Connect with us

News

New AI tool can predict pancreatic cancer three years in advance

Published

on

A new artificial intelligence tool may be able to successfully identify people at risk of pancreatic cancer up to three years in advance.

The breakthrough AI model used patients’ medical records and information from previous scans to detect those at risk of the deadly disease, which can be hard to catch early, difficult to treat, and kills more than half of sufferers within five years of diagnosis.

Research led by investigators at Harvard Medical School and the University of Copenhagen in collaboration with VA Boston Healthcare System, Dana-Farber Cancer Institute, and the Harvard TH Chan School of Public Health, suggests AI was able to determine a person’s risk of developing pancreatic cancer with astounding accuracy.

The findings published in Nature Medicine implies AI-based population screening could be valuable in finding those at elevated risk of developing the disease, which has an average age of diagnosis of 72 and affects both men and women.

Currently, there are no population-based tools to screen broadly for pancreatic cancer, which in its early stages can have no specific symptoms.

Those with a family history and certain genetic mutations that predispose them to the disease are screened in a targeted fashion. But such focused screenings can miss other cases that fall outside of those categories, the researchers said.

Study co-senior investigator Chris Sander, faculty member in the Department of Systems Biology in the Blavatnik Institute at Harvard Medical School, said: ” One of the most important decisions clinicians face day to day is who is at high risk for a disease, and who would benefit from further testing, which can also mean more invasive and more expensive procedures that carry their own risks.

“An AI tool that can zero in on those at highest risk for pancreatic cancer who stand to benefit most from further tests could go a long way toward improving clinical decision-making.”

Applied at scale, such an approach could expedite detection of pancreatic cancer, lead to earlier treatment, and improve outcomes and prolong patients’ life spans, Dr Sander added.

According to World Cancer Research, pancreatic cancer is the 12th most common in the world with nearly 500,000 new cases in 2020. Globally, the incidence of the disease is projected to increase to 18.6% per 100,000 by 2050, meaning it will pose a significant public health burden.

Søren Brunak, professor of disease systems biology and director of research at the Novo Nordisk Foundation Center for Protein Research at the University of Copenhagen, said: “Many types of cancer, especially those hard to identify and treat early, exert a disproportionate toll on patients, families and the healthcare system as a whole.

“AI-based screening is an opportunity to alter the trajectory of pancreatic cancer, an aggressive disease that is notoriously hard to diagnose early and treat promptly when the chances for success are highest.”

In the study the researchers applied an AI algorithm to clinical date from nine million patient records from the US and Denmark. They asked the AI model to look for tell tale signs based on the data contained in the records.

Based on combinations of disease codes and the timing of their occurrence, the model was able to predict which patients are likely to develop pancreatic cancer in the future. Notably, many of the symptoms and disease codes were not directly related to or stemming from the pancreas.

The researchers tested different versions of the AI models for their ability to detect people at elevated risk for disease development within different time scales — six months, one year, two years, and three years – and found their methods were “substantially more accurate at predicting who would develop pancreatic cancer than current population-wide estimates of disease incidence.”

Among 22 people with lung nodules that eventually were diagnosed with the cancer, the AI flagged 18 as having a high risk of developing the disease.

The researchers said they believe the model is at least as accurate in predicting disease occurrence as are current genetic sequencing tests that are usually available only for a small subset of patients in data sets.

Relatively simple screening tests have become common for many other cancers like breast, cervix, and prostate. By picking up signs of disease early, they have transformed the outcome for patients.

But pancreatic cancer is harder and more expensive to screen and test for.

Medics look mainly at family history and the presence of genetic mutations, which, while important indicators of future risk, often miss many patients.

The researchers say one particular advantage of the AI tool is that it could be used on any and all patients for whom health records and medical history are available – not just in those with a known family history or genetic predisposition for the disease.

This is especially important, the researchers add, because many patients at high risk may not even be aware of their genetic predisposition or family history.

In the absence of symptoms and without a clear indication that someone is at high risk for pancreatic cancer, clinicians may be cautious to recommend more sophisticated and  expensive testing, such as CT scans, MRI or endoscopic ultrasound.

When these tests are used and suspicious lesions discovered, the patient must undergo a procedure to obtain a biopsy. Positioned deep inside the abdomen, the organ is hard to access and easy to provoke and inflame. Its irritability has earned it the nickname ‘the angry organ.’

An AI tool that identifies those at the highest risk for pancreatic cancer would ensure that clinicians test the right population, while sparing others unnecessary testing and additional procedures, the researchers said.

About 44% of people diagnosed in the early stages of pancreatic cancer survive five years after diagnosis, but only 12% of cases are diagnosed that early. Researchers estimate the survival rate drops to between 2-9% in those whose tumours have grown beyond their site of origin.

Dr Sander said: “That low survival rate is despite marked advances in surgical techniques, chemotherapy, and immunotherapy. So, in addition to sophisticated treatments, there is a clear need for better screening, more targeted testing, and earlier diagnosis, and this is where the AI-based approach comes in as the first critical step in this continuum.”

AI has come in for criticism recently due to fears about privacy, intellectual property rights, bias and ethics.

Many scientists are also worried that the technology could soon outperform humans.

But it is being embraced in medicine where it is already being used to help develop new drugs, in surgery and for personalising treatment.

In March this year researchers in Canada announced that artificial intelligence had developed a treatment for the most common type of liver cancer, hepatocellular carcinoma, in just 30 days and could predict a patient’s survival rate.

News

On a mission to show that hearing loss is not inevitable

Published

on

The world’s largest investigation into the effectiveness of hearing training kicks off this week – as part of a movement to prove that hearing loss is not an inevitable part of ageing.

The research project aims to attract a minimum of 10,000 participants to better understand how hearing training impacts auditory processing skills like speech comprehension and the ability to locate where sounds are coming from.

Researchers are interested in the impact of hearing training on users who start training with different hearing ability levels, as well as training adherence in groups with different attitudes to smartphone technology.

Their aim is to find new ways to deliver and improve auditory training at scale and for a wider range of hearing skills; and to measure factors which influence training engagement.

The research is led by health tech firm Eargym. Co-founder Andy Shanks says:  Contrary to popular belief, hearing loss is not an inevitable consequence of ageing. We can take steps to improve and protect our hearing throughout our lives, yet preventative measures like hearing training have traditionally been under-researched.

“Our data shows the transformative impact hearing training can have on our ability to process sounds. Now, we want to deepen and widen our research and use our platform to make hearing training even more effective and accessible. Imagine improving and maintaining your hearing by up to 20% or more: it could make a big difference to the lives of so many people.”

The games on the Eargym app include a “busy barista” exercise, where users must discern speech over a cafe’s bustling background noise; and a “sound seeking” exercise, where users make their way through forests, jungles and oceans to locate the sources of different sounds. Each game is designed to be immersive and to help users practise specific auditory processing skills regularly.

Eargym was set up by former NHS CEO Amanda Philpott and DJ Andy Shanks in 2020, after they were both diagnosed with hearing loss. Amanda has moderate age related hearing loss, whilst Andy has “notch” or noise-induced hearing loss due to DJ-ing. Both found hearing loss isolating and it impacted their ability to socialise and communicate. They created eargym to empower others to better understand their hearing health and take proactive steps to protect it.

Hearing loss currently affects 18 million adults in the UK, with around one billion young people at risk of developing hearing loss due to increased use of headphones. Hearing loss is closely associated with increased dementia risk. Despite this, people wait an average ten years before seeking help for hearing loss.

Eargym plans to publish the findings of its research in early 2025.

Continue Reading

News

Interview: Exploring electrical stimulation for Parkinson’s disease

Published

on

The STEPS II study is investigating functional electrical stimulation (FES) in people with Parkinson’s disease to help improve their walking. Dr Paul Taylor, co-founder and Clinical Director of Odstock Medical Ltd (OML), spoke to Agetech World to tell us more.

Bradykinesia – slowness of movement which can lead to difficulty walking – affects many people living with Parkinson’s disease. The symptom can cause Parkinson’s patients to walk or move slowly, increasing the risk of falls, leading to a reduced quality of life and an increased dependence on others. 

Funded by the National Institute for Health and Care Research, sponsored by Salisbury NHS Foundation Trust, and managed by the University of Plymouth’s Peninsula Clinical Trials Unit, the STEPS II study is exploring the use of an FES device in Parkinson’s patients to help improve bradykinesia. 

The FES device, which has been pioneered by Salisbury researchers as a drop foot treatment for stroke and MS patients, is attached to the patient’s leg and produces small electrical impulses that improve movement.

“If you have Bradykinesia you’re moving slowly. The predominant treatment for Parkinson’s is medication and these can be very effective, but they have the problem of not working all the time,” explains Taylor, co-founder of Odstock Medical Ltd, a company owned by Salisbury NHS Foundation Trust.

”The effects of the drugs will wear off and after a period of time they become less effective, so, there’s a need for improvement.”

Taylor explains that deep brain stimulators are currently available, however, they are very invasive, expensive and can be risky. 

“We’re trying to do something which is a bit simpler and cheaper, which may possibly be able to help people at an earlier stage of Parkinson’s,” Taylor says.

“We’re stimulating the common peroneal nerve, which is the nerve that goes down the leg to the muscles, using a device called a drop foot stimulator. The device is commonly used for stroke and multiple sclerosis.”

A small feasibility study has already been conducted, which showed that FES can help patients walk faster and reduce some symptoms of Parkinson’s. 

In the STEPS II study, researchers hope to confirm the long-term effects of FES on walking speed and daily life with 234 participants at sites across Salisbury, Birmingham, Prestwick, Leeds, Swansea and Carlisle.

Taylor continues: “Our original idea was that we could use electrical stimulation to overcome freezing – which is the effect where people with Parkinson’s will stop walking, particularly when they come to doorways or very narrow areas. It’s to do with the processing of information from the outside world. 

“We wanted to see if we could use electrical stimulation to overcome that freezing and, to a certain extent, we did find that is the case for some patients, but more commonly and with a greater number of patients FES affected bradykinesia – speeding up their movement and helping with more effective walking.”

For the STEPS II study, participants will be randomised into a care as normal group, or a care as normal plus FES group. They will use the stimulator if they are in the FES group for 18 weeks, then the stimulator is taken away, with patients followed up one month later to see if the effects are continued.

Measurements of walking speed and movement will be analysed, along with sensory perception, balance, coordination, muscle strength, as well as secondary effects such as how the device impacts daily living and quality of life.

OML has established clinics around the country with trained therapists where the device will be used if the study is successful. 

“There’s a network of clinics already experienced in using the treatment so we plan to reach those clinics to include Parkinson’s patients in their cohorts,” says Taylor. “Then we’ll work with our contacts to see if we can get it overseas as well.”

OML is currently recruiting participants for the study, to find out more please visit: https://www.plymouth.ac.uk/research/penctu/steps-2 

Continue Reading

News

Quit Googling to stave off dementia onset, expert urges

Published

on

Resisting the temptation to search the web for information that could otherwise be recalled be exercising your brain could help to reduce the risk of dementia.

That is according to Canadian academic Professor Mohamed I. Elmasry who believes simple daily habits such as afternoon naps, memory ‘workouts’ and not reaching for a smartphone can increase the odds of healthy aging.

His new book, iMind: Artificial and Real Intelligence, says the focus has shifted too far away from RI (natural, or real) intelligence in favour of AI (machine, or artificial) intelligence. Elmasry instead calls us to nurture our human mind which, like smartphones, has ‘hardware’, ‘software’ and ‘apps’ but is many times more powerful – and will last much longer with the right care.

Professor Elmasry, an internationally recognised expert in microchip design and AI, was inspired to write the book after the death of his brother-in-law from Alzheimer’s and others very close to him, including his mother, from other forms of dementia.

Although he says that smart devices are ‘getting smarter all the time’, he argues in iMind that none comes close to ‘duplicating the capacity, storage, longevity, energy efficiency, or self-healing capabilities of the original human brain-mind’.

He writes that: “The useful life expectancy for current smartphones is around 10 years, while a healthy brain-mind inside a healthy human body can live for 100 years or longer.

“Your brain-mind is the highest-value asset you have, or will ever have. Increase its potential and longevity by caring for it early in life, keeping it and your body healthy so it can continue to develop.

“Humans can intentionally develop and test their memories by playing ‘brain games,’ or performing daily brain exercises. You can’t exercise your smartphone’s memory to make it last longer or encourage it to perform at a higher level.”

In iMind: Artificial and Real Intelligence Professor Elmasry shares an anecdote about his grandchildren having to use the search engine on their smartphones to name Cuba’s capital—they had just spent a week in the country with their parents.

The story illustrates how young people have come to rely on AI smartphone apps instead of using their real intelligence (RI), he says, adding: “A healthy memory goes hand-in-hand with real intelligence. Our memory simply can’t reach its full potential without RI.”

Published by Routledge, iMind: Artificial and Real Intelligence includes extensive background on the history of microchip design, machine learning and AI and their role in smartphones and other technology.

The book also explains how both AI and human intelligence really work, and how brain function links the mind and memory. It compares the human mind and brain function with that of smartphones, ChatGPT and other AI-based systems.

Drawing on comprehensive existing research, iMind aims to narrow the knowledge gap between real and artificial intelligence, to address the current controversy around AI, and to inspire researchers to find new treatments for Alzheimer’s, other neurodegenerative conditions and cancer.

It argues that current or even planned AI cannot match the capabilities of the human brain-mind for speed, accuracy, storage capacity and other functions. Healthy aging, Professor Elmasry notes, is as important as climate change but doesn’t attract a fraction of the publicity.

He calls for policymakers to adopt a series of key reforms to promote healthy aging. Among such changes, he suggests that bingo halls could transition from their sedentary entertainment function to become active and stimulating learning centers.

As well as napping to refresh our memories and other brain and body functions, he also outlines a series of practical tips to boost brain power and enhance our RI (Real Intelligence).

These include building up ‘associative’ memory – the brain’s ‘dictionary of meaning’ where it attaches new information to what it already knows. Try reading a book aloud, using all of your senses instead of going on autopilot and turning daily encounters into fully-lived experiences.

Other techniques include integrating a day for true rest into the week, reviewing your lifestyle as early as your 20s or 30s, adopting a healthy diet, and eliminating or radically moderating alcohol consumption to reduce the risk of dementia.

Continue Reading

Trending