A data-driven regional amyloid PET score predicts cognitive decline beyond Centiloid

Abstract

BackgroundThe Centiloid (CL) scale standardizes global amyloid PET quantification and is widely used to define amyloid positivity. As a global summary measure, however, CL may not fully reflect the regional distribution of amyloid deposition, which can carry additional prognostic information about the rate of cognitive decline.

ObjectiveTo develop and externally validate a fixed, regional amyloid PET composite score that complements CL for predicting cognitive decline in Alzheimers disease.

MethodsThe Regional Amyloid PET Score (RAPS) was derived from 82 FreeSurfer regions using machine learning with bootstrap stability selection to predict the rate of change in CDR-Sum of Boxes (CDR-SB) in 433 amyloid-positive ADNI [18F]florbetapir participants. The fixed nine-region weights were applied without retraining in a cross-tracer ADNI [18F]florbetaben subset (N = 71; largely overlapping the discovery participants) and two external validation cohorts, NACC SCAN (N = 1531; four tracers) and OASIS-3 (N = 428).

ResultsRAPS comprised nine regions. In ADNI, RAPS correlated more strongly with CDR-SB slope than CL and showed higher discrimination of rapid decliners (AUC 0.813 vs 0.713). Performance was directionally consistent across validation cohorts; in NACC SCAN, RAPS and CL independently predicted clinical progression. Cross-cohort meta-analysis of the three independent cohorts supported incremental discrimination beyond CL (pooled {Delta}AUC +0.066; I2 = 0%).

ConclusionsRAPS, a fixed regional amyloid PET-derived score, may complement CL for prognostic stratification in Alzheimers disease research.

CSF APOE Secondary Glycosylation Predicts Cognitive Decline in Mild Cognitive Impairment
Yang Jiao, Chao Du, Yanfei Ding +4
Biomedicines29 Sep 2026Peer-reviewedCC BYFull textGeneral medicineEurope PMC
Amyloid PET Quantitation and Centiloid Thresholds in the Diagnosis of Alzheimer Disease
Ganna Blazhenets, David N Soleimani-Meigooni, Konstantinos Chiotis +117
JAMA Cardiology13 Jul 2026Peer-reviewedLicence not stated7 citedNeuroscience Systems & synthetic biologyHAL
When Is Amyloid Really Cleared? Substantial Discordance Between Centiloid Quantification and Visual Reads of Amyloid PET after Amyloid-Targeting Therapy
R. La Joie, M. Lin, Y. Wang +16
medRxiv3 Oct 2026PreprintCC BY-NC-NDFull textMedical imaging & radiologymedRxiv
Stage-dependent associations of Cardiovascular-Kidney-Metabolic Syndrome with Cognitive Decline, Depression, and Neuroimaging Signatures in multi-regional older adults
Haoran Zhang, Yingqi Liao, Wanheng Zhang +18
medRxiv21 Oct 2026PreprintCC BY-NC-NDFull textCardiovascular medicinemedRxivPMC
Preprocedural cerebral small vessel disease burden predicts one-year cognitive decline in patients with atrial fibrillation undergoing left atrial appendage occlusion: a prediction model and mediation analysis
Zhe Wang, Liang Chen
Frontiers in Cardiovascular Medicine30 Oct 2026Peer-reviewedCC BY 4.0Cardiovascular medicineCrossref

Cite

BibTeX RIS

BibTeX

@misc{hirose2026datadriven,
  title = {{A data-driven regional amyloid PET score predicts cognitive decline beyond Centiloid}},
  author = {T. Hirose and W. Akamatsu and T. Kato},
  howpublished = {medRxiv},
  year = {2026},
  month = aug,
  doi = {10.64898/2026.08.26.26360248},
  url = {https://www.medrxiv.org/content/10.64898/2026.08.26.26360248v1},
  note = {CC BY-NC-ND},
}

RIS

TY  - UNPB
TI  - A data-driven regional amyloid PET score predicts cognitive decline beyond Centiloid
AU  - T. Hirose
AU  - W. Akamatsu
AU  - T. Kato
PY  - 2026
DA  - 2026/08/26
PB  - medRxiv
DO  - 10.64898/2026.08.26.26360248
UR  - https://www.medrxiv.org/content/10.64898/2026.08.26.26360248v1
AB  - BackgroundThe Centiloid (CL) scale standardizes global amyloid PET quantification and is widely used to define amyloid positivity. As a global summary measure, however, CL may not fully reflect the regional distribution of amyloid deposition, which can carry additional prognostic information about the rate of cognitive decline.  ObjectiveTo develop and externally validate a fixed, regional amyloid PET composite score that complements CL for predicting cognitive decline in Alzheimers disease.  MethodsThe Regional Amyloid PET Score (RAPS) was derived from 82 FreeSurfer regions using machine learning with bootstrap stability selection to predict the rate of change in CDR-Sum of Boxes (CDR-SB) in 433 amyloid-positive ADNI [18F]florbetapir participants. The fixed nine-region weights were applied without retraining in a cross-tracer ADNI [18F]florbetaben subset (N = 71; largely overlapping the discovery participants) and two external validation cohorts, NACC SCAN (N = 1531; four tracers) and OASIS-3 (N = 428).  ResultsRAPS comprised nine regions. In ADNI, RAPS correlated more strongly with CDR-SB slope than CL and showed higher discrimination of rapid decliners (AUC 0.813 vs 0.713). Performance was directionally consistent across validation cohorts; in NACC SCAN, RAPS and CL independently predicted clinical progression. Cross-cohort meta-analysis of the three independent cohorts supported incremental discrimination beyond CL (pooled {Delta}AUC +0.066; I2 = 0%).  ConclusionsRAPS, a fixed regional amyloid PET-derived score, may complement CL for prognostic stratification in Alzheimers disease research.
ER  -

Abstract

Related

Cite