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

by   Shenda Hong, et al.

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 accuracy and sub-second latency on 64-bed simulation.


Visualizing Patient Timelines in the Intensive Care Unit

Electronic Health Records (EHRs) contain a large volume of heterogeneous...

Optimal discharge of patients from intensive care via a data-driven policy learning framework

Clinical decision support tools rooted in machine learning and optimizat...

Cocktail: Leveraging Ensemble Learning for Optimized Model Serving in Public Cloud

With a growing demand for adopting ML models for a varietyof application...

Time Aggregation and Model Interpretation for Deep Multivariate Longitudinal Patient Outcome Forecasting Systems in Chronic Ambulatory Care

Clinical data for ambulatory care, which accounts for 90 healthcare spen...

Multi-Task Prediction of Clinical Outcomes in the Intensive Care Unit using Flexible Multimodal Transformers

Recent deep learning research based on Transformer model architectures h...

BARISTA: Efficient and Scalable Serverless Serving System for Deep Learning Prediction Services

Pre-trained deep learning models are increasingly being used to offer a ...

DeepClean -- self-supervised artefact rejection for intensive care waveform data using generative deep learning

Waveform physiological data is important in the treatment of critically ...

Please sign up or login with your details

Forgot password? Click here to reset