Personalized medicine aims to tailor treatments to individual patients. Until now, this has been done using a small number of parameters to predict the course of a disease. However, these few parameters are often not enough to understand the complexity of diseases such as cancer.
A team of researchers from the Faculty of Medicine at the University of Duisburg-Essen (UDE), LMU Munich, and the Berlin Institute for the Foundations of Learning and Data (BIFOLD) at TU Berlin has developed a new approach to this problem using artificial intelligence.
Based on the smart hospital infrastructure at University Hospital Essen, the researchers have integrated data from different modalities—medical history, laboratory values, imaging, and genetic analyses—to support clinical decision-making.
“Although large amounts of clinical data are available in modern medicine, the promise of truly personalized medicine often remains unfulfilled,” says Prof. Jens Kleesiek from the Institute for Artificial Intelligence in Medicine (IKIM) at University Hospital Essen and the Cancer Research Center Cologne Essen (CCCE).
Interaction of 350 parameters examined
Oncological clinical practice currently uses rather rigid assessment systems, such as the classification of cancer stages, which take little account of individual differences such as sex, nutritional status, or comorbidities.
“Modern AI technologies, in particular explainable artificial intelligence (xAI), can be used to decipher these complex interrelationships and personalize cancer medicine to a much greater extent,” says Prof. Frederick Klauschen, Director of the Institute of Pathology at LMU and research group leader at BIFOLD, where this approach was developed together with Prof. Klaus-Robert Müller.
For the recent study published in Nature Cancer, the AI was trained with data from more than 15,000 patients with a total of 38 different solid tumors. The interaction of 350 parameters was examined, including clinical data, laboratory values, data from imaging procedures, and genetic tumor profiles.
“We identified key factors that account for the majority of the decision-making processes in the neural network, as well as a large number of prognostically relevant interactions between the parameters,” explains Dr. Julius Keyl, Clinician Scientist at the Institute for Artificial Intelligence in Medicine (IKIM).
Transparent decisions
The AI model was then successfully tested on the data from more than 3,000 lung cancer patients to validate the identified interactions. The AI combines the data and calculates an overall prognosis for each individual patient. As an explainable AI, the model makes its decisions transparent to clinicians by showing how each parameter contributed to the prognosis.
“Our results show the potential of artificial intelligence to look at clinical data not in isolation but in context, to re-evaluate them, and thus to enable personalized, data-driven cancer therapy,” says Dr. Philipp Keyl from LMU. An AI method like this could also be used in emergency cases where it is vital to be able to assess diagnostic parameters in their entirety as quickly as possible.
The researchers also aim to uncover complex cross-cancer interrelationships, which have remained undetected thus far using conventional statistical methods.
“At the National Center for Tumor Diseases (NCT), together with other oncological networks such as the Bavarian Center for Cancer Research (BZKF), we have the ideal conditions to take the next step: proving the real patient benefit of our technology in clinical trials,” adds Prof. Martin Schuler, Managing Director of the NCT West site and Head of the Department of Medical Oncology at University Hospital Essen.
More information:
Julius Keyl et al, Decoding pan-cancer treatment outcomes using multimodal real-world data and explainable artificial intelligence, Nature Cancer (2025). DOI: 10.1038/s43018-024-00891-1
Citation:
AI tool deciphers complex interrelationships to improve personalized cancer treatment (2025, January 30)
retrieved 30 January 2025
from https://medicalxpress.com/news/2025-01-ai-tool-deciphers-complex-interrelationships.html
This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
part may be reproduced without the written permission. The content is provided for information purposes only.
Personalized medicine aims to tailor treatments to individual patients. Until now, this has been done using a small number of parameters to predict the course of a disease. However, these few parameters are often not enough to understand the complexity of diseases such as cancer. A team of researchers from the Faculty of Medicine at the University of Duisburg-Essen (UDE), LMU Munich, and the Berlin Institute for the Foundations of Learning and Data (BIFOLD) at TU Berlin has developed a new approach to this problem using artificial intelligence. Based on the smart hospital infrastructure at University Hospital Essen, the researchers have integrated data from different modalities—medical history, laboratory values, imaging, and genetic analyses—to support clinical decision-making. “Although large amounts of clinical data are available in modern medicine, the promise of truly personalized medicine often remains unfulfilled,” says Prof. Jens Kleesiek from the Institute for Artificial Intelligence in Medicine (IKIM) at University Hospital Essen and the Cancer Research Center Cologne Essen (CCCE). Oncological clinical practice currently uses rather rigid assessment systems, such as the classification of cancer stages, which take little account of individual differences such as sex, nutritional status, or comorbidities. “Modern AI technologies, in particular explainable artificial intelligence (xAI), can be used to decipher these complex interrelationships and personalize cancer medicine to a much greater extent,” says Prof. Frederick Klauschen, Director of the Institute of Pathology at LMU and research group leader at BIFOLD, where this approach was developed together with Prof. Klaus-Robert Müller. For the recent study published in Nature Cancer, the AI was trained with data from more than 15,000 patients with a total of 38 different solid tumors. The interaction of 350 parameters was examined, including clinical data, laboratory values, data from imaging procedures, and genetic tumor profiles. “We identified key factors that account for the majority of the decision-making processes in the neural network, as well as a large number of prognostically relevant interactions between the parameters,” explains Dr. Julius Keyl, Clinician Scientist at the Institute for Artificial Intelligence in Medicine (IKIM). The AI model was then successfully tested on the data from more than 3,000 lung cancer patients to validate the identified interactions. The AI combines the data and calculates an overall prognosis for each individual patient. As an explainable AI, the model makes its decisions transparent to clinicians by showing how each parameter contributed to the prognosis. “Our results show the potential of artificial intelligence to look at clinical data not in isolation but in context, to re-evaluate them, and thus to enable personalized, data-driven cancer therapy,” says Dr. Philipp Keyl from LMU. An AI method like this could also be used in emergency cases where it is vital to be able to assess diagnostic parameters in their entirety as quickly as possible. The researchers also aim to uncover complex cross-cancer interrelationships, which have remained undetected thus far using conventional statistical methods. “At the National Center for Tumor Diseases (NCT), together with other oncological networks such as the Bavarian Center for Cancer Research (BZKF), we have the ideal conditions to take the next step: proving the real patient benefit of our technology in clinical trials,” adds Prof. Martin Schuler, Managing Director of the NCT West site and Head of the Department of Medical Oncology at University Hospital Essen. More information: Citation: This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no
Interaction of 350 parameters examined
Transparent decisions
Julius Keyl et al, Decoding pan-cancer treatment outcomes using multimodal real-world data and explainable artificial intelligence, Nature Cancer (2025). DOI: 10.1038/s43018-024-00891-1
AI tool deciphers complex interrelationships to improve personalized cancer treatment (2025, January 30)
retrieved 30 January 2025
from https://medicalxpress.com/news/2025-01-ai-tool-deciphers-complex-interrelationships.html
part may be reproduced without the written permission. The content is provided for information purposes only.
