This article was originally published in
German
and has been automatically translated.
Genetic changes are the driving force behind cancers such as leukemia. Leukemias are the most common malignant diseases in children. They develop in the bone marrow and are characterized by uncontrolled, clonal growth of precursor cells of the hematopoietic system. It is particularly important for doctors to correctly interpret the wealth of data available. This has a strong influence on prognosis and treatment.
Anzeige
As reported by Informationsdienst Wissenschaft (IDW), the clinALL data integration system, which works with artificial intelligence, combines genetic and clinical data on a user-friendly platform. It allows clinical and diagnostic values to be recorded, merged and analyzed in a new way. Professor Dr. Anke K. Bergmann, Senior Consultant and Deputy Director of the Institute of Human Genetics at Hannover Medical School (MHH), is leading this project. Together with Dr. Michelle Tang and Dr. Željko Antić, Bergmann forms a team in the international Leibniz Future Laboratory for Artificial Intelligence (LeibnizAILab).
This future lab, funded by the German Federal Ministry of Education and Research and coordinated by Leibniz Universität Hannover, focuses on acute lymphoblastic leukemia (ALL) in its sub-project. Here, the participants are looking for additional diagnostic and prognostic markers for ALL in children. As part of a study, the researchers investigated the benefits of the AI tool.
AI supports routine diagnostics
The study, published open access in June 2024 by eBIOMedicine, included 1,365 patients with blood cancer, mainly cases of pediatric leukemia. The patients underwent routine genetic diagnostics with various standard tests. The research team emphasizes that the increasing volume and complexity of sequencing data represents a major challenge. Other clinical and diagnostic data, such as drug response or measurable residual disease, also complicate clinical detection. These factors make medical interpretation and diagnostics particularly challenging.
The clinALL tool provides an artificial intelligence-powered framework that integrates genomic and clinical data in a user-friendly interface. This supports routine diagnostics and provides valuable insights into malignant diseases of the blood and lymphatic system. According to the researchers, the study results directly benefit the clinical care of patients. “In this way, we were able to characterize 78 percent of patients who could not be identified using conventional methods. We have therefore helped to clarify difficult cases in particular,” says Bergmann.
Accurate diagnostics and suitable therapies
The human geneticist and head of the “AI4ALL” project at the Leibniz Future Laboratory goes on to explain that clinALL has also discovered other important patterns. Among other things, it was possible to identify certain patient groups in which the disease returns after treatment. This makes both diagnosis and therapy more precise. New cases are recognized at an early stage and new subgroups are identified. Despite the rather small number of cases in the study, the tool works reliably according to the researchers and provides important findings that have a strong influence on patient care. clinALL is now in clinical use at the MHH.
“The tool enables the integration of comprehensive clinical data with affordable, targeted genetic tests. This means clinALL is also interesting for small laboratories in developing countries, for example,” emphasizes Dr. Michelle Tang. The system is designed to improve risk assessment and decision-making in the field. It delivers clinically relevant findings in a timely manner. This represents a significant advance in medicine and treatment options for children with leukemia, according to the physician.
At the Comprehensive Cancer Center (CCC) at the MHH, scientists from various disciplines work together to research cancer, its causes and new treatment approaches. The CCC uses its many years of international experience in basic and translational research to quickly translate findings into clinical application. The study has been published on ScienceDirect.
(psz)
