JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

Penalized landmark supermodels (penLM) for dynamic prediction for time-to-event outcomes in high-dimensional data

  • 0Department of Management Science and Engineering, Stanford University, Stanford, CA, 94304, USA.
Bmc Medical Research Methodology +

|

January 28, 2025

|

January 28, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

This study introduces a penalized landmark supermodel (penLM) for dynamic cancer risk prediction. The penLM framework effectively integrates diverse data sources to improve long-term outcome predictions for cancer patients.

Area Of Science

  • Oncology
  • Biostatistics
  • Health Informatics

Background

  • Accurate dynamic prognosis is crucial for monitoring cancer patient outcomes.
  • Challenges exist in feature selection, data alignment, and performance evaluation for high-dimensional longitudinal data.

Purpose Of The Study

  • To develop a framework for dynamic risk prediction using the penalized landmark supermodel (penLM).
  • To introduce novel metrics for evaluating model performance across different timepoints.
  • To apply the penLM framework to predict lung cancer mortality using multi-source data.

Main Methods

  • Utilized the penalized landmark supermodel (penLM) for dynamic risk prediction.
  • Developed novel metrics ([Formula: see text] and [Formula: see text]) for model performance evaluation.
  • Applied penLM to longitudinal data from SEER registries, Medicare claims, Medicare Health Outcome Survey, and U.S. Census for lung cancer patients.

Main Results

  • Simulations confirmed the validity of the proposed summary metrics.
  • Key predictors of lung cancer mortality included treatments, race, socioeconomic factors, and patient-reported outcomes.
  • The multi-source penLM model ([Formula: see text] = 0.77) outperformed single-source models ([Formula: see text] range: 0.50-0.74).

Conclusions

  • The penLM framework provides effective dynamic risk prediction for cancer patients.
  • Leveraging high-dimensional, multi-source longitudinal data enhances predictive accuracy.
  • Novel evaluation metrics aid in summarizing and comparing model performance.

Keywords:

Related Concept Videos

End Point Prediction: Gran Plot 01:07

265

A Gran plot is used to predict the equivalence volume or endpoint of a potentiometric or acid-base titration without reaching the endpoint. Typically, titration data is collected as a function of the titrant's volume up to a point less than the equivalence volume and then transformed into a linear format. The straight line is extended to the x-axis, indicating the necessary titrant volume to achieve the equivalence point.
For potentiometric titration, the Gran plot is created by plotting...

Prediction Intervals 01:03

2.2K

The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y. 

Regression Toward the Mean 01:52

6.3K

Regression toward the mean (“RTM”) is a phenomenon in which extremely high or low values—for example, and individual’s blood pressure at a particular moment—appear closer to a group’s average upon remeasuring. Although this statistical peculiarity is the result of random error and chance, it has been problematic across various medical, scientific, financial and psychological applications. In particular, RTM, if not taken into account, can interfere when...

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models 01:06

56

Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...

Outliers and Influential Points 01:08

4.0K

An outlier is an observation of data that does not fit the rest of the data. It is sometimes called an extreme value. When you graph an outlier, it will appear not to fit the pattern of the graph. Some outliers are due to mistakes (for example, writing down 50 instead of 500), while others may indicate that something unusual is happening. Outliers are present far from the least squares line in the vertical direction. They have large "errors," where the "error" or residual is the...

Clearance Models: Noncompartmental Models 01:17

37

Clearance is a pharmacokinetic parameter traditionally defined by compartment models, signifying the rate at which a drug is expelled from the body. However, a noncompartmental model offers an alternative method for assessing clearance, primarily employing empirical data obtained after administering a single drug dose.
The noncompartmental approach capitalizes on extensive sampling data, correlating the volume of distribution to systemic exposure and the administered dosage. This method enables...