skip to main content

Search for: All records

Creators/Authors contains: "Himmelfarb, Jonathan"

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

  1. Tree-based machine learning models such as random forests, decision trees and gradient boosted trees are popular nonlinear predictive models, yet comparatively little attention has been paid to explaining their predictions. Here we improve the interpretability of tree-based models through three main contributions. (1) A polynomial time algorithm to compute optimal explanations based on game theory. (2) A new type of explanation that directly measures local feature interaction effects. (3) A new set of tools for understanding global model structure based on combining many local explanations of each prediction. We apply these tools to three medical machine learning problems and show how combining many high-quality local explanations allows us to represent global structure while retaining local faithfulness to the original model. These tools enable us to (1) identify high-magnitude but low-frequency nonlinear mortality risk factors in the US population, (2) highlight distinct population subgroups with shared risk characteristics, (3) identify nonlinear interaction effects among risk factors for chronic kidney disease and (4) monitor a machine learning model deployed in a hospital by identifying which features are degrading the model’s performance over time. Given the popularity of tree-based machine learning models, these improvements to their interpretability have implications across a broad set of domains. 
    more » « less
  2. Abstract

    Engineering functional human tissues in vitro is currently limited by difficulty replicating the small caliber, complex connectivity, cellularity, and 3D curvature of the native microvasculature. Multiphoton ablation has emerged as a promising technique for fabrication of microvascular structures with high resolution and full 3D control, but cellularization and perfusion of complex capillary‐scale structures has remained challenging. Here, multiphoton ablation combined with guided endothelial cell growth from pre‐formed microvessels is used to successfully create perfusable and cellularized organ‐specific microvascular structures at anatomic scale within collagen hydrogels. Fabrication and perfusion of model 3D pulmonary and renal microvascular beds is demonstrated, as is replication and perfusion of a brain microvascular unit derived from in vivo data. Successful endothelialization and blood perfusion of a kidney‐specific microvascular structure is achieved, using laser‐guided angiogenesis. Finally, proof‐of‐concept hierarchical blood vessels and complex multicellular models are created, using multistep patterning with multiphoton ablation techniques. These successes open new doors for the creation of engineered tissues and organ‐on‐a‐chip devices.

    more » « less