• Corpus ID: 88520585

A Brief Introduction to the Temporal Group LASSO and its Potential Applications in Healthcare

@article{SaldanaMiranda2017ABI,
  title={A Brief Introduction to the Temporal Group LASSO and its Potential Applications in Healthcare},
  author={Diego Saldana Miranda},
  journal={arXiv: Machine Learning},
  year={2017}
}
The Temporal Group LASSO is an example of a multi-task, regularized regression approach for the prediction of response variables that vary over time. The aim of this work is to introduce the reader to the concepts behind the Temporal Group LASSO and its related methods, as well as to the type of potential applications in a healthcare setting that the method has. We argue that the method is attractive because of its ability to reduce overfitting, select predictors, learn smooth effect patterns… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 23 REFERENCES
Modeling disease progression via fused sparse group lasso
TLDR
Novel multi-task learning techniques to predict the disease progression measured by cognitive scores and select biomarkers predictive of the progression and performs longitudinal stability selection to identify and analyze the temporal patterns of biomarkers in disease progression are developed.
Model selection and estimation in regression with grouped variables
Summary.  We consider the problem of selecting grouped variables (factors) for accurate prediction in regression. Such a problem arises naturally in many practical situations with the multifactor
Regularization and variable selection via the elastic net
TLDR
It is shown that the elastic net often outperforms the lasso, while enjoying a similar sparsity of representation, and an algorithm called LARS‐EN is proposed for computing elastic net regularization paths efficiently, much like algorithm LARS does for the lamba.
Methods for drug safety signal detection in longitudinal observational databases: LGPS and LEOPARD
  • M. Schuemie
  • Biology
    Pharmacoepidemiology and drug safety
  • 2011
TLDR
A sequential set of methods for detecting and filtering drug safety signals in longitudinal databases is presented.
Predicting patient ‘cost blooms’ in Denmark: a longitudinal population-based study
TLDR
Comparing the ability of standard versus enhanced models to predict future high-cost patients, especially those who move from a lower to the upper decile of per capita healthcare expenditures within 1 year, shows models enhanced with a large and diverse set of features led to better performance.
A multi-task learning formulation for predicting disease progression
TLDR
This paper proposes a multi-task learning formulation for predicting the disease progression measured by the cognitive scores and selecting markers predictive of the progression and shows that most markers selected by the proposed algorithm are consistent with findings from existing cross-sectional studies.
Regression Shrinkage and Selection via the Lasso
TLDR
A new method for estimation in linear models called the lasso, which minimizes the residual sum of squares subject to the sum of the absolute value of the coefficients being less than a constant, is proposed.
Statistical learning theory for high dimensional prediction: Application to criterion-keyed scale development.
TLDR
It is concluded that despite their differences from the classic null-hypothesis testing approach-or perhaps because of them-SLT methods may hold value as a statistically rigorous approach to exploratory regression.
Structural equation modeling with longitudinal data: strategies for examining group differences and reciprocal relationships.
  • A. Farrell
  • Psychology
    Journal of consulting and clinical psychology
  • 1994
This article describes the use of structural equation modeling with latent variables to examine group differences and test competing models about cause-effect relationships in passive longitudinal
Effectively Selecting a Target Population for a Future Comparative Study
TLDR
This article shows a systematic, effective way to identify a promising population, for which the new treatment is expected to have a desired benefit, using the data from a current study involving similar comparator treatments, and proposes the best scoring system among all competing models.
...
...