Adaptive spatiotemporal encoding network for cognitive assessment using resting state EEG

Jingnan Sun; Anruo Shen; Yike Sun; Xiaogang Chen; Yunxia Li; Xiaorong Gao; Bai Lu

doi:10.1038/s41746-024-01384-2

Adaptive spatiotemporal encoding network for cognitive assessment using resting state EEG

NPJ Digit Med. 2024 Dec 23;7(1):375. doi: 10.1038/s41746-024-01384-2.

Authors

Jingnan Sun^{1

2}, Anruo Shen^{1

2}, Yike Sun^{1

2}, Xiaogang Chen³, Yunxia Li^{4

5

6}, Xiaorong Gao^{7

8}, Bai Lu^{9

10}

Affiliations

¹ Department of Biomedical Engineering, Tsinghua University, 100084, Beijing, China.
² IDG/McGovern Institute for Brain Research, Tsinghua University, 100084, Beijing, China.
³ Institute of Biomedical Engineering, Chinese Academy of MedicalSciences and Peking Union Medical College, Tianjin, 300192, China.
⁴ Department of Neurology, Shanghai Pudong Hospital, Fudan University Pudong Medical Center, 2800 Gongwei Road, 201339, Shanghai, China. [email protected].
⁵ Shanghai Key Laboratory of Vascular Lesions Regulation and Remodeling, 200120, Shanghai, China. [email protected].
⁶ Department of Neurology, Tongji Hospital, School of Medicine, Tongji University, 200092, Shanghai, China. [email protected].
⁷ Department of Biomedical Engineering, Tsinghua University, 100084, Beijing, China. [email protected].
⁸ IDG/McGovern Institute for Brain Research, Tsinghua University, 100084, Beijing, China. [email protected].
⁹ IDG/McGovern Institute for Brain Research, Tsinghua University, 100084, Beijing, China. [email protected].
¹⁰ School of Pharmaceutical Sciences, Tsinghua University, 100084, Beijing, China. [email protected].

Abstract

Cognitive impairment, marked by neurodegenerative damage, leads to diminished cognitive function decline. Accurate cognitive assessment is crucial for early detection and progress evaluation, yet current methods in clinical practice lack objectivity, precision, and convenience. This study included 743 participants, including healthy individuals, mild cognitive impairment (MCI), and dementia patients, with collected resting-state EEG data and cognitive scale scores. An adaptive spatiotemporal encoding framework was developed based on resting-state EEG, achieving an MAE of 3.12% (95% CI: 2.9034, 3.3975) in testing (sensitivity: 0.97, 95% CI: 0.779,1; specificity: 0.97, 95% CI: 0.779,1). The model's effectiveness was also validated on the neurofeedback (sensitivity: 0.867, 95% CI: 0.621, 0.963; specificity: 1, 95% CI: 0.439, 1.0) and TMS datasets (sensitivity: 0.833, 95% CI: 0.608, 0.942), which effectively reflect the participants' cognitive changes. The model effectively extracted repetitive spatiotemporal patterns from resting-state EEG, aiding in cognitive disease diagnosis and assessment in various scenarios.