In the dementia area it is often of interest to study relationships among regional brain measures; however, it is often necessary to adjust for covariates. Partial correlations are frequently used to correlate two variables while adjusting for other variables. Complete case analysis is typically the analysis of choice for partial correlations with missing data. However, complete case analysis will lead to biased and inefficient results when the data are missing at random. We have extended the partial correlation coefficient in the presence of missing data using the expectation-maximization (EM) algorithm, and compared it with a multiple imputation method and complete case analysis using simulation studies. The EM approach performed the best of all methods with multiple imputation performing almost as well. These methods were illustrated with regional imaging data from an Alzheimer's disease study.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3772686 | PMC |
| http://dx.doi.org/10.4172/2155-6180.1000155 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Rapid and accurate multi-phenotype imputation for millions of individuals.
Nat Commun
January 2025
Key Laboratory of Healthy Mariculture for the East China Sea, Ministry of Agriculture and Rural Affairs & Fisheries college, Jimei University, Xiamen, Fujian, People's Republic of China.
Deep phenotyping can enhance the power of genetic analysis, including genome-wide association studies (GWAS), but the occurrence of missing phenotypes compromises the potential of such resources. Although many phenotypic imputation methods have been developed, the accurate imputation of millions of individuals remains challenging. In the present study, we have developed a multi-phenotype imputation method based on mixed fast random forest (PIXANT) by leveraging efficient machine learning (ML)-based algorithms.
View Article and Find Full Text PDFA foundation model with weak experiential guidance in detecting muscle invasive bladder cancer on MRI.
Cancer Lett
January 2025
Department of Radiology, the First Affiliated Hospital of Nanjing Medical University, Nanjing, Jiangsu Province, P.R. China, 210029; The Affiliated Suqian First People's Hospital of Nanjing Medical University, Suqian, Jiangsu Province, China. Electronic address:
Preoperative detection of muscle-invasive bladder cancer (MIBC) remains a great challenge in practice. We aimed to develop and validate a deep Vesical Imaging Network (ViNet) model for the detection of MIBC using high-resolution Tweighted MR imaging (hrTWI) in a multicenter cohort. ViNet was designed using a modified 3D ResNet, in which, the encoder layers were pretrained using a self-supervised foundation model on over 40,000 cross-modal imaging datasets for transfer learning, and the classification modules were weakly supervised by an experiential knowledge-domain mask indicated by a nnUNet segmentation model.
View Article and Find Full Text PDFPIRADS 3 MRI lesions: are biopsies still necessary?
Fr J Urol
January 2025
Department of Urology, North Hospital, AP-HM, Marseille, France.
Introduction: A significant proportion of newly diagnosed prostate cancer (PCa) cases are slow growing with a low risk of metastatic progression. There is a lack of data concerning the optimal biopsy regimen for improving diagnosis yield in PI-RADS3 lesions. This study aimed to assess the diagnostic value of current biopsy regimens in PI-RADS 3 lesions and identify clinical predictors to improve clinically significant PCa (csPCa) detection.
View Article and Find Full Text PDFPredicting the likelihood of readmission in patients with ischemic stroke: An explainable machine learning approach using common data model data.
Int J Med Inform
December 2024
Department of Health Policy and Management, School of Medicine, Kangwon National University, 510 School of Medicine Building #1 (N414), 1, Kangwondaehak-gil, Chuncheon-si, Gangwon-do 24341, Republic of Korea; Department of Preventive Medicine, Kangwon National University Hospital, 156 Baengnyeong-ro, Chuncheon-si, Gangwon-do 24289, Republic of Korea; Team of Public Medical Policy Development, Gangwon State Research Institute for People's Health, 880 Baksa-ro, Seo-myeon, Chuncheon-si, Gangwon-do 24461, Republic of Korea. Electronic address:
Background: Ischemic stroke affects 15 million people worldwide, causing five million deaths annually. Despite declining mortality rates, stroke incidence and readmission risks remain high, highlighting the need for preventing readmission to improve the quality of life of survivors. This study developed a machine-learning model to predict 90-day stroke readmission using electronic medical records converted to the common data model (CDM) from the Regional Accountable Care Hospital in Gangwon state in South Korea.
View Article and Find Full Text PDFNoise power properties of a cone-beam CT scanner with unconventional scanning geometry.
Phys Med
January 2025
Department of Physics "A. Pontremoli", University of Milan & INFN sez. Milano, Milano, Italy. Electronic address:
Purpose: This work aims at investigating, via in-silico evaluations, the noise properties of an innovative scanning geometry in cone-beam CT (CBCT): eCT. This scanning geometry substitutes each of the projections in CBCT with a series of collimated projections acquired over an oscillating scanning trajectory. The analysis focused on the impact of the number of the projections per period (PP) on the noise characteristics.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!