To identify promising high-performance markers suitable for accurately diagnosing AD and prognostic stratification of at-risk populations.

Despite important advances in current biomarker research, the biology of Alzheimer's disease (AD) remains largely unknown. Expanding additional biomarkers becomes essential. Cerebrospinal fluid (CSF) proteomic profiling, possibly directly mirroring biochemical alterations in the brain, opens up a golden opportunity to investigate the above concern.

This study included 707 participants of cognitively normal, mild cognitive impairment, and AD dementia from the ADNI. CSF proteins were quantified using the SomaScan assay. Multiple linear regressions were run to identify the proteins with differential expression. Those dysregulated proteins were fed into the LGBM classifier and ranked based on their contributions to diagnosing AD. Receiver operating characteristic analyses were performed to assess the discriminative accuracies. Kaplan-Meier survival curves were constructed to evaluate the predictive performance. Enrichment analysis, Mendelian randomization, and druggability profiling were employed to depict enriched pathways, investigate causal links, and explore potential drug targets.

Among 6,361 CSF proteins, YWHAG performed best in diagnosing both biologically (area under the curve (AUC)=0.969) and clinically (AUC=0.857) defined AD. Four (YWHAG, SMOC1, PIGR, and TMOD2) and five (ACHE, YWHAG, PCSK1, MMP10, and IRF1) protein panels greatly improved the accuracy to 0.987 and 0.975, respectively. Their superior performance was validated in an independent external cohort, and in discriminating autopsy-confirmed AD versus non-AD, rivaling even canonical CSF ATN biomarkers. Moreover, they effectively predicted the clinical progression to AD dementia and were strongly associated with AD core biomarkers and cognitive decline. Synaptic, neurogenic, and infectious pathways were enriched in distinct AD stages. Mendelian randomization didn’t support the significant genetic link between CSF proteins and AD.

Our findings revealed promising high-performance biomarkers for AD diagnosis and prediction, with implications for clinical trials targeting different pathomechanisms.