Machine learning (ML), deep learning, and AI have transformed several industries and areas of science. With continued application, these tools are now used to address the challenges of cancer biomarker discovery. This involves analysis of vast amounts of imaging and molecular data beyond the capability of traditional statistical tools and analyses.
A special edition of Cancer Biomarkers discusses how researchers propose various method and examine some of the unique challenges of using ML, DL, and AI to improve the accuracy and predictive power of biomarkers for cancer and other diseases.
The biomarker field is replete with imaging and molecular-based data, and at the same time the data is overwhelming for not a single individual to comprehend it.
AI provides a solution to this problem, and it has the potential to unveil novel interactions that reflect the biology of cancer and other diseases more accurately.
The special edition for promising applications of AI, ML, and DL covered in this issue include identify early-stage cancers, infer the site of specific cancer, aid in assignment of suitable therapeutic options for each patient, characterize the tumor microenvironment, and predict the response for immunotherapy.
A comprehensive literature illustrates underlying principles and perceives the gaps and challenges that are faced regarding the use of approaches of AI to identify biomarkers for ovarian and pancreatic cancer
While pancreatic and ovarian cancer are rare, but are lethal because there is lack of early symptoms and detection. A team of researchers at Biomedical Data science Lab describe studies using ML and AI to analyse images for the early detection of disease, and models that can be built to anticipate likely outcomes for patients. Some of the challenges such as difficulty pertaining to collecting large datasets are discussed.
