Skip to content

Building and Testing a Small-Sample Deep Learning Model for Alzheimer's Classification Based on Cross-Population Transfer Learning

Building and Testing a Small-Sample Deep Learning Model for Alzheimer's Classification Based on Cross-Population Transfer Learning

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600127731
Enrollment
Unknown
Registered
2026-07-06
Start date
2026-07-07
Completion date
Unknown
Last updated
2026-07-13

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

Alzheimers disease

Interventions

Gold Standard:Aß-PET or plasma p-tau217
Index test:Using deep learning methods to classify diseases, the model diagnoses patient images

Sponsors

The First Affiliated Hospital of Dalian Medical University
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: 1. Patients with MCI and AD met the diagnostic criteria set by the NIA-AA of the United States in 2024. 2. The patients with normal cognition collected in the hospital had no history of diseases that affected cognitive impairment; their MMSE score was >= 27 points; and their MoCA score was >= 26 points.

Exclusion criteria

Exclusion criteria: 1.A history of external injuries, other neurological diseases, mental illnesses, or taking psychiatric medications; 2.A history of serious cardiovascular diseases like severe arrhythmia, heart failure, or extracranial/intracranial arterial stenosis; 3.The image has serious artifacts

Design outcomes

Primary

MeasureTime frame
Accuracy;Transfer Gain;

Secondary

MeasureTime frame
F1-score;Sensitivity;Specificity;Area under the receiver operating characteristic curve;Precision;

Countries

China

Contacts

Public ContactChao Yang

The second hospital of Dalian Medical University

dryangchao@163.com+86 411 8363 5963

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Jul 23, 2026