Machine learning predicts the future with more reliable diagnostics
Headquarters of the Higher Council for Scientific Research (CSIC).
a bone scan Every two years for all women aged 50-69. Since 1990, i.e. The biggest test challenge for the national health systemAnd it aims to prevent one of the most common cancers in Spain, that is Mother, The method is X-rays that detect potentially cancerous areas; If anything suspicious is found, this test is followed by other tests, often High probability of false positives, harmful and costly,
they are curvature This is the main reason why screening is limited to the groups most at risk. By adding predictive algorithms to mammograms, the risk areas of a patient’s breasts would be limited and diagnostic confidence increased to 90%. They can therefore be made with Often and the age range of women they target Expansion,
It is a process that already exists, which uses artificial intelligenceand that . develop a team of Superior Council for Scientific Research (CSIC), more precisely the Institute of Corpuscular Physics (IFIC). it is part of the scope of machine learning (machine learning) in precision medicine, and a research network that aims to increase the efficiency with which each patient is treated and optimize healthcare resources.
To understand how, you must first understand the concepts that come into play. The first is artificial intelligence. “the ability of a computer or robot to perform tasks normally associated with intelligent beings”, defined as sara degli apostic You sierra carlos, author of the CPISC white paper on the subject. In other words, it is the processes that are used replace human labor with robotsWith the aim of achieving this with greater precision and efficiency.
And where can artificial intelligence work in medicine today? “On many fronts,” he replies. dolores del castilloResearchers from the Center for Automation and Robotics of the CSIC, “From administration to the management of clinical documentation. And, more specifically, in the analysis of images, or in the monitoring and follow-up of patients”. And where are the even greater limits? Above all, “in the field of health care, in the legal and ethical aspects when it comes to important questions”. And in addition, the road is still long, explains Del Castillo, who works among other things on the projects. neurological movement disorderTraining of a large part of the nursing staff.
We find the second concept as a sub-field of artificial intelligence, with its advantages and disadvantages: machine learning, This can be translated as machine learning. That is to say, artificial intelligence that works thanks to computers thatand find patterns in population groupsWith these models, predictions are made about what is most likely to happen. machine learning translate data Algorithm,
Precision medicine to predict disease
and after artificial intelligence and machine learningThere is a third concept: the precision medicine, The one that suits the person, their genes, their background, their way of life, their socialization. a model that must first be able to foreseeable illnessSecondly, IFIC’s Francisco Albiol, “continues to assess each patient, apply the best treatment based on clinical evidence, identify the most complex cases and evaluate their inclusion in management programs. charge”.
It makes sense high impact disease, and does not make sense for serious illnesses; For example, distinguishing flu from a cold in primary care, as the benefits will not outweigh the effort required.
The key to the use of artificial intelligence in medicine is also cost optimization, which is very important for public health. The Spanish population has increased from 42 to 47 million inhabitants between 2003 and 2022, i.e. more than 10%. and from 2005 to 2022, The average age of the population has risen from 40 to 44We are getting older and older.
Therefore, according to Dolores del Castillo, “the projects best evaluated and, therefore, likely to be funded, are those that integrate artificial intelligence techniques to address the prevention, diagnosis and treatment of cardiovascular diseases, neurodegenerative diseases, cancer and obesity”. “There is also a particular focus on personal and home medicine, care for the elderly and new drug offerings.” The need for health care has been increased by our demographics, and The goal should be to reduce and simplify technology challengeswe tried machine learning“, sums up Albiol.
Albiol is one of the scientists who led a program to improve breast cancer detection through algorithms. He defends, like other researchers, that if we mix machine learning and precision medicine, we should speak of 4p medicine. Which includes four features: “Predictive, personal, preventive and participatory”,
Because most purists confine precision medicine to the realm of patient genetics, and wouldn’t include it in the bag that takes into account more characteristics. Those who do say that we are talking about something much broader: “Applied to precision medicine, machine learning allows Analyze large amounts of very different types of data (genomic, biochemical, social, medical imaging, etc.) and model them be able to offer together individual diagnosisa more precise and therefore more effective treatment”, summarizes the researcher Lara Loret Iglesias of the Institute of Physics of Cantabria.
Lloret is part of a network of scientists who, like Albiol or Del Castillo, are dedicated to projects on machine learning and precision medicine. One of them developed by his team, which he leads with fellow physicist Miriam Kobo Cano, is called Branyas. It is in honor of the oldest woman in Spain, Maria Branyas, who managed to beat Covid-19: she did it at the age of 113. In this, they bring together the many casuistry of more than 3,000 elderly people, let alone genetics: machine learning implement Risk profile of getting sick or dying from coronavirusWe have drawn data from the analysis of three risk profiles: a sociodemographic, a biological and an extended biological, which will provide information on questions such as aspects related to the intestinal microbiota, vaccination and immunity.
Precision Medicine, Cancer and Alzheimer’s
also explain this Joseph Lewis Arcosfrom the Artificial Intelligence Research Institute. Common illnesses There are cancers and Alzheimer’s linked to precision medicine, but they stood out with the Ictus project. Launched in the midst of a pandemic (which made things difficult, he admits), he treated patients at Belwitz Hospital in Barcelona who suffered strokes and, after a severe and acute phase, became long term,
In particular, those who have difficulty moving one or both hands. made more than 700 sessions In which patients were asked to play the keyboard of the electronic piano. Next, they transferred the finger movement analysis to the results to see what the patterns of difficulty and improvement were. And they’ve had particularly positive feedback from users “because it’s not just about doing an exercise, but it touches a very emotional part.” The aim now is to extend it to hospitals in the UK.,
and future? Dolores del Castillo replies: “I believe that the challenge of artificial intelligence in medicine is to integrate the results of research into daily practice in a generalized way”, but always without forgetting that “it is the experts who have the last word “. To do this, “physicians must be able to rely on these systems and Interact with them in the most natural and easy wayEven helping to design it”.
Lara Loret believes that we “must be able to build generalizable prediction systems, i.e. the efficiency of the model does not depend on unnecessary things such as the machine in which the data is taken or the way in which calibration is done”. Francisco Albiol focuses on a problem that could be long term “must have a solution”Currently, “large hospitals are preferred in these technologies to small towns or villages. convenience and lower the costs It is also about reaching everyone. »
Although it may include statements, data, or notes from healthcare institutions or professionals, the information in medical writing is edited and prepared by journalists. We advise the reader to consult a healthcare practitioner with any health-related questions.