Special Edition: Junior Commentary https://doi.org/10.47488/dhrp.v3iS1.95 DHR Proceedings ǀ http://dhrproceedings.org 1 2023, Vol. 3 No. S1 1--10 COMMENTARY AI-Powered Precision Oncology: Computational Insights Redefining Therapeutic Landscapes Adhira Tippur1 1Mathematics and Science Academy at the University of Texas Rio Grande Valley, Edinburg, TX Received: August 15, 2023 Accepted for publication: October 25, 2023 Published: October 27, 2023 Introduction Cancer is one of the world’s leading causes of deaths creating a worldwide health challenge (1). The number of cancer deaths is rising, presenting a formidable and concerning challenge in healthcare. Cancer involves the uncontrolled proliferation of abnormal cells, disrupting the body's normal growth regulation. Moreover, the immune system, which typically acts as a defense against such abnormalities, may falter, leading to the evasion of cancerous cells from detection and elimination (1). Among the various types of cancer, the most frequently diagnosed ones include lung cancer (accounting for 12.7% of cases), breast cancer (10.9% of cases), colorectal cancer (9.7% of cases), and gastric cancer (7.81% of cases) (2). Over the years from 1991 to 2018, cancer-related mortality has shown a steady decline of 31%, primarily attributed to advancements in early detection, treatment, and reductions in smoking (3). Despite this positive trend, cancer continues to be a significant contributor to global mortality rates. Anticipated data for the year 2023 reveals a projected 1,958,310 new cancer cases, accompanied by 609,820 cancer-related deaths across the United States (4). During the period from 2014 to 2019, prostate cancer experienced a concerning annual increase of 3% in incidence, leading to the diagnosis of approximately 99,000 additional cases. Conversely, other cancer incidence trends demonstrated a more favorable outlook in men when compared to women, further emphasizing the importance of ongoing research and targeted interventions to address these disparities. Additionally, recent findings highlight a concerning increase in early onset cancer incidence among younger individuals, while overall rates remain stable or decline; unfortunately, younger cancer patients are often diagnosed at more advanced stages, significantly impacting their chances of successful treatment and cure (5). Despite significant advancements in cancer research and treatment, the disease remains challenging to cure completely. Consequently, the pressing need for alternative approaches becomes paramount, especially to offer effective solutions for high-risk patients. Therefore, cancer research will undoubtedly remain at the forefront in the years to come, driven by a resolute commitment to saving lives and pioneering groundbreaking advancements. Artificial intelligence (AI) is a dynamic and evolving field of research that involves the application of computer systems to replicate and simulate human intelligence (6). With the aid of advanced algorithms, AI strives to emulate cognitive functions, enabling computers to analyze data, recognize patterns, make decisions, and learn from experiences, much like the human mind. Machine learning and deep learning are the major constituents of artificial intelligence (Figure 1). Machine learning represents a fascinating scientific discipline centered around the art of computer systems learning from data (7). It emerges from the confluence of statistics, which delves into deciphering relationships from data, and computer science, with its core focus on devising efficient computing algorithms. The seamless integration of mathematics and computer science in machine learning emerges as a result of the complex computational intricacies required to construct statistical models from extensive Special Edition: Junior Commentary https://doi.org/10.47488/dhrp.v3iS1.95 DHR Proceedings ǀ http://dhrproceedings.org 2 2023, Vol. 3 No. S1 1--10 datasets, which can consist of billions or even trillions of data points (8). Deep learning utilizes multi-layered computational models to learn data representations with multiple levels of abstraction (9). By employing the backpropagation algorithm, machines adjust their internal parameters, computing representations in each layer based on the previous layer's representation (10). Figure 1: Relationship between artificial intelligence (AI), machine learning (ML), and deep learning (DL). Created with BioRender.com The surge in artificial intelligent systems has generated significant interest in their applications within the medical domain (11). Recent times have witnessed a swift integration of AI into medical practices, driven by the goal of augmenting patient care through swifter procedures and enhanced precision, thereby laying the foundation for elevated healthcare standards. This development marks a pivotal stride towards healthcare advancement. AI's seamless integration into the medical landscape encompasses a broad spectrum of informatics techniques, spanning from the intricacies of deep learning-driven information management to the comprehensive oversight of health management systems, notably electronic health records (12). This comprehensive expansion extends to the domain of clinical decision-making, offering valuable guidance to physicians, while also embracing the innovative deployment of robots to assist both elderly patients and attending surgeons. Within this transformative framework, machine learning assumes a prominent role, actively engaging in the assessment of radiological images, pathology slides, and electronic medical records (EMR) of patients. This concerted endeavor enhances diagnostic and treatment paradigms, amplifying physician capabilities, and significantly contributing to the overall advancement of healthcare quality (13). This paper meticulously examines the major applications of artificial intelligence in the field of cancer medicine. Ranging from its role in imaging enhancement to its prowess in predictive analytics, these applications showcase AI's multifaceted potential in transforming cancer care. Current Challenges in Cancer Care Despite remarkable progress in cancer care over the years, the field continues to grapple with certain challenges that demand attention and innovative solutions. These challenges underscore the importance of ongoing research and collaborative efforts to further enhance cancer treatment and patient outcomes. The interplay of rapid urbanization, lifestyle choices, and rising life expectancy stands as a significant driving force behind the changing landscape of cancer incidence rates. According to GLOBOCAN predictions, the number of cancer cases is expected to reach 28.4 million by 2040 (14). Globally, female breast cancer has now surpassed lung cancer as the most prevalent cancer (11.7%), closely followed by lung (11.4%), colorectal (10.0%), prostate (7.3%), and stomach (5.6%) cancers. Lung cancer stands as the leading cause for death, accounting for 1.8 million deaths (18%), followed by colorectal (9.4%), liver (8.3%), stomach (7.7%), and female breast (6.9%) cancers. Among men, lung, prostate, and colorectal cancers are the most prevalent, while breast, colorectal, and lung cancers are the leading types among women. In fact, cancer cases are expected to rise significantly in lower-resource settings and countries with a low Human Development Index (HDI), while the burden decreases with higher national HDI levels (15). In many high-income countries (HICs), cancer-screening programs like mammography for breast cancer, low-dose CT scan for lung cancer and colonoscopy for colorectal cancer are challenging to implement in low- and middle- income countries (LMICs) due to limited resources and insufficient trained personnel. This calls for the development of technology-driven, cost-effective, and user-friendly point-of-care screening and diagnostic tools (16). Cancer immunotherapy is a well-established and crucially important approach in the treatment of cancer patients. Over the past decade, therapeutic advancements in cancer immunotherapy (CIT) have swiftly emerged, underscoring the vital interplay between the human immune system and cancer. However, it is essential to acknowledge that only a minority of patients experience sustainable life- changing survival outcomes. Cancer immunotherapy faces several challenges, including uncertainties in effectively translating preclinical findings into successful clinical applications and identifying the best combinations of immune-based therapies personalized to each patient's needs (17). Additionally, Special Edition: Junior Commentary https://doi.org/10.47488/dhrp.v3iS1.95 DHR Proceedings ǀ http://dhrproceedings.org 3 2023, Vol. 3 No. S1 1--10 despite substantial advancements, small-molecule targeted anti-cancer drugs still confront several hurdles, such as low response rates and the development of drug resistance (18). Efforts to address these challenges are critical to further improve cancer treatment outcomes and advancing the frontier of cancer care. These challenges really highlight the urgent need for better treatment and prediction methods in cancer care. Therefore, prioritizing AI-driven innovative approaches in technology-based, cost- effective, and user-friendly point-of-care screening and diagnostics can bridge cancer care gaps globally. Addressing disparities and strategic healthcare resource allocation are essential in combating the growing burden in vulnerable regions. Role of Artificial Intelligence in Cancer Care The potential of AI applications is immense, as they can enhance clinician decision-making, optimize clinical care processes, improve patient outcomes, and lead to reduced healthcare costs (19). The rapid expansion of artificial intelligence (AI) within the healthcare sector has been remarkable over the past decade. AI applications have demonstrated their potential in transforming healthcare by leveraging clinical data to uncover valuable information (Figure 2). Through aiding healthcare providers in various critical tasks, such as disease diagnosis, patient triage, risk analysis, and surgical procedures, AI has become an indispensable tool in enhancing overall clinical care and patient outcomes (20). AI has achieved prominence as a widely adopted technology with a diverse array of multifaceted applications across various fields–which will be gone over in the following paragraphs. AI has rapidly become an integral component in various healthcare applications, spanning drug discovery, remote patient monitoring, medical diagnostics and imaging, risk management, wearables, virtual assistants, and hospital management (21). Its diverse and ever- expanding utilization in these areas showcases the transformative potential of AI technology in revolutionizing the healthcare landscape. As AI continues to evolve and intertwine with healthcare practices, it holds the promise of enhancing efficiency, accuracy, and overall patient care, ushering in a new era of medical innovation. Figure 2: Applications of AI in oncology to solve healthcare issues and predict optimal treatment outcomes. Created with BioRender.com Cancer Imaging and Diagnosis AI's remarkable ability to identify intricate patterns in medical images revolutionizes image interpretation, making it a quantifiable and reproducible process. Additionally, AI uncovers information imperceptible to human eyes, enhancing clinical decision-making (22). Conventional machine learning and deep learning techniques are used for lesion detection and classification, aiming to reduce reading time and enhance accuracy in differentiating between benign and malignant cases (23). By integrating diverse data streams, including radiographic images, genomics, pathology, electronic health records, and social networks, AI empowers the development of powerful diagnostic systems with far- reaching potential. Advancements in computer programs have led to the development and approval of clinical tools such as computer-aided detection (CAD) or computer-assisted detection, assisting radiologists in detecting potential abnormalities on diagnostic radiology exams, thereby reducing false negative rates (24). By incorporating CAD into clinical practice, the accuracy and reliability of diagnostic radiology are enhanced, leading to improved patient outcomes and more effective care. Radiology traditionally relies on skilled physicians' visual assessments, but this approach can be subjective, influenced by their education and experience. In contrast, AI excels in recognizing intricate patterns within imaging data, enabling an objective and automated quantitative assessment (21). Integrating AI as a supportive tool enhances radiology assessments, advancing patient care and outcomes. This collaborative approach, combining human expertise and AI-driven precision, elevates radiological practices to new heights of efficiency and effectiveness (25). As AI continues to evolve in radiology, its role as an invaluable ally in disease detection, characterization, and monitoring becomes increasingly evident, promising a future of Special Edition: Junior Commentary https://doi.org/10.47488/dhrp.v3iS1.95 DHR Proceedings ǀ http://dhrproceedings.org 4 2023, Vol. 3 No. S1 1--10 precision and excellence in medical imaging and diagnosis. Artificial Intelligence-Driven Precision Medicine The integration of artificial intelligence (AI) and precision medicine stands poised to catalyze a profound transformation within the healthcare landscape. Precision medicine introduces a paradigm shift, aiming to advance the healthcare model where diagnostics, prevention, and treatment strategies are meticulously tailored to an individual's unique genetic, environmental, and lifestyle attributes (26). This approach is instrumental in discerning distinctive patient phenotypes marked by uncommon treatment responses and specific healthcare requirements. Leveraging intricate computational capabilities, AI serves as a catalyst, enabling sophisticated reasoning, learning, and augmented intelligence, thus empowering clinical decision-makers to navigate complex healthcare scenarios and deliver personalized care with heightened efficacy. The discovery potential inherent in precision medicine augments our understanding of unexplored therapeutic avenues, extending the boundaries of healthcare possibilities (27). Critical to the personalization of medical care are the diverse data collection and analytical technologies that underpin precision medicine's core principles (28). Real-time treatment recommendations hinge upon the precision of machine-learning algorithms that anticipate patients' potential medication requirements based on their genomic profiles. At the heart of tailored drug administration lies preemptive patient genotyping, ensuring optimal therapeutic interventions (29). This paradigm underscores a seminal example of AI and precision medicine synergy, manifesting in the seamless convergence of AI techniques with the meticulous interpretation of high-throughput genomic data (30). Predictive Analytics and Prognosis Artificial Intelligence (AI) is increasingly utilized to develop cancer prediction models (31). Various methods, including statistical, machine learning, and deep learning approaches, have been employed to enhance prediction accuracy (32-33). Machine Learning (ML) algorithms can leverage extensive screening data to develop robust models that can predict drug responses in cancer patients (34). The incorporation of various data types demands more resources than analyzing individual data types alone, requiring modeling algorithms capable of comprehending vast amounts of intricate features (35). As a result, AI-driven algorithms are increasingly employed to automate cancer prediction by identifying the development of cancer and even characterizing it (36). A study that was conducted showed the proficiency of these machine-learning approaches in cancer prediction (36). In this study, differences in clinicopathological characteristics were observed between the two datasets, with a specific dataset showing superior survival rates. In predicting 5-year survival, the machine learning model employing light gradient boosting surpassed conventional staging methods. Notably, age, examined lymph nodes, and tumor size emerged as pivotal factors shaping the model's performance. The validation set further provided sensitivity and positive predictive values for survival prediction. This underscores the ML-based model's remarkable advancement, surpassing conventional staging techniques in providing highly precise individualized survival estimations (37). In addition to machine learning techniques, two primary factors contribute to the attractiveness of deep learning in computational biology (38). First and foremost, this potent model class has the capacity to approximate virtually any input-to-output mapping with sufficient data. For instance, when predicting transcription factor binding locations, there is no necessity to confine the model's expressivity to a single sequence motif (39). Notably, deep learning models have been harnessed for prediction purposes in a conducted study (40). A deep learning model (DeepDR) was made to forecast drug responses in cancer cells and tumors. DeepDR seamlessly integrates mutation and expression data, comprising three pivotal components: one for mutation comprehension, another for expression analysis, and a final component for drug response prediction. Its predictive prowess extends to 265 drugs, envisaging their efficacy grounded in genetic and expression profiles. Rigorously tested on 622 cancer cell lines, DeepDR showcased remarkable performance, surpassing existing methods in drug response prediction. Demonstrating its breadth, the model further predicted drug responses across 9059 tumors spanning 33 cancer types. In doing so, it unveiled known efficacious drugs and unearthed novel candidates, shedding light on drug mechanisms, resistance patterns, and proposing a promising therapeutic avenue for gliomas and blood cancers. Drug Discovery and Development Artificial intelligence (AI) presents a transformative potential in reshaping both drug design strategies and patient treatment paradigms. The challenges encompassing drug design, including time constraints, production costs, inefficient target delivery, and imprecise dosing, have propelled the Special Edition: Junior Commentary https://doi.org/10.47488/dhrp.v3iS1.95 DHR Proceedings ǀ http://dhrproceedings.org 5 2023, Vol. 3 No. S1 1--10 exploration of AI-driven solutions (41). Traditional drug development barriers, underscored by intricacies in big data handling, have found resolution through AI integration, transcending conventional computational approaches (42). This synergy has yielded expedited drug candidate development, fostering cost-effective and structured solutions within notably reduced timeframes (43). Complementing this, emerging machine learning techniques, notably deep learning, have harnessed vast data reservoirs to predict molecular structures, in-vivo vs. in-vitro characteristics, and outcomes, streamlining drug discovery without compromising efficiency (44). AI's potential extends to revolutionary platforms like the quadratic phenotypic optimization platform (QPOP), which, unlike conventional methods, tailors drug combinations to specific disease models or patient profiles based on empirical data, transcending preconceived mechanistic assumptions (45). In parallel, AI models, spanning patient stratification, pathophysiological casualties, drug candidate design, and virtual patient predictions, hold paramount significance (46-47). Notably, AI's prowess in delineating structure-activity relationships (SAR) and exploiting massive sequencing data, such as next- generation sequencing (NGS), illuminates novel drug target identification, augmenting drug discovery pathways (48). Within the AI arsenal, artificial neural networks, deep neural networks, support vector machines, classification and regression techniques, generative adversarial networks, symbolic learning, and meta-learning algorithms have been harnessed to elevate drug design and discovery (49). The culmination of individual patient attributes and extensive drug candidate predictions within these models fosters a new era of personalized and optimized treatment strategies, revolutionizing disease management practices (50-51). As AI continues to reshape drug design and patient-oriented approaches, the potential for personalized and precision medicine stands poised for unprecedented advancement. Challenges and Limitations of Artificial Intelligence in Cancer Care While AI holds promise in bolstering the healthcare sector and improving cancer care, apprehensions arise about the potential difficulty in validating and questioning AI-mediated decisions, which might lead to unconventional outcomes (52). The instances of AI integration in healthcare serve as pivotal examples, highlighting the significance of assessing both the benefits and risks associated with emerging AI-driven systems (53). The primary hurdle in advancing clinical AI applications in oncology, and healthcare in general, lies in data constraints, encompassing both quality and quantity aspects. Pertinent challenges encompass data curation, aggregation transparency, potential bias, and reliability concerns (54). The deployment of deep learning in precision oncology faces obstacles such as scarce phenotypically rich data and the imperative for more interpretable deep learning models (55). Ethical, copyright, transparency, and legal issues, alongside the risk of biases, plagiarism, inaccuracies, limited knowledge, incorrect citations, and cybersecurity vulnerabilities, underscore AI's limitations (56). The issues of AI model interpretability, trust, reproducibility, and generalizability have garnered substantial attention, with growing recognition of biases in demographic factors like sex and ethnicity (57). For instance, an AI tool for using 129,450 images for detecting skin cancer displayed parity with dermatologists but faced criticism for underrepresentation of darker skin tones, raising concerns about reproducibility and applicability (58- 59). Additionally, the meticulous curation and storage of data for machine learning models, along with evolving data stewardship expectations, further complicate AI advancement (60). Fostering AI applications in cancer care demands a focus on clinical validity, utility, and usability. Achieving this entails a patient-centric, clinical decision-oriented approach to model development and assessment (61). From challenges in training machine learning systems to accountability uncertainties, the incremental implementation of AI remains complex (62). Moreover, physician comprehension of AI's potential remains a significant aspect that needs to be addressed (63). This domain undoubtedly holds immense promise, yet it is marked by notable gaps and ambiguities requiring attention. The primary hurdle lies not in the rapid technological advancements, which continually unveil new application areas, but rather in the deficient legal framework. Inadequate regulations, coupled with political, ethical, and financial intricacies, underscore the challenge (64). Hence, a collaborative effort among technologists, policymakers, and ethicists becomes paramount. The imperative is to establish a robust legal structure that guides innovation while upholding ethical norms. This harmonious convergence has the potential to unleash the realm's possibilities, dissipating uncertainties and nurturing responsible advancement. Special Edition: Junior Commentary https://doi.org/10.47488/dhrp.v3iS1.95 DHR Proceedings ǀ http://dhrproceedings.org 6 2023, Vol. 3 No. S1 1--10 Ethical and Regulatory Considerations Artificial intelligence (AI), while transforming the medical landscape, raises significant ethical considerations. While AI holds potential in healthcare, its implementation necessitates careful oversight akin to physician conduct. To ensure safe utilization and assessment of AI technology, regulatory frameworks are imperative, coupled with research into its medical capabilities and constraints (63). Given that patients interact with physicians during vulnerable moments, maintaining sensitivity to this fact is crucial (65). Protecting health data, which encompasses private patient and caregiver details and medical histories, is paramount. Breaches could lead to personal repercussions such as bullying, higher insurance premiums, and job loss (66-67). Security, privacy, and trust are non-negotiable (68). AI will not supplant human roles entirely, but integration into physicians' routines can be pivotal (68). Transitioning towards personalized, evidence- based patient management warrants rigorous evaluations of AI technologies, particularly in cancer risk or management scenarios (68). Ethical concerns include the opaque nature of AI decisions, its influence on patient engagement and shared decision-making, and the allocation of responsibility if AI predictions falter (69). Other ethical issues encompass informed data consent, safety, transparency, algorithmic fairness, biases, and data privacy (65). With AI gaining prominence in high-stakes contexts, ensuring accountable, equitable, and transparent AI design and governance is paramount (70). Transparency hinges on accessible and comprehensible information (71). Further interdisciplinary collaboration and research hold potential to markedly enhance patient care quality, rebalance clinician workloads, and revolutionize medical practice (72). This dynamic journey toward ethical AI integration demands collective dedication and thoughtful navigation. Conclusion and Discussion The dynamic landscape of cancer care poses challenges that necessitate innovative and collaborative solutions. Factors like urbanization, shifting lifestyles, and extended longevity contribute to changing cancer rates, underlining the urgency of targeted interventions and equitable healthcare access. The complexities of cancer prevalence across regions and demographics further underscore the need for tailored approaches and resource allocation. However, implementing effective cancer screening and diagnostics remains particularly daunting in resource- constrained settings, emphasizing the demand for technology-driven and user-friendly solutions. Challenges persist in immunotherapy and targeted drug development, requiring solutions for issues such as translation and resistance. Artificial intelligence (AI) emerges as a potent tool to address these challenges and reshape cancer care paradigms. Integrating AI-driven innovations into point-of-care screening and diagnostics has the potential to bridge global cancer care gaps, especially in resource-limited regions. Beyond diagnosis and treatment, AI enhances clinician decision-making, streamlines clinical processes, and drives cost reduction. The rapid growth of AI across healthcare domains, from drug discovery to medical imaging, underscores its transformative impact. AI's proficiency in pattern recognition catalyzes a revolution in radiology, enhancing precise and efficient image interpretation and elevating patient care. Moreover, AI's synergy with precision medicine introduces a pivotal shift, enabling tailored treatments grounded in individual genetic and environmental variables. Nonetheless, the substantial potential of AI must be approached with ethical considerations and vigilance. Prioritizing privacy, security, transparency, and bias mitigation is pivotal to ensure AI's equitable and responsible deployment in healthcare. Collaborative efforts among technologists, policymakers, and ethicists are essential to establish a robust regulatory framework that guides AI innovation while upholding ethical norms. Addressing concerns about data quality, model interpretability, and accountability remains imperative in AI's ongoing evolution. In light of these prospects and challenges, the integration of AI into cancer care holds promise for overcoming obstacles and reshaping patient outcomes. By harnessing AI's capabilities and fostering collaboration, the healthcare community can strive for personalized, effective, and ethically sound cancer care on a global scale. This transformative journey demands a comprehensive approach, uniting technological innovation, regulatory diligence, and ethical contemplation. As we navigate this path, the convergence of AI and cancer care stands as a beacon of hope, promising a future marked by enhanced patient well-being and advanced medical progress. Special Edition: Junior Commentary https://doi.org/10.47488/dhrp.v3iS1.95 DHR Proceedings ǀ http://dhrproceedings.org 7 2023, Vol. 3 No. S1 1-10 References 1. Yin W, Wang J, Jiang L, James Kang Y. Cancer and stem cells. Exp Biol Med (Maywood). 2021;246(16):1791-1801. doi:10.1177/15353702211005390 2. Hazafa A, Rehman KU, Jahan N, Jabeen Z. The Role of Polyphenol (Flavonoids) Compounds in the Treatment of Cancer Cells. Nutr Cancer. 2020;72(3):386- 397. doi:10.1080/01635581.2019.1637006 3. Siegel RL, Miller KD, Fuchs HE, Jemal A. Cancer Statistics, 2021 [published correction appears in CA Cancer J Clin. 2021 Jul;71(4):359]. CA Cancer J Clin. 2021;71(1):7-33. doi:10.3322/caac.21654 4. Siegel RL, Miller KD, Wagle NS, Jemal A. Cancer statistics, 2023. CA Cancer J Clin. 2023;73(1):17-48. doi:10.3322/caac.21763 5. Radkiewicz C, Andersson TM, Lagergren J. Reranking cancer mortality using years of life lost. JNCI Cancer Spectr. 2023;7(3):pkad038. doi:10.1093/jncics/pkad038 6. Shimizu H, Nakayama KI. Artificial intelligence in oncology. Cancer Sci. 2020;111(5):1452-1460. doi:10.1111/cas.14377 7. Choi RY, Coyner AS, Kalpathy-Cramer J, Chiang MF, Campbell JP. Introduction to Machine Learning, Neural Networks, and Deep Learning. Transl Vis Sci Technol. 2020;9(2):14. Published 2020 Feb 27. doi:10.1167/tvst.9.2.14 8. Deo RC. Machine Learning in Medicine. Circulation. 2015;132(20):1920-1930. doi:10.1161/CIRCULATIONAHA.115. 001593 9. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436- 444. doi:10.1038/nature14539 10. Esteva A, Robicquet A, Ramsundar B, et al. A guide to deep learning in healthcare. Nat Med. 2019;25(1):24-29. doi:10.1038/s41591-018-0316-z 11. Rajpurkar P, Chen E, Banerjee O, Topol EJ. AI in health and medicine. Nat Med. 2022;28(1):31-38. doi:10.1038/s41591- 021-01614-0 12. Hamet P, Tremblay J. Artificial intelligence in medicine. Metabolism. 2017;69S:S36-S40. doi:10.1016/j.metabol.2017.01.011 13. Mintz Y, Brodie R. Introduction to artificial intelligence in medicine. Minim Invasive Ther Allied Technol. 2019;28(2):73-81. doi:10.1080/13645706.2019.1575882 14. Sung H, Ferlay J, Siegel RL, et al. Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality Worldwide for 36 Cancers in 185 Countries. CA Cancer J Clin. 2021;71(3):209-249. doi:10.3322/caac.21660 15. Soerjomataram I, Bray F. Planning for tomorrow: global cancer incidence and the role of prevention 2020-2070. Nat Rev Clin Oncol. 2021;18(10):663-672. doi:10.1038/s41571-021-00514-z 16. Deo SVS, Sharma J, Kumar S. GLOBOCAN 2020 Report on Global Cancer Burden: Challenges and Opportunities for Surgical Oncologists. Ann Surg Oncol. 2022;29(11):6497- 6500. doi:10.1245/s10434-022-12151-6 17. Hegde PS, Chen DS. Top 10 Challenges in Cancer Immunotherapy. Immunity. 2020;52(1):17-35. doi:10.1016/j.immuni.2019.12.011 18. Zhong L, Li Y, Xiong L, et al. Small molecules in targeted cancer therapy: advances, challenges, and future perspectives. Signal Transduct Target Ther. 2021;6(1):201. Published 2021 May 31. doi:10.1038/s41392-021- 00572-w 19. Yin J, Ngiam KY, Teo HH. Role of Artificial Intelligence Applications in Real-Life Clinical Practice: Systematic Review. J Med Internet Res. 2021;23(4):e25759. Published 2021 Apr 22. doi:10.2196/25759 20. He J, Baxter SL, Xu J, Xu J, Zhou X, Zhang K. The practical implementation of artificial intelligence technologies in medicine. Nat Med. 2019;25(1):30-36. doi:10.1038/s41591-018-0307-0 21. Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL. Artificial Special Edition: Junior Commentary https://doi.org/10.47488/dhrp.v3iS1.95 DHR Proceedings ǀ http://dhrproceedings.org 8 2023, Vol. 3 No. S1 1-10 intelligence in radiology. Nat Rev Cancer. 2018;18(8):500-510. doi:10.1038/s41568-018-0016-5 22. Bi WL, Hosny A, Schabath MB, et al. Artificial intelligence in cancer imaging: Clinical challenges and applications. CA Cancer J Clin. 2019;69(2):127-157. doi:10.3322/caac.21552 23. Mendes J, Domingues J, Aidos H, Garcia N, Matela N. AI in Breast Cancer Imaging: A Survey of Different Applications. J Imaging. 2022;8(9):228. Published 2022 Aug 26. doi:10.3390/jimaging8090228 24. Castellino RA. Computer aided detection (CAD): an overview. Cancer Imaging. 2005;5(1):17-19. Published 2005 Aug 23. doi:10.1102/1470- 7330.2005.0018 25. Aerts HJ. The Potential of Radiomic- Based Phenotyping in Precision Medicine: A Review. JAMA Oncol. 2016;2(12):1636-1642. doi:10.1001/jamaoncol.2016.2631 26. Aronson SJ, Rehm HL. Building the foundation for genomics in precision medicine. Nature. 2015;526(7573):336- 342. doi:10.1038/nature15816 27. Azad RK, Shulaev V. Metabolomics technology and bioinformatics for precision medicine. Brief Bioinform. 2019;20(6):1957-1971. doi:10.1093/bib/bbx170 28. Johnson KB, Wei WQ, Weeraratne D, et al. Precision Medicine, AI, and the Future of Personalized Health Care. Clin Transl Sci. 2021;14(1):86-93. doi:10.1111/cts.12884 29. Schildcrout JS, Shi Y, Danciu I, et al. A prognostic model based on readily available clinical data enriched a pre- emptive pharmacogenetic testing program. J Clin Epidemiol. 2016;72:107-115. doi:10.1016/j.jclinepi.2015.08.028 30. Deep learning for genomics. Nat Genet. 2019;51(1):1. doi:10.1038/s41588-018- 0328-0 31. Swanson K, Wu E, Zhang A, Alizadeh AA, Zou J. From patterns to patients: Advances in clinical machine learning for cancer diagnosis, prognosis, and treatment. Cell. 2023;186(8):1772- 1791. doi:10.1016/j.cell.2023.01.035 32. Kalafi EY, Nor NAM, Taib NA, Ganggayah MD, Town C, Dhillon SK. Machine Learning and Deep Learning Approaches in Breast Cancer Survival Prediction Using Clinical Data. Folia Biol (Praha). 2019;65(5-6):212-220. 33. Ganggayah MD, Taib NA, Har YC, Lio P, Dhillon SK. Predicting factors for survival of breast cancer patients using machine learning techniques. BMC Med Inform Decis Mak. 2019;19(1):48. Published 2019 Mar 22. doi:10.1186/s12911-019-0801-4 34. Baptista D, Ferreira PG, Rocha M. Deep learning for drug response prediction in cancer. Brief Bioinform. 2021;22(1):360-379. doi:10.1093/bib/bbz171 35. Libbrecht MW, Noble WS. Machine learning applications in genetics and genomics. Nat Rev Genet. 2015;16(6):321-332. doi:10.1038/nrg3920 36. Osman MH, Mohamed RH, Sarhan HM, et al. Machine Learning Model for Predicting Postoperative Survival of Patients with Colorectal Cancer. Cancer Res Treat. 2022;54(2):517-524. doi:10.4143/crt.2021.206 37. Skrede OJ, De Raedt S, Kleppe A, et al. Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. Lancet. 2020;395(10221):350-360. doi:10.1016/S0140-6736(19)32998-8 38. Issa NT, Stathias V, Schürer S, Dakshanamurthy S. Machine and deep learning approaches for cancer drug repurposing. Semin Cancer Biol. 2021;68:132-142. doi:10.1016/j.semcancer.2019.12.011 39. Jones W, Alasoo K, Fishman D, Parts L. Computational biology: deep learning. Emerg Top Life Sci. 2017;1(3):257-274. doi:10.1042/ETLS20160025 40. Chiu YC, Chen HH, Zhang T, et al. Predicting drug response of tumors from integrated genomic profiles by deep neural networks [published correction appears in BMC Med Genomics. 2019 Aug 12;12(1):119]. BMC Med Genomics. 2019;12(Suppl 1):18. Published 2019 Jan 31. doi:10.1186/s12920-018-0460-9 41. Gupta R, Srivastava D, Sahu M, Tiwari S, Ambasta RK, Kumar P. Artificial intelligence to deep learning: machine intelligence approach for drug Special Edition: Junior Commentary https://doi.org/10.47488/dhrp.v3iS1.95 DHR Proceedings ǀ http://dhrproceedings.org 9 2023, Vol. 3 No. S1 1-10 discovery. Mol Divers. 2021;25(3):1315-1360. doi:10.1007/s11030-021-10217-3 42. Wang L, Alexander CA. Big data analytics in medical engineering and healthcare: methods, advances and challenges. J Med Eng Technol. 2020;44(6):267-283. doi:10.1080/03091902.2020.1769758 43. Tripathi MK, Nath A, Singh TP, Ethayathulla AS, Kaur P. Evolving scenario of big data and Artificial Intelligence (AI) in drug discovery. Mol Divers. 2021;25(3):1439-1460. doi:10.1007/s11030-021-10256-w 44. Zhao L, Ciallella HL, Aleksunes LM, Zhu H. Advancing computer-aided drug discovery (CADD) by big data and data- driven machine learning modeling. Drug Discov Today. 2020;25(9):1624- 1638. doi:10.1016/j.drudis.2020.07.005 45. Zhang L, Tan J, Han D, Zhu H. From machine learning to deep learning: progress in machine intelligence for rational drug discovery. Drug Discov Today. 2017;22(11):1680-1685. doi:10.1016/j.drudis.2017.08.010 46. Moingeon P. Artificial intelligence- driven drug development against autoimmune diseases. Trends Pharmacol Sci. 2023;44(7):411-424. doi:10.1016/j.tips.2023.04.005 47. Workman P, Antolin AA, Al-Lazikani B. Transforming cancer drug discovery with Big Data and AI. Expert Opin Drug Discov. 2019;14(11):1089-1095. doi:10.1080/17460441.2019.1637414 48. Qin D. Next-generation sequencing and its clinical application. Cancer Biol Med. 2019;16(1):4-10. doi:10.20892/j.issn.2095- 3941.2018.0055 49. Zhu H. Big Data and Artificial Intelligence Modeling for Drug Discovery. Annu Rev Pharmacol Toxicol. 2020;60:573-589. doi:10.1146/annurev-pharmtox- 010919-023324 50. Chopra H, Baig AA, Gautam RK, Kamal MA. Application of Artificial Intelligence in Drug Discovery. Curr Pharm Des. 2022;28(33):2690-2703. doi:10.2174/138161282866622060814 1049 51. Rashid MBMA, Chow EK. Artificial Intelligence-Driven Designer Drug Combinations: From Drug Development to Personalized Medicine. SLAS Technol. 2019;24(1):124-125. doi:10.1177/2472630318800774 52. Liyanage H, Liaw ST, Jonnagaddala J, et al. Artificial Intelligence in Primary Health Care: Perceptions, Issues, and Challenges. Yearb Med Inform. 2019;28(1):41-46. doi:10.1055/s-0039- 1677901 53. Küster D, Schultz T. Künstliche Intelligenz und Ethik im Gesundheitswesen – Spagat oder Symbiose? [Artificial intelligence and ethics in healthcare-balancing act or symbiosis?]. Bundesgesundheitsblatt Gesundheitsforschung Gesundheitsschutz. 2023;66(2):176- 183. doi:10.1007/s00103-022-03653-5 54. Norgeot B, Quer G, Beaulieu-Jones BK, et al. Minimum information about clinical artificial intelligence modeling: the MI-CLAIM checklist. Nat Med. 2020;26(9):1320-1324. doi:10.1038/s41591-020-1041-y 55. Tran KA, Kondrashova O, Bradley A, Williams ED, Pearson JV, Waddell N. Deep learning in cancer diagnosis, prognosis and treatment selection. Genome Med. 2021;13(1):152. Published 2021 Sep 27. doi:10.1186/s13073-021-00968-x 56. Sallam M. ChatGPT Utility in Healthcare Education, Research, and Practice: Systematic Review on the Promising Perspectives and Valid Concerns. Healthcare (Basel). 2023;11(6):887. Published 2023 Mar 19. doi:10.3390/healthcare11060887 57. Beam AL, Manrai AK, Ghassemi M. Challenges to the Reproducibility of Machine Learning Models in Health Care. JAMA. 2020;323(4):305-306. doi:10.1001/jama.2019.20866 58. Esteva A, Kuprel B, Novoa RA, et al. Dermatologist-level classification of skin cancer with deep neural networks [published correction appears in Nature. 2017 Jun 28;546(7660):686]. Nature. 2017;542(7639):115-118. doi:10.1038/nature21056 59. Zou J, Schiebinger L. AI can be sexist and racist - it's time to make it fair. Nature. 2018;559(7714):324-326. doi:10.1038/d41586-018-05707-8 Special Edition: Junior Commentary https://doi.org/10.47488/dhrp.v3iS1.95 DHR Proceedings ǀ http://dhrproceedings.org 10 2023, Vol. 3 No. S1 1-10 60. Wilkinson MD, Dumontier M, Aalbersberg IJ, et al. The FAIR Guiding Principles for scientific data management and stewardship [published correction appears in Sci Data. 2019 Mar 19;6(1):6]. Sci Data. 2016;3:160018. Published 2016 Mar 15. doi:10.1038/sdata.2016.18 61. Kann BH, Hosny A, Aerts HJWL. Artificial intelligence for clinical oncology. Cancer Cell. 2021;39(7):916- 927. doi:10.1016/j.ccell.2021.04.002 62. Chomutare T, Tejedor M, Svenning TO, et al. Artificial Intelligence Implementation in Healthcare: A Theory-Based Scoping Review of Barriers and Facilitators. Int J Environ Res Public Health. 2022;19(23):16359. Published 2022 Dec 6. doi:10.3390/ijerph192316359 63. Aung YYM, Wong DCS, Ting DSW. The promise of artificial intelligence: a review of the opportunities and challenges of artificial intelligence in healthcare. Br Med Bull. 2021;139(1):4- 15. doi:10.1093/bmb/ldab016 64. Pashkov VM, Harkusha AO, Harkusha YO. ARTIFICIAL INTELLIGENCE IN MEDICAL PRACTICE: REGULATIVE ISSUES AND PERSPECTIVES. Wiad Lek. 2020;73(12 cz 2):2722-2727. 65. Naik N, Hameed BMZ, Shetty DK, et al. Legal and Ethical Consideration in Artificial Intelligence in Healthcare: Who Takes Responsibility?. Front Surg. 2022;9:862322. Published 2022 Mar 14. doi:10.3389/fsurg.2022.862322 66. Thapa C, Camtepe S. Precision health data: Requirements, challenges and existing techniques for data security and privacy. Comput Biol Med. 2021;129:104130. doi:10.1016/j.compbiomed.2020.10413 0 67. Sheikh A, Anderson M, Albala S, et al. Health information technology and digital innovation for national learning health and care systems. Lancet Digit Health. 2021;3(6):e383-e396. doi:10.1016/S2589-7500(21)00005-4 68. Rompianesi G, Pegoraro F, Ceresa CD, Montalti R, Troisi RI. Artificial intelligence in the diagnosis and management of colorectal cancer liver metastases. World J Gastroenterol. 2022; 28(1):108-122. doi:10.3748/wjg.v28.i1.108 69. Hunter B, Hindocha S, Lee RW. The Role of Artificial Intelligence in Early Cancer Diagnosis. Cancers (Basel). 2022;14(6):1524. Published 2022 Mar 16. doi:10.3390/cancers14061524 70. Morley J, Machado CCV, Burr C, et al. The ethics of AI in health care: A mapping review. Soc Sci Med. 2020;260:113172. doi:10.1016/j.socscimed.2020.113172 71. Char DS, Abràmoff MD, Feudtner C. Identifying Ethical Considerations for Machine Learning Healthcare Applications. Am J Bioeth. 2020;20(11):7-17. doi:10.1080/15265161.2020.1819469 72. Xu L, Sanders L, Li K, Chow JCL. Chatbot for Health Care and Oncology Applications Using Artificial Intelligence and Machine Learning: Systematic Review. JMIR Cancer. 2021;7(4):e27850. Published 2021 Nov 29. doi:10.2196/27850