A pragmatic approach to estimating average treatment effects from EHR data: the effect of prone positioning on mechanically ventilated COVID-19 patients

• URL: http://arxiv.org/abs/2109.06707v1
• Date: Tue, 14 Sep 2021 14:14:37 GMT
• Title: A pragmatic approach to estimating average treatment effects from EHR data: the effect of prone positioning on mechanically ventilated COVID-19 patients
• Authors: Adam Izdebski, Patrick J Thoral, Robbert C A Lalisang, Dean M McHugh, Robert Entjes, Nardo J M van der Meer, Dave A Dongelmans, Age D Boelens, Sander Rigter, Stefaan H A Hendriks, Remko de Jong, Marlijn J A Kamps, Marco Peters, A Karakus, Diederik Gommers, Dharmanand Ramnarain, Evert-Jan Wils, Sefanja Achterberg, Ralph Nowitzky, Walter van den Tempel, Cornelis P C de Jager, Fleur G C A Nooteboom, Evelien Oostdijk, Peter Koetsier, Alexander D Cornet, Auke C Reidinga, Wouter de Ruijter, Rob J Bosman, Tim Frenzel, Louise C Urlings-Strop, Paul de Jong, Ellen G M Smit, Olaf L Cremer, Frits H M van Osch, Harald J Faber, Judith Lens, Gert B Brunnekreef, Barbara Festen-Spanjer, Tom Dormans, Bram Simons, A A Rijkeboer, Annemieke Dijkstra, Sesmu Arbous, Marcel Aries, Menno Beukema, Rutger van Raalte, Martijn van Tellingen, Niels C Gritters van den Oever, Paul W G Elbers, Giovanni Cin\`a
• Abstract summary: There is no agreed upon methodology to glean treatment effect estimation from observational data. This article showcases a pragmatic methodology to obtain preliminary estimation of treatment effect from observational studies.
• Score: 29.983525001333625
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite the recent progress in the field of causal inference, to date there is no agreed upon methodology to glean treatment effect estimation from observational data. The consequence on clinical practice is that, when lacking results from a randomized trial, medical personnel is left without guidance on what seems to be effective in a real-world scenario. This article showcases a pragmatic methodology to obtain preliminary estimation of treatment effect from observational studies. Our approach was tested on the estimation of treatment effect of the proning maneuver on oxygenation levels, on a cohort of COVID-19 Intensive Care patients. We modeled our study design on a recent RCT for proning (the PROSEVA trial). Linear regression, propensity score models such as blocking and DR-IPW, BART and two versions of Counterfactual Regression were employed to provide estimates on observational data comprising first wave COVID-19 ICU patient data from 25 Dutch hospitals. 6371 data points, from 745 mechanically ventilated patients, were included in the study. Estimates for the early effect of proning -- P/F ratio from 2 to 8 hours after proning -- ranged between 14.54 and 20.11 mm Hg depending on the model. Estimates for the late effect of proning -- oxygenation from 12 to 24 hours after proning -- ranged between 13.53 and 15.26 mm Hg. All confidence interval being strictly above zero indicated that the effect of proning on oxygenation for COVID-19 patient was positive and comparable in magnitude to the effect on non COVID-19 patients. These results provide further evidence on the effectiveness of proning on the treatment of COVID-19 patients. This study, along with the accompanying open-source code, provides a blueprint for treatment effect estimation in scenarios where RCT data is lacking. Funding: SIDN fund, CovidPredict consortium, Pacmed.

Related papers

• Estimating average causal effects from patient trajectories [18.87912848546951]
  In medical practice, treatments are selected based on the expected causal effects on patient outcomes. In this paper, we aim at estimating the average causal effect (ACE) from observational data (patient trajectories) that are collected over time.
  arXiv  Detail & Related papers  (2022-03-02T16:45:19Z)
• Disentangled Counterfactual Recurrent Networks for Treatment Effect Inference over Time [71.30985926640659]
  We introduce the Disentangled Counterfactual Recurrent Network (DCRN), a sequence-to-sequence architecture that estimates treatment outcomes over time. With an architecture that is completely inspired by the causal structure of treatment influence over time, we advance forecast accuracy and disease understanding. We demonstrate that DCRN outperforms current state-of-the-art methods in forecasting treatment responses, on both real and simulated data.
  arXiv  Detail & Related papers  (2021-12-07T16:40:28Z)
• Development and Validation of a Deep Learning Model for Prediction of Severe Outcomes in Suspected COVID-19 Infection [9.524156465126758]
  COVID-19 patient triaging with predictive outcome of the patients upon first present to emergency department (ED) is crucial for improving patient prognosis. We trained a deep feature fusion model to predict patient outcomes. Model output was patient outcomes defined as the most insensitive oxygen therapy required. Predictive risk scores for COVID-19 severe outcomes ("CO-RISK" score) were derived from model output and evaluated on the testing dataset.
  arXiv  Detail & Related papers  (2021-03-21T00:03:27Z)
• CDSM -- Casual Inference using Deep Bayesian Dynamic Survival Models [3.9169188005935927]
  We have developed a causal dynamic survival model (CDSM) that uses the potential outcomes framework with the Bayesian recurrent sub-networks to estimate the difference in survival curves. Using simulated survival datasets, CDSM has shown good causal effect estimation performance across scenarios of sample dimension, event rate, confounding and overlapping.
  arXiv  Detail & Related papers  (2021-01-26T09:15:49Z)
• Increasing the efficiency of randomized trial estimates via linear adjustment for a prognostic score [59.75318183140857]
  Estimating causal effects from randomized experiments is central to clinical research. Most methods for historical borrowing achieve reductions in variance by sacrificing strict type-I error rate control.
  arXiv  Detail & Related papers  (2020-12-17T21:10:10Z)
• Individualized Prediction of COVID-19 Adverse outcomes with MLHO [9.197411456718708]
  We developed an end-to-end Machine Learning framework that leverages iterative feature and algorithm selection to predict Health outcomes. We modeled the four adverse outcomes utilizing about 600 features representing patients' pre-COVID health records and demographics. Our results demonstrated that while demographic variables are important predictors of adverse outcomes after a COVID-19 infection, the incorporation of the past clinical records are vital for a reliable prediction model.
  arXiv  Detail & Related papers  (2020-08-10T02:44:52Z)
• Integrative Analysis for COVID-19 Patient Outcome Prediction [53.11258640541513]
  We combine radiomics of lung opacities and non-imaging features from demographic data, vital signs, and laboratory findings to predict need for intensive care unit admission. Our methods may also be applied to other lung diseases including but not limited to community acquired pneumonia.
  arXiv  Detail & Related papers  (2020-07-20T19:08:50Z)
• Enabling Counterfactual Survival Analysis with Balanced Representations [64.17342727357618]
  Survival data are frequently encountered across diverse medical applications, i.e., drug development, risk profiling, and clinical trials. We propose a theoretically grounded unified framework for counterfactual inference applicable to survival outcomes.
  arXiv  Detail & Related papers  (2020-06-14T01:15:00Z)
• Predicting COVID-19 Pneumonia Severity on Chest X-ray with Deep Learning [57.00601760750389]
  We present a severity score prediction model for COVID-19 pneumonia for frontal chest X-ray images. Such a tool can gauge severity of COVID-19 lung infections that can be used for escalation or de-escalation of care.
  arXiv  Detail & Related papers  (2020-05-24T23:13:16Z)
• Joint Prediction and Time Estimation of COVID-19 Developing Severe Symptoms using Chest CT Scan [49.209225484926634]
  We propose a joint classification and regression method to determine whether the patient would develop severe symptoms in the later time. To do this, the proposed method takes into account 1) the weight for each sample to reduce the outliers' influence and explore the problem of imbalance classification. Our proposed method yields 76.97% of accuracy for predicting the severe cases, 0.524 of the correlation coefficient, and 0.55 days difference for the converted time.
  arXiv  Detail & Related papers  (2020-05-07T12:16:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.