The landscape of cancer research and patient care has experienced various shifts over the years, with many breakthroughs toward better management of the disease. Despite those shifts, it remains a highly complex and demanding one, with many challenges. Within the context of cancer, issues such as delayed diagnosis, futile treatment, and adverse effects continue to significantly influence the clinical outcomes of cancer. Cancer puts an immense pressure on health care systems around the world, accounting for significant morbidity and mortality. In 2020, 19.3 million new cancer cases were recorded1; the same studies project that by 2040, 30.2 million new cancer cases will be diagnosed.1

In an effort to achieve improved management and control of cancer, digital technologies have acquired a prominent position. The capabilities they introduce in health care are unique and can help clinicians, researchers, managers, and patients in a variety of ways to achieve better outcomes across the disease continuum. The readiness to incorporate such technologies across the cancer continuum is in different developmental stages. To date, numerous algorithms used in machine learning (eg, Naive Bayes algorithm) and clinical decision support systems (CDSS) have been successful in demonstrating properties that can be considered equivalent or superior to human experts. As a result, an increasing number of health care aspects have been touched by technologies such as artificial intelligence (AI), big data, and machine learning (ML). Breakthroughs in technology development have allowed to make sense of valuable data and gain further insights in terms of procedural, technical, medical, and other types of improvements in health care through the analysis of big datasets in a cost- and time-effective manner. What has been previously considered an impossible task has now become routine in many aspects, allowing clinical oncology and researchers in the field to make the most of what these technologies have to offer.

AI: The definition of artificial intelligence lays in the works of Alan Turing, who is considered one of the founders of modern computers and AI. In simple terms, AI aims to mimic human cognitive functions. AI is a wide-ranging branch of computer science concerned with building smart machines capable of performing tasks that typically require human intelligence.2

ML: Machine learning is considered one of the most prominent types of AI and entails various statistical techniques that allow computers that have not being explicitly programmed to learn from experience. According to the experience acquired, the learning is reflected to how an algorithm works and, in this case, becomes different from its original programming.3 A neural network consists of a higher level of ML that is capable of viewing problems in terms of inputs and outputs and can demonstrate the weights of variables that associate inputs with outputs.4

Big data: Although the term big data has gained a universal profile over the years, a universal consensus has not yet been reached on the use of this term. One of the most prominent definitions of big data defines them in terms of the volume—high-velocity and high-variety information assets that demand cost-effective, innovative forms of information processing for enhanced insight and decision making.5

In recent years, conditions have matured toward allowing the increased use of technologies such as AI, big data, and ML within health care. The conditions do not solely refer to the scale of cancer cases worldwide but also reflect the increasing complexity in the management and control of cancer across the disease continuum. Furthermore, the end to what has been called the AI winter6 has also been facilitated by breakthroughs in both the availability and accessibility of health care data and advancements in computational and processing power.7, 8, 9

The application of these technologies within health care has increased expediently, while new opportunities continue to arise as technology advances. Medicine scoring systems derived from evidence-based data have been informing medical fields, including oncology, toward the estimation of the cancer risk and diagnosis of the disease, prognostic staging, and treatment.9 However, the increased level of complexity of such systems, due to the constant introduction of new predictors and the need to understand the interactions among emerging and established disease factors, has made traditional models redundant. At the same time, this challenge has paved the way toward the uptake of AI and big data as means to overcome these limitations. Therefore, their contribution and impact became pivotal in areas such as personalizing the provided care according to personal features, improving early detection and screening methods, and making connections and drawing conclusions based on vast and complex datasets.10 The complexity of care and the diversity and volume of data have provided a unique opportunity to expand the applicability of such technologies including analysis of multi-omics data. This entails a new approach where the datasets of different omic groups (eg, enome, proteome, transcriptome) are combined during analysis. Multi-omics analyses can provide researchers with a greater understanding of the flow of information, from the original cause of disease (genetic, environmental, or developmental) to the functional consequences or relevant interactions.11 As a result, within oncology their contribution increasingly expands to include diagnostic, prognostic, and therapeutic applications (eg, markers), images analysis, and interpretation (eg, radiology), clinical trials and preclinical research.12