1
|
Chang JF, Chen PC, Hsieh CY, Liou JC. A Growth Differentiation Factor 15-Based Risk Score Model to Predict Mortality in Hemodialysis Patients. Diagnostics (Basel) 2021; 11:diagnostics11020286. [PMID: 33670413 PMCID: PMC7918408 DOI: 10.3390/diagnostics11020286] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/10/2020] [Revised: 01/22/2021] [Accepted: 02/07/2021] [Indexed: 12/19/2022] Open
Abstract
BACKGROUND The risk of cardiovascular (CV) and fatal events remains extremely high in patients with maintenance hemodialysis (MHD), and the growth differentiation factor 15 (GDF15) has emerged as a valid risk stratification biomarker. We aimed to develop a GDF15-based risk score as a death prediction model for MHD patients. METHODS Age, biomarker levels, and clinical parameters were evaluated at study entry. One hundred and seventy patients with complete information were finally included for data analysis. We performed the Cox regression analysis of various prognostic factors for mortality. Then, age, GDF15, and robust clinical predictors were included as a risk score model to assess the predictive accuracy for all-cause and CV death in the receiver operating characteristic (ROC) curve analysis. RESULTS Age, GDF15, and albumin were significantly associated with higher all-cause and CV mortality risk that were combined as a risk score model. The highest tertile of GDF-15 (>1707.1 pg/mL) was associated with all-cause mortality (adjusted hazard ratios (aHRs): 3.06 (95% confidence interval (CI): 1.20-7.82), p < 0.05) and CV mortality (aHRs: 3.11 (95% CI: 1.02-9.50), p < 0.05). The ROC analysis of GDF-15 tertiles for all-cause and CV mortality showed 0.68 (95% CI = 0.59 to 0.77) and 0.68 (95% CI = 0.58 to 0.79), respectively. By contrast, the GDF15-based prediction model for all-cause and CV mortality showed 0.75 (95% CI: 0.67-0.82) and 0.72 (95% CI: 0.63-0.81), respectively. CONCLUSION Age, GDF15, and hypoalbuminemia predict all-cause and CV death in MHD patients, yet a combination scoring system provides more robust predictive powers. An elevated GDF15-based risk score warns clinicians to determine an appropriate intervention in advance. In light of this, the GDF15-based death prediction model could be developed in the artificial intelligence-based precision medicine.
Collapse
Affiliation(s)
- Jia-Feng Chang
- Division of Nephrology, Department of Internal Medicine, En Chu Kong Hospital, New Taipei City 237, Taiwan; (J.-F.C.); (C.-Y.H.)
- Department of Nursing, Yuanpei University of Medical Technology, Hsinchu 300, Taiwan
- Division of Nephrology, Department of Internal Medicine, Shuang Ho Hospital, Taipei Medical University, New Taipei City 235, Taiwan
- Graduate Institute of Aerospace and Undersea Medicine, Department of Medicine, National Defense Medical Center, Taipei 114, Taiwan
- Renal Care Joint Foundation, New Taipei City 220, Taiwan
| | - Po-Cheng Chen
- Department of Urology, En Chu Kong Hospital, New Taipei City 237, Taiwan;
| | - Chih-Yu Hsieh
- Division of Nephrology, Department of Internal Medicine, En Chu Kong Hospital, New Taipei City 237, Taiwan; (J.-F.C.); (C.-Y.H.)
- School of Biomedical Engineering, Taipei Medical University, Taipei 110, Taiwan
| | - Jian-Chiun Liou
- School of Biomedical Engineering, Taipei Medical University, Taipei 110, Taiwan
- Correspondence:
| |
Collapse
|
2
|
Pan P, Li Y, Xiao Y, Han B, Su L, Su M, Li Y, Zhang S, Jiang D, Chen X, Zhou F, Ma L, Bao P, Xie L. Prognostic Assessment of COVID-19 in the Intensive Care Unit by Machine Learning Methods: Model Development and Validation. J Med Internet Res 2020; 22:e23128. [PMID: 33035175 PMCID: PMC7661105 DOI: 10.2196/23128] [Citation(s) in RCA: 62] [Impact Index Per Article: 15.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/02/2020] [Revised: 09/06/2020] [Accepted: 10/08/2020] [Indexed: 01/08/2023] Open
Abstract
BACKGROUND Patients with COVID-19 in the intensive care unit (ICU) have a high mortality rate, and methods to assess patients' prognosis early and administer precise treatment are of great significance. OBJECTIVE The aim of this study was to use machine learning to construct a model for the analysis of risk factors and prediction of mortality among ICU patients with COVID-19. METHODS In this study, 123 patients with COVID-19 in the ICU of Vulcan Hill Hospital were retrospectively selected from the database, and the data were randomly divided into a training data set (n=98) and test data set (n=25) with a 4:1 ratio. Significance tests, correlation analysis, and factor analysis were used to screen 100 potential risk factors individually. Conventional logistic regression methods and four machine learning algorithms were used to construct the risk prediction model for the prognosis of patients with COVID-19 in the ICU. The performance of these machine learning models was measured by the area under the receiver operating characteristic curve (AUC). Interpretation and evaluation of the risk prediction model were performed using calibration curves, SHapley Additive exPlanations (SHAP), Local Interpretable Model-Agnostic Explanations (LIME), etc, to ensure its stability and reliability. The outcome was based on the ICU deaths recorded from the database. RESULTS Layer-by-layer screening of 100 potential risk factors finally revealed 8 important risk factors that were included in the risk prediction model: lymphocyte percentage, prothrombin time, lactate dehydrogenase, total bilirubin, eosinophil percentage, creatinine, neutrophil percentage, and albumin level. Finally, an eXtreme Gradient Boosting (XGBoost) model established with the 8 important risk factors showed the best recognition ability in the training set of 5-fold cross validation (AUC=0.86) and the verification queue (AUC=0.92). The calibration curve showed that the risk predicted by the model was in good agreement with the actual risk. In addition, using the SHAP and LIME algorithms, feature interpretation and sample prediction interpretation algorithms of the XGBoost black box model were implemented. Additionally, the model was translated into a web-based risk calculator that is freely available for public usage. CONCLUSIONS The 8-factor XGBoost model predicts risk of death in ICU patients with COVID-19 well; it initially demonstrates stability and can be used effectively to predict COVID-19 prognosis in ICU patients.
Collapse
Affiliation(s)
- Pan Pan
- Chinese PLA General Hospital, Medical School Of Chinese PLA, College of Pulmonary and Critical Care Medicine, Beijing, China
| | - Yichao Li
- DHC Mediway Technology Co Ltd, Beijing, China
| | - Yongjiu Xiao
- The 940th Hospital of Jiont Logistics Support Force of Chinese People's Liberation Army, Lanzhou, China
| | - Bingchao Han
- The 980th Hospital of Jiont Logistics Support Force of Chinese People's Liberation Army, Shijiazhuang, China
| | - Longxiang Su
- Peking Union Medical College Hospital, Beijing, China
| | | | - Yansheng Li
- DHC Mediway Technology Co Ltd, Beijing, China
| | - Siqi Zhang
- DHC Mediway Technology Co Ltd, Beijing, China
| | | | - Xia Chen
- DHC Mediway Technology Co Ltd, Beijing, China
| | - Fuquan Zhou
- DHC Mediway Technology Co Ltd, Beijing, China
| | - Ling Ma
- The 940th Hospital of Jiont Logistics Support Force of Chinese People's Liberation Army, Lanzhou, China
| | - Pengtao Bao
- College of Pulmonary and Critical Care Medicine, Chinese PLA General Hospital, Beijing, China
| | - Lixin Xie
- College of Pulmonary and Critical Care Medicine, Chinese PLA General Hospital, Beijing, China
| |
Collapse
|
3
|
Ma X, Li A, Jiao M, Shi Q, An X, Feng Y, Xing L, Liang H, Chen J, Li H, Li J, Ren Z, Sun R, Cui G, Zhou Y, Cheng M, Jiao P, Wang Y, Xing J, Shen S, Zhang Q, Xu A, Yu Z. Characteristic of 523 COVID-19 in Henan Province and a Death Prediction Model. Front Public Health 2020; 8:475. [PMID: 33014973 PMCID: PMC7506160 DOI: 10.3389/fpubh.2020.00475] [Citation(s) in RCA: 13] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/15/2020] [Accepted: 07/27/2020] [Indexed: 01/10/2023] Open
Abstract
Certain high-risk factors related to the death of COVID-19 have been reported, however, there were few studies on a death prediction model. This study was conducted to delineate the clinical characteristics of patients with coronavirus disease 2019 (covid-19) of different degree and establish a death prediction model. In this multi-centered, retrospective, observational study, we enrolled 523 COVID-19 cases discharged before February 20, 2020 in Henan Province, China, compared clinical data, screened for high-risk fatal factors, built a death prediction model and validated the model in 429 mild cases, six fatal cases discharged after February 16, 2020 from Henan and 14 cases from Wuhan. Out of the 523 cases, 429 were mild, 78 severe survivors, 16 non-survivors. The non-survivors with median age 71 were older and had more comorbidities than the mild and severe survivors. Non-survivors had a relatively delay in hospitalization, with higher white blood cell count, neutrophil percentage, D-dimer, LDH, BNP, and PCT levels and lower proportion of eosinophils, lymphocytes and albumin. Discriminative models were constructed by using random forest with 16 non-survivors and 78 severe survivors. Age was the leading risk factors for poor prognosis, with AUC of 0.907 (95% CI 0.831-0.983). Mixed model constructed with combination of age, demographics, symptoms, and laboratory findings at admission had better performance (p = 0.021) with a generalized AUC of 0.9852 (95% CI 0.961-1). We chose 0.441 as death prediction threshold (with 0.85 sensitivity and 0.987 specificity) and validated the model in 429 mild cases, six fatal cases discharged after February 16, 2020 from Henan and 14 cases from Wuhan successfully. Mixed model can accurately predict clinical outcomes of COVID-19 patients.
Collapse
Affiliation(s)
- Xiaoxu Ma
- Department of Respiration, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Ang Li
- Department of Henan Gene Hospital, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.,Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Mengfan Jiao
- Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Qingmiao Shi
- Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Xiaocai An
- Department of Respiration, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Yonghai Feng
- Department of Respiration, The Fifth Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Lihua Xing
- Department of Respiration, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Hongxia Liang
- Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Jiajun Chen
- Department of Medical Services, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Huiling Li
- Department of Respiration, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Juan Li
- Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Zhigang Ren
- Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Ranran Sun
- Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Guangying Cui
- Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Yongjian Zhou
- Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Ming Cheng
- Department of Medical Information, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Pengfei Jiao
- Department of Respiration, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Yu Wang
- Department of Henan Gene Hospital, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Jiyuan Xing
- Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Shen Shen
- Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Qingxian Zhang
- Department of Respiration, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Aiguo Xu
- Department of Respiration, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| | - Zujiang Yu
- Department of Henan Gene Hospital, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China.,Department of Infectious Diseases, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
| |
Collapse
|