Unique ID issued by UMIN | UMIN000051776 |
---|---|
Receipt number | R000059089 |
Scientific Title | A Retrospective Study to Explore Early Screening Indicators for AD pathology |
Date of disclosure of the study information | 2023/08/31 |
Last modified on | 2025/03/31 11:56:02 |
A Retrospective Study to Explore Early Screening Indicators for AD pathology
A Retrospective Study to Explore Early Screening Indicators for AD pathology
A Retrospective Study to Explore Early Screening Indicators for AD pathology
A Retrospective Study to Explore Early Screening Indicators for AD pathology
Japan |
Mild Cognitive impairment
Healthy adult volunteers
Neurology | Adult |
Others
NO
To identify combinations of background factors and clinical indicators useful for prescreening Amyloid-beta accumulation in the brain of patients with MCI due to AD/preclinical AD, based on subject background (age, gender, comorbidities, medical history, lifestyle, educational history, etc.) and clinical laboratory data (general blood test values, etc.) accessible to primary care doctors.
Others
Biomarker
Exploratory
Not applicable
To construct a prediction model for the presence or absence of Amyloid-beta accumulation in the brain using machine learning based on clinical information (variables) collected retrospectively, and to evaluate its prediction accuracy.
Observational
Not applicable |
Not applicable |
Male and Female
Subjects of this study are participants in Usuki Cohort (the cohort of local elderly residents in Usuki City, Oita Prefecture) and those who visited Oita University Hospital, and they meet all the following inclusion criteria.
1. MCI who fulfilled the diagnostic criteria of Petersen (CDR 0.5), or healthy adult volunteers who did not fulfill the diagnostic criteria of Petersen (CDR 0).
2. Subjects undergone amyloid PET ([11C]PiB: Pittsburgh compound-B) testing.
Subjects of this study are participants in Usuki Cohort (the cohort of local elderly residents in Usuki City, Oita Prefecture) and those who visited Oita University Hospital, and they meet all the following inclusion criteria.
1. Subjects with some missing data.
2. Subjects who have stated their willingness to participate in the research.
3. Any other subjects who are judged to be ineligible by the principal investigator or sub-investigator.
200
1st name | Noriyuki |
Middle name | |
Last name | Kimura |
Oita University Faculty of Medicine
Department of Neurology
879-5593
1-1 Idaigaoka, Hasama, Yufu, Oita 879-5593, Japan
097-586-5814
noriyuki@oita-u.ac.jp
1st name | Noriyuki |
Middle name | |
Last name | Kimura |
Oita University Faculty of Medicine
Department of Neurology
879-5593
1-1 Idaigaoka, Hasama, Yufu, Oita 879-5593, Japan
097-586-5814
noriyuki@oita-u.ac.jp
Oita University
Eisai Co., Ltd.
Profit organization
Eisai Co., Ltd.
Oita University Faculty of Medicine Ethics Committee
1-1 Idaigaoka, Hasama, Yufu, Oita 879-5593, Japan
097-586-6380
rinrikenkyu@oita-u.ac.jp
NO
大分大学医学部神経内科学講座(大分県)
エーザイ株式会社(東京都)
2023 | Year | 08 | Month | 31 | Day |
Published
https://alzres.biomedcentral.com/articles/10.1186/s13195-024-01650-1
260
The classification performance using L2-regularized logistic regression showed that Model 1 (demographic characteristics, MMSE subscores) and Model 2 (demographic characteristics, blood test results) had similar performance (ROC AUC [SD], 0.70 [0.01]). However, Model 3 (demographic characteristics, blood test results, MMSE subscores) demonstrated improved performance (ROC AUC [SD], 0.73 [0.01]). The most important variables were MMSE subscores for delayed recall and orientation place, age, TSH, and MCV.
2025 | Year | 03 | Month | 31 | Day |
2025 | Year | 01 | Month | 21 | Day |
In total, 38.5% (101/262) of participant records were amyloid-beta positive, 79.8% (209/262) had MCI (CDR = 0.5), and 20.2% (53/262) were cognitively normal (CDR = 0). The mean (SD) age was 73.8 (7.8) years, 51.9% (136/262) were male, and the mean (SD) MMSE score was 26.3 (2.4).
Of the 855 patients in the USUKI cohort and the 230 patients who visited Oita University Hospital, 703 and 71, respectively, were excluded because they did not have amyloid PiB-PET data, and 8 and 13, respectively, because they had a CDR > 0.5; additionally, 1 case in the USUKI cohort was excluded because of an MMSE score < 20, indicating dementia, and 4 in Oita University Hospital because they did not have CDR data. No participants were excluded because of a large number of missing or abnormal values. The participant with the most missing values had 11 of 34 variables missing (11 MMSE subscores). Prior to analysis, it was determined that exclusion of this participant because of the high number of missing values was not necessary. Note that out of 285, two participants overlapped across the two cohorts, and therefore the dataset screened for eligibility included 283 unique participants. The overlapping records for the two participants were treated as separate records because the PiB-PET scan dates were approximately 4 years apart between the two cohorts. Overall, 285 records of participants with MCI or normal cognitive function were screened for eligibility and 262 (260 unique participants) were included in the analysis set; 22 were excluded because there was a > 365-day period between their PiB-PET and the collection of data related to other variables, and one patient in the USUKI cohort was excluded because of missing blood test records.
The primary endpoint was the classification performance of the presence or absence of intracerebral amyloid-beta accumulation using five different machine learning models.
・ Model 0: demographic characteristics (age, sex, body mass index, years of education)
・ Model 1: Model 0 plus all MMSE subscores
・ Model 2: Model 0 plus blood test results (excluding ApoE4 phenotype) and the other demographic characteristics (medical history, current alcohol consumption, smoking status)
・ Model 3: Model 2 plus all MMSE subscores
・ Model 4: Model 3 plus ApoE4 phenotype
The true label for positive amyloid-beta accumulation, or the positive presence of intracerebral amyloid-beta accumulation, was defined as a mean PiB standardized uptake value ratio (SUVR) of 1.2 or higher.
Completed
2023 | Year | 05 | Month | 12 | Day |
2023 | Year | 06 | Month | 22 | Day |
2023 | Year | 09 | Month | 01 | Day |
2024 | Year | 04 | Month | 30 | Day |
Retrospective observational study
Condition:
(1) Healthy adult volunteers
(2) Patients with MCI due to AD/preclinical AD
Data:
(A) Usuki cohort data from October 1, 2015 to November 30, 2017 which met the eligibility criteria.
(B) Data from Oita University Hospital: Patients were seen between September 1, 2012 and November 30, 2017 and met the eligibility criteria.
Method: To construct a prediction model for the presence or absence of Amyloid-beta accumulation in the brain using machine learning based on clinical information (variables) collected retrospectively, and to evaluate its prediction accuracy.
2023 | Year | 08 | Month | 01 | Day |
2025 | Year | 03 | Month | 31 | Day |
Value
https://center6.umin.ac.jp/cgi-open-bin/ctr_e/ctr_view.cgi?recptno=R000059089