Peta Rolls grew accustomed to receiving the AI's regular check-in at 10am.
A routine morning call by an automated voice assistant was not part of the service Rolls expected when she enrolled for St Vincent’s in-home support however when she was invited to be part of the trial four months ago, the elderly lady said yes because she wished to contribute. Even though, truth be told, her hopes were low.
Even so, when the call came through, she states: “I was amazed by how responsive the AI was. It was impressive for a robot.”
“She’d always ask ‘how are you feeling today?’ and that gives you an opportunity if you feel unwell to mention your symptoms, or I just say ‘I’m fine, thank you’.”
“The AI would then pose questions – ‘have you had a chance to step outside today?’”
The virtual assistant would also ask what Rolls was planning for the day and “she would respond to that properly.”
“When I mentioned I plan to go shopping, it would ask are you shopping for clothes or groceries? It was quite engaging.”
AI Reducing the Workload on Medical Staff
This pilot, which has now wrapped up its first phase, is an example in which advances in artificial intelligence are being integrated in healthcare.
Health tech firm the provider partnered with St Vincent’s about the program to use its advanced AI system to provide social interaction, along with an opportunity for home care clients to log any medical concerns or issues for a caregiver to address.
A senior director, national director of St Vincent’s At Home, says the service being trialled does not replace any in-person visits.
“Recipients continue to get a weekly face to face meeting, but between these meetings … the automated system allows a daily check-in, which can then escalate any potential concerns to either our team or a client’s family,” Jones notes.
The managing director, the CEO of Healthily, says there haven’t been any adverse incidents reported from the pilot program.
The company uses open AI “with very clear guardrails and prompts” to ensure the interaction is safe and mechanisms are established to address serious health issues quickly, Campbell says. For example, if a patient is experiencing chest pains, it would be alerted to the care team and the call ended so the individual could call emergency services.
She believes artificial intelligence has an important role amid staffing shortages throughout the healthcare sector.
“The benefit securely, using such systems, is reduce the administrative load on the staff so trained clinicians can focus on performing the duties that they specialize in,” she says.
Artificial Intelligence Long Established as Often Believed
Prof Enrico Coiera, the co-founder of the Australian Alliance for Artificial Intelligence in Healthcare, explains older forms of AI have been a standard part of healthcare for a considerable period, frequently in “back office services” such as interpreting medical images, cardiograms and lab reports.
“Software that carries out a task that requires judgment in some way is AI, irrespective of how it achieves that,” says Coiera, who is also the head of the Centre for Health Informatics at a leading university.
“When visiting the radiology unit, medical imaging center or pathology lab, you will find programs in machines performing these tasks.”
In recent years, newer forms of AI called “deep learning” – a neural network method that enables systems to learn from extensive datasets – have been employed to read medical imaging and improve diagnosis, the expert notes.
Recently, a screening service became Australia’s pioneering population-based screening program to adopt machine reading technology to support specialists in interpreting a select range of breast scans.
These represent specialized tools that continue to need a specialist doctor to interpret the diagnosis they might suggest, and the accountability for a medical decision sits with the medical practitioner, the professor says.
AI’s Role in Early Disease Detection
A research center in Melbourne has been collaborating with researchers from a UK university who pioneered artificial intelligence techniques to identify epilepsy brain abnormalities known as specific brain malformations from MRI images.
These lesions trigger seizures that crequently cannot be controlled with drugs, meaning surgical intervention to remove them becomes the sole option. But, the procedure can proceed if the surgeons can locate the abnormal tissue.
A study recently released in the journal Epilepsia, a team from the institute, headed by specialist the lead researcher, showed their “neural network tool” could detect the lesions in up to 94% of cases from advanced imaging in a specific form of the lesions that have traditionally been missed in the majority of patients (sixty percent).
The AI was trained on the scans of 54 patients and then evaluated with 17 children and adult patients. Of the 17 children, 12 had surgery and 11 are now seizure free.
The tool uses AI algorithms similar to the mammography analysis – flagging suspicious areas, which are subsequently reviewed by specialists “speeding up the process to reach a conclusion,” the researcher says.
She stresses the researchers are still in the “early phases” of the project, with a further study necessary to get the technology heading towards clinical implementation.
Prof Mark Cook, a neurologist who was independent from the research, says modern imaging now produce such huge amounts of high-resolution data that it is hard for a human to review it accurately. So for doctors the challenge of finding these lesions was like “identifying the needle in the haystack.”
“It’s a great demonstration of how AI can support doctors in making earlier, more accurate diagnoses, and has the ability to improve surgical access and results for children with otherwise intractable epilepsy,” the professor comments.
Illness Identification in the Years Ahead
Dr Stefan Buttigieg, the vice-president of the international body's digital health and artificial intelligence section, says deep neural networks are also helping to track and forecast disease outbreaks.
Buttigieg, who spoke recently at the Public Health of Australia’s conference in the city, cited Blue Dot, a company set up by infectious disease specialists and which was one of the first organisations to detect the Covid-19 outbreak.
Content-creating AI is a further subset of machine learning, in which the system can produce original material using training data. Such applications in medicine include tools such as the virtual assistant along with the AI scribes clinicians are increasingly using.
Dr Michael Wright, the head of the national GP body, says GPs have been embracing digital assistants, which captures the appointment and turns into a consultation note that can be included in the health file.
The president says the primary advantage of the tools is that it improves the quality of the communication between the physician and individual.
A medical leader, the president of the Australian Medical Association, concurs that scribes are assisting physicians manage schedules and says AI also has the potential to prevent repeated examinations and scans for their clients, if the {promised digitisation|planned digitalization
