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.
Objective: A standardised multi-site approach to manage paediatric post-operative chylothorax does not exist and leads to unnecessary practice variation. The Chylothorax Work Group utilised the Pediatric Critical Care Consortium infrastructure to address this gap. Methods: Over 60 multi-disciplinary providers representing 22 centres convened virtually as a quality initiative to develop an algorithm to manage paediatric post-operative chylothorax. Agreement was objectively quantified for each recommendation in the algorithm by utilising an anonymous survey. “Consensus” was defined as ≥ 80% of responses as “agree” or “strongly agree” to a recommendation. In order to determine if the algorithm recommendations would be correctly interpreted in the clinical environment, we developed ex vivo simulations and surveyed patients who developed the algorithm and patients who did not. Results: The algorithm is intended for all children (<18 years of age) within 30 days of cardiac surgery. It contains rationale for 11 central chylothorax management recommendations; diagnostic criteria and evaluation, trial of fat-modified diet, stratification by volume of daily output, timing of first-line medical therapy for “low” and “high” volume patients, and timing and duration of fat-modified diet. All recommendations achieved “consensus” (agreement >80%) by the workgroup (range 81–100%). Ex vivo simulations demonstrated good understanding by developers (range 94–100%) and non-developers (73%–100%). Conclusions: The quality improvement effort represents the first multi-site algorithm for the management of paediatric post-operative chylothorax. The algorithm includes transparent and objective measures of agreement and understanding. Agreement to the algorithm recommendations was >80%, and overall understanding was 94%.
Background Ideal “cardiovascular health” (CVH)–optimal diet, exercise, nonsmoking, BMI, BP, lipids, and glucose—is associated with healthy longevity in adults. Pediatric heart transplant (HT) patients may be at risk for suboptimal CVH. Methods Single-center retrospective study of HT patients 2003–2014 who survived 1 year post-transplant. Five CVH metrics were collected at listing, 1, 3 and 5 years post-transplant (diet and exercise were unavailable). CVH was scored by summing individual metrics: ideal = 2, intermediate = 1, and poor = 0 points; total scores of 8–10 points were considered high (favorable). CVH was compared between HT patients and the US pediatric population (GP) utilizing NHANES 2007–2016. Logistic regression was performed to examine the association of CVH 1 year post-transplant with a composite adverse outcome (death, re-listing, coronary vasculopathy, or chronic kidney disease) 3 years post-transplant. Results We included 110 HT patients (median age at HT: 6 years [range 0.1–21]) and 19,081 NHANES participants. CVH scores among HT patients were generally high at listing (75%), 1 (74%), 3 (87%) and 5 (76%) years post-transplant and similar to GP, but some metrics (e.g., glucose) were worse among HT patients. Among HT patients, CVH was poorer with older age and non-Caucasian race/ethnicity. Per 1-point higher CVH score, the demographic-adjusted OR for adverse outcomes was 0.95 (95% CI, 0.7–1.4). Conclusions HT patients had generally favorable CVH, but some metrics were unfavorable and CVH varied by age and race/ethnicity. No significant association was detected between CVH and adverse outcomes in this small sample, but study in a larger sample is warranted.
No abstract
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.