Artificial Intelligence (AI) is a field within computer science that has wide applications and has transformed medical technologies. It is often considered the branch of computer science that can handle complex problems with minimal theory and multiple applications. AI is used to assist researchers in analyzing large data sets, enabling precision medicine and assisting clinicians in improving patient outcomes. New techniques in AI can bring together different types of data to understand new information obtained from multiomics datasets. Analysis of high-quality data combined with machine learning, a subset of AI, can help modify unhealthy behaviors of patients, predict the risk or recurrence of chronic diseases after surgical and curative treatments, predict the progression and survival rates of patients with chronic diseases, identify therapeutic need, create better clinical trial interpretations, and identify new targets. However, to effectively implement precision medicine in healthcare, a more user-friendly interface will be required. If AI technologies are applied correctly, fairly and robustly in close collaboration with human intelligence, it is expected to open up new possibilities for effective and personalized healthcare services worldwide. In this review, an overview of the general outline of AI technology, its application areas in healthcare and its future is given.
Introduction
Healthcare costs are rising everywhere. The increasing prevalence of chronic diseases, longer life expectancy and the ongoing development of expensive new treatments all contribute to this trend. It is therefore not surprising that academics predict a gloomy future for the viability of healthcare systems globally. Artificial intelligence (AI) has the potential to mitigate the effects of these advancements by increasing and optimizing healthcare expenditure. When smartphones, wearable devices, sensors and communication systems first appeared, medical technologies were primarily known as traditional medical devices (such as implants, stents and prostheses). However, with the advent of these devices and their ability to place AI-powered tools (such as applications) into incredibly small forms, a revolution in medical technology took place. AI is a field within computer science that has wide applications and has transformed medical technologies. It is often considered the branch of computer science that can handle complex problems with minimal theory and many applications. AI is used to assist researchers in analyzing large data sets, enable precision medicine, and assist clinicians in improving patient outcomes.
AI algorithms can help doctors make better decisions (“clinical decision support”, CDS), localize tumors in magnetic resonance (MR) images, read and analyze reports written by radiologists and pathologists, and much more. In the near future, reports legible by humans can also be generated with the help of generative AI and natural language processing (NLP) systems like Chat Generative Pre-trained Transformer (ChatGPT). AI includes various techniques like machine learning (ML), deep learning (DL) and NLP. AI was still in its infancy and was mostly the focus of scholarly research at that time. John McCarthy first used the phrase “artificial intelligence” at the Dartmouth Conference in 1956. The modern AI era began with this event. Expert and rule-based systems were the main topics of AI research in the 1960s and 1970s. But the lack of additional data and processing power made this strategy impractical. Artificial intelligence (AI) research in the 1980s and 1990s turned to ML and neural networks, which helped machines learn from data and gradually improve their performance. New techniques in AI can bring together different types of data to understand new information obtained from multiomics datasets. Analysis of high-quality data combined with machine learning, a subset of AI, can help modify unhealthy behaviors of patients, predict the risk or recurrence of chronic diseases after surgical and curative treatments, predict progression and survival rates of patients with chronic diseases, identify therapeutic unmet need, create better clinical trial interpretations, and identify new targets. The application of AI models for diagnosis and prognostic assessments in the context of certain cancers is widely accepted.
The ability of AI models to discover nonlinear patterns embedded within complex multivariate datasets can potentially lead to a better understanding of the complex mechanisms underlying carcinogenesis and cancer progression. Over the past decade, the number of large and complex omics datasets has grown enormously, especially thanks to large-scale consortium projects such as The Cancer Genome Atlas (TCGA), which has sampled multiomics measurements from more than 30,000 patients and dozens of cancer types. These rich omics data provide unprecedented opportunities to systematically characterize the biological mechanisms underlying cancer development and to understand how the tumor microenvironment (TME) contributes to this development.
However, the idea that AI is essentially an opaque “black box” that cannot be interpreted mechanically and therefore cannot meet the high levels of accountability, transparency, and reliability required in medical decision-making has led to major criticism of the incorporation of AI, particularly deep learning in the medical field. “Black box” AI models produce results with remarkable accuracy, but no one can understand and analyze how the algorithms arrive at their predictions. When AI suggests a decision, decision makers need to understand the underlying reasons. In recent years, AI researchers have been conducting extensive research to open up this “black box” concept and turn it into a transparent system. At the forefront of this research is Explainable Artificial Intelligence (XAI), also known as “white box”. Explainability is the ability to explain AI decision-making in terms understandable to humans how a decision is made. The goal of this system is to obtain more transparent, more reliable and explainable results by explaining to users what it has done, what it is doing and what it will do next thanks to its developed algorithm. In the XAI method, the entire process can be analyzed retrospectively. Although studies on the use of AI in medicine have increased in recent years, the study of XAI systems using explainable algorithms has just begun. Breast cancer is the leading cause of cancer-related deaths worldwide and the most common type of cancer in women.
Amoroso et al. used XAI modeling for breast cancer treatment and showed that XAI can summarize the most important clinical feature for the patient and the oncological treatment designed for the patient.
Read Also:
- Findings And Discussions On Artificial Intelligence (AI) In Healthcare
- Artificial Intelligence (AI) (Online Resource): The Panacea For SMEs In Healthcare
- Artificial Intelligence (AI) (Online Resource): The Panacea For SMEs In Healthcare
- Artificial Intelligence (AI) In Healthcare In India
- Ethical, Legal And Other Challenges In The Use Of Artificial Intelligence (AI) In Health Care
Leave a Reply