Proline is an important amino acid that widely affects life activities. It plays an important role in the occurrence and development of diseases. It is of great significance to monitor the metabolism of the machine. With the great advantages of deep learning in feature extraction, near-infrared analysis technology has great potential and has been widely used in various fields. This study explored the potential application of near-infrared spectroscopy in the detection of serum proline. We collected blood samples from clinical sources, separated the serum, established a quantitative model, and determined the changes in proline. Four algorithms of SMLR, PLS, iPLS, and SA were used to model proline in serum. The root mean square errors of prediction were 0.00111, 0.00150, 0.000770, and 0.000449, and the correlation coefficients (Rp) were 0.84, 0.67, 0.91, and 0.97, respectively. The experimental results show that the model is relatively robust and has certain guiding significance for the clinical monitoring of proline. This method is expected to replace the current mainstream but time-consuming HPLC, or it can be applied to rapid online monitoring at the bedside.