Doctors continue to progress medical technology using artificial intelligence (AI) as a new tool, dubbed the Pre-Act Project, which has reportedly been designed to predict cancer patients' tendencies to the side effects brought by their breast cancer treatments. 

According to reports, a team of multinational experts developed the tool, which was presented at the 14th European Breast Cancer Conference. The technology can reportedly identify patients with breast cancer who may be more vulnerable to adverse effects after radiation and surgery treatments.

(Photo: Angiola Harry from Unsplash It's been a rollercoaster ride for the American woman who battled triple-negative breast cancer before she received the much-needed vaccine for the deadly disease.

While some of the risk factors for side effects are already known, the PRE-ACT project (Prediction of Radiotherapy side Effects using explainable AI for patient Communication and Treatment modification) aims to provide physicians and patients with easily understandable explanations and more accurate predictions for each patient. 

While it is a good thing that long-term survival rates for breast cancer are rising, some patients will have to deal with treatment side effects like skin changes, scarring, painful arm swellings called lymphoedema, and even heart damage from radiation therapy, according to Dr. Tim Rattay, an associate professor and consultant breast surgeon at the University of Leicester. 

Researchers from six European nations trained several machine learning algorithms to predict arm swelling up to three years following surgery and radiation treatment using data from three European and French datasets containing 6,361 patients with breast cancer. 

Read Also: This New Robot Could Help Diagnose Breast Cancer Early

AI Tool's Effectiveness

The final, best-performing model, according to Dr. Guido Bologna, an associate professor at the University of Applied Sciences and Arts of Western Switzerland in Geneva and a co-investigator on the project, makes predictions based on 32 distinct patient and treatment features, such as the type of radiation therapy administered, whether or not patients underwent chemotherapy, and whether or not sentinel lymph node biopsy under the armpit was performed.  

In the three datasets, 6% of patients had significant lymphoedema. In 81.6% of cases, the AI tool accurately predicted lymphoedema, while in 72.9% of cases, it properly identified people who would not acquire it. The model's overall prediction accuracy was 73.4%.

AI Cancer Detection's Future

The researchers will integrate the present AI model into software that may give physicians and patients assessments and forecasts. Later this year, when the PRE-ACT-01 clinical trial begins, this will be put to the test.

Additionally, the program is being developed further to forecast other negative effects, like harm to the skin and heart. Although they will not be utilized to generate predictions in the PRE-ACT study, the researchers will gather information on genetic markers and imaging data as part of the experiment to increase the precision of the AI tools. 

AI proves useful in both facets of breast cancer treatment, as previous reports indicate that AI can speed up breast cancer scans. Lunit, back in November 2023, also unveiled a groundbreaking AI tool that can outperform radiologists in detecting breast cancers. 

Related Article: AI Could Speed up Breast Cancer Scans, New Study Shows

(Photo: Tech Times)