Prediction of Proliferation Rate of Pre‐Osteoblasts Using Raman Spectroscopy and Machine Learning Models

ABSTRACT This novel study focuses on using Raman spectroscopy and machine learning (ML) models to forecast the murine pre‐osteoblast (OB) proliferation rate. The proliferating behavior of pre‐OBs was analyzed using Raman spectroscopy for the cellular biomarkers in the fingerprint region between 400 and 1700 cm −1 for different lengths of time, Days 7, 10, and 14. Key Raman bands included Phenylalanine at 1003 cm −1 , DNA purine bases at 1335 cm −1 , glycosaminoglycans (GAG) at 1375 cm −1 , lipids at 1450 cm −1 , DNA at 1585 cm −1 , and Amide I at 1605 cm −1 . Principal component analysis (PCA) was used to find significant spectral features linked to temporal fluctuations. Identification of prospective biomarkers was made possible by the correlation between the strength of these features and the proliferation rate as determined by the biochemical assay, water‐soluble tetrazolium‐1 (WST‐1) assay. Using pre‐OBs–specific Raman spectral characteristics and accompanying proliferation rates, ML models were created. Model performance was judged using accuracy, the mean squared error (MSE), and R ‐squared metrics. The algorithms used included random forest, support vector machine (SVM), and ridge regression. Results showed that ML could accurately forecast the proliferation of pre‐OBs, with identified Raman peaks acting as potential indications. This study adds to our understanding of pre‐OB cellular dynamics and offers valuable information for bone tissue regeneration applications. It also presents a novel method for forecasting cell proliferation rates using Raman spectroscopy along with quantitative biochemical assay data and ML, opening the door to individualized cell therapies and better patient outcomes.