AI and Real-World Data Boost Oncology Clinical Research

Experts highlight that tools such as machine learning and deep learning can improve diagnosis, optimize recruitment in clinical trials, and advance towards more personalized therapies.

Artificial intelligence (AI ) and real-life data ( RWD ) are gaining ground as tools to improve clinical research in oncology. In this way, some AI technologies, such as machine learning and deep learning, can help in diagnosis or in recruiting patients for clinical trials.

These topics were addressed during the meeting “Understanding Clinical Research in Oncology and its Real Impact,” organized by Gilead Sciences this Wednesday in Madrid. Dr. Luis de la Cruz, Head of the Medical Oncology Department at the Virgen Macarena University Hospital, highlighted the “significant limitations” of clinical trials.

He pointed out that a large number of trials are not completed due to insufficient patient recruitment. Therefore, tools like machine learning, which is artificial intelligence learning based on patterns, can be of great help to clinical research.

Machine learning “allows for a specific analysis of each patient being evaluated,” explained Dr. Luis de la Cruz

This technology is able to detect patterns in databases and check them against the clinical information of the candidates with the requirements of each trial, which “allows for a specific analysis of each patient being evaluated ,” explained Dr. De la Cruz.

Deep learning, which involves creating complex neural networks, could aid in diagnosis by analyzing and identifying tumor characteristics that are not visible to the naked eye. This will make diagnoses “more accurate and reliable,” according to the head of the Medical Oncology Department at the Virgen Macarena University Hospital.

AI can also aid in the discovery of new therapies, based on multi-omics analysis. This approach, through the integration of data such as DNA, RNA, genetic mutations, epigenetics, proteomics, and microbiota, allows for the identification of new therapeutic targets and a better understanding of tumor biology.

AI can also help in the discovery of new therapies, based on multi-omics analysis

However, Dr. de la Cruz has pointed out that there are drawbacks to using these tools. The biases inherent in this technology are one of them.

Therefore, he emphasizes that human oversight is always necessary to supervise its operation. He adds that another challenge is “the human resources needed to use this technology; you need trained personnel to operate, for example, a tomosynthesis machine, or diagnostic imaging personnel to interpret the results.”

Use of Real Word Data

The use of real-world data, combined with AI, allows for the generation of predictive models capable of anticipating patients’ responses to specific therapies or forecasting potential adverse effects. This capability can help to better select patients who will truly benefit from a treatment, optimize the design of clinical trials, and even create virtual control arms based on existing data.

Elisenda Martínez , president of the Spanish Association of Metastatic Breast Cancer ( Aecmm ), highlighted how this data, in turn, helps to identify unmet needs, evaluate results in larger populations and contribute to more informed decision-making.

“We believe that patient-reported outcomes, such as quality of life, mental health, and social impact, should be systematically collected because they are also part of the clinical outcome ,” she explained. She also emphasized the role of patient associations in “generating and contributing relevant data” to improve our understanding of cancer.

__

(Featured image by Igor Omilaev via Unsplash)

DISCLAIMER: This article was written by a third party contributor and does not reflect the opinion of Born2Invest, its management, staff or its associates. Please review our disclaimer for more information.

This article may include forward-looking statements. These forward-looking statements generally are identified by the words “believe,” “project,” “estimate,” “become,” “plan,” “will,” and similar expressions. These forward-looking statements involve known and unknown risks as well as uncertainties, including those discussed in the following cautionary statements and elsewhere in this article and on this site. Although the Company may believe that its expectations are based on reasonable assumptions, the actual results that the Company may achieve may differ materially from any forward-looking statements, which reflect the opinions of the management of the Company only as of the date hereof. Additionally, please make sure to read these important disclosures.

First published in iSanidad. A third-party contributor translated and adapted the article from the original. In case of discrepancy, the original will prevail.

Although we made reasonable efforts to provide accurate translations, some parts may be incorrect. Born2Invest assumes no responsibility for errors, omissions or ambiguities in the translations provided on this website. Any person or entity relying on translated content does so at their own risk. Born2Invest is not responsible for losses caused by such reliance on the accuracy or reliability of translated information. If you wish to report an error or inaccuracy in the translation, we encourage you to contact us.