Alert button
Picture for Larsson Omberg

Larsson Omberg

Alert button

A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Models

Aug 02, 2022
Chao Yan, Yao Yan, Zhiyu Wan, Ziqi Zhang, Larsson Omberg, Justin Guinney, Sean D. Mooney, Bradley A. Malin

Figure 1 for A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Models
Figure 2 for A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Models
Figure 3 for A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Models
Figure 4 for A Multifaceted Benchmarking of Synthetic Electronic Health Record Generation Models
Viaarxiv icon

The NLP Sandbox: an efficient model-to-data system to enable federated and unbiased evaluation of clinical NLP models

Jun 28, 2022
Yao Yan, Thomas Yu, Kathleen Muenzen, Sijia Liu, Connor Boyle, George Koslowski, Jiaxin Zheng, Nicholas Dobbins, Clement Essien, Hongfang Liu, Larsson Omberg, Meliha Yestigen, Bradley Taylor, James A Eddy, Justin Guinney, Sean Mooney, Thomas Schaffter

Figure 1 for The NLP Sandbox: an efficient model-to-data system to enable federated and unbiased evaluation of clinical NLP models
Figure 2 for The NLP Sandbox: an efficient model-to-data system to enable federated and unbiased evaluation of clinical NLP models
Figure 3 for The NLP Sandbox: an efficient model-to-data system to enable federated and unbiased evaluation of clinical NLP models
Figure 4 for The NLP Sandbox: an efficient model-to-data system to enable federated and unbiased evaluation of clinical NLP models
Viaarxiv icon

Stable predictions for health related anticausal prediction tasks affected by selection biases: the need to deconfound the test set features

Nov 09, 2020
Elias Chaibub Neto, Phil Snyder, Solveig K Sieberts, Larsson Omberg

Figure 1 for Stable predictions for health related anticausal prediction tasks affected by selection biases: the need to deconfound the test set features
Figure 2 for Stable predictions for health related anticausal prediction tasks affected by selection biases: the need to deconfound the test set features
Viaarxiv icon