Inteligencia Artificial en Oncología Quirúrgica: Entre la Innovación Tecnológica y el Juicio Clínico

Inteligencia Artificial en Oncología Quirúrgica: Entre la Innovación Tecnológica y el Juicio Clínico

Artificial Intelligence in Surgical Oncology: Between Technological Innovation and Clinical Judgment

José Manuel Fernández Madrid*

* Servicio de Cirugía General y del Aparato Digestivo,
     Hospital Universitario HLA Moncloa. Cátedra de Oncología Quirúrgica ASISA / Universidad de Alcalá (UAH).

DOI: https://doi.org/10.14679/5200

Resumen:

La oncología quirúrgica está cambiando poco a poco con la digitalización, el manejo de grandes volúmenes de datos y la incorporación de la IA. Todo ello está ayudando a comprender mejores situaciones complejas, afinar el diagnóstico y planificar la cirugía con mayor precisión.
En este trabajo se analiza la evolución desde las formas tradicionales de aprendizaje clínico, basadas en el estudio, la experiencia acumulada junto a los pacientes y el conocimiento transmitido a través de tratados, artículos científicos y, más recientemente, Internet, hacia modelos apoyados en IA y Deep Learning.
El objetivo es centrarse en aquellas aplicaciones que ya tienen una utilidad real en la práctica clínica, como el análisis avanzado de imágenes o la cirugía guiada por imagen. Pero también se señalan sus limitaciones, especialmente la dificultad para comprender cómo algunos algoritmos alcanzan determinadas conclusiones, lo que conocemos como «caja negra», así como el riesgo de sesgos derivados de los datos con los que han sido entrenados.
Más allá de lo que aportan, se plantea también una mirada crítica. En un paciente oncológico hay decisiones que no son solo técnicas y, si dejamos demasiado peso en la IA, corremos el riesgo de perder parte de lo que siempre ha sido la base de la medicina: la experiencia, el aprendizaje y la capacidad de comprender a la persona que tienes delante.
También se abordan las implicaciones éticas y legales, especialmente en relación con la responsabilidad y la necesidad de mantener una relación médicopaciente real. La IA es una herramienta útil, muy útil, casi imprescindible hoy, pero sigue siendo eso, una ayuda. El criterio y la responsabilidad no pueden delegarse.
Palabras Clave: Oncología quirúrgica; Inteligencia artificial (IA); Deep Learning; Radiómica; Cirugía de precisión; Big Data; Ética médica; Modelos predictivos; Toma de decisiones clínicas; Medicina personalizada.

Abstract:

Surgical oncology is gradually changing with digitalization, the management of large volumes of data, and the incorporation of artificial intelligence (AI). All of this is helping to better understand complex situations, refine diagnosis, and plan surgery with greater precision.
This paper analyses the evolution from traditional forms of clinical learning — based on study, experience accumulated alongside patients, and knowledge transmitted through treatises, scientific articles, and, more recently, the Internet — toward models supported by AI and Deep Learning.
The aim is to focus on those applications that already have real utility in clinical practice, such as advanced image analysis or image-guided surgery, while also highlighting their limitations, particularly the difficulty in understanding how certain algorithms reach specific conclusions — what is known as the “black box” problem — as well as the risk of biases arising from the data on which they have been trained.
Beyond what they contribute, a critical perspective is also offered. In an oncological patient, some decisions are not merely technical, and if we place too much weight on AI, we risk losing part of what has always been the foundation of medicine: experience, learning, and the ability to understand the person in front of us.
Ethical and legal implications are also addressed, particularly regarding responsibility and the need to maintain a genuine doctor-patient relationship. AI is a useful tool — very useful, almost indispensable today — but it remains just that: an aid. Judgment and responsibility cannot be delegated.
Key words: Surgical oncology; Artificial intelligence (AI); Deep Learning; Radiomics; Precision surgery; Big Data; Medical ethics; Predictive models; Clinical decision-making; Personalized medicine.

Bibliografía

1. 1. 1. Schein M. Common Sense Emergency Abdominal Surgery. 4th ed. Berlin: Springer; 2010.
      2. Álvarez Lopera JE. El Greco: estudio y catálogo. Madrid: Fundación Arte Hispánico; 2005.
      3. Marañón G. Vocación y ética y otros ensayos. Madrid: Espasa-Calpe; 1966.
      4. Topol EJ. Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. New York: Basic Books; 2019.
      5. Charon R. Narrative medicine: a model for empathy, reflection, profession, and trust. JAMA. 2001;286(15):1897-1902.
      6. Verghese A, Shah NH, Harrington RA. What this computer needs is a physician: humanism and artificial intelligence. JAMA. 2018;319(1):19-20.
      7. LeCun Y, Bengio Y, Hinton G. Deep learning. Nature. 2015;521(7553):436-444.
      8. Goodfellow I, Bengio Y, Courville A. Deep Learning. Cambridge (MA): MIT Press; 2016.
      9. Esteva A, Robicquet A, Ramsundar B, et al. A guide to deep learning in healthcare. Nat Med. 2019;25(1):24-29.
      10. Samek W, Wiegand T, Müller KR. Explainable Artificial Intelligence: Understanding, Visualizing and Interpreting Deep Learning Models. ITU J ICT Discoveries. 2017;1(1):1-10.
      11. Topol EJ. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 2019;25(1):44-56.
      12. Jiang F, Jiang Y, Zhi H, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2(4):230-243.
      13. Yu KH, Beam AL, Kohane IS. Artificial intelligence in healthcare. Nat Biomed Eng. 2018;2(10):719-731.
      14. Lambin P, Leijenaar RTH, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017;14(12):749-762.
      15. Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts HJWL. Artificial intelligence in radiology. Nat Rev Cancer. 2018;18(8):500-510.
      16. Samarajiwa S, Ho JWK, Sanguinetti G, et al. Early detection and diagnosis of cancer with interpretable machine learning to uncover cancer-specific DNA methylation patterns. Biol Methods Protoc. 2024;9(1):bpae028.
      17. Cha KH, Hadjiiski L, Samala RK, et al. Bladder cancer treatment response assessment in CT using radiomics with deep-learning. Sci Rep. 2017;7:8738.
      18. Kather JN, Krisam J, Charoentong P, et al. Predicting survival from colorectal cancer histology slides using deep learning. PLoS Med. 2019;16(1):e1002730.
      19. Laín Entralgo P. El médico y el enfermo. Madrid: Revista de Occidente; 1964.
      20. Kelly CJ, Karthikesalingam A, Suleyman M, Corrado G, King D. Key challenges for delivering clinical impact with artificial intelligence. BMC Med. 2019;17:195.
      21. Hashimoto DA, Rosman G, Rus D, Meireles OR. Artificial intelligence in surgery: promises and perils. Ann Surg. 2018;268(1):70-76.
      22. Maier-Hein L, Vedula SS, Speidel S, et al. Surgical data science for next-generation interventions. Nat Biomed Eng. 2017;1:691-696.
      23. Vining CC, Eng OS, Hogg ME, et al. Virtual surgical planning and three-dimensional printing in gastrointestinal and hepatopancreatobiliary surgery. J Gastrointest Surg. 2021;25(2):523-532.
      24. Wake N, Rosenkrantz AB, Huang R, et al. Patient-specific 3D printed and augmented reality kidney and prostate cancer models. Radiographics. 2019;39(6):1786-1801.
      25. Lanfranco AR, Castellanos AE, Desai JP, Meyers WC. Robotic surgery: a current perspective. Ann Surg. 2004;239(1):14-21.
      26. Collins T, Bartoli A. Computer vision for image-guided surgery. Int J Comput Vis. 2018;126(1):110-119.
      27. Mascagni P, Vardazaryan A, Alapatt D, et al. Artificial intelligence for surgical safety: automatic anatomical recognition in minimally invasive surgery. Ann Surg. 2022;275(5):955-962.
      28. Boni L, David G, Mangano A, et al. Clinical applications of indocyanine green fluorescence in laparoscopic surgery. Surg Endosc. 2015;29(7):2046-2055.
      29. Condino S, Turini G, Parchi PD, et al. How to build patient-specific augmented reality models for surgery. J Healthc Eng. 2018;2018:1814741.
      30. Twinanda AP, Shehata S, Mutter D, et al. EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans Med Imaging. 2017;36(1):86-97.
      31. Hantel A, Walsh TP, Marron JM, Kehl KL, Sharp R, Van Allen E, et al. Perspectives of Oncologists on the Ethical Implications of Using Artificial Intelligence for Cancer Care. JAMA Netw Open. 2024;7(3).
      32. Gerke S, Minssen T, Cohen IG. Ethical and legal challenges of artificial intelligence-driven healthcare. In: Bohr A, Memarzadeh K, editors. Artificial Intelligence in Healthcare. London: Academic Press; 2020. p. 295-336.
      33. Price WN II, Gerke S, Cohen IG. Potential liability for physicians using artificial intelligence. JAMA. 2019;322(18):1765-1766.
      34. Cohen IG, Amarasingham R, Shah A, Xie B, Lo B. The legal and ethical concerns that arise from using complex predictive analytics in health care. Health Aff (Millwood). 2014;33(7):1139-1147.
      35. European Commission. Ethics Guidelines for Trustworthy AI. Brussels: European Commission; 2019.
      36. Weinstein MC, Torrance G, McGuire A. QALYs: the basics. Value Health. 2009;12(Suppl 1):S5-S9.
      37. Love-Koh J, Cookson R, Claxton K, Griffin S. Estimating social variation in the health effects of changes in health care expenditure. Med Decis Making. 2020;40(2):170-182.
      38. Persad G, Wertheimer A, Emanuel EJ. Principles for allocation of scarce medical interventions. Lancet. 2009;373(9661):423-431.
      39. Mittelstadt BD, Allo P, Taddeo M, Wachter S, Floridi L. The ethics of algorithms: mapping the debate. Big Data Soc. 2016;3(2):1-21.