The Grand Arrival of Artificial Intelligence: New Opportunities in Cancer Research – Onco’Zine

Artificial intelligence Or Artificial intelligence And Learning the machine It has received much attention over the past 5 years, and scientists are exploring its potential to transform cancer care and improve patient outcomes. While most of the discussion about the applications of artificial intelligence and machine learning still focuses on the correct and more important. safe use, In the field of medicine, he excelled in a wide range of practical applications, including breast cancer diagnosis from mammography, molecular identification of tumors and their microenvironment, drug discovery and reuse of existing drugs, prediction of treatment outcomes, reshaping of cancer research. showed potential and personal clinical. to care.

Additionally, available AI-guided surgical systems map out an approach to meet each patient’s specific surgical needs, guiding and simplifying entire surgical procedures.

And this year artificial intelligence finally succeededGreat entry into the public debate

more accurate?
Study in the magazine Nature It shows that artificial intelligence is more accurate than doctors in diagnosing breast cancer through mammography. Researchers from Google Health And Imperial College London Designing and training a computer model on X-ray images of nearly 29,000 women. The same study found that AI programs are particularly accurate Forecast Breast Cancer the danger Compared to traditional methods, diagnostic tools based on artificial intelligence are designed to improve the quality of diagnosis by helping to distinguish between cancer and benign cases, as well as determining tumor subtypes.

During the upcoming ESMO 2023 Congress in Madrid, Spain, October 20-24, 2023, dedicated sessions focused on artificial intelligence will highlight the strides being made with modern computational methods applied to oncology.[1][2]

Advertisement number 3

The impact of technology
Amaras Law* says that We tend to overestimate the impact of a technology in the short term and underestimate its effects in the long term. However, in any field that deals with human health, caution is necessary along with enthusiasm, and therefore, newer technologies such as artificial intelligence, machine learning, and big data analytics are slower and more cautious than others. Sections are introduced. Examples of their use in clinical practice have so far been limited to the triage of biopsy images, mammograms, and computed tomography (CT) scans of the lung used to screen patients for tumors, and to some areas of cancer research. However, implementation of these technologies into mainstream oncology research and practice has been far from uniform, signaling potential barriers that risk slowing adoption and the benefits it could bring along cancer research and care, including pathways to prevention, screening and take care.

Using the potential of artificial intelligence to improve cancer diagnosis
Based on a qualitative study presented at ESMO Congress 2023 [3] Dr Raquel Pérez-López, a radiologist at the university, investigated the potential of AI-based technologies to improve cancer imaging, diagnosis and delay in seven European countries. Institute of Oncology Vall dHebron in Barcelona, ​​Spain, which was not involved in the study, argues that existing well-defined guidelines on cancer screening and diagnosis are not uniformly applied even in Europe for reasons that may be economic and cultural. .

Perez-Lopez saw the potential of emerging digital solutions to intervene upstream and prioritize patients for screening based on their medical records.

Artificial intelligence-based platforms now exist that allow for the analysis of data routinely collected in electronic health records and medical imaging units, and can inform prevention and screening programs by identifying people at risk of developing the disease. to support But these resources are underutilized, Pérez-López noted, attributing this to the lack of an adequate legal framework for using patient data in this way.

Controlling artificial intelligence to unleash real-world research
Perhaps less tangible, but equally important applications of modern computational methods are revolutionizing certain areas of cancer research. For example, in the field of cancer genetics, many of the mutations found in modern genomic reports used to match patients to targeted therapies are identified by artificial intelligence tools that compare the genetic profiles of hundreds of thousands of patients and make predictions about their role in development. These technologies have also recently begun to be used more widely to analyze different types of data in real-world evidence-based studies. [4] which are considered as a tool to generate evidence in settings such as rare cancers, when traditional randomized clinical trials are not feasible, or to bridge the frequently observed gap between results obtained in clinical trials and real-world patient outcomes.

It is no coincidence that it was released recently ESMO Guidelines for Oncology Real World Evidence Reporting (GROW), [5] Developed to guide scientific reporting in this field, it also covers the topic of artificial intelligence-based technologies. In particular, the ESMO-GROW guideline aims to harmonize research practices in oncology by providing detailed recommendations for the testing and validation steps necessary to accurately and transparently report real-world data.

Included among these recommendations are considerations for using AI algorithms to analyze data in real-world evidence-based studies, which are essential to capture all considerations relevant to oncology and predict future developments.

Data processing conversion
In the near future, we could see AI tools transform data processing in hospital information systems and electronic health records by structuring doctors’ free-text notes and summarizing large amounts of information at the push of a button, which will greatly This makes it easier. “Extracting real-world data from medical records to generate new research insights,” said Dr. Rodrigo Dinstmann, Editor-in-Chief of the ESMO Journal Real World Data and Digital Oncology, and Director of Oncoclnicas Precision Medicine, São Paulo, Brazil. This manuscript addresses this possible future scenario where data used for research are no longer collected and structured by a human expert, but processed and summarized by a machine.

Adopting a standardized method for evaluating AI technologies with the same degree of reliability as we can evaluate drugs in clinical trials will be key to maximizing their benefits, while ensuring that their adoption minimizes the risk of bias that can be introduced. It does not increase inequality in patient care. . Dienstman emphasized.

Implementation of digital oncology in practice
Real-world research with advanced data analysis is becoming increasingly ubiquitous as a supplement to clinical trials, and is also beginning to spread to regulatory agencies that use it in the approval process for new drugs. Therefore, the ability to accurately interpret this type of evidence will be an essential skill for all oncologists in the future. this ESMO Real World Data and Digital Oncology JournalA new open-access, peer-reviewed platform dedicated to publishing high-quality data science and education about transforming cancer care with real-world evidence and digital technologies.

According to Deinstmann, oncologists as a group are not yet ready for this evolution, with training needs that will increase as artificial intelligence enters the clinical workflow.

He reported that there are many concerns about the impact of artificial intelligence on the profession when machines overtake doctors in a number of their traditional repetitive tasks.

We must educate clinicians to use these tools wisely and confidently, and based on a clear understanding of their value and limitations, machines and humans together achieve better patient outcomes than either alone. The ESMO journal Real World Data and Digital Oncology is a resource for clinicians who will encounter the implementation of digital oncology in their routine work.

Note: * Roy Charles Amara, an American researcher, scientist, futurist and president of the Future Institute, is best known for establishing Amara’s Law for predicting the effects of technology. The law of numbers says: “We tend to underestimate the impact of a technology in the short term and underestimate its impact in the long term.”

[1] A special session on Artificial Intelligence in Forecasting by Sanjay Aneja and Anne Vincent-Salomon will be held on Monday, October 23, 14:45-16:15 CEST in Room 3, Granada.
[2] Training session Are we entering a new era of oncology with big data and artificial intelligence? President Rudolph S. Fehrmann and James McKay will be in the Cdiz Auditorium of the NCC on Saturday, October 21, 10:15 – 11:45 CEST.
[3] Abstract 1218P Examining cancer care pathways in seven European countries: identifying barriers and opportunities for the role of artificial intelligence will be presented by Sherin Nabhani during an on-site poster presentation, Sunday, October 22, 2023 at ESMO Congress 2023.
[4] The future of real-world research is published today in the official ESMO Daily Reporter
[5] Costello Branco L et al ESMO Guidelines for Oncology Real World Evidence Reporting (GROW)” ESMO Real World Data & Digital Oncol2023; 1: 10.1016/j.esmorw.2023.10.001; and Ann Oncol2023; 34: 10.1016/j.annonc.2023.10.001
[6] Abstract 1218P Examining cancer care pathways in seven European countries: identifying barriers and opportunities for the role of artificial intelligence.

Featured image by Growtika on Unsplash

Advertisement number 5

#Grand #Arrival #Artificial #Intelligence #Opportunities #Cancer #Research #OncoZine
Image Source :

Leave a Comment