Multiomics and artificial intelligence enabled peripheral blood-based prediction of amnestic mild cognitive impairment

Yota Tatara; Hiromi Yamazaki; Fumiki Katsuoka; Mitsuru Chiba; Daisuke Saigusa; Shuya Kasai; Tomohiro Nakamura; Jin Inoue; Yuichi Aoki; Miho Shoji; Ikuko N Motoike; Yoshinori Tamada; Katsuhito Hashizume; Mikio Shoji; Kengo Kinoshita; Koichi Murashita; Shigeyuki Nakaji; Masayuki Yamamoto; Ken Itoh

doi:10.1016/j.retram.2022.103367

Multiomics and artificial intelligence enabled peripheral blood-based prediction of amnestic mild cognitive impairment

Curr Res Transl Med. 2023 Jan-Mar;71(1):103367. doi: 10.1016/j.retram.2022.103367. Epub 2022 Oct 22.

Authors

Yota Tatara¹, Hiromi Yamazaki¹, Fumiki Katsuoka², Mitsuru Chiba³, Daisuke Saigusa², Shuya Kasai¹, Tomohiro Nakamura⁴, Jin Inoue², Yuichi Aoki², Miho Shoji⁵, Ikuko N Motoike², Yoshinori Tamada⁶, Katsuhito Hashizume⁵, Mikio Shoji⁷, Kengo Kinoshita⁸, Koichi Murashita⁹, Shigeyuki Nakaji¹⁰, Masayuki Yamamoto¹¹, Ken Itoh¹²

Affiliations

¹ Department of Stress Response Science, Center for Advanced Medical Research, Graduate School of Medicine, Hirosaki University, 5 Zaifu-cho, Hirosaki, Aomori 036-8562, Japan.
² Department of Integrative Genomics, Tohoku Medical Megabank Organization, Tohoku University, 2-1 Seiryo-Machi, Aoba-ku, Sendai, Miyagi 980-8573, Japan.
³ Department of Bioscience and Laboratory Medicine, Hirosaki University Graduate School of Health Sciences, 66-1 Hon-cho, Hirosaki, Aomori 036-8564, Japan.
⁴ Department of Preventive Medicine and Epidemiology, Tohoku Medical Megabank Organization, Tohoku University, Division of Personalized Prevention and Epidemiology, 2-1 Seiryo-Machi, Aoba-ku, Sendai, Miyagi 980-8573, Japan.
⁵ Human Metabolome Technologies, Inc., 246-2 Mizukami, Kakuganji, Tsuruoka, Yamagata 997-0052, Japan.
⁶ Innovation Center for Health Promotion, Graduate School of Medicine, Hirosaki University, 5 Zaifu-cho, Hirosaki, Aomori 036-8562, Japan.
⁷ Department of Neurology, Gunma University Hospital, 3-39-15 Showamachi, Maebashi, Gunma 371-8511, Japan; Department of Neurology, Dementia Research Center, Geriatrics Research Institute and Hospital, 3-26-8 Ootomo-machi, Maebashi, Gunma 371-0847 Japan; COI Research Initiatives Organization, Hirosaki University, 5 Zaifu-cho, Hirosaki, Aomori 036-8216, Japan.
⁸ Department of Integrative Genomics, Tohoku Medical Megabank Organization, Tohoku University, 2-1 Seiryo-Machi, Aoba-ku, Sendai, Miyagi 980-8573, Japan; Department of Applied Information Sciences, Graduate School of Information Sciences, Tohoku University, 6-6-05 Aramaki Aza Aoba, Aoba-ku, Sendai, Miyagi 980-8579, Japan; Advanced Research Center for Innovations in Next-Generation Medicine, Tohoku University, 2-1 Seiryo-machi, Aoba-ku, Sendai, Miyagi 980-8573, Japan.
⁹ COI Research Initiatives Organization, Hirosaki University, 5 Zaifu-cho, Hirosaki, Aomori 036-8216, Japan.
¹⁰ Department of Social Medicine, Hirosaki University Graduate School of Medicine, 5 Zaifu-cho, Hirosaki, Aomori 036-8216, Japan.
¹¹ Department of Integrative Genomics, Tohoku Medical Megabank Organization, Tohoku University, 2-1 Seiryo-Machi, Aoba-ku, Sendai, Miyagi 980-8573, Japan; Department of Medical Biochemistry, Graduate School of Medicine, Tohoku University, 2-1 Seiryo-Machi, Aoba-ku, Sendai, Miyagi 980-8575, Japan.
¹² Department of Stress Response Science, Center for Advanced Medical Research, Graduate School of Medicine, Hirosaki University, 5 Zaifu-cho, Hirosaki, Aomori 036-8562, Japan. Electronic address: itohk@hirosaki-u.ac.jp.

PMID: 36446162
DOI: 10.1016/j.retram.2022.103367

Abstract

Background: Since dementia is preventable with early interventions, biomarkers that assist in diagnosing early stages of dementia, such as mild cognitive impairment (MCI), are urgently needed.

Methods: Multiomics analysis of amnestic MCI (aMCI) peripheral blood (n = 25) was performed covering the transcriptome, microRNA, proteome, and metabolome. Validation analysis for microRNAs was conducted in an independent cohort (n = 12). Artificial intelligence was used to identify the most important features for predicting aMCI.

Findings: We found that hsa-miR-4455 is the best biomarker in all omics analyses. The diagnostic index taking a ratio of hsa-miR-4455 to hsa-let-7b-3p predicted aMCI patients against healthy subjects with 97% overall accuracy. An integrated review of multiomics data suggested that a subset of T cells and the GCN (general control nonderepressible) pathway are associated with aMCI.

Interpretation: The multiomics approach has enabled aMCI biomarkers with high specificity and illuminated the accompanying changes in peripheral blood. Future large-scale studies are necessary to validate candidate biomarkers for clinical use.

Keywords: Biomarker; Cohort; Metabolome; Mild cognitive impairment, Alzheimer's disease with dementia; Proteome; Regulatory T cells; Transcriptome; miRNA.

Publication types

Research Support, Non-U.S. Gov't

MeSH terms

Artificial Intelligence
Biomarkers
Cognitive Dysfunction* / diagnosis
Cognitive Dysfunction* / genetics
Cognitive Dysfunction* / psychology
Dementia*
Disease Progression
Humans
MicroRNAs*
Multiomics
Neuropsychological Tests

Substances

MicroRNAs
Biomarkers