Each week, we publish lay abstracts of new articles from our prestigious portfolio of journals in statistics. The aim is to highlight the latest research to a broader audience in an accessible format.The article featured today is from Statistics in Medicine and is now available to read in full here. (OPEN ACCESS)
, , . Early detection of ovarian cancer by wavelet analysis of protein mass spectra. Statistics in Medicine. 2023; 1– 17. doi: 10.1002/sim.9722
Early and accurate detection of ovarian cancer is crucial for effective treatment. Proteomic pattern analysis is a potential method for early detection, which involves analyzing the protein patterns in serum samples to identify diagnostic patterns associated with diseased states. However, protein mass spectra are complex data structures, making it challenging to identify pathological changes using existing diagnostic techniques. This study proposes a new method that automatically searches protein mass spectra for discriminatory features in the wavelet domain. The new method characterizes self-similar behavior in a way that is robust to outliers and noise, and combines it with features from existing methods to improve diagnostic performance. The results suggest that not only the magnitude of expression levels for individual proteins, but also the interplay among protein expression levels, is critical in detecting ovarian cancer from protein mass spectra.