fatty acids during digestion, which are linked to reduced inflammation, better metabolism and better heart and circulatory health.
These good bacteria also help digest polyphenols, natural plant chemicals thought to have antioxidant properties and which may help lower blood pressure.
By contrast, harmful gut bacteria, which thrive on diets high in fat and red meat, produce chemicals that can cause problems in the heart and blood vessels by increasing inflammation and altering how cholesterol is processed in the body.
Beneficial bacteria thrive on varied diets high in prebiotics, non-digestible fibres found in foods such as wholegrains, oats, beans, lentils, bananas and onions.
People with diabetes may have undiagnosed heart failure that could be detected by a simple screening blood test, research suggests.
The TARTAN-HF trial found that one in four patients with diabetes who had at least one other risk factor for heart failure had undiagnosed heart failure detected through screening with a blood test and ultrasound scanning of the heart.
Experts said the findings show the extent of unrecognised heart failure in people with diabetes, and how the condition can be detected using a widely available blood test called NT-proBNP, which measures how much strain the heart is under.
They suggest a heart failure screening programme for diabetics could improve diagnosis rates, lead to earlier treatment and potentially reduce the risk of hospitalisation and death.
The study, involving 700 patients, was led by the University of Glasgow in collaboration with AstraZeneca, Roche Diagnostics, Us2.ai, NHS Greater Glasgow and Clyde and NHS Lanarkshire.
Dr Kieran Docherty, clinical senior lecturer at the University of Glasgow’s School of Cardiovascular and Metabolic Health, said: “Our results from the landmark TARTAN-HF trial identified heart failure in a large proportion of people living with diabetes, emphasising the need for a heart failure screening strategy in this group of patients.
“We know that many of the symptoms and signs of heart failure are non-specific, and may go unrecognised as potentially being due to heart failure for a long time.
“The strategy used in our trial is simple and easy to implement in clinical practice, and will aid in the early identification of heart failure in people with diabetes, and facilitate the initiation of medications that we know improve outcomes in patients with heart failure.”
The study, which began more than three years ago, involved more than 700 people with diabetes from the two health board areas who had at least one other risk factor for heart failure.
They were randomly assigned either to receive heart failure screening or to continue with their usual care.
Researchers found screening uncovered a large number of previously unrecognised cases of heart failure. Around one in four, or 24.9 per cent, of those screened were found to have the condition within six months, compared with 1 per cent in the group continuing their usual care.
The study, involving patients with type 1 and type 2 diabetes, found almost all of the participants found to have heart failure had preserved ejection fraction, which can be difficult to detect without dedicated testing.
The findings of the TARTAN-HF trial were presented at the American College of Cardiology conference taking place from 28 to 30 March in New Orleans in the US.
Dr Edward Piper, medical director at AstraZeneca UK, said: “Delayed diagnosis and treatment of heart failure in people with type 2 diabetes contributes to poor long-term outcomes. TARTAN-HF demonstrates that targeted, risk-based screening can identify previously undiagnosed heart failure in approximately one in four high-risk patients with diabetes, enabling earlier intervention with guideline-directed therapy.”
Dr Christian Simon, head of global medical affairs at Roche Diagnostics, said: “We are proud to have supported the landmark TARTAN-HF trial. These findings demonstrate the transformative power of early, accessible diagnostics like the NT-proBNP blood test.
“By identifying unrecognised heart failure in people with diabetes, we enable clinicians to initiate appropriate treatments sooner, ultimately improving patient outcomes and lives.”
The UK has launched a £6.3m men’s health fund to back local projects aimed at helping men and boys live longer, healthier lives.
The Men’s Health Community Fund is a partnership between the Department of Health and Social Care, Movember and People’s Health Trust.
The government is contributing £3m, while the two charities are more than doubling that to take the total to £6.3m.
Grants will support community projects reaching underserved men and boys aged 16 and over, particularly in the most disadvantaged areas and at key points in their lives such as becoming a father, losing a job or retiring.
Projects could include support for new fathers, activities for men facing loneliness and social isolation, services to help young men engage with the health system, and support for men in work, out of work and moving into retirement.
The programme will bring together voluntary, community and social enterprise organisations to test new ways of reaching men who are least likely to use traditional health services.
An evaluation funded through the National Institute for Health and Care Research will assess what works and help inform future policy and delivery.
Health and social care secretary Wes Streeting said: “Too many men across the country are living shorter, less healthy lives, particularly those in our most disadvantaged communities.
“This new partnership will help men get the support they need in the places they feel most comfortable, their communities, among people they trust.
“By working with expert charities and local organisations, we can reach the men who are too often missed by traditional services and help them take better care of their mental and physical health.”
“It is a key step in delivering our first ever Men’s Health Strategy and driving forward our ambition to halve the gap in healthy life expectancy between the richest and poorest areas.”
The Men’s Health Strategy sets out plans to tackle the physical and mental health challenges men and boys face.
Men can be less likely to seek help and more likely to suffer in silence, while higher rates of smoking, drinking, gambling and drug use are damaging men’s health and affecting families, workplaces and communities.
The government is also investing £3.6m over the next three years in suicide prevention projects for middle-aged men in local communities across areas of England where men are most at risk, many of which are also among the most deprived. Suicide is one of the biggest killers of men under 50, and three-quarters of all suicides are men.
The projects will aim to break down barriers middle-aged men face in seeking support, including stigma around asking for help and a lack of awareness of what is available and how to access it.
They will be co-designed with experts and men with lived experience of mental health crises and suicidal thoughts.
Gut-friendly foods may damage heart, charity warns
Diabetes patients face increased risk of undiagnosed heart failure
UK government announces £6.3m fund to boost men’s health
Brain health collaboratory launches in Gulf South
