Comprehensive assessment of the role of spectral data pre-processing in spectroscopy-based liquid biopsy

• Published in: Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy Vol. 339; p. 126261
• Main Authors: Vrtělka, Ondřej, Králová, Kateřina, Fousková, Markéta, Setnička, Vladimír
• Format: Journal Article
• Language: English
• Published: England Elsevier B.V 15.10.2025
• Subjects: Algorithms; Carcinoma, Hepatocellular - diagnosis; Carcinoma, Hepatocellular - pathology; Chiroptical spectroscopy; Classification; Data pre-processing; Diagnostics; Humans; Least-Squares Analysis; Liquid biopsy; Liquid Biopsy - methods; Liver Cirrhosis - diagnosis; Liver Cirrhosis - pathology; Liver Neoplasms - diagnosis; Liver Neoplasms - pathology; Machine learning; Spectrophotometry, Infrared - methods; Spectrum Analysis, Raman - methods; Vibrational spectroscopy; Chiroptical spectroscopy; Diagnostics; Machine learning; Classification; Liquid biopsy; Data pre-processing; Vibrational spectroscopy

[Display omitted] •The choice of data pre-processing and classifier greatly affects classification.•The suitability of each pre-processing step depends on the data type and quality.•Certain pre-processing steps have a greater impact on classification than others.•Top pre-processing pipelines reached...