Using artificial intelligence, lung cancer prediction has become possible

Weather of Arabia - Artificial intelligence models have been effectively improved to determine a simpler method for lung cancer screening, through the efforts of researchers from University College London and the University of Cambridge, and these developments are one step closer to making personal screening for this type of cancer more effective.

It turns out that the new model outperforms or performs well in predicting a person's risk of developing lung cancer over the next five years, compared to the best currently available models, using only a quarter of the necessary information. The report resulting from this research indicates that lung cancer is the most common cause of death. Cancer globally, highlighting the importance of early detection.

The results of this research were published in the journal PLOS Medicine , where it is expected that effective screening will contribute to reducing the proportion of deaths associated with lung cancer by up to 20-24% . Although the current method for determining the risk of lung cancer requires intensive resources, this analytical model is considered a A promising step towards making in-person screening more effective and easier to implement.

It is worth noting that the United Kingdom is currently planning to implement a national lung cancer screening programme, using a 17-question-based risk model.

Artificial intelligence technology to improve lung cancer screening

The team examined more than 60 different AI pathways using data sets, with the aim of identifying the most effective ones in predicting an individual's risk of lung cancer. This was done using just three variables: age, number of years of smoking, and average number of cigarettes per day.

Among these models, the researchers selected four models, and grouped them into an “ensemble,” which were able to predict an individual’s risk of developing lung cancer with the same or improved accuracy as current models. Most importantly, they were able to achieve this accuracy using only three variables, which greatly simplifies Large data collection process required.

Dr. Tom Callender , first author of the study, said:

“Cancer screening saves lives, and we are increasingly able to personalize this process as our study shows that AI can be used to accurately predict lung cancer risk using just three pieces of information, which is easy to collect during routine GP appointments, whether online or over the phone. "Applications: This approach has the potential to greatly simplify population-level lung cancer screening and help make it a reality."

The models used in the study have been externally validated through a prostate, lung, colorectal and ovarian cancer screening trial, demonstrating their strength in comparison with currently prevailing models. The researchers believe this approach could also be effective in simplifying the screening process for other diseases, such as diabetes. Type II and cardiovascular diseases.

Professor Mihaela van der Schaar , lead author of the study from the University of Cambridge, said:

“This study represents a prime example of how advanced AI tools such as automatic diagnosis, along with innovative research efforts by clinicians, can make a real impact on health care at the population level. Although automatic diagnosis has already been applied to predict risk and diagnose many diseases, “This is the first time it has been used to determine the minimum information needed to screen patients. I believe this is the future of preventive medicine, and I feel optimistic about the possibility of applying the same approach to detecting other diseases.”

The team aspires to benefit from the results to facilitate and accelerate the implementation of a national lung cancer screening program, in addition to maintaining the main goal of reducing lung cancer deaths.

For his part, Professor Sam Janes from the University College London of Medicine , senior author of the study, said:

“The launch of a national lung cancer screening program in the UK is an important step towards tackling this disease, which remains the leading cause of cancer-related deaths in the country and across the world. However, the good news from the study shows us that, regardless of large initiatives, Overcoming the challenges to ensure the successful implementation of national screening programs and stimulating the effective participation of people, and that these results are a positive sign in this context.”

This work was supported by prestigious organizations such as Wellcome, the National Science Foundation, the Medical Research Council and Cancer Research UK.

Also know:

Printed bones and tendons...a robotic hand that resembles a human hand

A screen in your hand...an artificial intelligence device that may replace smartphones

Sources:

ucl.ac.uk

elfann