The healthcare algorithm: what are the challenges and possibilities of AI in the sector?
Alexandre Chiavegatto navigates the universe of artificial intelligence in healthcare, answering the biggest current questions on the topic
Estimated reading time: 10 minutes
In the thirteenth edition of Green Rock Insights, we take a journey on the use of artificial intelligence in healthcare. Much is said about the applications of AI in diagnosis, treatment and health management, as well as the potential of this tool to expand access to quality healthcare and shape the future of the sector. However, understanding the moment of this evolution that we are experiencing and the obstacles that need to be overcome is still a great challenge. To better understand this entire context, we have an exclusive interview with Alexandre Chiavegatto, a specialist at USP in artificial intelligence in the health sector.
All of our texts will be available on the blog in three versions (Portuguese, English and Spanish).
Good reading!
Much has been said about artificial intelligence in healthcare and its potential in various fields. For example, the 2023 edition of the Future Health Index, a report that raises some perspectives on the future of health around the world, found that 83% of the leaders interviewed plan to invest in AI in the next three years, highlighting two priorities: the application of AI as a clinical decision support tool and the use of technology brings greater operational and clinical efficiency.
However, at the same time that these tools are seen as part of a major trend – which has been increasingly reflected, especially with the popularization of ChatGPT – the understanding of what artificial intelligence really is, how it works and what has been implemented today in healthcare is still very diffuse.
To help understand all these issues and this imprecise scenario of the potential and use of artificial intelligence in healthcare, we had the help of Alexandre Chiavegatto Filho in an exclusive interview. He is a professor specializing in machine learning in healthcare at the University of São Paulo (USP), has a post-doctorate at Harvard University and is a columnist for Estadão on this topic.
After all, what is the definition of artificial intelligence?
Very simply, Alexandre Chiavegatto defines artificial intelligence as “the ability of machines to make intelligent decisions”. In this sense, the great challenge would be the definition of what intelligence is, a philosophical discussion that he answers with the following meaning: “it would be the ability to make the best possible decision based on the available information”. In other words, at the end of the day, artificial intelligence is a matter of data processing analysis.
Still in relation to the definition and functioning of artificial intelligence, it has become common to hear the terms “machine learning” and “deep learning”, but without a precise explanation of what they mean. Chiavegatto explains that currently the area of artificial intelligence is dominated by machine learning, but that was not always like that.
“Before, we had machines making intelligent decisions based on rules pre-established by humans. This is what we call ‘classical artificial intelligence’ today. But today AI is almost a synonym for machine learning, which works in the following way: instead of inserting the rules for the computer to make an intelligent decision, we guide the computer’s learning of them based on available data and examples.”
As for what is called deep learning, he explains that it is just one of the algorithms that is used today for learning rules, and is therefore a subfield within the area of machine learning.
For every dose of “hype”, a dose of skepticism is recommended
It has become increasingly common to access the news and see headlines, both internationally and in Brazil, that point to artificial intelligence in healthcare as a “gigantic market” or a “great revolution”. These calls bring an air of justifiable optimism, since these technologies have great potential in the sector, but the truth is that we are just at the beginning, as Chiavegatto points out.
“Today we are in the prehistory of artificial intelligence. Today it practically does not exist in the most important area of all, which is health. So we hear people say ‘wow, we are experiencing a hype where they are putting AI in everything’, but the truth is that artificial intelligence has not even started to enter 99% of areas”, he adds.
Furthermore, the professor emphasizes that today we can call practically any data analysis artificial intelligence, due to the fact that it learned from data. This undoubtedly contributes to this perception that “artificial intelligence is everywhere”. But, as he highlights, there are many low-quality analyses, given that today there are still not many people who understand the area in depth and are able to evaluate what is being done. In this sense, he recommends: “a first tip is to be very skeptical about what people present as results”.
Healthcare is still not experiencing its “ChatGPT moment”
Chiavegatto says that the application of artificial intelligence in healthcare is still very early, mainly because it is a very “consequential” area. In other words, if an algorithm presents an incorrect probability of prognosis, this can have very profound consequences on the lives of patients. In this sense, much greater care must be taken when inserting this type of tool into clinical practice.
“We still don’t have a major AI milestone in healthcare. We have several discoveries that indicate the possibilities of use in the sector, but there has not yet been any major ‘ChatGPT moment’, in the sense of changing the direction of the area. We are waiting for the area to mature and trying to resolve all the technical problems to put this into practice.”
However, he reports that laboratories have discovered that the algorithms that work in the health sector are the same as those that work with several everyday applications, such as Instagram, Waze, Netflix and ChatGPT. Apparently, it is these same algorithms that will transform healthcare. “We just need more care and patience”, adds Chiavegatto.
The complexity and challenges in applying artificial intelligence in healthcare
The professor also talks about some problems raised in the Big Data and Predictive Analysis in Health Laboratory at the Faculty of Public Health at USP. Since Brazil is a country of continental dimensions and health is an extremely complex area, does an algorithm that learns from data from patients in São Paulo work in the same way in the interior of another state in another completely different Brazilian region? Chiavegatto replies no.
“If we compare São Paulo with, for example, a city in the interior of Pará, it is clear that there are other types of patients, there is a different training of health professionals, a different availability of tests. In this sense, our studies have shown that quality drops significantly due to the huge differences within Brazil. So a challenge that we are working on is precisely how can we transfer this knowledge to different regions of the country? We call this transfer learning.”
Furthermore, another challenge is the issue of continuous learning. Alexandre Chiavegatto explains that, as the algorithm predicts things, it relearns from the results, which is very important in healthcare, where there is an expectation of changes regarding protocols and processes. There is a need to readapt the algorithm to these new realities.
There is still another sensitive point, which concerns the identification and correction of possible biases in artificial intelligence due to the data available for its learning. “There is, for example, a real risk that the algorithm will recommend better decisions for rich people than for the poorest population, since today there is a reality that we collect more data from richer patients”, he explains.
The dynamism of artificial intelligence in the health regulatory environment and the idea of the “scapegoat”
A frequent question amid this debate concerns the healthcare regulatory environment and how it affects the development of artificial intelligence in the sector. It is clear that healthcare is an extremely regulated area, as it should be. In this sense, Chiavegatto highlights that there is a very big challenge for both the FDA in the United States and Anvisa in Brazil.
“It is difficult to regulate because they are, in a way, healthcare devices that will change over time. How do we regulate something that is making a decision today in one way but that maybe 3 months from now will make a different decision or help in another way? This is because the algorithms are relearning as they receive more data. But Anvisa has been debating this for a long time and the FDA has already regulated several AI devices,” he says.
In addition to the regulatory issue, there are also questions about the possibility of holding artificial intelligence accountable through a decision made, a topic that still generates confusion. After all, could artificial intelligence be blamed for a wrong clinical choice and be made as a scapegoat? Chiavegatto explains that no, since algorithms will not make health decisions.
“In health, nothing is 100%. I can’t say that there is a 100% chance of a given patient having cancer within 5 years, for example. It is always a probability that will be passed on to the healthcare professional to use along with other tools in their daily lives. The difference is that machine learning will unify all exams and patient health data into the same result, providing probability. It is guidance for the doctor to make the best decision possible.”
Possible applications of AI in healthcare: expanding access and more time to practice medicine
When thinking about the potential of artificial intelligence in healthcare, there are many expectations. In this sense, the USP professor raises two central applications that the tool can have in healthcare, namely the assistance of AI in clinical decisions, which should occur more in the long term, and the reduction of bureaucracy, which should be incorporated more quickly by the sector as a whole.
For him, the greatest potential of artificial intelligence lies in its ability to help medical professionals make the best clinical decisions regarding the diagnosis and prognosis of patients. Chiavegatto highlights that this application of AI expands access to quality healthcare in all Brazilian regions, even in those that do not have medical specialists.
“There are many Brazilian cities that only have a single doctor and he needs to play the role of cardiologist, pulmonologist, etc., because there is no specialist to refer the patient. In the coming years, artificial intelligence will help a lot with this. Doctors will have access to the same quality of diagnosis and clinical decision-making. This will radically change health care in Brazil. But this is also the hardest part and will take the most time.”
On the other hand, the application of AI that must be carried out more quickly involves reducing the doctor’s time spent on bureaucracy. Chiavegatto points out that one of the main complaints – from both doctors and patients – in outpatient care is that professionals spend a lot of time typing information into the electronic medical record. In this way, the professor shares that there are already algorithms that can listen to the conversation between the doctor and the patient and are capable of filling out the medical record automatically.
“Another point is that the doctor will not spend as much time reviewing the medical records. There will be an algorithm drawing your attention to the information in the medical record that is relevant to the symptoms reported by the patient, providing a summary of what matters for that clinical picture. Other points include filling out reports, reimbursements, consultation and surgery reports. There will be more time for the doctor to actually practice medicine”, he adds.
The great, but little explored, Brazilian potential in the field of artificial intelligence in healthcare
Regarding Brazilian potential in the area, Chiavegatto assesses that “Brazil, in the health sector, has the potential to be the most advanced country in the world in artificial intelligence”, which is mainly due to the fact that the majority of care in the country occur within the same system, which is the SUS, which collects unified data.
“There are other countries, even those that are more developed, that have much worse health information systems than Brazil. They have difficulty collecting unified data on deaths, births, hospitalizations, etc. Brazil collects a lot of data and 75% of the population uses exclusively the same system, which is the SUS”.
Although the country has the potential to lead this transformation, the USP professor comments that this is not what happens. “Some of our representatives have a greater focus on regulating the area of artificial intelligence, unlike the vast majority of other countries whose leaders are focused on encouraging and promoting the area of artificial intelligence”, Chiavegatto adds.
On the other hand, on the medical education side, he highlights that he has seen a growing interest among medical students in artificial intelligence. Chiavegatto says that, although many outsiders believe that doctors would be averse to these tools, he is no longer asked by these professionals whether “AI will replace the doctor”. In fact, he reports that he has seen many students looking for courses, starting to program and developing algorithms.
“The USP residency, for example, already has a mandatory subject on digital health and undergraduate students are being introduced to various subjects around this topic, something that will be inevitable for the future of doctors and will enhance their impact. This has attracted many students,” he concludes.