 This study proposes a novel approach for analyzing FNIRS data to detect MCI. It uses Bayesian optimization-based auto hyperparameter tuning neural networks to evaluate 1D channel-wise, 2D spatial, and 3D spatiotemporal features of FNIRS measurements for detecting MCI patients. The highest test accuracies of 70.83%, 76.92%, and 80.77% were achieved for 1D, 2D, and 3D features, respectively. Through extensive comparisons, the 3D time point oxyhemoglobin feature was proven to be a more promising FNIRS feature for detecting MCI by using an FNIRS dataset of 127 participants. This study also presents a potential approach for FNIRS data processing, and the design models require no manual hyperparameter tuning, which promotes the general utilization of FNIRS modality with neural network-based classification to detect MCI. This article was authored by Chu Tianzong, Hong Junyang, Qin Chen Fan, and others. We are article.tv, links in the description below.