Transfer Learning via Latent Factor Modeling to Improve Prediction of Surgical Complications

TL;DR

This paper introduces a transfer learning framework using latent factor models to improve prediction of surgical complications by leveraging large-scale national and institutional data, accounting for differences between datasets.

Contribution

The authors develop a hierarchical latent factor model with a scale mixture extension to effectively transfer knowledge between source and target datasets in surgical risk prediction.

Findings

Model effectively captures dependence structures in complex data.

Framework improves prediction accuracy for surgical complications.

Handles heterogeneity between different data sources.

Abstract

We aim to create a framework for transfer learning using latent factor models to learn the dependence structure between a larger source dataset and a target dataset. The methodology is motivated by our goal of building a risk-assessment model for surgery patients, using both institutional and national surgical outcomes data. The national surgical outcomes data is collected through NSQIP (National Surgery Quality Improvement Program), a database housing almost 4 million patients from over 700 different hospitals. We build a latent factor model with a hierarchical prior on the loadings matrix to appropriately account for the different covariance structure in our data. We extend this model to handle more complex relationships between the populations by deriving a scale mixture formulation using stick-breaking properties. Our model provides a transfer learning framework that utilizes all information from both the source and target data, while modeling the underlying inherent differences between them.