Development of a machine learning model for early prediction of plasma leakage in suspected dengue patients.
Background At least a third of dengue patients develop plasma leakage with increased risk of life-threatening complications. Predicting plasma leakage using laboratory parameters obtained in early infection as means of triaging patients for hospital admission is important for resource-limited settin...
Published in: | PLOS Neglected Tropical Diseases |
---|---|
Main Authors: | , , , , , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Public Library of Science (PLoS)
2023
|
Subjects: | |
Online Access: | https://doi.org/10.1371/journal.pntd.0010758 https://doaj.org/article/2f6ace7c13724425818e57d6c7ba35d8 |
id |
ftdoajarticles:oai:doaj.org/article:2f6ace7c13724425818e57d6c7ba35d8 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:2f6ace7c13724425818e57d6c7ba35d8 2023-05-15T15:11:47+02:00 Development of a machine learning model for early prediction of plasma leakage in suspected dengue patients. Ramtin Zargari Marandi Preston Leung Chathurani Sigera Daniel Dawson Murray Praveen Weeratunga Deepika Fernando Chaturaka Rodrigo Senaka Rajapakse Cameron Ross MacPherson 2023-03-01T00:00:00Z https://doi.org/10.1371/journal.pntd.0010758 https://doaj.org/article/2f6ace7c13724425818e57d6c7ba35d8 EN eng Public Library of Science (PLoS) https://doi.org/10.1371/journal.pntd.0010758 https://doaj.org/toc/1935-2727 https://doaj.org/toc/1935-2735 1935-2727 1935-2735 doi:10.1371/journal.pntd.0010758 https://doaj.org/article/2f6ace7c13724425818e57d6c7ba35d8 PLoS Neglected Tropical Diseases, Vol 17, Iss 3, p e0010758 (2023) Arctic medicine. Tropical medicine RC955-962 Public aspects of medicine RA1-1270 article 2023 ftdoajarticles https://doi.org/10.1371/journal.pntd.0010758 2023-04-09T00:33:21Z Background At least a third of dengue patients develop plasma leakage with increased risk of life-threatening complications. Predicting plasma leakage using laboratory parameters obtained in early infection as means of triaging patients for hospital admission is important for resource-limited settings. Methods A Sri Lankan cohort including 4,768 instances of clinical data from N = 877 patients (60.3% patients with confirmed dengue infection) recorded in the first 96 hours of fever was considered. After excluding incomplete instances, the dataset was randomly split into a development and a test set with 374 (70%) and 172 (30%) patients, respectively. From the development set, five most informative features were selected using the minimum description length (MDL) algorithm. Random forest and light gradient boosting machine (LightGBM) were used to develop a classification model using the development set based on nested cross validation. An ensemble of the learners via average stacking was used as the final model to predict plasma leakage. Results Lymphocyte count, haemoglobin, haematocrit, age, and aspartate aminotransferase were the most informative features to predict plasma leakage. The final model achieved the area under the receiver operating characteristics curve, AUC = 0.80 with positive predictive value, PPV = 76.9%, negative predictive value, NPV = 72.5%, specificity = 87.9%, and sensitivity = 54.8% on the test set. Conclusion The early predictors of plasma leakage identified in this study are similar to those identified in several prior studies that used non-machine learning based methods. However, our observations strengthen the evidence base for these predictors by showing their relevance even when individual data points, missing data and non-linear associations were considered. Testing the model on different populations using these low-cost observations would identify further strengths and limitations of the presented model. Article in Journal/Newspaper Arctic Directory of Open Access Journals: DOAJ Articles Arctic PLOS Neglected Tropical Diseases 17 3 e0010758 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Arctic medicine. Tropical medicine RC955-962 Public aspects of medicine RA1-1270 |
spellingShingle |
Arctic medicine. Tropical medicine RC955-962 Public aspects of medicine RA1-1270 Ramtin Zargari Marandi Preston Leung Chathurani Sigera Daniel Dawson Murray Praveen Weeratunga Deepika Fernando Chaturaka Rodrigo Senaka Rajapakse Cameron Ross MacPherson Development of a machine learning model for early prediction of plasma leakage in suspected dengue patients. |
topic_facet |
Arctic medicine. Tropical medicine RC955-962 Public aspects of medicine RA1-1270 |
description |
Background At least a third of dengue patients develop plasma leakage with increased risk of life-threatening complications. Predicting plasma leakage using laboratory parameters obtained in early infection as means of triaging patients for hospital admission is important for resource-limited settings. Methods A Sri Lankan cohort including 4,768 instances of clinical data from N = 877 patients (60.3% patients with confirmed dengue infection) recorded in the first 96 hours of fever was considered. After excluding incomplete instances, the dataset was randomly split into a development and a test set with 374 (70%) and 172 (30%) patients, respectively. From the development set, five most informative features were selected using the minimum description length (MDL) algorithm. Random forest and light gradient boosting machine (LightGBM) were used to develop a classification model using the development set based on nested cross validation. An ensemble of the learners via average stacking was used as the final model to predict plasma leakage. Results Lymphocyte count, haemoglobin, haematocrit, age, and aspartate aminotransferase were the most informative features to predict plasma leakage. The final model achieved the area under the receiver operating characteristics curve, AUC = 0.80 with positive predictive value, PPV = 76.9%, negative predictive value, NPV = 72.5%, specificity = 87.9%, and sensitivity = 54.8% on the test set. Conclusion The early predictors of plasma leakage identified in this study are similar to those identified in several prior studies that used non-machine learning based methods. However, our observations strengthen the evidence base for these predictors by showing their relevance even when individual data points, missing data and non-linear associations were considered. Testing the model on different populations using these low-cost observations would identify further strengths and limitations of the presented model. |
format |
Article in Journal/Newspaper |
author |
Ramtin Zargari Marandi Preston Leung Chathurani Sigera Daniel Dawson Murray Praveen Weeratunga Deepika Fernando Chaturaka Rodrigo Senaka Rajapakse Cameron Ross MacPherson |
author_facet |
Ramtin Zargari Marandi Preston Leung Chathurani Sigera Daniel Dawson Murray Praveen Weeratunga Deepika Fernando Chaturaka Rodrigo Senaka Rajapakse Cameron Ross MacPherson |
author_sort |
Ramtin Zargari Marandi |
title |
Development of a machine learning model for early prediction of plasma leakage in suspected dengue patients. |
title_short |
Development of a machine learning model for early prediction of plasma leakage in suspected dengue patients. |
title_full |
Development of a machine learning model for early prediction of plasma leakage in suspected dengue patients. |
title_fullStr |
Development of a machine learning model for early prediction of plasma leakage in suspected dengue patients. |
title_full_unstemmed |
Development of a machine learning model for early prediction of plasma leakage in suspected dengue patients. |
title_sort |
development of a machine learning model for early prediction of plasma leakage in suspected dengue patients. |
publisher |
Public Library of Science (PLoS) |
publishDate |
2023 |
url |
https://doi.org/10.1371/journal.pntd.0010758 https://doaj.org/article/2f6ace7c13724425818e57d6c7ba35d8 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_source |
PLoS Neglected Tropical Diseases, Vol 17, Iss 3, p e0010758 (2023) |
op_relation |
https://doi.org/10.1371/journal.pntd.0010758 https://doaj.org/toc/1935-2727 https://doaj.org/toc/1935-2735 1935-2727 1935-2735 doi:10.1371/journal.pntd.0010758 https://doaj.org/article/2f6ace7c13724425818e57d6c7ba35d8 |
op_doi |
https://doi.org/10.1371/journal.pntd.0010758 |
container_title |
PLOS Neglected Tropical Diseases |
container_volume |
17 |
container_issue |
3 |
container_start_page |
e0010758 |
_version_ |
1766342578326732800 |