Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach
<h4>Background</h4> The COVID-19 pandemic has demonstrated the need for efficient and comprehensive, simultaneous assessment of multiple combined novel therapies for viral infection across the range of illness severity. Randomized Controlled Trials (RCT) are the gold standard by which ef...
Main Authors: | , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Public Library of Science (PLoS)
2023-01-01
|
Series: | PLoS ONE |
Online Access: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9997963/?tool=EBI |
_version_ | 1811154326983278592 |
---|---|
author | Hamidreza Moradi H. Timothy Bunnell Bradley S. Price Maryam Khodaverdi Michael T. Vest James Z. Porterfield Alfred J. Anzalone Susan L. Santangelo Wesley Kimble Jeremy Harper William B. Hillegass Sally L. Hodder |
author_facet | Hamidreza Moradi H. Timothy Bunnell Bradley S. Price Maryam Khodaverdi Michael T. Vest James Z. Porterfield Alfred J. Anzalone Susan L. Santangelo Wesley Kimble Jeremy Harper William B. Hillegass Sally L. Hodder |
author_sort | Hamidreza Moradi |
collection | DOAJ |
description | <h4>Background</h4> The COVID-19 pandemic has demonstrated the need for efficient and comprehensive, simultaneous assessment of multiple combined novel therapies for viral infection across the range of illness severity. Randomized Controlled Trials (RCT) are the gold standard by which efficacy of therapeutic agents is demonstrated. However, they rarely are designed to assess treatment combinations across all relevant subgroups. A big data approach to analyzing real-world impacts of therapies may confirm or supplement RCT evidence to further assess effectiveness of therapeutic options for rapidly evolving diseases such as COVID-19. <h4>Methods</h4> Gradient Boosted Decision Tree, Deep and Convolutional Neural Network classifiers were implemented and trained on the National COVID Cohort Collaborative (N3C) data repository to predict the patients’ outcome of death or discharge. Models leveraged the patients’ characteristics, the severity of COVID-19 at diagnosis, and the calculated proportion of days on different treatment combinations after diagnosis as features to predict the outcome. Then, the most accurate model is utilized by eXplainable Artificial Intelligence (XAI) algorithms to provide insights about the learned treatment combination impacts on the model’s final outcome prediction. <h4>Results</h4> Gradient Boosted Decision Tree classifiers present the highest prediction accuracy in identifying patient outcomes with area under the receiver operator characteristic curve of 0.90 and accuracy of 0.81 for the outcomes of death or sufficient improvement to be discharged. The resulting model predicts the treatment combinations of anticoagulants and steroids are associated with the highest probability of improvement, followed by combined anticoagulants and targeted antivirals. In contrast, monotherapies of single drugs, including use of anticoagulants without steroid or antivirals are associated with poorer outcomes. <h4>Conclusions</h4> This machine learning model by accurately predicting the mortality provides insights about the treatment combinations associated with clinical improvement in COVID-19 patients. Analysis of the model’s components suggests benefit to treatment with combination of steroids, antivirals, and anticoagulant medication. The approach also provides a framework for simultaneously evaluating multiple real-world therapeutic combinations in future research studies. |
first_indexed | 2024-04-10T04:13:53Z |
format | Article |
id | doaj.art-7ad79c3b4017475797580dfc7423f4b7 |
institution | Directory Open Access Journal |
issn | 1932-6203 |
language | English |
last_indexed | 2024-04-10T04:13:53Z |
publishDate | 2023-01-01 |
publisher | Public Library of Science (PLoS) |
record_format | Article |
series | PLoS ONE |
spelling | doaj.art-7ad79c3b4017475797580dfc7423f4b72023-03-12T05:32:23ZengPublic Library of Science (PLoS)PLoS ONE1932-62032023-01-01183Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approachHamidreza MoradiH. Timothy BunnellBradley S. PriceMaryam KhodaverdiMichael T. VestJames Z. PorterfieldAlfred J. AnzaloneSusan L. SantangeloWesley KimbleJeremy HarperWilliam B. HillegassSally L. Hodder<h4>Background</h4> The COVID-19 pandemic has demonstrated the need for efficient and comprehensive, simultaneous assessment of multiple combined novel therapies for viral infection across the range of illness severity. Randomized Controlled Trials (RCT) are the gold standard by which efficacy of therapeutic agents is demonstrated. However, they rarely are designed to assess treatment combinations across all relevant subgroups. A big data approach to analyzing real-world impacts of therapies may confirm or supplement RCT evidence to further assess effectiveness of therapeutic options for rapidly evolving diseases such as COVID-19. <h4>Methods</h4> Gradient Boosted Decision Tree, Deep and Convolutional Neural Network classifiers were implemented and trained on the National COVID Cohort Collaborative (N3C) data repository to predict the patients’ outcome of death or discharge. Models leveraged the patients’ characteristics, the severity of COVID-19 at diagnosis, and the calculated proportion of days on different treatment combinations after diagnosis as features to predict the outcome. Then, the most accurate model is utilized by eXplainable Artificial Intelligence (XAI) algorithms to provide insights about the learned treatment combination impacts on the model’s final outcome prediction. <h4>Results</h4> Gradient Boosted Decision Tree classifiers present the highest prediction accuracy in identifying patient outcomes with area under the receiver operator characteristic curve of 0.90 and accuracy of 0.81 for the outcomes of death or sufficient improvement to be discharged. The resulting model predicts the treatment combinations of anticoagulants and steroids are associated with the highest probability of improvement, followed by combined anticoagulants and targeted antivirals. In contrast, monotherapies of single drugs, including use of anticoagulants without steroid or antivirals are associated with poorer outcomes. <h4>Conclusions</h4> This machine learning model by accurately predicting the mortality provides insights about the treatment combinations associated with clinical improvement in COVID-19 patients. Analysis of the model’s components suggests benefit to treatment with combination of steroids, antivirals, and anticoagulant medication. The approach also provides a framework for simultaneously evaluating multiple real-world therapeutic combinations in future research studies.https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9997963/?tool=EBI |
spellingShingle | Hamidreza Moradi H. Timothy Bunnell Bradley S. Price Maryam Khodaverdi Michael T. Vest James Z. Porterfield Alfred J. Anzalone Susan L. Santangelo Wesley Kimble Jeremy Harper William B. Hillegass Sally L. Hodder Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach PLoS ONE |
title | Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach |
title_full | Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach |
title_fullStr | Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach |
title_full_unstemmed | Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach |
title_short | Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach |
title_sort | assessing the effects of therapeutic combinations on sars cov 2 infected patient outcomes a big data approach |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9997963/?tool=EBI |
work_keys_str_mv | AT hamidrezamoradi assessingtheeffectsoftherapeuticcombinationsonsarscov2infectedpatientoutcomesabigdataapproach AT htimothybunnell assessingtheeffectsoftherapeuticcombinationsonsarscov2infectedpatientoutcomesabigdataapproach AT bradleysprice assessingtheeffectsoftherapeuticcombinationsonsarscov2infectedpatientoutcomesabigdataapproach AT maryamkhodaverdi assessingtheeffectsoftherapeuticcombinationsonsarscov2infectedpatientoutcomesabigdataapproach AT michaeltvest assessingtheeffectsoftherapeuticcombinationsonsarscov2infectedpatientoutcomesabigdataapproach AT jameszporterfield assessingtheeffectsoftherapeuticcombinationsonsarscov2infectedpatientoutcomesabigdataapproach AT alfredjanzalone assessingtheeffectsoftherapeuticcombinationsonsarscov2infectedpatientoutcomesabigdataapproach AT susanlsantangelo assessingtheeffectsoftherapeuticcombinationsonsarscov2infectedpatientoutcomesabigdataapproach AT wesleykimble assessingtheeffectsoftherapeuticcombinationsonsarscov2infectedpatientoutcomesabigdataapproach AT jeremyharper assessingtheeffectsoftherapeuticcombinationsonsarscov2infectedpatientoutcomesabigdataapproach AT williambhillegass assessingtheeffectsoftherapeuticcombinationsonsarscov2infectedpatientoutcomesabigdataapproach AT sallylhodder assessingtheeffectsoftherapeuticcombinationsonsarscov2infectedpatientoutcomesabigdataapproach |