Peta Rolls grew accustomed to receiving Aida's daily call at 10am.
A daily check-in call by an automated voice assistant wasn't initially included in the care package the participant envisioned when she signed up for the in-home support but when she was invited to be part of the pilot program several months back, the 79-year-old said yes because she wished to contribute. Even though, truth be told, her expectations weren't high.
Nevertheless, when she got the call, she states: “I was amazed by how interactive the AI was. It was impressive for a robot.”
“The system would inquire ‘how are you feeling today?’ and that provides a chance if you feel unwell to say you felt sick, or I just say ‘I'm well, thanks’.”
“The AI would then pose questions – ‘did you manage to go outdoors today?’”
Aida would also ask what the user had planned for the day and “it would reply appropriately.”
“If I would say I’m going shopping, it would ask are you shopping for clothes or groceries? It was quite engaging.”
This pilot, which has now wrapped up its initial stage, is one of the ways in which advances in artificial intelligence are being integrated in the medical field.
Digital health company the provider approached the care organization about the program to utilize its generative AI technology to provide social interaction, as well as an option for elderly recipients to log any medical concerns or issues for a staff member to follow up.
A senior director, national director of St Vincent’s At Home, says the AI check-in under evaluation is not a substitute for any face to face interactions.
“Recipients still receive a weekly personal visit, but in between visits … the [AI] system allows a daily check-in, which can then flag any possible issues to care staff or a client’s family,” Jones says.
Dr Tina Campbell, the managing director of Healthily, says there have been no any adverse incidents noted from the pilot program.
Healthily uses open AI “with very clear guardrails and prompts” to guarantee the conversation is secure and mechanisms are in place to address critical medical problems quickly, Campbell states. For example, if a client is experiencing heart symptoms, it would be alerted to the care team and the conversation terminated so the person could call emergency services.
Campbell thinks AI has an important role amid staffing shortages across the healthcare sector.
“The benefit very safely, with technology like this, is reduce the administrative load on the staff so trained clinicians can focus on performing the duties that they specialize in,” she says.
An expert, the founder of the national AI health alliance, explains older forms of AI have been a common feature of medicine for a long time, often in “administrative functions” such as interpreting medical images, cardiograms and lab reports.
“Software that carries out a function that requires judgment in certain aspects is AI, irrespective of how it achieves that,” says the professor, who is also the director of the Centre for Health Informatics at a leading university.
“If you go the imaging department, radiology department or diagnostic laboratory, you will find software in equipment doing just that.”
Over the past decade, advanced versions of AI known as “machine learning” – a neural network method that allows systems to analyze extensive datasets – have been employed to interpret diagnostic scans and improve diagnosis, the expert says.
Recently, BreastScreen NSW became Australia’s first population-based screening program to introduce AI analysis tools to support radiologists in interpreting a specific set of mammography images.
These represent specialized tools that continue to need a qualified physician to evaluate the diagnosis they could indicate, and the responsibility for a clinical judgment sits with the healthcare provider, the professor emphasizes.
The Murdoch Children’s Research Institute in the city has been working alongside scientists from UCL London who pioneered artificial intelligence techniques to identify epilepsy brain abnormalities called focal cortical dysplasias from MRI images.
These abnormalities cause seizures that crequently cannot be controlled with drugs, so surgical intervention to excise the tissue becomes the only treatment available. But, the procedure can proceed if the doctors can pinpoint the abnormal tissue.
In research published this week in the scientific publication, a group from the research body, headed by specialist the lead researcher, demonstrated their “AI epilepsy detective” could identify the abnormalities in up to 94% of instances from advanced imaging in a specific form of the lesions that have historically been missed in the majority of cases (sixty percent).
The system was trained on the images of 54 patients and then evaluated with 17 children and adult patients. Among the youngsters, twelve underwent operations and 11 are now seizure free.
This technology uses neural network classifiers similar to the breast cancer screening – highlighting regions of abnormality, which are still checked by experts “speeding up the process to get to the answers,” the researcher explains.
She stresses the researchers are still in the “early phases” of the work, with a additional research required to advance the tool heading towards real-world use.
Prof Mark Cook, a brain specialist who was not involved in the study, says MRI scans now produce such vast quantities of detailed information that it is challenging for a human to go through it accurately. So for doctors the difficulty of locating these abnormalities was like “searching for a needle in a haystack.”
“This illustrates of how artificial intelligence can support clinicians in making quicker, precise identifications, and has the potential to enhance operation opportunities and results for children with treatment-resistant seizures,” the professor says.
Dr Stefan Buttigieg, the deputy head of the European Public Health Association’s digital health and artificial intelligence section, explains advanced AI systems are also helping to monitor and predict disease outbreaks.
Buttigieg, who presented recently at the national health summit in the city, cited Blue Dot, a company established by medical experts and which was one of the first organisations to identify the Covid-19 outbreak.
Generative AI is a further subset of deep learning, in which the system can generate new content based on training data. Such applications in medicine include tools such as Healthily’s AI voice bot as well as the automated note-takers doctors and allied health professionals are increasingly using.
Dr Michael Wright, the head of the national GP body, reports family doctors have been embracing digital assistants, which captures the appointment and converts it to a medical summary that can be included in the health file.
The president says the main benefit of the tools is that it improves the quality of the communication between the doctor and patient.
Dr Danielle McMullen, the president of the Australian Medical Association, agrees that scribes are helping physicians manage schedules and says artificial intelligence also has the potential to help doctors avoid duplication of tests and imaging for their clients, if the {promised digitisation|planned digitalization
Tech enthusiast and writer with a passion for exploring emerging technologies and their impact on society.
