Bayesian variable selection for high dimensional predictors and self-reported outcomes

• Published in: BMC medical informatics and decision making Vol. 20; no. 1; pp. 212 - 11
• Main Authors: Gu, Xiangdong, Tadesse, Mahlet G, Foulkes, Andrea S, Ma, Yunsheng, Balasubramanian, Raji
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 07.09.2020; BioMed Central; BMC
• Subjects: African Americans; Algorithms; Bayes Theorem; Bayesian analysis; Bayesian variable selection; Clinical trials; Computer simulation; Datasets; Diabetes; Diabetes mellitus; Diabetes mellitus (non-insulin dependent); Diabetes Mellitus, Type 2 - diagnosis; Diabetes Mellitus, Type 2 - epidemiology; Diabetes Mellitus, Type 2 - genetics; Diagnostic systems; Diagnostic tests; Feature selection; Female; Generalized linear models; Health informatics; Health risks; High dimensional data; Hispanic American women; Hispanic Americans; Human papillomavirus; Humans; Laboratories; Medical errors; Minority & ethnic groups; Nucleotides; Patient Reported Outcome Measures; Pediatrics; Polymorphism, Single Nucleotide; Prospective Studies; Random variables; Self Report; Self-reports; Single nucleotide polymorphisms; Single-nucleotide polymorphism; Source code; Type 2 diabetes; Women's studies; Womens health; Self-reports; Bayesian variable selection; High dimensional data

The onset of silent diseases such as type 2 diabetes is often registered through self-report in large prospective cohorts. Self-reported outcomes are cost-effective; however, they are subject to error. Diagnosis of silent events may also occur through the use of imperfect laboratory-based diagnostic...