'AI brings new opportunities to healthcare'

AI helps predict diseases more accurately and personalize treatment, according to Professor Karin Verspoor, Head of the School of Computer Science, RMIT University Australia.

The application of AI in healthcare is gradually becoming a global booming trend. Discussing this issue, Professor Karin Verspoor had a talk with VnExpress about the advances in this field.

- Professor, please analyze the trends of AI application in healthcare globally?

- When it comes to healthcare, one of the most mature areas of AI is image processing. For example, computer vision applications that leverage machine learning can diagnose and detect diseases. The technology can also be used to interpret chest X-ray results or classify skin lesions that could be signs of cancer. Many hospitals also deploy robotic surgical assistants with high precision and efficiency, supporting surgeons based on the characteristics of each patient.

We are seeing increasing progress in using AI to guide clinical decision making using more diverse clinical data, such as data recorded in electronic health records – including both structured data (e.g. blood biomarkers, vital signs) and unstructured data (data from notes, reports, genetic information).

Another notable trend, there are broader AI applications related to clinical environments. You can see devices that can assist in clinical documentation by taking notes automatically, clinical narrative during surgery, or recording patient histories during physician consultations.

Professor Karin Verspoor at the third annual Vietnam-Australia seminar on cooperation to promote Industry 4.0, held on October 20, 2022. Photo: Provided by the character

- Why is image processing technology having such a profound impact in the healthcare field?

- This is due to the fact that the healthcare industry has more frequent and systematic data than many other types of clinical data. In the healthcare industry, there are a limited number of imaging devices and manufacturers, so the data is quite consistent.

Additionally, images are well suited to current AI algorithms. They can be viewed as completely dense pixel matrices, meaning that every cell in the matrix has a value. This type of data is well suited to the types of representations and mathematical analysis that AI methods can perform.

There is also a large amount of labeled image data – i.e. known diagnoses associated with each image. This means that supervised machine learning is straightforward to implement. These systems have proven to be very effective, performing on par with, or even better than, human experts in some cases.

- In that general picture, in Vietnam, how is AI applied in public health care?

- In developing countries, the implementation of software systems such as electronic health records may be less widespread. These countries also have less access to technology and health resources, affecting the development of some applications that depend on electronic data collection.

However, technology and AI can still bring significant benefits to users in these countries and Vietnam. AI brings specialized expertise even if it is not available locally. Instead of specialized devices, you can use sensors on common products such as mobile phones and smartwatches to record health data. Some tools can analyze cough recordings to diagnose Covid-19 or detect atrial fibrillation from heart rate using data on these devices.

Smart health assistants can be deployed through an app, thereby empowering patients to take more control over their health.

- So what are the barriers to applying AI in healthcare?

- The main barrier to AI in clinical decision-making involves collecting data from the Vietnamese population. Any AI tool needs to be tailored to the specific characteristics of the population. That is, the input data must be consistent with the data on which the model was trained.

AI tools are often not easily portable from one context to another. This implies that, for AI to confidently perform well in the Vietnamese context, tools need to be adapted and evaluated appropriately in that context. This requires investment in digital infrastructure in Vietnamese healthcare facilities. Investments must be made across all aspects: healthcare facilities, electronic health records systems, and data sharing and linkage mechanisms between healthcare providers.

A bigger challenge involves identifying the problems that need to be addressed in the unique environment in Vietnam, where AI can be most valuable. This requires collaboration between researchers, AI innovators, and healthcare leaders to identify opportunities, set priorities, and drive investment.

- Can you share some experiences from Australia in this field?

- In Australia, Covid-19 has accelerated the adoption of digital health technologies and made the need for them even stronger. Lockdowns and restrictions have led people to turn to online healthcare. This has changed the healthcare landscape, creating a trend of using technology to support health care and general wellbeing.

These changes have been noticed and supported by the community, leading to national conversations – within government and in the media – about the regulation of software as a medical device, the ethics of using AI in a medical context, and the value of health data as a public resource. As well as its value, organizations need to respect the sensitivity and privacy of this data.

I think Vietnam can learn from this experience, which is to engage the public and understand the opportunities that AI brings to healthcare. Ultimately, it is patients and consumers who will benefit from the adoption of these technologies. But we will also rely on their data to build and evaluate them. So it is important to build trust in AI systems, from patients and healthcare providers.

Professor Karin Verspoor (far left) in a discussion with experts on the potential of AI. Photo: Character provided

- How do you predict the future development of AI in healthcare?

- Today, AI is on people's minds more than ever. The excitement around ChatGPT and generative AI has made people more interested in using artificial intelligence to solve countless problems in business and life.

The application of AI in health and wellbeing is no exception and we will certainly see increased innovation in this area. I believe there will be many opportunities to leverage AI to improve patient care, through multi-modal data integration and complex predictive modeling.

AI will help us better predict patient outcomes and disease progression, and provide highly personalized treatment plans. We will be able to leverage technology to capture recorded medical activity, providing knowledge and evidence of the impact of treatment. This will lead to further improvements in practice – a virtuous cycle known as a Learning Health System.

We can improve the patient experience by proactively suggesting steps in the treatment process, providing clinicians with the right information to support their decisions. We can even improve the patient experience by leveraging AI to make interactions with the healthcare system more “human.” For example, by assisting with preparation and documentation tasks so that doctors can have more time to talk to their patients. Some real-time translation tools allow for multilingual settings, helping to translate complex medical language into more understandable information, increasing the efficiency of patient communication.

Patients will have more autonomy in their own health care. They will also use digital technology to collect, manage, analyze and interpret their own health data, thereby becoming more informed in their interactions with the health system.

Minh Tu

Source link: https://vnexpress.net/ai-mang-den-nhung-co-hoi-moi-cho-y-te-4661285.html