🔗 Share this article

Peta Rolls grew accustomed to receiving Aida's daily call at 10am.

A routine morning call by an automated voice assistant was not part of the care package Rolls expected when she signed up for the home care but when she was invited to participate in the pilot program several months back, the elderly lady agreed because she wanted to help. Although, to be honest, her hopes weren't high.

Even so, when the call came through, she says: “I was amazed by how interactive she was. It was remarkable for a machine.”

“The system would inquire ‘how you are today?’ and that gives you an opportunity if you’re feeling sick to mention your symptoms, or I might reply ‘I’m fine, thank you’.”

“The AI would then pose follow-up questions – ‘did you manage to go outdoors today?’”

The virtual assistant would also ask what the user was planning for the day and “it would reply appropriately.”

“When I mentioned I’m going shopping, it would ask nice shopping or food shopping? I found it entertaining.”

AI Reducing the Workload on Medical Staff

This pilot, which has recently concluded its initial stage, is an example in which advances in artificial intelligence are being taken up in healthcare.

Health tech firm the provider approached the care organization regarding the trial to use its generative AI technology to provide companionship, along with an opportunity for elderly recipients to log any medical concerns or concerns for a caregiver to address.

Dean Jones, head of the home care division, says the AI check-in being trialled is not a substitute for any in-person visits.

“Recipients still receive a weekly face to face meeting, but between these meetings … the [AI] system allows a routine call, which can then flag any potential concerns to care staff or a family members,” Jones notes.

The managing director, the CEO of the company, says there have been no any adverse incidents noted from the pilot program.

The company employs open AI “with strict safety protocols” to guarantee the interaction is safe and procedures are established to address serious health issues quickly, Campbell states. For example, if a client is experiencing heart symptoms, it would be alerted to the medical staff and the call terminated so the person could dial triple zero.

Campbell believes artificial intelligence has an important role given staffing shortages throughout the medical industry.

“What we can do very safely, with technology like this, is reduce the admin burden on the staff so trained clinicians can concentrate on performing the duties that they specialize in,” she comments.

AI Not as New as Often Believed

Prof Enrico Coiera, the co-founder of the national AI health alliance, explains older forms of artificial intelligence have been a common feature of medicine for a considerable period, often in “administrative functions” such as analyzing scans, cardiograms and pathology test results.

“Software that performs a function that involves decision making in some way is artificial intelligence, irrespective of how it achieves that,” says the professor, who is also the head of the Centre for Health Informatics at Macquarie University.

“When visiting the imaging department, radiology department or pathology lab, you’ll see programs in machines doing just that.”

In recent years, advanced versions of AI known as “deep learning” – an algorithmic approach that allows systems to learn from extensive datasets – have been used to interpret medical imaging and enhance detection, Coiera notes.

Recently, a screening service became the nation's first population-based screening program to introduce machine reading technology to assist radiologists in reviewing a specific set of breast scans.

These represent advanced systems that still require a specialist doctor to evaluate the diagnosis they might suggest, and the accountability for a medical decision sits with the medical practitioner, the professor says.

AI’s Role in Identifying Illness Early

The Murdoch Children’s Research Institute in Melbourne has been collaborating with scientists from UCL London who first developed AI methods to identify epilepsy brain abnormalities known as focal cortical dysplasias from MRI images.

These abnormalities cause epileptic episodes that often cannot be controlled with medication, so surgical intervention to excise the tissue becomes the sole option. However, the procedure can only be performed if the surgeons can pinpoint the affected area.

In research published this week in the scientific publication, a team from the research body, headed by neurologist Emma Macdonald-Laurs, showed their “neural network tool” could identify the lesions in up to 94% of cases from MRI and PET scans in a specific form of the malformations that have traditionally been overlooked in the majority of patients (60%).

The AI was developed using the scans of 54 patients and then evaluated with 17 children and 12 adults. Of the 17 children, 12 had surgery and eleven became free of seizures.

The tool uses AI algorithms comparable with the breast cancer screening – highlighting suspicious areas, which are subsequently reviewed by experts “speeding up the process to reach a conclusion,” the researcher explains.

She stresses the team are still in the “early phases” of the work, with a further study necessary to advance the tool heading towards clinical implementation.

A leading neurologist, a brain specialist who was independent from the research, says MRI scans now generate such vast quantities of detailed information that it is hard for a human to go through it thoroughly. So for doctors the difficulty of finding these abnormalities was like “identifying the needle in the haystack.”

“It’s a great demonstration of how artificial intelligence can support doctors in making earlier, more accurate diagnoses, and has the potential to improve operation opportunities and results for kids with otherwise intractable epilepsy,” Cook comments.

Illness Identification in the Future

A public health expert, the deputy head of the international body's digital health and artificial intelligence section, explains deep neural networks are also helping to monitor and predict epidemics.

Buttigieg, who presented last month at the national health summit in the city, gave as an example Blue Dot, a company established by medical experts and which was one of the first organisations to identify the Covid-19 outbreak.

Content-creating AI is a additional branch of machine learning, in which the system can generate new content based on existing information. These uses in healthcare include tools such as Healthily’s AI voice bot along with the AI scribes doctors and allied health professionals are increasingly using.

A GP representative, the president of the national GP body, says family doctors have been adopting AI scribes, which records the consultation and turns into a consultation note that can be included in the health file.

Wright says the main benefit of the tools is that it enhances the quality of the communication between the doctor and patient.

Dr Danielle McMullen, the chair of the Australian Medical Association, concurs that AI note-takers are helping doctors optimise their time and adds artificial intelligence also has the potential to help doctors avoid repeated examinations and scans for their patients, if the {promised digitisation|planned digitalization