Research
How AI speech analysis could predict dementia onset
AI could be used to predict whether a person will develop Alzheimer’s-associated dementia by simply analysing their speech, scientists believe.
Researchers at Boston University are exploring how analysis of speech patterns via a machine learning model could detect with a high degree of accuracy whether someone with mild cognitive impairment will develop Alzheimer’s-associated dementia within six years
They say their model can predict, with an accuracy rate of 78.5 percent, whether someone with mild cognitive impairment is likely to remain stable over the next six years—or fall into the dementia associated with Alzheimer’s disease.
While allowing clinicians to make earlier diagnoses, the researchers say their work could also help make cognitive impairment screening more accessible by automating parts of the process; with no expensive lab tests, imaging exams, or office visits required.
Ioannis (Yannis) Paschalidis, director of the Boston University Rafik B. Hariri Institute for Computing and Computational Science & Engineering, says: “We wanted to predict what would happen in the next six years—and we found we can reasonably make that prediction with relatively good confidence and accuracy.
“We hope, as everyone does, that there will be more and more Alzheimer’s treatments made available.
“If you can predict what will happen, you have more of an opportunity and time window to intervene with drugs, and at least try to maintain the stability of the condition and prevent the transition to more severe forms of dementia.”
The project involves a multidisciplinary team of engineers, neurobiologists, and computer and data scientists.
“We hope, as everyone does, that there will be more and more Alzheimer’s treatments made available,” says Paschalidis.
“If you can predict what will happen, you have more of an opportunity and time window to intervene with drugs, and at least try to maintain the stability of the condition and prevent the transition to more severe forms of dementia.”
To train and build their new model, the researchers turned to data from one of the oldest and longest-running studies in the US —the BU-led Framingham Heart Study.
Although the Framingham study is focused on cardiovascular health, participants showing signs of cognitive decline undergo regular neuropsychological tests and interviews, producing a wealth of longitudinal information on their cognitive well-being.
Paschalidis and his colleagues were given audio recordings of 166 initial interviews with people, between ages 63 and 97, diagnosed with mild cognitive impairment—76 who would remain stable for the next six years and 90 whose cognitive function would progressively decline.
They then used a combination of speech recognition tools—similar to the programs powering your smart speaker—and machine learning to train a model to spot connections between speech, demographics, diagnosis, and disease progression.
After training it on a subset of the study population, they tested its predictive prowess on the rest of the participants.
“We combine the information we extract from the audio recordings with some very basic demographics—age, gender, and so on—and we get the final score,” says Paschalidis. “You can think of the score as the likelihood, the probability, that someone will remain stable or transition to dementia. It had significant predictive ability.”
Rather than using acoustic features of speech, like enunciation or speed, the model is just pulling from the content of the interview—the words spoken, how they’re structured.
And Paschalidis says the information they put into the machine learning program is rough around the edges: the recordings, for example, are messy—low-quality and filled with background noise.
“It’s a very casual recording,” he says. “And still, with this dirty data, the model is able to make something out of it.”
That’s important, because the project was partly about testing AI’s ability to make the process of dementia diagnosis more efficient and automated, with little human involvement.
In the future, the researchers say, models like theirs could be used to bring care to patients who aren’t near medical centers or to provide routine monitoring through interaction with an at-home app, drastically increasing the number of people who get screened.
According to Alzheimer’s Disease International, the majority of people with dementia worldwide never receive a formal diagnosis, leaving them shut off from treatment and care.
Rhoda Au, a coauthor on the paper, says AI has the power to create “equal opportunity science and healthcare.”
The study builds on the same team’s previous work, where they found AI could accurately detect cognitive impairment using voice recordings.
In future research, Paschalidis would like to explore using data not just from formal clinician-patient interviews—with their scripted questions and predictable back-and-forth—but also from more natural, everyday conversations.
He’s already looking ahead to a project on if AI can help diagnose dementia via a smartphone app, as well as expanding the current study beyond speech analysis—the Framingham tests also include patient drawings and data on daily life patterns—to boost the model’s predictive accuracy.
“Digital is the new blood,” says Au. “You can collect it, analyse it for what is known today, store it, and reanalyse it for whatever new emerges tomorrow.”
NICE will review whether new Alzheimer’s drugs should be offered on the NHS after an appeal found their wider impact was not fully counted.
An appeal found that the National Institute for Health and Care Excellence had failed to properly account for the wider impact of the treatments, including the heavy burden on unpaid carers, when calculating the cost effectiveness of the medicines.
Both treatments, lecanemab and donanemab, will now return to a NICE committee for further consideration.
“Today’s ruling is an opportunity for NICE to consider the real cost of Alzheimer’s on people and their families, and we welcome the decision to look again at whether new medicines could be provided on the NHS,” said David Thomas, head of policy and public affairs at Alzheimer’s Research UK.
Lecanemab and donanemab do not cure Alzheimer’s, but they slow it by targeting and clearing clumps of amyloid proteins, sticky protein build-ups in the brain linked to the disease.
While the drugs are available privately in the UK for people who can afford them, NICE ruled last year that they were too expensive to be made available on the NHS in England and Wales.
It is estimated informal dementia care costs the economy more than £20bn a year.
Alzheimer’s Research UK wants NICE to update how it assesses the value of new dementia drugs and factor in the huge additional costs this condition places on society and the wider economy.
NICE and its expert committees assess whether new drugs are good value for money for the NHS based on a wide range of evidence.
This includes how treatments perform in clinical trials, the experiences of patients and carers, and the costs of new drugs as well as any changes to NHS services needed to provide access.
When NICE weighs up whether a new Alzheimer’s drug is cost effective for the NHS, it carries out a limited assessment of the impact dementia has on the health of carers.
But the condition takes an enormous toll on families and society because caring for someone with dementia can lead people to become more isolated and give up work.
It can have a major emotional impact and put families under financial strain.
Thomas said: “Research has delivered new treatments with the potential to provide people with valuable extra months of independence, lessening the burden on carers.
“While these treatments offer modest benefits and can cause serious side effects, they provide the foundation for a future where dementia becomes a treatable condition.
“Now we need NICE to look again at how these medicines could benefit both people with early Alzheimer’s and their carers.”
Chris, whose mother Shirley is living with Alzheimer’s disease, said: “The real cost of Alzheimer’s is far greater than many people realise.
“In order to give my mum the care she needed, I moved back home to help my dad as the care was too much for him alone. After my dad passed away from Covid in 2021, I became sole carer for my mum.
“It was a very difficult period, working a full-time job, caring for Mum and dealing with the loss of my dad. Eventually I got some in-home care support to help.
“The family has borne most of the cost of Mum’s care, both in time and fees, and the family home has been sold to finance it.”
“The emotional and financial strain Alzheimer’s has taken on our family is horrendous, and I know many families across the UK are experiencing this pressure.”
He is backing Alzheimer’s Research UK’s call for NICE to change how it evaluates new dementia treatments.
The timeframe for the next NICE meetings to discuss the drugs is still to be set, and it is not certain follow-up hearings would change NICE’s guidance on access to the medicines.
But Alzheimer’s Research UK is continuing to push to make sure dementia is now a main priority for political and NHS decision-makers.
The head of the ongoing independent review into adult social care, Baroness Louise Casey, has called on the government to act, show leadership and prioritise dementia.
She has proposed appointing a dementia tsar to drive forward the prevention, treatment and care of dementia.
Baroness Casey has also argued for more funding for dementia treatment trials.
With more than 130 Alzheimer’s drugs in clinical trials worldwide, the charity says it is vital the NHS runs trials of new treatments now to understand how to deliver them to eligible patients in future.
In addition to changing how NICE assesses new medicines, the health service needs to collect real-world evidence on new dementia drugs and prepare for diagnostic tests and innovative treatments that are coming.
“Alzheimer’s Research UK is calling on the government to give dementia the same political determination that transformed cancer care,” Thomas said.
“We urgently need investment and a clear UK-wide plan so new treatments can be assessed in the NHS and reach the people who stand to benefit.”
Health and social care secretary Wes Streeting has said dementia is “one of the greatest challenges of our time” and pledged that the UK should become a world leader in dementia clinical trials.
Osteoporosis drugs may lower dementia risk, with a study suggesting one widely used treatment could help prevent Alzheimer’s and related dementias.
The research found that nitrogen-containing bisphosphonates, drugs widely used to treat osteoporosis, may significantly reduce the risk of Alzheimer’s disease and related dementias in older adults with osteoporosis or fragility fractures.
Osteoporosis and dementia often coexist in older adults and share several risk factors, including advanced age, female sex and reduced physical activity.
Researchers at the University of Hong Kong’s department of pharmacology and pharmacy carried out a large study using the city’s electronic medical records, covering more than 120,000 patients aged 60 and above with osteoporosis or fragility fractures between 2005 and 2020.
The team found that NBP users had a 16 per cent lower risk of developing Alzheimer’s disease and related dementias than untreated patients, and a 24 per cent lower risk than those who received other osteoporosis medicines.
The association was especially marked in women and patients with hip fractures.
The researchers estimated that treating 48 patients with NBPs for five years could potentially prevent one case of dementia, underlining the possible public health value of NBPs in high-risk groups.
Professor Cheung Ching-lung, associate professor in the department of pharmacology and pharmacy at the University of Hong Kong, said: “Our study provides evidence that NBPs may offer dual benefits in strengthening bones and reducing fracture risk, as well as potentially preventing ADRD.
“Their potential neuroprotective role provides an empirical basis and supports future research on the actual effectiveness of this medication in preventing or delaying cognitive decline associated with ADRD.
“These findings are significant as they demonstrate a potential approach for reducing dementia risk in a vulnerable population using safe and widely available NBPs.
“In our rapidly ageing society, these findings suggest that while waiting for the novel therapies, existing medications can also provide additional protection for high-risk populations.”
The same research team has previously found that osteoporosis and fractures are independent risk factors for dementia, and that patients with dementia are at higher risk of falls and fractures.
This suggests treating osteoporosis may also help reduce the burden of dementia.
NBPs, including alendronate and zoledronate, are well established and commonly prescribed osteoporosis drugs.
Emerging biological research suggests the pathways affected by NBPs may also play a role in the development of Alzheimer’s disease and related dementias, raising the possibility that they could be repurposed for prevention.
A prebiotic fibre supplement may ease arthritis pain and improve grip strength in people with knee osteoarthritis, a study suggests.
The daily supplement, made from inulin, a dietary fibre found in chicory root, Jerusalem artichokes and other vegetables, also lowered pain sensitivity and saw fewer people drop out than a digital physiotherapy programme tested alongside it.
Dr Afroditi Kouraki, lead author of the study from the University of Nottingham, said: ‘Our findings suggest that targeting gut health with a prebiotic supplement is a safe, well-tolerated, and effective way to reduce pain in people with knee osteoarthritis.
“The very low dropout rate compared to the exercise group is also encouraging from a public health perspective, people were able to fit this supplement easily into their daily lives.’
Osteoarthritis of the knee, a wear-and-tear joint condition, affects hundreds of millions of people worldwide and is a leading cause of pain and disability, particularly in older adults.
Current treatments rely heavily on pain medication, which can cause side effects, or exercise programmes, which many patients find hard to maintain.
The INSPIRE trial, led by researchers at the University of Nottingham, involved 117 adults with knee osteoarthritis and tested four groups: inulin alone, digital physiotherapy-supported exercise alone, a combination of both, and a placebo. Both inulin and physiotherapy independently reduced knee pain.
However, inulin alone improved grip strength and reduced pain sensitivity, measures linked to how the nervous system processes pain, while physiotherapy did not.
The dropout rate for those taking the supplement was just 3.6 per cent, compared with 21 per cent for the physiotherapy group, suggesting a daily supplement may be easier for people to stick with than an exercise programme.
Inulin works as a prebiotic, meaning it feeds beneficial bacteria in the gut.
This leads to the production of compounds called short-chain fatty acids, particularly butyrate, which can affect inflammation and pain pathways throughout the body.
Participants taking inulin also showed increased levels of both butyrate and GLP-1, a gut hormone linked to pain regulation and muscle health.
Higher GLP-1 levels were associated with improved grip strength, pointing to a possible gut-muscle connection.
Senior author Professor Ana Valdes added: ‘The link we observed between GLP-1 and grip strength is particularly intriguing and points to a broader gut-muscle-pain axis that warrants further investigation. This could have implications not just for osteoarthritis, but for understanding how gut health influences ageing and physical resilience more broadly.’
Professor Lucy Donaldson, director of research at Arthritis UK, said: “The pain of arthritis can severely impact quality of life. Our recent lived experience survey showed that six in ten people are living in pain most or all of the time due to their arthritis.
“Researchers are starting to explore the role of the gut microbiome in our experience of pain.
“This exciting preliminary research highlights how diet and physiotherapy can act in different ways to have benefits for people with arthritis.
“We know a variety and balance of healthy foods, including fibre, and regular physical activity matter, and we’re glad to be supporting research that explores how they work to help people with arthritis.”
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
