A predictive analytics model using machine learning algorithms to estimate the risk of shock development among dengue patients
Dengue is a common viral disease in tropical and subtropical countries. The clinical manifestation of dengue has a wide spectrum, from asymptomatic seroconversion to severe dengue infection. Severe dengue is defined as dengue with the presence of specific symptoms, including severe plasma leakage le...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-06-01
|
| Series: | Healthcare Analytics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772442523001570 |
| _version_ | 1827223330909847552 |
|---|---|
| author | Jun Kit Chaw Sook Hui Chaw Chai Hoong Quah Shafrida Sahrani Mei Choo Ang Yanfeng Zhao Tin Tin Ting |
| author_facet | Jun Kit Chaw Sook Hui Chaw Chai Hoong Quah Shafrida Sahrani Mei Choo Ang Yanfeng Zhao Tin Tin Ting |
| author_sort | Jun Kit Chaw |
| collection | DOAJ |
| description | Dengue is a common viral disease in tropical and subtropical countries. The clinical manifestation of dengue has a wide spectrum, from asymptomatic seroconversion to severe dengue infection. Severe dengue is defined as dengue with the presence of specific symptoms, including severe plasma leakage leading to shock or the accumulation of fluids with respiratory distress, severe bleeding, and severe organ impairment. Examining the progression of shock with the integration of patients’ physiological information and biochemical parameters would help in understanding the progression of the disease and early detection of shock. In this study, physiological patient data diagnosed with dengue are collected from a University Malaya Medical Centre’s electronic record. A prediction model learned from the measurement of a patient’s physiological data is the basis for effective treatment and prevention of shock development in critically ill patients. Hence, this study presents the predictive performance of machine learning algorithms to estimate the risk of shock development among dengue patients. Logistic regression, decision trees, support vector machines and neural networks are evaluated. Lastly, ensemble learnings of bagging and boosting are also applied to the weak learner to optimize performance. The experimental results show that the bagging algorithm outperforms other competing methods with a 14.5% improvement from the individual decision tree. The full blood count (FBC) specifically haemoglobin (Hb) on day 2 is found to be a strong predictor for severe dengue occurrence. |
| first_indexed | 2024-03-08T23:09:58Z |
| format | Article |
| id | doaj.art-ed934226556f41ceba81850ca1323cf9 |
| institution | Directory Open Access Journal |
| issn | 2772-4425 |
| language | English |
| last_indexed | 2025-03-21T16:52:41Z |
| publishDate | 2024-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Healthcare Analytics |
| spelling | doaj.art-ed934226556f41ceba81850ca1323cf92024-06-15T06:14:50ZengElsevierHealthcare Analytics2772-44252024-06-015100290A predictive analytics model using machine learning algorithms to estimate the risk of shock development among dengue patientsJun Kit Chaw0Sook Hui Chaw1Chai Hoong Quah2Shafrida Sahrani3Mei Choo Ang4Yanfeng Zhao5Tin Tin Ting6Institute of Visual Informatics, National University of Malaysia, Bangi, Selangor, Malaysia; Corresponding author.Department of Anaesthesiology, Faculty of Medicine, Universiti Malaya, Kuala Lumpur, MalaysiaPenang General Hospital, George Town, Pulau Pinang, MalaysiaInstitute of Visual Informatics, National University of Malaysia, Bangi, Selangor, MalaysiaInstitute of Visual Informatics, National University of Malaysia, Bangi, Selangor, MalaysiaInstitute of Visual Informatics, National University of Malaysia, Bangi, Selangor, MalaysiaFaculty of Data Science and Information Technology, INTI International University, Nilai, Negeri Sembilan, MalaysiaDengue is a common viral disease in tropical and subtropical countries. The clinical manifestation of dengue has a wide spectrum, from asymptomatic seroconversion to severe dengue infection. Severe dengue is defined as dengue with the presence of specific symptoms, including severe plasma leakage leading to shock or the accumulation of fluids with respiratory distress, severe bleeding, and severe organ impairment. Examining the progression of shock with the integration of patients’ physiological information and biochemical parameters would help in understanding the progression of the disease and early detection of shock. In this study, physiological patient data diagnosed with dengue are collected from a University Malaya Medical Centre’s electronic record. A prediction model learned from the measurement of a patient’s physiological data is the basis for effective treatment and prevention of shock development in critically ill patients. Hence, this study presents the predictive performance of machine learning algorithms to estimate the risk of shock development among dengue patients. Logistic regression, decision trees, support vector machines and neural networks are evaluated. Lastly, ensemble learnings of bagging and boosting are also applied to the weak learner to optimize performance. The experimental results show that the bagging algorithm outperforms other competing methods with a 14.5% improvement from the individual decision tree. The full blood count (FBC) specifically haemoglobin (Hb) on day 2 is found to be a strong predictor for severe dengue occurrence.http://www.sciencedirect.com/science/article/pii/S2772442523001570Machine learningDengueEnsemble learningPredictive analyticsFeature importancePerformance evaluation |
| spellingShingle | Jun Kit Chaw Sook Hui Chaw Chai Hoong Quah Shafrida Sahrani Mei Choo Ang Yanfeng Zhao Tin Tin Ting A predictive analytics model using machine learning algorithms to estimate the risk of shock development among dengue patients Healthcare Analytics Machine learning Dengue Ensemble learning Predictive analytics Feature importance Performance evaluation |
| title | A predictive analytics model using machine learning algorithms to estimate the risk of shock development among dengue patients |
| title_full | A predictive analytics model using machine learning algorithms to estimate the risk of shock development among dengue patients |
| title_fullStr | A predictive analytics model using machine learning algorithms to estimate the risk of shock development among dengue patients |
| title_full_unstemmed | A predictive analytics model using machine learning algorithms to estimate the risk of shock development among dengue patients |
| title_short | A predictive analytics model using machine learning algorithms to estimate the risk of shock development among dengue patients |
| title_sort | predictive analytics model using machine learning algorithms to estimate the risk of shock development among dengue patients |
| topic | Machine learning Dengue Ensemble learning Predictive analytics Feature importance Performance evaluation |
| url | http://www.sciencedirect.com/science/article/pii/S2772442523001570 |
| work_keys_str_mv | AT junkitchaw apredictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT sookhuichaw apredictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT chaihoongquah apredictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT shafridasahrani apredictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT meichooang apredictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT yanfengzhao apredictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT tintinting apredictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT junkitchaw predictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT sookhuichaw predictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT chaihoongquah predictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT shafridasahrani predictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT meichooang predictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT yanfengzhao predictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients AT tintinting predictiveanalyticsmodelusingmachinelearningalgorithmstoestimatetheriskofshockdevelopmentamongdenguepatients |