{"database":"biostudies-literature","file_versions":[],"scores":null,"additional":{"submitter":["Hyun N"],"funding":["Intramural NIH HHS"],"pagination":["1063-1084"],"full_dataset_link":["https://www.ebi.ac.uk/biostudies/studies/S-EPMC6586434"],"repository":["biostudies-literature"],"omics_type":["Unknown"],"volume":["11(2)"],"pubmed_abstract":["Electronic health records are a large and cost-effective data source for developing risk-prediction models. However, for screen-detected diseases, standard risk models (such as Kaplan-Meier or Cox models) do not account for key issues encountered with electronic health record data: left-censoring of pre-existing (prevalent) disease, interval-censoring of incident disease, and ambiguity of whether disease is prevalent or incident when definitive disease ascertainment is not conducted at baseline. Furthermore, researchers might conduct novel screening tests only on a complex two-phase subsample. We propose a family of weighted mixture models that account for left/interval-censoring and complex sampling via inverse-probability weighting in order to estimate current and future absolute risk: w"],"journal":["The annals of applied statistics"],"pubmed_title":["FLEXIBLE RISK PREDICTION MODELS FOR LEFT OR INTERVAL-CENSORED DATA FROM ELECTRONIC HEALTH RECORDS."],"pmcid":["PMC6586434"],"funding_grant_id":["Z99 CA999999"],"pubmed_authors":["Hyun N","Cheung LC","Katki HA","Schiffman M","Pan Q"],"additional_accession":[]},"is_claimable":false,"name":"FLEXIBLE RISK PREDICTION MODELS FOR LEFT OR INTERVAL-CENSORED DATA FROM ELECTRONIC HEALTH RECORDS.","description":"Electronic health records are a large and cost-effective data source for developing risk-prediction models. However, for screen-detected diseases, standard risk models (such as Kaplan-Meier or Cox models) do not account for key issues encountered with electronic health record data: left-censoring of pre-existing (prevalent) disease, interval-censoring of incident disease, and ambiguity of whether disease is prevalent or incident when definitive disease ascertainment is not conducted at baseline. Furthermore, researchers might conduct novel screening tests only on a complex two-phase subsample. We propose a family of weighted mixture models that account for left/interval-censoring and complex sampling via inverse-probability weighting in order to estimate current and future absolute risk: w","dates":{"release":"2017-01-01T00:00:00Z","publication":"2017 Jun","modification":"2026-05-07T16:53:04.154Z","creation":"2019-07-24T07:24:35Z"},"accession":"S-EPMC6586434","cross_references":{"pubmed":["31223347"],"doi":["10.1214/17-aoas1036","10.1214/17-AOAS1036"]}}