The damage caused by restraint stress is often subtle, which makes accurate identification challenging. This study aims to investigate the organs most sensitive to restraint stress in rats, specifically the heart, liver, spleen, lungs, kidneys, and brain, and to identify biomarkers for their damage. Additionally, the study attempts to establish a model for detecting restraint stress based on Fourier Transform Infrared (FTIR) spectroscopy and machine learning methods. Eighteen rats were selected to construct the restraint stress model, and FTIR spectroscopy was performed on tissue samples from each group of organs. Machine learning models such as Principal Component Analysis (PCA), Partial Least Squares Discriminant Analysis (PLS-DA), and Support Vector Machine (SVM) were employed to analyze the spectral data. The results indicated that the heart is the organ most sensitive to restraint stress, with Amide I being the primary biomarker for its damage, while Amide II also contributes to the identification of damage. Moreover, the combination of PCA and SVM showed the greatest potential as a diagnostic model, with precision, recall, and accuracy rates of 97.55 %, 97.50 %, and 97.50 %, respectively. This indicates that FTIR imaging is a powerful analytical tool with the potential for detecting restraint stress, offering valuable support for forensic professionals in identifying restraint stress induced damage.