A descriptive study of random forest algorithm for predicting COVID-19 patients outcome
Background The outbreak of coronavirus disease 2019 (COVID-19) that occurred in Wuhan, China, has become a global public health threat. It is necessary to identify indicators that can be used as optimal predictors for clinical outcomes of COVID-19 patients. Methods The clinical information from 126...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
PeerJ Inc.
2020-09-01
|
| Series: | PeerJ |
| Subjects: | |
| Online Access: | https://peerj.com/articles/9945.pdf |
| _version_ | 1827606557649534976 |
|---|---|
| author | Jie Wang Heping Yu Qingquan Hua Shuili Jing Zhifen Liu Xiang Peng Cheng’an Cao Yongwen Luo |
| author_facet | Jie Wang Heping Yu Qingquan Hua Shuili Jing Zhifen Liu Xiang Peng Cheng’an Cao Yongwen Luo |
| author_sort | Jie Wang |
| collection | DOAJ |
| description | Background The outbreak of coronavirus disease 2019 (COVID-19) that occurred in Wuhan, China, has become a global public health threat. It is necessary to identify indicators that can be used as optimal predictors for clinical outcomes of COVID-19 patients. Methods The clinical information from 126 patients diagnosed with COVID-19 were collected from Wuhan Fourth Hospital. Specific clinical characteristics, laboratory findings, treatments and clinical outcomes were analyzed from patients hospitalized for treatment from 1 February to 15 March 2020, and subsequently died or were discharged. A random forest (RF) algorithm was used to predict the prognoses of COVID-19 patients and identify the optimal diagnostic predictors for patients’ clinical prognoses. Results Seven of the 126 patients were excluded for losing endpoints, 103 of the remaining 119 patients were discharged (alive) and 16 died in the hospital. A synthetic minority over-sampling technique (SMOTE) was used to correct the imbalanced distribution of clinical patients. Recursive feature elimination (RFE) was used to select the optimal subset for analysis. Eleven clinical parameters, Myo, CD8, age, LDH, LMR, CD45, Th/Ts, dyspnea, NLR, D-Dimer and CK were chosen with AUC approximately 0.9905. The RF algorithm was built to predict the prognoses of COVID-19 patients based on the best subset, and the area under the ROC curve (AUC) of the test data was 100%. Moreover, two optimal clinical risk predictors, lactate dehydrogenase (LDH) and Myoglobin (Myo), were selected based on the Gini index. The univariable logistic analysis revealed a substantial increase in the risk for in-hospital mortality when Myo was higher than 80 ng/ml (OR = 7.54, 95% CI [3.42–16.63]) and LDH was higher than 500 U/L (OR = 4.90, 95% CI [2.13–11.25]). Conclusion We applied an RF algorithm to predict the mortality of COVID-19 patients with high accuracy and identified LDH higher than 500 U/L and Myo higher than 80 ng/ml to be potential risk factors for the prognoses of COVID-19 patients in the early stage of the disease. |
| first_indexed | 2024-03-09T06:39:01Z |
| format | Article |
| id | doaj.art-30ec0583675a4824998d0492dfbc9002 |
| institution | Directory Open Access Journal |
| issn | 2167-8359 |
| language | English |
| last_indexed | 2024-03-09T06:39:01Z |
| publishDate | 2020-09-01 |
| publisher | PeerJ Inc. |
| record_format | Article |
| series | PeerJ |
| spelling | doaj.art-30ec0583675a4824998d0492dfbc90022023-12-03T10:53:48ZengPeerJ Inc.PeerJ2167-83592020-09-018e994510.7717/peerj.9945A descriptive study of random forest algorithm for predicting COVID-19 patients outcomeJie Wang0Heping Yu1Qingquan Hua2Shuili Jing3Zhifen Liu4Xiang Peng5Cheng’an Cao6Yongwen Luo7Department of Otolaryngology-Head and Neck Surgery, Renmin Hospital of Wuhan University, Wuhan, Hubei, ChinaDepartment of Nail and Breast Surgery, Wuhan Forth Hospital, Wuhan, Hubei, ChinaDepartment of Otolaryngology-Head and Neck Surgery, Renmin Hospital of Wuhan University, Wuhan, Hubei, ChinaDepartment of Otolaryngology-Head and Neck Surgery, Renmin Hospital of Wuhan University, Wuhan, Hubei, ChinaDepartment of Nephrology, Wuhan Forth Hospital, Wuhan, Hubei, ChinaDepartment of Neurosurgery, Wuhan Forth Hospital, Wuhan, Hubei, ChinaDepartment of Neurosurgery, Wuhan Forth Hospital, Wuhan, Hubei, ChinaDepartment of Urology, Zhongnan Hospital of Wuhan University, Wuhan, Hubei, ChinaBackground The outbreak of coronavirus disease 2019 (COVID-19) that occurred in Wuhan, China, has become a global public health threat. It is necessary to identify indicators that can be used as optimal predictors for clinical outcomes of COVID-19 patients. Methods The clinical information from 126 patients diagnosed with COVID-19 were collected from Wuhan Fourth Hospital. Specific clinical characteristics, laboratory findings, treatments and clinical outcomes were analyzed from patients hospitalized for treatment from 1 February to 15 March 2020, and subsequently died or were discharged. A random forest (RF) algorithm was used to predict the prognoses of COVID-19 patients and identify the optimal diagnostic predictors for patients’ clinical prognoses. Results Seven of the 126 patients were excluded for losing endpoints, 103 of the remaining 119 patients were discharged (alive) and 16 died in the hospital. A synthetic minority over-sampling technique (SMOTE) was used to correct the imbalanced distribution of clinical patients. Recursive feature elimination (RFE) was used to select the optimal subset for analysis. Eleven clinical parameters, Myo, CD8, age, LDH, LMR, CD45, Th/Ts, dyspnea, NLR, D-Dimer and CK were chosen with AUC approximately 0.9905. The RF algorithm was built to predict the prognoses of COVID-19 patients based on the best subset, and the area under the ROC curve (AUC) of the test data was 100%. Moreover, two optimal clinical risk predictors, lactate dehydrogenase (LDH) and Myoglobin (Myo), were selected based on the Gini index. The univariable logistic analysis revealed a substantial increase in the risk for in-hospital mortality when Myo was higher than 80 ng/ml (OR = 7.54, 95% CI [3.42–16.63]) and LDH was higher than 500 U/L (OR = 4.90, 95% CI [2.13–11.25]). Conclusion We applied an RF algorithm to predict the mortality of COVID-19 patients with high accuracy and identified LDH higher than 500 U/L and Myo higher than 80 ng/ml to be potential risk factors for the prognoses of COVID-19 patients in the early stage of the disease.https://peerj.com/articles/9945.pdfCOVID-19Patient outcomeDescriptive studyRandom forest algorithm |
| spellingShingle | Jie Wang Heping Yu Qingquan Hua Shuili Jing Zhifen Liu Xiang Peng Cheng’an Cao Yongwen Luo A descriptive study of random forest algorithm for predicting COVID-19 patients outcome PeerJ COVID-19 Patient outcome Descriptive study Random forest algorithm |
| title | A descriptive study of random forest algorithm for predicting COVID-19 patients outcome |
| title_full | A descriptive study of random forest algorithm for predicting COVID-19 patients outcome |
| title_fullStr | A descriptive study of random forest algorithm for predicting COVID-19 patients outcome |
| title_full_unstemmed | A descriptive study of random forest algorithm for predicting COVID-19 patients outcome |
| title_short | A descriptive study of random forest algorithm for predicting COVID-19 patients outcome |
| title_sort | descriptive study of random forest algorithm for predicting covid 19 patients outcome |
| topic | COVID-19 Patient outcome Descriptive study Random forest algorithm |
| url | https://peerj.com/articles/9945.pdf |
| work_keys_str_mv | AT jiewang adescriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT hepingyu adescriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT qingquanhua adescriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT shuilijing adescriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT zhifenliu adescriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT xiangpeng adescriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT chengancao adescriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT yongwenluo adescriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT jiewang descriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT hepingyu descriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT qingquanhua descriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT shuilijing descriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT zhifenliu descriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT xiangpeng descriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT chengancao descriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome AT yongwenluo descriptivestudyofrandomforestalgorithmforpredictingcovid19patientsoutcome |