A PHP Error was encountered

Severity: 8192

Message: Non-static method URL_tube::usage() should not be called statically, assuming $this from incompatible context

Filename: url_tube/pi.url_tube.php

Line Number: 13

KDD 2020 | HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units

Accepted Papers

HOLMES: Health OnLine Model Ensemble Serving for Deep Learning Models in Intensive Care Units

Shenda Hong: Georgia Institute of Technology; Yanbo Xu: Georgia Institute of Technology; Alind Khare: Georgia Institute of Technology; Satria Priambada: Georgia Institute of Technology; Kevin Maher: Children’s Healthcare of Atlanta; Alaa Aljiffry: Children’s Healthcare of Atlanta; Jimeng Sun: University of Illinois Urbana-Champaign; Alexey Tumanov: Georgia Institute of Technology


Deep learning models have achieved expert-level performance in healthcare with an exclusive focus on training accurate models. However, in many clinical environments such as intensive care unit (ICU), real-time model serving is equally if not more important than accuracy, because in ICU patient care is simultaneously more urgent and more expensive. Clinical decisions and their timeliness, therefore, directly affect both the patient outcome and the cost of care. To make timely decisions, we argue the underlying serving system must be latency-aware. To compound the challenge, health analytic applications often require a combination of models instead of a single model, to better specialize individual models for different targets, multi-modal data, different prediction windows, and potentially personalized predictions. To address these challenges, we propose HOLMES—-an online model ensemble serving framework for healthcare applications. HOLMES dynamically identifies the best performing set of models to ensemble for highest accuracy, while also satisfying sub-second latency constraints on end-to-end prediction. We demonstrate that HOLMES is able to navigate the accuracy/latency tradeoff efficiently, compose the ensemble, and serve the model ensemble pipeline, scaling to simultaneously streaming data from 100 patients, each producing waveform data at 250~Hz. HOLMES outperforms the conventional offline batch-processed inference for the same clinical task in terms of accuracy and latency (by order of magnitude). HOLMES is tested on risk prediction task on pediatric cardio ICU data with above 95% prediction accuracy and sub-second latency on 64-bed simulation.

How can we assist you?

We'll be updating the website as information becomes available. If you have a question that requires immediate attention, please feel free to contact us. Thank you!

Please enter the word you see in the image below: