ASN's Mission

To create a world without kidney diseases, the ASN Alliance for Kidney Health elevates care by educating and informing, driving breakthroughs and innovation, and advocating for policies that create transformative changes in kidney medicine throughout the world.

learn more

Contact ASN

1401 H St, NW, Ste 900, Washington, DC 20005

email@asn-online.org

202-640-4660

The Latest on Twitter

Kidney Week

Abstract: TH-PO477

Assessing the Form of Predictor-Outcome Association for Machine Learning Models of Patient-Reported Outcomes in Nephrotic Syndrome

Session Information

Category: Glomerular Diseases

  • 1303 Glomerular Diseases: Clinical‚ Outcomes‚ and Trials

Authors

  • Rubin, Jeremy, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, United States
  • Mariani, Laura H., University of Michigan Michigan Medicine, Ann Arbor, Michigan, United States
  • Smith, Abigail R., Arbor Research Collaborative for Health, Ann Arbor, Michigan, United States
  • Zee, Jarcy, University of Pennsylvania Perelman School of Medicine, Philadelphia, Pennsylvania, United States
Background

Penalized regression models can be used to identify and rank risk factors for poor quality of life, but they often assume covariates have linear associations with the outcome. There is no standard, automated method for determining the optimal functional forms (shapes of relationships) between predictors and the outcome in high-dimensional data settings.

Methods

We propose a novel algorithm, Ridge regression for functional form Identification of continuous Predictors (RIP), that models each continuous covariate with linear, quadratic, quartile, and cubic spline basis components in a ridge regression model to capture potential nonlinear relationships between continuous predictors and outcomes. We used a simulation study to test the performance of RIP compared to standard and spline ridge regression models. Then, we applied RIP to identify top predictors of baseline Patient-Reported Outcomes Measurement Information System (PROMIS) adult global mental and physical health scores using demographic and clinical characteristics among N=107 glomerular disease patients enrolled in the Nephrotic Syndrome Study Network (NEPTUNE).

Results

RIP resulted in better predictive accuracy in 56-80% of simulation repetitions under a variety of data characteristics. When applied to the PROMIS scores in NEPTUNE, RIP resulted in the lowest error for predicting physical scores, but the highest error for the mental scores. Further, RIP identified functional forms of top predictors of the physical scores that were missed by the other models [Figure 1].

Conclusion

The RIP algorithm can capture nonlinear functional forms of predictors that are missed by standard ridge regression models. The top predictors of PROMIS scores vary greatly across methods. RIP should be considered alongside other machine learning models in the prediction of patient-reported outcomes.

For the RIP algorithm, functional forms per predictor are given in parentheses by the predictor name. Num of times are past 6 mos.