Exploring and predicting mortality among patients with end-stage liver disease without cancer: a machine learning approach

Abstract

Objective End-stage liver disease is a global public health problem with a high mortality rate. Early identification of people at risk of poor prognosis is fundamental for decision-making in clinical settings. This study created a machine learning prediction system that provides several related models with visualized graphs, including decision trees, ensemble learning and clustering, to predict mortality in patients with end-stage liver disease. Methods A retrospective cohort study was conducted: the training data were from patients enrolled from January 2009 to December 2010 and followed up to December 2014; validation data were from patients enrolled from January 2015 to December 2016 and followed up to January 2019. Hospitalized patients with noncancer-related chronic liver disease were identified from the hospital’s electrical medical records. Results In traditional multivariable logistic regression and Cox proportional hazard model, prothrombin time of international normalized ratio, which was significant with P value = 0.002, odds ratio = 2.790 and hazard ratio 1.363. Besides, blood urea nitrogen and C-reactive protein were also significant, with P value <0.001 and 0.026. The area under the curve was 0.771 in the receiver operating characteristic curve. In machine learning, blood urea nitrogen and age were regarded as the primary factors for predicting mortality. Creatinine, prothrombin time of international normalized ratio and bilirubin were also significant mortality predictors. The area under the curve of the random forest and AdaBoost was 0.838 and 0.792. Conclusion The machine learning techniques provided a comprehensive assessment of patient conditions; it could help physicians make an accurate diagnosis of chronic liver disease and improve healthcare management.

Association between liver stiffness measurement by transient elastography and chronic kidney disease

“…And other studies also reveal that patients with severe liver diseases have abnormal creatinine and BUN outcomes. [ 38 , 39 ] However, there are some factors that would affect the evaluation performance for the liver stiffness by TE, such as the number of measurements, liver volumes, patient's conditions such as overweight or obesity or other complications as well as the fibrosis stage and experience of operators. Currently, it is generally agreed that 3 measurements are sufficient to obtain consistent results for assessing liver fibrosis.…”

“…Therefore, based on the results of the present study, there is a correlation between the severity of hepatic stiffness and eGFR. And other studies also reveal that patients with severe liver diseases have abnormal creatinine and BUN outcomes [38,39] . However, there are some factors that would affect the evaluation performance for the liver stiffness by TE, such as the number of measurements, liver volumes, patient's conditions such as overweight or obesity or other complications as well as the fibrosis stage and experience of operators.…”

Prognostic value of albumin‐related ratios in HBV‐associated decompensated cirrhosis

“…According to recent studies, BUN was associated with unfavorable outcomes in various settings, including acute heart failure, 22 critically ill patients, 23 acute aortic dissection, 24 and pancreatitis 25 . Furthermore, Yu et al 35 identified BUN and age as predictive factors for poor prognosis in advanced liver diseases using machine learning. Kidney dysfunction is a common comorbid condition in liver disease, and several reports have indicated that kidney dysfunction is linked to mortality in cirrhotic patients 36 .…”

Specific patterns and potential risk factors to predict 3-year risk of death among non-cancer patients with advanced chronic kidney disease by machine learning

“…Machine learning (ML) has been applied successfully to different chronic diseases, such as chronic liver diseases, CVD, chronic obstructive pulmonary disease, and metabolic syndrome. [15][16][17][18][19][20][21][22][23] Furthermore, several studies in the past 2 years have utilized time-series ML techniques to predict the COVID-19 pandemic trend. [20] Previous studies also used unsupervised learning and network visualization of big data for chronic disease diagnoses.…”

“…[15][16][17][18][19][20][21][22][23] Furthermore, several studies in the past 2 years have utilized time-series ML techniques to predict the COVID-19 pandemic trend. [20] Previous studies also used unsupervised learning and network visualization of big data for chronic disease diagnoses. [24] Machine learning techniques were used in several research about renal problems such as CKD early detection in the EHR database or prediction for acute kidney injury.…”