Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Learning to Detect Sepsis with a Multitask Gaussian Process RNN Classifier
Authors: Joseph Futoma, Sanjay Hariharan, Katherine Heller
ICML 2017 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In a large cohort of heterogeneous inpatient encounters at our university health system we find that it outperforms several baselines at predicting sepsis, and yields 19.4% and 55.5% improved areas under the Receiver Operating Characteristic and Precision Recall curves as compared to the NEWS score currently used by our hospital. |
| Researcher Affiliation | Academia | 1Dept. of Statistical Science, Duke University, Durham NC, USA. Correspondence to: Joseph Futoma <EMAIL>. |
| Pseudocode | Yes | Algorithm 1 Lanczos Method to approximate Σ1/2ξ |
| Open Source Code | Yes | 1https://github.com/jfutoma/MGP-RNN |
| Open Datasets | No | Our dataset consists of 49,312 inpatient admissions from our university health system spanning 18 months, extracted directly from our EHR. |
| Dataset Splits | Yes | We train our method to 80% of the full dataset, setting aside 10% as a validation set to select hyperparameters and a final 10% for testing. |
| Hardware Specification | Yes | On a server with 63GB RAM and 12 Intel Xeon E5-2680 2.50GHz CPUs |
| Software Dependencies | No | We implemented our methods in Tensorflow1. No specific version number for TensorFlow or other software dependencies is provided. |
| Experiment Setup | Yes | We train all models using stochastic gradient descent with the ADAM optimizer (Kingma & Ba, 2015) using minibatches of 100 encounters at a time and a learning rate of 0.001. |