Machine Learning for Community-Acquired Pneumonia Diagnosis Using Routine Clinical and Laboratory Data

Background: Community-acquired pneumonia (CAP) is diagnosed based on clinical information, laboratory tests, and chest imaging. However, chest radiography is often inaccessible in primary care, causing variability in clinical diagnosis. This study aims to develop a machine learning model to diagnose...

Full description

Saved in:
Bibliographic Details
Main Authors: Sung Yoon Lim, Eunhye Cho, Bokhee Jung, Jaeyeon Lee, Miyoung Kim, Sooyoung Yoo, Seyoung Jung, Joon Yhup Lee, Sejin Nam, Hyunju Lee, Eu Suk Kim
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Journal of Global Antimicrobial Resistance
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2213716524004090
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850251819142348800
author Sung Yoon Lim
Eunhye Cho
Bokhee Jung
Jaeyeon Lee
Miyoung Kim
Sooyoung Yoo
Seyoung Jung
Joon Yhup Lee
Sejin Nam
Hyunju Lee
Eu Suk Kim
author_facet Sung Yoon Lim
Eunhye Cho
Bokhee Jung
Jaeyeon Lee
Miyoung Kim
Sooyoung Yoo
Seyoung Jung
Joon Yhup Lee
Sejin Nam
Hyunju Lee
Eu Suk Kim
author_sort Sung Yoon Lim
collection DOAJ
description Background: Community-acquired pneumonia (CAP) is diagnosed based on clinical information, laboratory tests, and chest imaging. However, chest radiography is often inaccessible in primary care, causing variability in clinical diagnosis. This study aims to develop a machine learning model to diagnose CAP using only clinical and laboratory data. METHODS: This study included patients who presented with fever and respiratory symptoms to the outpatient clinic or emergency room of a tertiary care center between 2009 and 2018. A total of 10,707 adult patients were randomly divided into training (70%) and test (30%) sets. We analyzed the model for internal validation on 1,364 patients who visited the same institution between August 2019 and December 2020.The performance of the machine-learning models was measured using the area under the receiver operating characteristic curve (AUROC). RESULTS: Among the algorithms tested, eXtreme Gradient Boosting (XGBOOST) achieved the highest AUROC (0.936, 95% CI: 0.924-0.947), followed by the gradient boost (0.931, 95% CI: 0.919-0.943) and random forest (0.926, 95% CI: 0.912-0.938) models in the test set. The most significant independent variables for diagnosing pneumonia were the presence of cough, crackle lung sounds, and CRP levels. In the validation set, XGBOOST achieved an AUC of 0.919 (95% CI: 0.886-0.933), with a sensitivity of 82.30%, specificity of 88.92%, and accuracy of 87.90%. CONCLUSIONS: The machine learning model accurately diagnosed community-acquired pneumonia, indicating its potential to assist in primary care settings without relying on chest imaging.
format Article
id doaj-art-daa7163bed0849c2ba3c98965441c4e7
institution OA Journals
issn 2213-7165
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Journal of Global Antimicrobial Resistance
spelling doaj-art-daa7163bed0849c2ba3c98965441c4e72025-08-20T01:57:48ZengElsevierJournal of Global Antimicrobial Resistance2213-71652024-12-01397210.1016/j.jgar.2024.10.232Machine Learning for Community-Acquired Pneumonia Diagnosis Using Routine Clinical and Laboratory DataSung Yoon Lim0Eunhye Cho1Bokhee Jung2Jaeyeon Lee3Miyoung Kim4Sooyoung Yoo5Seyoung Jung6Joon Yhup Lee7Sejin Nam8Hyunju Lee9Eu Suk Kim10Division of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Seoul National University College of Medicine, Seoul National University Bundang Hospital, Seongnam, South KoreaDivision of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Seoul National University College of Medicine, Seoul National University Bundang Hospital, Seongnam, South KoreaDivision of Pulmonary and Critical Care Medicine, Department of Internal Medicine, Seoul National University College of Medicine, Seoul National University Bundang Hospital, Seongnam, South KoreaOffice of eHealth Research and Businesses, Seoul National University Bundang Hospital, Seongnam, Republic of KoreaOffice of eHealth Research and Businesses, Seoul National University Bundang Hospital, Seongnam, Republic of KoreaOffice of eHealth Research and Businesses, Seoul National University Bundang Hospital, Seongnam, Republic of KoreaOffice of eHealth Research and Businesses, Seoul National University Bundang Hospital, Seongnam, Republic of KoreaR&D Center, ezCaretech Co., Ltd, Republic of KoreaR&D Center, ezCaretech Co., Ltd, Republic of KoreaDepartment of Pediatrics, Seoul National University Bundang Hospital and Seoul National University College of Medicine, Seongnam, Republic of KoreaDivisions of Infectious disease, Department of Internal medicine, Seoul National University College of Medicine, Seoul National University Bundang Hospital, Seongnam, South KoreaBackground: Community-acquired pneumonia (CAP) is diagnosed based on clinical information, laboratory tests, and chest imaging. However, chest radiography is often inaccessible in primary care, causing variability in clinical diagnosis. This study aims to develop a machine learning model to diagnose CAP using only clinical and laboratory data. METHODS: This study included patients who presented with fever and respiratory symptoms to the outpatient clinic or emergency room of a tertiary care center between 2009 and 2018. A total of 10,707 adult patients were randomly divided into training (70%) and test (30%) sets. We analyzed the model for internal validation on 1,364 patients who visited the same institution between August 2019 and December 2020.The performance of the machine-learning models was measured using the area under the receiver operating characteristic curve (AUROC). RESULTS: Among the algorithms tested, eXtreme Gradient Boosting (XGBOOST) achieved the highest AUROC (0.936, 95% CI: 0.924-0.947), followed by the gradient boost (0.931, 95% CI: 0.919-0.943) and random forest (0.926, 95% CI: 0.912-0.938) models in the test set. The most significant independent variables for diagnosing pneumonia were the presence of cough, crackle lung sounds, and CRP levels. In the validation set, XGBOOST achieved an AUC of 0.919 (95% CI: 0.886-0.933), with a sensitivity of 82.30%, specificity of 88.92%, and accuracy of 87.90%. CONCLUSIONS: The machine learning model accurately diagnosed community-acquired pneumonia, indicating its potential to assist in primary care settings without relying on chest imaging.http://www.sciencedirect.com/science/article/pii/S2213716524004090PneumoniaDiagnosisMachine learning
spellingShingle Sung Yoon Lim
Eunhye Cho
Bokhee Jung
Jaeyeon Lee
Miyoung Kim
Sooyoung Yoo
Seyoung Jung
Joon Yhup Lee
Sejin Nam
Hyunju Lee
Eu Suk Kim
Machine Learning for Community-Acquired Pneumonia Diagnosis Using Routine Clinical and Laboratory Data
Journal of Global Antimicrobial Resistance
Pneumonia
Diagnosis
Machine learning
title Machine Learning for Community-Acquired Pneumonia Diagnosis Using Routine Clinical and Laboratory Data
title_full Machine Learning for Community-Acquired Pneumonia Diagnosis Using Routine Clinical and Laboratory Data
title_fullStr Machine Learning for Community-Acquired Pneumonia Diagnosis Using Routine Clinical and Laboratory Data
title_full_unstemmed Machine Learning for Community-Acquired Pneumonia Diagnosis Using Routine Clinical and Laboratory Data
title_short Machine Learning for Community-Acquired Pneumonia Diagnosis Using Routine Clinical and Laboratory Data
title_sort machine learning for community acquired pneumonia diagnosis using routine clinical and laboratory data
topic Pneumonia
Diagnosis
Machine learning
url http://www.sciencedirect.com/science/article/pii/S2213716524004090
work_keys_str_mv AT sungyoonlim machinelearningforcommunityacquiredpneumoniadiagnosisusingroutineclinicalandlaboratorydata
AT eunhyecho machinelearningforcommunityacquiredpneumoniadiagnosisusingroutineclinicalandlaboratorydata
AT bokheejung machinelearningforcommunityacquiredpneumoniadiagnosisusingroutineclinicalandlaboratorydata
AT jaeyeonlee machinelearningforcommunityacquiredpneumoniadiagnosisusingroutineclinicalandlaboratorydata
AT miyoungkim machinelearningforcommunityacquiredpneumoniadiagnosisusingroutineclinicalandlaboratorydata
AT sooyoungyoo machinelearningforcommunityacquiredpneumoniadiagnosisusingroutineclinicalandlaboratorydata
AT seyoungjung machinelearningforcommunityacquiredpneumoniadiagnosisusingroutineclinicalandlaboratorydata
AT joonyhuplee machinelearningforcommunityacquiredpneumoniadiagnosisusingroutineclinicalandlaboratorydata
AT sejinnam machinelearningforcommunityacquiredpneumoniadiagnosisusingroutineclinicalandlaboratorydata
AT hyunjulee machinelearningforcommunityacquiredpneumoniadiagnosisusingroutineclinicalandlaboratorydata
AT eusukkim machinelearningforcommunityacquiredpneumoniadiagnosisusingroutineclinicalandlaboratorydata