{"id":9388,"date":"2025-11-18T12:49:14","date_gmt":"2025-11-18T08:49:14","guid":{"rendered":"https:\/\/medscriptum.org\/?p=9388"},"modified":"2025-11-18T13:35:23","modified_gmt":"2025-11-18T09:35:23","slug":"the-future-of-oncology-what-does-esmo-ai-digital-oncology-2025-teach-us","status":"publish","type":"post","link":"https:\/\/medscriptum.org\/en\/the-future-of-oncology-what-does-esmo-ai-digital-oncology-2025-teach-us\/","title":{"rendered":"The Future of Oncology: What Does ESMO AI & Digital Oncology 2025 Teach Us?"},"content":{"rendered":"

David Kvaratskhelia, Oncology Resident, Todua Clinic<\/strong><\/p>\n

There are moments when medical reality changes so rapidly that you feel the boundaries of your profession have expanded infinitely. For me, attending ESMO AI & Digital Oncology 2025<\/a> in Berlin was exactly that kind of experience. It wasn\u2019t just a scientific conference; it was a touchpoint with the future, a future that is practically already here.<\/p>\n

Why does this congress hold special significance?<\/strong><\/h3>\n

ESMO, the European Society for Medical Oncology, has long demonstrated that modern oncology must be built on clear standards, evidence-based practice, and teamwork. However, the AI & Digital Oncology congress is on another scale entirely. It is a place where an oncologist meets a data scientist, a morphologist meets an engineer, and a clinical mind meets an algorithm.<\/p>\n

Arthur Clarke has a well-known quote: \u201cAny sufficiently advanced technology is indistinguishable from magic.\u201d<\/em> At ESMO AI & Digital Oncology 2025 in Berlin, I felt precisely this, that the \u201cmagic\u201d has already become very real. What a few years ago appeared only on the final \u201cfuture directions\u201d slides of presentations has now become everyday clinical tools.<\/p>\n

The congress showcased the full wave of technologies currently entering oncology:<\/p>\n

    \n
  • \n

    Digital morphology<\/strong> \u2013 whole-slide scanning of histology specimens, digitization, and algorithmic analysis. This includes quantitative analytics, detailed evaluation of the tumor microenvironment, and immune infiltration.<\/p>\n<\/li>\n

  • \n

    Virtual 3D simulations in morphology<\/strong> \u2013 three-dimensional tumor modeling, predicting invasiveness and spread, and visualizing different treatment scenarios. This is no longer just a visual effect, it is data used for decision-making.<\/p>\n<\/li>\n

  • \n

    \u201cBlack box\u201d technologies and Explainable AI<\/strong> \u2013 how to combine high accuracy with interpretability; how to explain to doctors and patients why an algorithm decided a certain way; what ethical and legal questions arise when AI partly participates in treatment planning.<\/p>\n<\/li>\n

  • \n

    Multi-omics integration<\/strong> \u2013 combining genomic, transcriptomic, immunologic, and clinical data into unified predictive models.<\/p>\n<\/li>\n

  • \n

    A strategic vision for digital oncology<\/strong> \u2013 what skills tomorrow\u2019s oncologist will need; how \u201ctechnically literate\u201d a doctor should be; how the education system must evolve.<\/p>\n<\/li>\n<\/ul>\n

    All of this created the feeling that modern oncology is rapidly transitioning into a new era, where a physician can no longer be just<\/em> a good clinician. They need technical thinking, at least basic data-handling skills, and a culture of collaborating with AI.<\/p>\n

    My contribution within this context<\/strong><\/h3>\n

    At ESMO AI & Digital Oncology 2025, I presented a poster titled:
    \u201cAI-Driven Immune Biomarker Classifier Predicts Clinical Benefit from Neoadjuvant Immunotherapy in Triple-Negative Breast Cancer.\u201d<\/strong><\/p>\n

    The aim of this project is to predict, in advance, which patients with triple-negative breast cancer will truly benefit from neoadjuvant immunotherapy.<\/p>\n

    The model is based on:<\/p>\n

      \n
    • \n

      multi-cohort datasets built from several international cohorts,<\/p>\n<\/li>\n

    • \n

      surrogate labels when long-term outcomes are not directly available, using surrogate data (e.g., 5-year disease-free survival, immune activity profiles),<\/p>\n<\/li>\n

    • \n

      a nested cross-validation framework to avoid overfitting and unnecessary optimization,<\/p>\n<\/li>\n

    • \n

      SHAP-based interpretation to observe which genes and immune features drive the model\u2019s decisions.<\/p>\n<\/li>\n<\/ul>\n

      The entire analytical pipeline was built using the Python ecosystem: preprocessing, modeling, interpretation, and visualization.<\/p>\n

      This research was developed at Todua Clinic, a medical institution that plays a leading role in integrating innovative approaches into daily clinical practice in Georgia. For me, this project is not merely a personal academic interest; it demonstrates that meaningful research can be created in Georgia that fits naturally onto international stages such as ESMO AI & Digital Oncology.<\/p>\n

      Insights gained from the poster discussions<\/strong><\/h3>\n

      The discussions surrounding the poster became a long-term roadmap. Conversations with experts from different countries clarified:<\/p>\n

        \n
      • \n

        where the primary strengths of the model lie,<\/p>\n<\/li>\n

      • \n

        how it can be expanded, additional clinical variables, more omics layers,<\/p>\n<\/li>\n

      • \n

        what kind of validation is needed for models like this to ultimately become part of real clinical decision-support platforms.<\/p>\n<\/li>\n<\/ul>\n

        This wasn\u2019t just a \u201cdemonstration.\u201d It was a dialogue, collaboration, and collective reflection on how to turn AI into a knowledgeable, trustworthy partner for the patient.<\/p>\n

        A personal experience<\/strong><\/h3>\n

        Attending this congress in Berlin became not only a professional but a deeply personal experience. Being physically present in the sessions, observing firsthand how oncologists, morphologists, data scientists, and engineers speak the same language,\u00a0 this cannot be replaced by a theoretical article. Only there, on site, does it become clear that clinicians increasingly need to speak at least some level of the technical language.<\/p>\n

        Even before returning to Georgia, I was already organizing my thoughts:
        What level of digital pathology development is realistic here?
        Which AI projects can we practically work on?
        What should be added to medical education so that the next generation has not only classical clinical thinking but also technically equipped vision?<\/p>\n

        To be honest, I was already quite motivated technically: programming, data analysis, bioinformatics, model explainability,\u00a0 all of this was part of my personal goals. ESMO AI & Digital Oncology 2025 added several more levels to this motivation. Now I see with much greater clarity that:<\/p>\n

          \n
        • \n

          a technically advanced doctor is no longer an \u201ceccentric exception\u201d; they must gradually become the norm;<\/p>\n<\/li>\n

        • \n

          the future oncologist\u2019s profile will require not only clinical intuition but also the ability to speak, to some degree, the language of algorithms;<\/p>\n<\/li>\n

        • \n

          active participation from Georgia in this global process is absolutely realistic, if we work systematically and purposefully.<\/p>\n<\/li>\n<\/ul>\n

          A thought to reflect on<\/strong><\/h3>\n

          Along with all of this, Isaac Asimov\u2019s words often come to mind:
          \u201cThe saddest aspect of life right now is that science gathers knowledge faster than society gathers wisdom.\u201d<\/em><\/p>\n

          This is exactly what we are seeing today in AI, digital oncology, and biomedicine: knowledge, algorithms, and models evolve at an unimaginable speed, while society, healthcare systems, and sometimes even physicians don\u2019t have enough time to turn this knowledge into wisdom, responsibility, and a culture of correct use. In these circumstances, forums like ESMO AI & Digital Oncology become especially important \u2014 they are spaces where both science and wisdom become visible simultaneously.<\/p>\n

          I returned from Berlin with a clear understanding that:
          the future of oncology and AI are inseparable;
          the technically skilled physician must become a standard;
          and Georgia is not behind in this global race, as long as we work structurally and purposefully.<\/p>\n

          To echo Clarke once more: our task is to give the \u201cmagic\u201d the right form \u2014 to make it reliable, ethical, patient-centered, and understandable to everyone.<\/p>\n

          And personally, as a future oncologist and researcher, I now know far more clearly that I don\u2019t want to be just an observer of this process. I want to be an active participant \u2014 in Georgia and in the global scientific community.<\/p>\n","protected":false},"excerpt":{"rendered":"

          David Kvaratskhelia, Oncology Resident, Todua Clinic There are moments when medical reality changes so rapidly that you feel the boundaries of your profession have expanded infinitely. For me, attending ESMO AI & Digital Oncology 2025 in Berlin was exactly that kind of experience. It wasn\u2019t just a scientific conference; it was a touchpoint with the […]<\/p>\n","protected":false},"author":9,"featured_media":9387,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[1651,1657,1659],"tags":[],"class_list":["post-9388","post","type-post","status-publish","format-standard","has-post-thumbnail","category-insight","category-science","category-technologies"],"acf":[],"_links":{"self":[{"href":"https:\/\/medscriptum.org\/en\/wp-json\/wp\/v2\/posts\/9388","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/medscriptum.org\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/medscriptum.org\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/medscriptum.org\/en\/wp-json\/wp\/v2\/users\/9"}],"replies":[{"embeddable":true,"href":"https:\/\/medscriptum.org\/en\/wp-json\/wp\/v2\/comments?post=9388"}],"version-history":[{"count":2,"href":"https:\/\/medscriptum.org\/en\/wp-json\/wp\/v2\/posts\/9388\/revisions"}],"predecessor-version":[{"id":9390,"href":"https:\/\/medscriptum.org\/en\/wp-json\/wp\/v2\/posts\/9388\/revisions\/9390"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/medscriptum.org\/en\/wp-json\/wp\/v2\/media\/9387"}],"wp:attachment":[{"href":"https:\/\/medscriptum.org\/en\/wp-json\/wp\/v2\/media?parent=9388"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/medscriptum.org\/en\/wp-json\/wp\/v2\/categories?post=9388"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/medscriptum.org\/en\/wp-json\/wp\/v2\/tags?post=9388"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}