Page 167 - Read Online

Page 60 Endo et al. Art Int Surg 2024;4:59-67 https://dx.doi.org/10.20517/ais.2024.09

INTRODUCTION
With the rapid evolution of modern technology, artificial intelligence (AI) has increasingly become
[1,2]
integrated into various aspects of human life, particularly the healthcare domain . AI, which is a broad
field of computer science, can be used to develop systems or machines equipped with the ability to tackle
[1]
tasks that traditionally necessitate human intelligence . Specifically, AI can be used to perform multifaceted
tasks that involve the synthesis of large amounts of data with the generation of solutions, algorithms, and
decision support tools . Synthesizing and analyzing large volumes of data, AI can incorporate
[2]
“unstructured” information including images or text and, in turn, identify a complex interplay among
various data points . In turn, the integration of AI into healthcare has the potential to yield numerous
[3,4]
benefits, including tools to refine patient outcomes, streamline healthcare delivery processes, and inform
medical research .
[5]

AI systems can analyze medical data, such as images, diagnostic tests, and patient records, yielding more
accurate tools for diagnosis, as well as prognostically stratifying patients . In particular, AI algorithms,
[6,7]
which are adept at analyzing large datasets, can identify intricate patterns and trends that are challenging for
humans to discern, enabling more accurate identification of disease patterns, as well as prediction of
potential health risks. Furthermore, AI holds the promise to prevent or manage diseases more
proactively . AI can also analyze genetic, clinical, and lifestyle data to facilitate the customization of
[8,9]
treatment plans tailored for individual patients . This personalized medicine approach, which more
[10]
adeptly considers the unique characteristics of each patient, may optimize treatment and increase
therapeutic efficacy while minimizing adverse effects. For instance, AI algorithms such as Virtual Twin
analysis or Optimal Policy Tree (OPT) [11,12] can differentiate patients into subsets, identifying who may
benefit from specific treatment plans, such as upfront surgery versus neoadjuvant or adjuvant
chemotherapy [13,14] . Moreover, AI can facilitate drug discovery and selection of chemotherapeutic agents by
analyzing massive datasets to predict the most promising drug candidates, as well as potentially optimizing
clinical trial designs, thereby reducing the time and cost of developing new drugs to market . Natural
[15]
Language Processing (NLP) algorithms can also sift through unstructured healthcare data, distilling valuable
insights in the electronic health records and medical literature, thus enhancing the accessibility of critical
[16]
information for healthcare providers and researchers . AI may also help to address healthcare disparities
by improving access to medical expertise in underserved or remote areas through AI-powered telemedicine,
[17]
thereby enabling remote consultations and earlier disease diagnoses .

Overall, AI plays a crucial role in healthcare transformation, enhancing diagnostic accuracy, personalizing
treatment, expediting research, and enhancing patient care. The ongoing integration of AI technologies
holds the promise of revolutionizing healthcare practices and outcomes. AI may be of particular interest in
the care of patients with complex cancers such as hepatobiliary (HB) tumors as these patients often require
a multimodal treatment approach with surgical resection, as well as therapy with a wide array of different
chemotherapy agents .
[18]

APPLICATION OF AI IN THE MEDICAL FIELD
Different AI approaches to healthcare data
AI can involve various statistical approaches based on different techniques and methodologies. Machine
learning (ML) and natural language processing (NLP) are generally among the most used
methodologies [19,20] . ML utilizes algorithms and statistical models to refine the performance of designated
tasks through experiential learning, while not utilizing explicit factor-based programming. In this way, ML
can facilitate the identification of new patterns of knowledge and enhance inferences that enable the
forecasting of outcomes or decision tools that are grounded in data. Through the analysis of large amounts