Dataset Information

Dynamic landmark prediction for mixture data.

ABSTRACT: In kin-cohort studies, clinicians want to provide their patients with the most current cumulative risk of death arising from a rare deleterious mutation. Estimating the cumulative risk is difficult when the genetic mutation status is unknown and only estimated probabilities of a patient having the mutation are available. We estimate the cumulative risk for this scenario using a novel nonparametric estimator that incorporates covariate information and dynamic landmark prediction. Our estimator has improved prediction accuracy over existing estimators that ignore covariate information. It is built within a dynamic landmark prediction framework whereby we can obtain personalized dynamic predictions over time. Compared to current standards, a simple transformation of our estimator provides more efficient estimates of marginal distribution functions in settings where patient-specific predictions are not the main goal. We show our estimator is unbiased and has more predictive accuracy compared to methods that ignore covariate information and landmarking. Applying our method to a Huntington disease study of mortality, we develop dynamic survival prediction curves incorporating gender and familial genetic information.

SUBMITTER: Garcia TP

PROVIDER: S-EPMC8286554 | biostudies-literature | 2021 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Dynamic landmark prediction for mixture data.

Garcia Tanya P TP Parast Layla L

Biostatistics (Oxford, England) 20210701 3

In kin-cohort studies, clinicians want to provide their patients with the most current cumulative risk of death arising from a rare deleterious mutation. Estimating the cumulative risk is difficult when the genetic mutation status is unknown and only estimated probabilities of a patient having the mutation are available. We estimate the cumulative risk for this scenario using a novel nonparametric estimator that incorporates covariate information and dynamic landmark prediction. Our estimator ha ...[more]

PMID: 31758793

Similar Datasets

Project description:BackgroundTo effectively monitor long-term outcomes among cancer patients, it is critical to accurately assess patients' dynamic prognosis, which often involves utilizing multiple data sources (e.g., tumor registries, treatment histories, and patient-reported outcomes). However, challenges arise in selecting features to predict patient outcomes from high-dimensional data, aligning longitudinal measurements from multiple sources, and evaluating dynamic model performance.MethodsWe provide a framework for dynamic risk prediction using the penalized landmark supermodel (penLM) and develop novel metrics ([Formula: see text] and [Formula: see text]) to evaluate and summarize model performance across different timepoints. Through simulations, we assess the coverage of the proposed metrics' confidence intervals under various scenarios. We applied penLM to predict the updated 5-year risk of lung cancer mortality at diagnosis and for subsequent years by combining data from SEER registries (2007-2018), Medicare claims (2007-2018), Medicare Health Outcome Survey (2006-2018), and U.S. Census (1990-2010).ResultsThe simulations confirmed valid coverage (~ 95%) of the confidence intervals of the proposed summary metrics. Of 4,670 lung cancer patients, 41.5% died from lung cancer. Using penLM, the key features to predict lung cancer mortality included long-term lung cancer treatments, minority races, regions with low education attainment or racial segregation, and various patient-reported outcomes beyond cancer staging and tumor characteristics. When evaluated using the proposed metrics, the penLM model developed using multi-source data ([Formula: see text]of 0.77 [95% confidence interval: 0.74-0.79]) outperformed those developed using single-source data ([Formula: see text]range: 0.50-0.74).ConclusionsThe proposed penLM framework with novel evaluation metrics offers effective dynamic risk prediction when leveraging high-dimensional multi-source longitudinal data.

Project description:BackgroundThe individual data collected throughout patient follow-up constitute crucial information for assessing the risk of a clinical event, and eventually for adapting a therapeutic strategy. Joint models and landmark models have been proposed to compute individual dynamic predictions from repeated measures to one or two markers. However, they hardly extend to the case where the patient history includes much more repeated markers. Our objective was thus to propose a solution for the dynamic prediction of a health event that may exploit repeated measures of a possibly large number of markers.MethodsWe combined a landmark approach extended to endogenous markers history with machine learning methods adapted to survival data. Each marker trajectory is modeled using the information collected up to the landmark time, and summary variables that best capture the individual trajectories are derived. These summaries and additional covariates are then included in different prediction methods adapted to survival data, namely regularized regressions and random survival forests, to predict the event from the landmark time. We also show how predictive tools can be combined into a superlearner. The performances are evaluated by cross-validation using estimators of Brier Score and the area under the Receiver Operating Characteristic curve adapted to censored data.ResultsWe demonstrate in a simulation study the benefits of machine learning survival methods over standard survival models, especially in the case of numerous and/or nonlinear relationships between the predictors and the event. We then applied the methodology in two prediction contexts: a clinical context with the prediction of death in primary biliary cholangitis, and a public health context with age-specific prediction of death in the general elderly population.ConclusionsOur methodology, implemented in R, enables the prediction of an event using the entire longitudinal patient history, even when the number of repeated markers is large. Although introduced with mixed models for the repeated markers and methods for a single right censored time-to-event, the technique can be used with any other appropriate modeling technique for the markers and can be easily extended to competing risks setting.

Project description:Landmark model (LM) is a dynamic prediction model that uses a longitudinal biomarker in time-to-event data to make prognosis prediction. This study was designed to improve this model and to apply it to assess the cardiovascular risk in on-treatment blood pressure patients. A frailty parameter was used in LM, landmark frailty model (LFM), to account the frailty of the patients and measure the correlation between different landmarks. The proposed model was compared with LM in different scenarios respecting data missing status, sample size (100, 200, and 400), landmarks (6, 12, 24, and 48), and failure percentage (30, 50, and 100%). Bias of parameter estimation and mean square error as well as deviance statistic between models were compared. Additionally, discrimination and calibration capability as the goodness of fit of the model were evaluated using dynamic concordance index (DCI), dynamic prediction error (DPE), and dynamic relative prediction error (DRPE). The proposed model was performed on blood pressure data, obtained from systolic blood pressure intervention trial (SPRINT), in order to calculate the cardiovascular risk. Dynpred, coxme, and coxphw packages in the R.3.4.3 software were used. It was proved that our proposed model, LFM, had a better performance than LM. Parameter estimation in LFM was closer to true values in comparison to that in LM. Deviance statistic showed that there was a statistically significant difference between the two models. In the landmark numbers 6, 12, and 24, the LFM had a higher DCI over time and the three landmarks showed better performance in discrimination. Both DPE and DRPE in LFM were lower in comparison to those in LM over time. It was indicated that LFM had better calibration in comparison to its peer. Moreover, real data showed that the structure of prognostic process was predicted better in LFM than in LM. Accordingly, it is recommended to use the LFM model for assessing cardiovascular risk due to its better performance.

Project description:BACKGROUND: Clustering is a popular data exploration technique widely used in microarray data analysis. Most conventional clustering algorithms, however, generate only one set of clusters independent of the biological context of the analysis. This is often inadequate to explore data from different biological perspectives and gain new insights. We propose a new clustering model that can generate multiple versions of different clusters from a single dataset, each of which highlights a different aspect of the given dataset. RESULTS: By applying our SigCalc algorithm to three yeast Saccharomyces cerevisiae datasets we show two results. First, we show that different sets of clusters can be generated from the same dataset using different sets of landmark genes. Each set of clusters groups genes differently and reveals new biological associations between genes that were not apparent from clustering the original microarray expression data. Second, we show that many of these new found biological associations are common across datasets. These results also provide strong evidence of a link between the choice of landmark genes and the new biological associations found in gene clusters. CONCLUSION: We have used the SigCalc algorithm to project the microarray data onto a completely new subspace whose co-ordinates are genes (called landmark genes), known to belong to a Biological Process. The projected space is not a true vector space in mathematical terms. However, we use the term subspace to refer to one of virtually infinite numbers of projected spaces that our proposed method can produce. By changing the biological process and thus the landmark genes, we can change this subspace. We have shown how clustering on this subspace reveals new, biologically meaningful clusters which were not evident in the clusters generated by conventional methods. The R scripts (source code) are freely available under the GPL license. The source code is available [see Additional File 1] as additional material, and the latest version can be obtained at http://www4.ncsu.edu/~pchopra/landmarks.html. The code is under active development to incorporate new clustering methods and analysis.

Dataset Information

Dynamic landmark prediction for mixture data.

Publications

Dynamic landmark prediction for mixture data.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets