Using Explainable Machine Learning Methods to Predict the Survivability Rate of Pediatric Respiratory Diseases

The mortality rate due to chronic pediatric respiratory diseases is increasing every year and it is important to assess the severity of these diseases. As symptoms of several pediatric respiratory disorders are frequently identical, identification might be difficult due to the ongoing spread of resp...

Full description

Saved in:
Bibliographic Details
Main Authors: Roshan Kumar, V Srirama, Krishnaraj Chadaga, H Muralikrishna, Niranjana Sampathila, Srikanth Prabhu, Rajagopala Chadaga
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10794659/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849220111340142592
author Roshan Kumar
V Srirama
Krishnaraj Chadaga
H Muralikrishna
Niranjana Sampathila
Srikanth Prabhu
Rajagopala Chadaga
author_facet Roshan Kumar
V Srirama
Krishnaraj Chadaga
H Muralikrishna
Niranjana Sampathila
Srikanth Prabhu
Rajagopala Chadaga
author_sort Roshan Kumar
collection DOAJ
description The mortality rate due to chronic pediatric respiratory diseases is increasing every year and it is important to assess the severity of these diseases. As symptoms of several pediatric respiratory disorders are frequently identical, identification might be difficult due to the ongoing spread of respiratory diseases. Large datasets of clinical variables are analyzed by machine learning (ML) to find patterns and co-relations that human clinicians might not be able to predict immediately. As a result, pediatric respiratory disease severity can be detected more quickly and accurately. The KBest feature selection method is used initially to get the best fifteen features from the dataset. The random forest classifier performed well with the best accuracy of 96% compared to other classifiers. Shapley Additive Values (SHAP), Explain Like I’m 5 (ELI5), QLattice, and Local Interpretable Model-agnostic Explanations (LIME) are four Explainable Artificial Intelligence (XAI) techniques used to interpret model predictions. The most significant attributes were patient transfer to the intensive care unit, Kaliemia, Creatinine Blood Test, Cyanosis, and Natremia. The promising results suggest integrating ML into pediatric respiratory disease diagnosis for predictive accuracy and improved patient outcomes.
format Article
id doaj-art-d0ebae811c66434d8528c0faf3fbcc09
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-d0ebae811c66434d8528c0faf3fbcc092024-12-20T00:00:41ZengIEEEIEEE Access2169-35362024-01-011218951518953410.1109/ACCESS.2024.351604510794659Using Explainable Machine Learning Methods to Predict the Survivability Rate of Pediatric Respiratory DiseasesRoshan Kumar0https://orcid.org/0009-0001-8930-2229V Srirama1Krishnaraj Chadaga2H Muralikrishna3https://orcid.org/0000-0002-6340-4227Niranjana Sampathila4https://orcid.org/0000-0002-3345-360XSrikanth Prabhu5https://orcid.org/0000-0002-3826-1084Rajagopala Chadaga6Department of Information Technology, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Manipal, Karnataka, IndiaDepartment of Information Technology, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, Manipal, Karnataka, IndiaDepartment of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, IndiaDepartment of Electronics and Communication Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, IndiaDepartment of Biomedical Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, IndiaDepartment of Computer Science and Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, IndiaDepartment of Mechanical and Industrial Engineering, Manipal Institute of Technology, Manipal Academy of Higher Education, Manipal, IndiaThe mortality rate due to chronic pediatric respiratory diseases is increasing every year and it is important to assess the severity of these diseases. As symptoms of several pediatric respiratory disorders are frequently identical, identification might be difficult due to the ongoing spread of respiratory diseases. Large datasets of clinical variables are analyzed by machine learning (ML) to find patterns and co-relations that human clinicians might not be able to predict immediately. As a result, pediatric respiratory disease severity can be detected more quickly and accurately. The KBest feature selection method is used initially to get the best fifteen features from the dataset. The random forest classifier performed well with the best accuracy of 96% compared to other classifiers. Shapley Additive Values (SHAP), Explain Like I’m 5 (ELI5), QLattice, and Local Interpretable Model-agnostic Explanations (LIME) are four Explainable Artificial Intelligence (XAI) techniques used to interpret model predictions. The most significant attributes were patient transfer to the intensive care unit, Kaliemia, Creatinine Blood Test, Cyanosis, and Natremia. The promising results suggest integrating ML into pediatric respiratory disease diagnosis for predictive accuracy and improved patient outcomes.https://ieeexplore.ieee.org/document/10794659/Clinical variablesexplainable artificial intelligencemachine learningpediatric respiratory diseases
spellingShingle Roshan Kumar
V Srirama
Krishnaraj Chadaga
H Muralikrishna
Niranjana Sampathila
Srikanth Prabhu
Rajagopala Chadaga
Using Explainable Machine Learning Methods to Predict the Survivability Rate of Pediatric Respiratory Diseases
IEEE Access
Clinical variables
explainable artificial intelligence
machine learning
pediatric respiratory diseases
title Using Explainable Machine Learning Methods to Predict the Survivability Rate of Pediatric Respiratory Diseases
title_full Using Explainable Machine Learning Methods to Predict the Survivability Rate of Pediatric Respiratory Diseases
title_fullStr Using Explainable Machine Learning Methods to Predict the Survivability Rate of Pediatric Respiratory Diseases
title_full_unstemmed Using Explainable Machine Learning Methods to Predict the Survivability Rate of Pediatric Respiratory Diseases
title_short Using Explainable Machine Learning Methods to Predict the Survivability Rate of Pediatric Respiratory Diseases
title_sort using explainable machine learning methods to predict the survivability rate of pediatric respiratory diseases
topic Clinical variables
explainable artificial intelligence
machine learning
pediatric respiratory diseases
url https://ieeexplore.ieee.org/document/10794659/
work_keys_str_mv AT roshankumar usingexplainablemachinelearningmethodstopredictthesurvivabilityrateofpediatricrespiratorydiseases
AT vsrirama usingexplainablemachinelearningmethodstopredictthesurvivabilityrateofpediatricrespiratorydiseases
AT krishnarajchadaga usingexplainablemachinelearningmethodstopredictthesurvivabilityrateofpediatricrespiratorydiseases
AT hmuralikrishna usingexplainablemachinelearningmethodstopredictthesurvivabilityrateofpediatricrespiratorydiseases
AT niranjanasampathila usingexplainablemachinelearningmethodstopredictthesurvivabilityrateofpediatricrespiratorydiseases
AT srikanthprabhu usingexplainablemachinelearningmethodstopredictthesurvivabilityrateofpediatricrespiratorydiseases
AT rajagopalachadaga usingexplainablemachinelearningmethodstopredictthesurvivabilityrateofpediatricrespiratorydiseases