Artificial intelligence in oncology: beyond fiction


Cite item

Full Text

Abstract

Artificial intelligence (AI) is rapidly transforming various fields of medicine, and oncology is no exception. Thanks to its ability to analyze vast amounts of data, identify hidden patterns, and provide accurate predictions, Artificial intelligence is opening new horizons in the diagnosis, treatment, and prevention of cancer. Today, artificial intelligence is revolutionizing oncology by offering new tools to combat cancer. It can analyze medical images for early and accurate diagnosis, develop personalized treatment plans considering the patient’s genetics, and predict recurrence risks. Artificial intelligence also optimizes radiation therapy and assists in monitoring treatment effectiveness. These capabilities make artificial intelligence a powerful ally for physicians in the fight against oncological diseases.

Full Text

1] Artificial intelligence (AI) has demonstrated high accuracy in the diagnosis of oncological diseases, especially in the analysis of medical images (for example, mammograms, CT, MRI).[2] In some cases, AI has surpassed the accuracy of diagnoses made by experienced doctors. For example, in a study on the diagnosis of melanoma, AI showed a sensitivity of 95%, which is higher than the average of dermatologists (86.6%).[5] Artificial intelligence is able to analyze large amounts of data in a fraction of a second, which significantly speeds up the diagnostic and decision-making process.[6] This is especially important in emergency situations and during mass screening.[3] AI is also able to detect early signs of cancer that may be overlooked by the human eye.[4] This makes it possible to start treatment at an early stage, which significantly improves patients' prognoses.[9] In addition, Artificial intelligence helps analyze genomic data and select individual treatment regimens, which increases the effectiveness of therapy. For example, AI can recommend optimal combinations of chemotherapy, targeted or immunotherapy based on data on clinical outcomes in thousands of patients.Artificial Intelligence (AI) in oncology — This is not a substitute for a doctor, but an effective tool that expands his capabilities.[7] Thus, the study confirms that AI is a powerful tool in oncology that can improve the diagnosis, treatment and prognosis of diseases, but its use requires caution and further development.[8] Properly implemented AI technologies provide a reliable "partner" that increases the accuracy and efficiency of decisions made, helps optimize workflow and improve treatment outcomes.[10]Conclusion. Artificial intelligence demonstrates high efficiency in the diagnosis of oncological diseases, especially in the early stages. Artificial intelligence algorithms are capable of analyzing large amounts of data, which makes it possible to identify patterns inaccessible to humans. A personalized treatment approach based on artificial intelligence data increases the chances of successful treatment. The introduction of artificial intelligence into oncology requires addressing ethical, technical, and regulatory issues. Further research and development in this area can significantly improve the quality of medical care and reduce deaths from cancer.">Introduction. The increasing incidence of cancer worldwide requires new approaches to diagnosis and treatment. Artificial intelligence offers revolutionary possibilities for analyzing large amounts of data, which is especially important in oncology. The use of artificial intelligence can reduce diagnostic time, improve accuracy, and personalize treatment. The relevance of the topic is due to the need to reduce the burden on doctors and improve patient treatment outcomes.The purpose of the work. To study the application and implementation points of AI algorithms for early diagnosis of oncological diseases, the use of AI for analyzing medical images (radiography, Magnetic resonance imaging, computed tomography) in order to identify tumors, the possibilities of optimizing the selection of personalized therapy, as well as predicting the course of the disease and evaluating the effectiveness of treatment.Materials and methods of research. Publications in databases Nature, Nature medicine, Medical Image Analysis, Science, Computational and Structural Biotechnology Journal, A Cancer Journal for Clinicians using keywords: Artificial intelligence, medicine, oncology, machine learning, deep learning, cancer, analysis, cancer screening. The study was conducted based on the analysis of data from articles and publications with an assessment of the possibilities of using artificial intelligence in oncology.The results of the study. Based on the analysis of these articles, it was possible to assess the importance and possibilities of using artificial intelligence in the diagnosis, treatment and prognosis of oncological diseases.[1] Artificial intelligence (AI) has demonstrated high accuracy in the diagnosis of oncological diseases, especially in the analysis of medical images (for example, mammograms, CT, MRI).[2] In some cases, AI has surpassed the accuracy of diagnoses made by experienced doctors. For example, in a study on the diagnosis of melanoma, AI showed a sensitivity of 95%, which is higher than the average of dermatologists (86.6%).[5] Artificial intelligence is able to analyze large amounts of data in a fraction of a second, which significantly speeds up the diagnostic and decision-making process.[6] This is especially important in emergency situations and during mass screening.[3] AI is also able to detect early signs of cancer that may be overlooked by the human eye.[4] This makes it possible to start treatment at an early stage, which significantly improves patients' prognoses.[9] In addition, Artificial intelligence helps analyze genomic data and select individual treatment regimens, which increases the effectiveness of therapy. For example, AI can recommend optimal combinations of chemotherapy, targeted or immunotherapy based on data on clinical outcomes in thousands of patients.Artificial Intelligence (AI) in oncology — This is not a substitute for a doctor, but an effective tool that expands his capabilities.[7] Thus, the study confirms that AI is a powerful tool in oncology that can improve the diagnosis, treatment and prognosis of diseases, but its use requires caution and further development.[8] Properly implemented AI technologies provide a reliable "partner" that increases the accuracy and efficiency of decisions made, helps optimize workflow and improve treatment outcomes.[10]Conclusion. Artificial intelligence demonstrates high efficiency in the diagnosis of oncological diseases, especially in the early stages. Artificial intelligence algorithms are capable of analyzing large amounts of data, which makes it possible to identify patterns inaccessible to humans. A personalized treatment approach based on artificial intelligence data increases the chances of successful treatment. The introduction of artificial intelligence into oncology requires addressing ethical, technical, and regulatory issues. Further research and development in this area can significantly improve the quality of medical care and reduce deaths from cancer.
 
×

About the authors

Daniil Labazanov

Burdenko Voronezh State Medical University

Author for correspondence.
Email: daniil.labazanov@yandex.ru
ORCID iD: 0009-0009-9816-3820

студент

Russian Federation, 394036, г. Воронеж, ул. Студенческая, д. 10

Ivan Moshurov

БУЗ ВО "ВОНКОЦ": г. Воронеж

Email: moshurov@vokod.vrn.ru
ORCID iD: 0000-0003-1333-5638

доктор медицинских наук, профессор

Russian Federation, 394036, Воронежская Область, г.Воронеж, ул.Вайцеховского, д.4

Svetlana Stikina

Burdenko Voronezh State Medical University

Email: stikina.pedfak@yandex.ru
ORCID iD: 0000-0002-3511-3553

кандидат медицинских наук, доцент

Russian Federation, 394036, г. Воронеж, ул. Студенческая, д. 10

References

  1. Topol EJ. “High-performance medicine: the convergence of human and artificial intelligence.” Nature Medicine (2019) 25(1): 44–56
  2. Haenssle HA, et al. “Man against machine: diagnostic performance of a deep learning convolutional neural network...” Annals of Oncology (2018) 29(8): 1836–1842
  3. McKinney SM, et al. “International evaluation of an AI system for breast cancer screening.” Nature (2020) 577: 89–94
  4. Ardila D, et al. “End-to-end lung cancer screening with three-dimensional deep learning on low-dose chest computed tomography.” Nature Medicine (2019) 25: 954–961
  5. Esteva A, et al. “Dermatologist-level classification of skin cancer with deep neural networks.” Nature (2017) 542: 115–118
  6. Yala A, et al. “Optimizing risk-based breast cancer screening policies with reinforcement learning.” Nature Medicine (2022) 28: 248–254
  7. Hosny, A., Parmar, C., Quackenbush, J., Schwartz, L. H., & Aerts, H. J. “Artificial Intelligence in Oncology: Current Applications and Future Perspectives.” CA: A Cancer Journal for Clinicians (2019)
  8. Finlayson SG, et al. “Adversarial attacks on medical machine learning.” Science (2019) 363(6433): 1287–1289
  9. Kourou K, et al. “Machine learning applications in cancer prognosis and prediction.” Computational and Structural Biotechnology Journal (2015) 13: 8–17
  10. Topol EJ. “Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again.” Basic Books (2019)

Supplementary files

There are no supplementary files to display.

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies