Personalized medicine aims to tailor treatment 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-Sessen (Ude), Lmu Munich, and the Berlin Institute for the Foundations of Learning and Data (Bifold) at Tu Berlin has been found This problem using artificial Intelligence.

Based on the Smart Hospital Infrastructure At University Essen, The Researchers have integrated data from different modalities – deedical history, laberatory Values, Igentic Analysis t clinical decision-making.

“Although Large Amounts of Clinical Data are available in Modern Medicine, The Promise of truly personalized medicine often remains unfined,” 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 RITHER RIGID Assessment Systems, Such as the Classification of Cancer Stages, Which Take Little Account of Individual Defirenace SEX, Nuttus, Or Comorbidities.

“Modern Ai Technologies, In Particular Explainable Artificial Intelligence (XAI), Can Be Used To Decipher these Complex InterralationShips and Personalize Cancer Medicine to a Much Great Great,” Says Prof. Frederick Klauschen, Director of the Institute of Pathology at Lmu and Research Group Leader at Bifold, where this approach was developed togeether with Prof. Klaus-robert müller.

For the recent study Published in Nature cancerThe 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 procedus, and genetic tumor profiles.

“We identified key factors that account for the decision-making processes in the neural network, as well as a large number of prognostically related to related to the PARAMETERS,” . 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 program for Each Individual Patient. As an explainable ai, the model makes its decisions transparent to clinicians by showing how Eve each parameter contributed to the program.

“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 perceonalized, data-driven cancer therapy,” Philipp keyl from lmu. An AI Method like this also be used in emergency cases where it is vital to be able to assess diagnostic parameters in their entryty 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 fit of our technology in clinical Trials, “Adds Prof. Martin Schler, Managing Director of the NCT West Site and Head of the Department of Medical Oncology at University Hospital Essen.