Dataset Information

ACCOUNTING FOR DEPENDENT ERRORS IN PREDICTORS AND TIME-TO-EVENT OUTCOMES USING ELECTRONIC HEALTH RECORDS, VALIDATION SAMPLES, AND MULTIPLE IMPUTATION

ABSTRACT: Data from electronic health records (EHR) are prone to errors, which are often correlated across multiple variables. The error structure is further complicated when analysis variables are derived as functions of two or more error-prone variables. Such errors can substantially impact estimates, yet we are unaware of methods that simultaneously account for errors in covariates and time-to-event outcomes. Using EHR data from 4217 patients, the hazard ratio for an AIDS-defining event associated with a 100 cell/mm3 increase in CD4 count at ART initiation was 0.74 (95%CI: 0.68–0.80) using unvalidated data and 0.60 (95%CI: 0.53–0.68) using fully validated data. Our goal is to obtain unbiased and efficient estimates after validating a random subset of records. We propose fitting discrete failure time models to the validated subsample and then multiply imputing values for unvalidated records. We demonstrate how this approach simultaneously addresses dependent errors in predictors, time-to-event outcomes, and inclusion criteria. Using the fully validated dataset as a gold standard, we compare the mean squared error of our estimates with those from the unvalidated dataset and the corresponding subsample-only dataset for various subsample sizes. By incorporating reasonably sized validated subsamples and appropriate imputation models, our approach had improved estimation over both the naive analysis and the analysis using only the validation subsample.

SUBMITTER: Giganti M

PROVIDER: S-EPMC7523695 | biostudies-literature | 2020 Jun

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectiveTo create an electronic frailty index (eFRAGICAP) using electronic health records (EHR) in Catalunya (Spain) and assess its predictive validity with a two-year follow-up of the outcomes: homecare need, institutionalization and mortality in the elderly. Additionally, to assess its concurrent validity compared to other standardized measures: the Clinical Frailty Scale (CFS) and the Risk Instrument for Screening in the Community (RISC).MethodsThe eFRAGICAP was based on the electronic frailty index (eFI) developed in United Kingdom, and includes 36 deficits identified through clinical diagnoses, prescriptions, physical examinations, and questionnaires registered in the EHR of primary health care centres (PHC). All subjects > 65 assigned to a PHC in Barcelona on 1st January, 2016 were included. Subjects were classified according to their eFRAGICAP index as: fit, mild, moderate or severe frailty. Predictive validity was assessed comparing results with the following outcomes: institutionalization, homecare need, and mortality at 24 months. Concurrent validation of the eFRAGICAP was performed with a sample of subjects (n = 333) drawn from the global cohort and the CFS and RISC. Discrimination and calibration measures for the outcomes of institutionalization, homecare need, and mortality and frailty scales were calculated.Results253,684 subjects had their eFRAGICAP index calculated. Mean age was 76.3 years (59.5% women). Of these, 41.1% were classified as fit, and 32.2% as presenting mild, 18.7% moderate, and 7.9% severe frailty. The mean age of the subjects included in the validation subsample (n = 333) was 79.9 years (57.7% women). Of these, 12.6% were classified as fit, and 31.5% presented mild, 39.6% moderate, and 16.2% severe frailty. Regarding the outcome analyses, the eFRAGICAP was good in the detection of subjects who were institutionalized, required homecare assistance, or died at 24 months (c-statistic of 0.841, 0.853, and 0.803, respectively). eFRAGICAP was also good in the detection of frail subjects compared to the CFS (AUC 0.821) and the RISC (AUC 0.848).ConclusionThe eFRAGICAP has a good discriminative capacity to identify frail subjects compared to other frailty scales and predictive outcomes.

Project description:ObjectiveElectronic health records (EHR), containing detailed longitudinal clinical information on a large number of patients and covering broad patient populations, open opportunities for comprehensive predictive modeling of disease progression and treatment response. However, since EHRs were originally constructed for administrative purposes not for research, in the EHR-linked studies, it is often not feasible to capture reliable information for analytical variables, especially in the survival setting, when both accurate event status and event times are needed for model building. For example, progression-free survival (PFS), a commonly used survival outcome for cancer patients, often involves complex information embedded in free-text clinical notes and cannot be extracted reliably. Proxies of PFS time such as time to the first mention of progression in the notes are at best good approximations to the true event time. This leads to difficulty in efficiently estimating event rates for an EHR patient cohort. Estimating survival rates based on error-prone outcome definitions can lead to biased results and hamper the power in the downstream analysis. On the other hand, extracting accurate event time information via manual annotation is time and resource intensive. The objective of this study is to develop a calibrated survival rate estimator using noisy outcomes from EHR data.Materials and methodsIn this paper, we propose a two-stage semi-supervised calibration of noisy event rate (SCANER) estimator that can effectively overcome censoring induced dependency and attains more robust performance (i.e., not sensitive to misspecification of the imputation model) by fully utilizing both a small-labeled set of gold-standard survival outcomes annotated via manual chart review and a set of proxy features automatically captured via EHR in the unlabeled set. We validate the SCANER estimator by estimating the PFS rates for a virtual cohort of lung cancer patients from one large tertiary care center and the ICU-free survival rates for COVID patients from two large tertiary care centers.ResultsIn terms of survival rate estimates, the SCANER had very similar point estimates compared to the complete-case Kaplan Meier estimator. On the other hand, other benchmark methods for comparison, which fail to account for the induced dependency between event time and the censoring time conditioning on surrogate outcomes, produced biased results across all three case studies. In terms of standard errors, the SCANER estimator was more efficient than the KM estimator, with up to 50% efficiency gain.ConclusionThe SCANER estimator achieves more efficient, robust, and accurate survival rate estimates compared to existing approaches. This promising new approach can also improve the resolution (i.e., granularity of event time) by using labels conditioning on multiple surrogates, particularly among less common or poorly coded conditions.

Dataset Information

ACCOUNTING FOR DEPENDENT ERRORS IN PREDICTORS AND TIME-TO-EVENT OUTCOMES USING ELECTRONIC HEALTH RECORDS, VALIDATION SAMPLES, AND MULTIPLE IMPUTATION

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets