New findings on the predictive power of gene expression signatures in breast cancer

If a woman is diagnosed with breast cancer, the difficult question arises as to which type of treatment is the right one. In addition to other methods, doctors also use so-called gene expression tests to make a prognosis on the course of the disease and select a suitable therapy based on this. However, the reliability of these tests has not yet been fully clarified. Scientists from the University of Leipzig and the Department of Pathology Hamburg-West have now used machine learning to analyse large amounts of data on this issue and found that gene expression signatures offer a high level of prognostic certainty, but not complete certainty.

The current study by Dimitrij Tschodu, PhD student at the Peter Debye Institute for Soft Matter Physics at the University of Leipzig, was carried out in close collaboration with Prof Dr Axel Niendorf from the Department of Pathology Hamburg-West and was recently published in the renowned journal Scientific Reports. Tschodu and his colleagues analysed around 10,000 signatures based on renowned breast cancer databases using various machine learning models to thoroughly evaluate their prognostic capacity.

The study results show that the analysed gene expression signatures lead to a correct patient prognosis in no more than 80 percent of cases. The researchers also point out that prognoses based solely on gene expression signatures take into account less than 50 per cent of the potentially available information. They therefore recommend using other parameters in addition to gene expression tests. Although our results confirm the importance of gene expression signatures for predicting patient prognosis, they also emphasise the urgent need for a holistic approach that takes into account molecular, clinical, histological and other complementary factors to ensure an accurate prognosis," explains Tschodu.

Holistic approach necessary

„The results of this study are crucial for understanding the limitations of gene expression signatures in cancer prognosis,“ adds Prof Dr Josef Käs, Head of the Department of Soft Matter Physics at the University of Leipzig. „Although gene expression signatures are undoubtedly valuable, our results highlight the need for a holistic approach to make accurate predictions and informed treatment decisions." 

The publication is part of the research area „Physics of Cancer“, which looks at cancer from a physical perspective and also investigates the mechanics of cells and tissues. Käs says: „This new study underlines the importance of the ‚Physics of Cancer‘ in the medical field and the need for interdisciplinary collaboration to find innovative solutions to the challenges in cancer treatment.“ Only recently, a research group led by Prof. Käs and Prof. Niendorf published new findings from this field, which could facilitate more precise diagnosis of the spread and formation of metastases in breast tumours.

Original title of the publication in Scientific Reports: 
“Re-evaluation of publicly available gene-expression databases using machine-learning yields a maximum prognostic power in breast cancer”, doi: 10.1038/s41598-023-41090-9

Press release of the "Universität Leipzig" from 05 October 2023