Dataset Information

Software Application Profile: dynamicLM-a tool for performing dynamic risk prediction using a landmark supermodel for survival data under competing risks.

ABSTRACT:

Motivation

Providing a dynamic assessment of prognosis is essential for improved personalized medicine. The landmark model for survival data provides a potentially powerful solution to the dynamic prediction of disease progression. However, a general framework and a flexible implementation of the model that incorporates various outcomes, such as competing events, have been lacking. We present an R package, dynamicLM, a user-friendly tool for the landmark model for the dynamic prediction of survival data under competing risks, which includes various functions for data preparation, model development, prediction and evaluation of predictive performance.

Implementation

dynamicLM as an R package.

General features

The package includes options for incorporating time-varying covariates, capturing time-dependent effects of predictors and fitting a cause-specific landmark model for time-to-event data with or without competing risks. Tools for evaluating the prediction performance include time-dependent area under the ROC curve, Brier Score and calibration.

Availability

Available on GitHub [https://github.com/thehanlab/dynamicLM].

SUBMITTER: Fries AH

PROVIDER: S-EPMC10749764 | biostudies-literature | 2023 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Software Application Profile: dynamicLM-a tool for performing dynamic risk prediction using a landmark supermodel for survival data under competing risks.

Fries Anya H AH Choi Eunji E Wu Julie T JT Lee Justin H JH Ding Victoria Y VY Huang Robert J RJ Liang Su-Ying SY Wakelee Heather A HA Wilkens Lynne R LR Cheng Iona I Han Summer S SS

International journal of epidemiology 20231201 6

<h4>Motivation</h4>Providing a dynamic assessment of prognosis is essential for improved personalized medicine. The landmark model for survival data provides a potentially powerful solution to the dynamic prediction of disease progression. However, a general framework and a flexible implementation of the model that incorporates various outcomes, such as competing events, have been lacking. We present an R package, dynamicLM, a user-friendly tool for the landmark model for the dynamic prediction ...[more]

PMID: 37670428

Similar Datasets

Project description:IntroductionLength of hospital stay (LOS), defined as the time from inpatient admission to discharge, death, referral, or abscondment, is one of the key indicators of quality in patient care. Reduced LOS lowers health care expenditure and minimizes the chance of in-hospital acquired infections. Conventional methods for estimating LOS such as the Kaplan-Meier survival curve and the Cox proportional hazards regression for time to discharge cannot account for competing risks such as death, referral, and abscondment. This study applied competing risk methods to investigate factors important for risk-stratifying patients based on LOS in order to enhance patient care.MethodsThis study analyzed data from ongoing safety surveillance of the malaria vaccine implementation program in Malawi's four district hospitals of Balaka, Machinga, Mchinji, and Ntchisi. Children aged 1-59 months who were hospitalized (spending at least one night in hospital) with a medical illness were consecutively enrolled between 1 November 2019 and 31 July 2021. Sub-distribution-hazard (SDH) ratios for the cumulative incidence of discharge were estimated using the Fine-Gray competing risk model.ResultsAmong the 15,463 children hospitalized, 8,607 (55.7%) were male and 6,856 (44.3%) were female. The median age was 22 months [interquartile range (IQR): 12-33 months]. The cumulative incidence of discharge was 40% lower among HIV-positive children compared to HIV-negative (sub-distribution-hazard ratio [SDHR]: 0.60; [95% CI: 0.46-0.76]; P < 0.001); lower among children with severe and cerebral malaria [SDHR: 0.94; (95% CI: 0.86-0.97); P = 0.04], sepsis or septicemia [SDHR: 0.90; (95% CI: 0.82-0.98); P = 0.027], severe anemia related to malaria [SDHR: 0.54; (95% CI: 0.48-0.61); P < 0.001], and meningitis [SDHR: 0.18; (95% CI: 0.09-0.37); P < 0.001] when compared to non-severe malaria; and also 39% lower among malnourished children compared to those that were well-nourished [SDHR: 0.61; (95% CI: 0.55-0.68); P < 0.001].ConclusionsThis study applied the Fine-Gray competing risk approach to more accurately model LOS as the time to discharge when there were significant rates of in-hospital mortality, referrals, and abscondment. Patient care can be enhanced by risk-stratifying by LOS based on children's age, HIV status, diagnosis, and nutritional status.

Dataset Information

Software Application Profile: dynamicLM-a tool for performing dynamic risk prediction using a landmark supermodel for survival data under competing risks.

Motivation

Implementation

General features

Availability

Publications

Software Application Profile: dynamicLM-a tool for performing dynamic risk prediction using a landmark supermodel for survival data under competing risks.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets