Prediction of the risk of cytopenia in hospitalized HIV/AIDS patients using machine learning methods based on electronic medical records
BackgroundCytopenia is a frequent complication among HIV-infected patients who require hospitalization. It can have a negative impact on the treatment outcomes for these patients. However, by leveraging machine learning techniques and electronic medical records, a predictive model can be developed t...
| Main Authors: | , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2023-07-01
|
| Series: | Frontiers in Public Health |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fpubh.2023.1184831/full |
| _version_ | 1797770428333162496 |
|---|---|
| author | Liling Huang Bo Xie Kai Zhang Yuanlong Xu Lingsong Su Yu Lv Yangjie Lu Jianqiu Qin Xianwu Pang Hong Qiu Lanxiang Li Xihua Wei Kui Huang Zhihao Meng Yanling Hu Yanling Hu Yanling Hu Jiannan Lv Jiannan Lv |
| author_facet | Liling Huang Bo Xie Kai Zhang Yuanlong Xu Lingsong Su Yu Lv Yangjie Lu Jianqiu Qin Xianwu Pang Hong Qiu Lanxiang Li Xihua Wei Kui Huang Zhihao Meng Yanling Hu Yanling Hu Yanling Hu Jiannan Lv Jiannan Lv |
| author_sort | Liling Huang |
| collection | DOAJ |
| description | BackgroundCytopenia is a frequent complication among HIV-infected patients who require hospitalization. It can have a negative impact on the treatment outcomes for these patients. However, by leveraging machine learning techniques and electronic medical records, a predictive model can be developed to evaluate the risk of cytopenia during hospitalization in HIV patients. Such a model is crucial for designing a more individualized and evidence-based treatment strategy for HIV patients.MethodThe present study was conducted on HIV patients who were admitted to Guangxi Chest Hospital between June 2016 and October 2021. We extracted a total of 66 clinical features from the electronic medical records and employed them to train five machine learning prediction models (artificial neural network [ANN], adaptive boosting [AdaBoost], k-nearest neighbour [KNN] and support vector machine [SVM], decision tree [DT]). The models were tested using 20% of the data. The performance of the models was evaluated using indicators such as the area under the receiver operating characteristic curve (AUC). The best predictive models were interpreted using the shapley additive explanation (SHAP).ResultThe ANN models have better predictive power. According to the SHAP interpretation of the ANN model, hypoproteinemia and cancer were the most important predictive features of cytopenia in HIV hospitalized patients. Meanwhile, the lower hemoglobin-to-RDW ratio (HGB/RDW), low-density lipoprotein cholesterol (LDL-C) levels, CD4+ T cell counts, and creatinine clearance (Ccr) levels increase the risk of cytopenia in HIV hospitalized patients.ConclusionThe present study constructed a risk prediction model for cytopenia in HIV patients during hospitalization with machine learning and electronic medical record information. The prediction model is important for the rational management of HIV hospitalized patients and the personalized treatment plan setting. |
| first_indexed | 2024-03-12T21:23:10Z |
| format | Article |
| id | doaj.art-dfca153831a74e238c6441879716f8d6 |
| institution | Directory Open Access Journal |
| issn | 2296-2565 |
| language | English |
| last_indexed | 2024-03-12T21:23:10Z |
| publishDate | 2023-07-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Public Health |
| spelling | doaj.art-dfca153831a74e238c6441879716f8d62023-07-28T13:30:20ZengFrontiers Media S.A.Frontiers in Public Health2296-25652023-07-011110.3389/fpubh.2023.11848311184831Prediction of the risk of cytopenia in hospitalized HIV/AIDS patients using machine learning methods based on electronic medical recordsLiling Huang0Bo Xie1Kai Zhang2Yuanlong Xu3Lingsong Su4Yu Lv5Yangjie Lu6Jianqiu Qin7Xianwu Pang8Hong Qiu9Lanxiang Li10Xihua Wei11Kui Huang12Zhihao Meng13Yanling Hu14Yanling Hu15Yanling Hu16Jiannan Lv17Jiannan Lv18Guangxi Clinical Center for AIDS Prevention and Treatment, Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, Guangxi, ChinaSchool of Information and Management, Guangxi Medical University, Nanning, Guangxi, ChinaGuangxi Clinical Center for AIDS Prevention and Treatment, Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, Guangxi, ChinaGuangxi Clinical Center for AIDS Prevention and Treatment, Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, Guangxi, ChinaGuangxi Clinical Center for AIDS Prevention and Treatment, Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, Guangxi, ChinaGuangxi Clinical Center for AIDS Prevention and Treatment, Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, Guangxi, ChinaGuangxi Clinical Center for AIDS Prevention and Treatment, Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, Guangxi, ChinaNanning Center for Disease Control and Prevention, Nanning, Guangxi, ChinaCenter for Genomic and Personalized Medicine, Guangxi key Laboratory for Genomic and Personalized Medicine, Guangxi Collaborative Innovation Center for Genomic and Personalized Medicine, Guangxi Medical University, Nanning, Guangxi, ChinaInstitute of Life Sciences, Guangxi Medical University, Nanning, Guangxi, ChinaBasic Medical College of Guangxi Medical University, Nanning, Guangxi, ChinaCenter for Genomic and Personalized Medicine, Guangxi key Laboratory for Genomic and Personalized Medicine, Guangxi Collaborative Innovation Center for Genomic and Personalized Medicine, Guangxi Medical University, Nanning, Guangxi, ChinaGuangxi Clinical Center for AIDS Prevention and Treatment, Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, Guangxi, ChinaGuangxi Clinical Center for AIDS Prevention and Treatment, Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, Guangxi, ChinaSchool of Information and Management, Guangxi Medical University, Nanning, Guangxi, ChinaCenter for Genomic and Personalized Medicine, Guangxi key Laboratory for Genomic and Personalized Medicine, Guangxi Collaborative Innovation Center for Genomic and Personalized Medicine, Guangxi Medical University, Nanning, Guangxi, ChinaInstitute of Life Sciences, Guangxi Medical University, Nanning, Guangxi, ChinaGuangxi Clinical Center for AIDS Prevention and Treatment, Chest Hospital of Guangxi Zhuang Autonomous Region, Liuzhou, Guangxi, ChinaDepartment of Infection, Affiliated Hospital of the Youjiang Medical University for Nationalities, Baise, Guangxi, ChinaBackgroundCytopenia is a frequent complication among HIV-infected patients who require hospitalization. It can have a negative impact on the treatment outcomes for these patients. However, by leveraging machine learning techniques and electronic medical records, a predictive model can be developed to evaluate the risk of cytopenia during hospitalization in HIV patients. Such a model is crucial for designing a more individualized and evidence-based treatment strategy for HIV patients.MethodThe present study was conducted on HIV patients who were admitted to Guangxi Chest Hospital between June 2016 and October 2021. We extracted a total of 66 clinical features from the electronic medical records and employed them to train five machine learning prediction models (artificial neural network [ANN], adaptive boosting [AdaBoost], k-nearest neighbour [KNN] and support vector machine [SVM], decision tree [DT]). The models were tested using 20% of the data. The performance of the models was evaluated using indicators such as the area under the receiver operating characteristic curve (AUC). The best predictive models were interpreted using the shapley additive explanation (SHAP).ResultThe ANN models have better predictive power. According to the SHAP interpretation of the ANN model, hypoproteinemia and cancer were the most important predictive features of cytopenia in HIV hospitalized patients. Meanwhile, the lower hemoglobin-to-RDW ratio (HGB/RDW), low-density lipoprotein cholesterol (LDL-C) levels, CD4+ T cell counts, and creatinine clearance (Ccr) levels increase the risk of cytopenia in HIV hospitalized patients.ConclusionThe present study constructed a risk prediction model for cytopenia in HIV patients during hospitalization with machine learning and electronic medical record information. The prediction model is important for the rational management of HIV hospitalized patients and the personalized treatment plan setting.https://www.frontiersin.org/articles/10.3389/fpubh.2023.1184831/fullHIVcytopeniaanemiathrombocytopenialeukopeniaelectronic medical records |
| spellingShingle | Liling Huang Bo Xie Kai Zhang Yuanlong Xu Lingsong Su Yu Lv Yangjie Lu Jianqiu Qin Xianwu Pang Hong Qiu Lanxiang Li Xihua Wei Kui Huang Zhihao Meng Yanling Hu Yanling Hu Yanling Hu Jiannan Lv Jiannan Lv Prediction of the risk of cytopenia in hospitalized HIV/AIDS patients using machine learning methods based on electronic medical records Frontiers in Public Health HIV cytopenia anemia thrombocytopenia leukopenia electronic medical records |
| title | Prediction of the risk of cytopenia in hospitalized HIV/AIDS patients using machine learning methods based on electronic medical records |
| title_full | Prediction of the risk of cytopenia in hospitalized HIV/AIDS patients using machine learning methods based on electronic medical records |
| title_fullStr | Prediction of the risk of cytopenia in hospitalized HIV/AIDS patients using machine learning methods based on electronic medical records |
| title_full_unstemmed | Prediction of the risk of cytopenia in hospitalized HIV/AIDS patients using machine learning methods based on electronic medical records |
| title_short | Prediction of the risk of cytopenia in hospitalized HIV/AIDS patients using machine learning methods based on electronic medical records |
| title_sort | prediction of the risk of cytopenia in hospitalized hiv aids patients using machine learning methods based on electronic medical records |
| topic | HIV cytopenia anemia thrombocytopenia leukopenia electronic medical records |
| url | https://www.frontiersin.org/articles/10.3389/fpubh.2023.1184831/full |
| work_keys_str_mv | AT lilinghuang predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT boxie predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT kaizhang predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT yuanlongxu predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT lingsongsu predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT yulv predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT yangjielu predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT jianqiuqin predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT xianwupang predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT hongqiu predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT lanxiangli predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT xihuawei predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT kuihuang predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT zhihaomeng predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT yanlinghu predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT yanlinghu predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT yanlinghu predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT jiannanlv predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords AT jiannanlv predictionoftheriskofcytopeniainhospitalizedhivaidspatientsusingmachinelearningmethodsbasedonelectronicmedicalrecords |