Skip to main content
Dryad logo

Data from: ClinicNet: machine learning for personalized order set recommendations

Citation

Wang, Jonathan; Sullivan, Delaney; Wells, Alex; Chen, Jonathan (2020), Data from: ClinicNet: machine learning for personalized order set recommendations, Dryad, Dataset, https://doi.org/10.5061/dryad.msbcc2fvm

Abstract

Objective

This study assesses whether neural networks trained on electronic health record (EHR) data can anticipate what individual clinical orders and existing institutional order set templates clinicians will use more accurately than existing decision support tools.

Materials and Methods

We process 57,624 patients-worth of clinical event EHR data from 2008-2014. We train a feed-forward neural network (ClinicNet) and logistic regression applied to the traditional problem structure of predicting individual clinical items  as well as our proposed workflow of predicting existing institutional order set template usage.

Results

ClinicNet predicts individual clinical orders (precision=0.32, recall=0.47) better than existing institutional order sets (precision=0.15, recall=0.46). The ClinicNet model predicts clinician usage of existing institutional order sets (avg. precision=0.31) with higher average precision than  a baseline of order set usage frequencies (avg. precision=0.20) or a logistic regression model (avg. precision=0.12).

Discussion

Machine learning methods can predict clinical decision-making patterns with greater accuracy and less manual effort than existing static order set templates. This can streamline existing clinical workflows, but may not fit if historical clinical ordering practices are incorrect. For this reason, manually authored content such as order set templates remain valuable for purposeful design of care pathways. ClinicNet’s capability of predicting such personalized order set templates illustrates the potential of combining both top-down and bottom-up approaches to delivering clinical decision support content.

Conclusion

ClinicNet illustrates the capability for machine learning methods applied to the EHR to anticipate both individual clinical orders and existing order set templates, which has the potential to improve upon current standards of practice in clinical order entry.

Methods

See manuscript Methods section.

Usage Notes

See README file

 

Files that end in .pkl are pickle files, they can be loaded using Python's pickle module (see pickle module documentation).

Files that end in .h5 are hdf5 files, they can be loaded using Python's h5py module (see h5py module documentation).  

Example for loading .h5 files:

h5f = h5py.File(filename, 'r')

data = h5f['key'].value
h5f.close()

Funding

National Institute of Environmental Health Sciences, Award: K01ES026837

Betty Moore Foundation, Award: GBMF8040

Stanford Human-Centered Artificial Intelligence Seed Grant

Stanford Undergraduate Advising and Research Grant

Stanford Human-Centered Artificial Intelligence Seed Grant

Stanford Undergraduate Advising and Research Grant