Automated Machine Learning in Predicting 30-Day Mortality in Patients with Non-Cholestatic Cirrhosis

被引:8
作者
Yu, Chenyan [1 ,2 ,3 ]
Li, Yao [1 ,2 ]
Yin, Minyue [1 ,2 ]
Gao, Jingwen [1 ,2 ]
Xi, Liting [1 ,2 ]
Lin, Jiaxi [1 ,2 ]
Liu, Lu [1 ,2 ]
Zhang, Huixian [3 ]
Wu, Airong [1 ,2 ]
Xu, Chunfang [1 ,2 ]
Liu, Xiaolin [1 ,2 ]
Wang, Yue [4 ]
Zhu, Jinzhou [1 ,2 ]
机构
[1] Soochow Univ, Affiliated Hosp 1, Dept Gastroenterol, 188 Shizi St, Suzhou 215006, Peoples R China
[2] Suzhou Clin Ctr Digest Dis, Suzhou 215000, Peoples R China
[3] Soochow Univ, Dushu Lake Hosp, Dept Gastroenterol, Suzhou 215000, Peoples R China
[4] Fifth Peoples Hosp Suzhou, Dept Hepatol, Suzhou 215000, Peoples R China
关键词
non-cholestatic cirrhosis; automated machine learning; shapley additive explanation; partial dependence plots; local interpretable model agnostic explanation; LIVER-DISEASE; SURVIVAL; PROGNOSIS; MODEL; SCORE;
D O I
10.3390/jpm12111930
中图分类号
R19 [保健组织与事业(卫生事业管理)];
学科分类号
摘要
Objective: To evaluate the feasibility of automated machine learning (AutoML) in predicting 30-day mortality in non-cholestatic cirrhosis. Methods: A total of 932 cirrhotic patients were included from the First Affiliated Hospital of Soochow University between 2014 and 2020. Participants were divided into training and validation datasets at a ratio of 8.5:1.5. Models were developed on the H2O AutoML platform in the training dataset, and then were evaluated in the validation dataset by area under receiver operating characteristic curves (AUC). The best AutoML model was interpreted by SHapley Additive exPlanation (SHAP) Plot, Partial Dependence Plots (PDP), and Local Interpretable Model Agnostic Explanation (LIME). Results: The model, based on the extreme gradient boosting (XGBoost) algorithm, performed better (AUC 0.888) than the other AutoML models (logistic regression 0.673, gradient boost machine 0.886, random forest 0.866, deep learning 0.830, stacking 0.850), as well as the existing scorings (the model of end-stage liver disease [MELD] score 0.778, MELD-Na score 0.782, and albumin-bilirubin [ALBI] score 0.662). The most key variable in the XGBoost model was high-density lipoprotein cholesterol, followed by creatinine, white blood cell count, international normalized ratio, etc. Conclusion: The AutoML model based on the XGBoost algorithm presented better performance than the existing scoring systems for predicting 30-day mortality in patients with non-cholestatic cirrhosis. It shows the promise of AutoML in its future medical application.
引用
收藏
页数:10
相关论文
共 32 条
[1]   Renal dysfunction in cirrhosis is not just a vasomotor nephropathy [J].
Adebayo, Danielle ;
Morabito, Vincenzo ;
Davenport, Andrew ;
Jalan, Rajiv .
KIDNEY INTERNATIONAL, 2015, 87 (03) :509-515
[2]   Serum Levels of Metabolites Produced by Intestinal Microbes and Lipid Moieties Independently Associated With Acute-on-Chronic Liver Failure and Death in Patients With Cirrhosis [J].
Bajaj, Jasmohan S. ;
Reddy, K. Rajender ;
O'Leary, Jacqueline G. ;
Vargas, Hugo E. ;
Lai, Jennifer C. ;
Kamath, Patrick S. ;
Tandon, Puneeta ;
Wong, Florence ;
Subramanian, Ram M. ;
Thuluvath, Paul ;
Fagan, Andrew ;
White, Melanie B. ;
Gavis, Edith A. ;
Sehrawat, Tejasav ;
Rodriguez, Randolph de la Rosa ;
Thacker, Leroy R. ;
Sikaroodi, Masoumeh ;
Garcia-Tsao, Guadalupe ;
Gillevet, Patrick M. .
GASTROENTEROLOGY, 2020, 159 (05) :1715-+
[3]   Survival in Infection-Related Acute-on-Chronic Liver Failure Is Defined by Extrahepatic Organ Failures [J].
Bajaj, Jasmohan S. ;
O'Leary, Jacqueline G. ;
Reddy, K. Rajender ;
Wong, Florence ;
Biggins, Scott W. ;
Patton, Heather ;
Fallon, Michael B. ;
Garcia-Tsao, Guadalupe ;
Maliakkal, Benedict ;
Malik, Raza ;
Subramanian, Ram M. ;
Thacker, Leroy R. ;
Kamath, Patrick S. .
HEPATOLOGY, 2014, 60 (01) :250-256
[4]   Association of AKI With Mortality and Complications in Hospitalized Patients With Cirrhosis [J].
Belcher, Justin M. ;
Garcia-Tsao, Guadalupe ;
Sanyal, Arun J. ;
Bhogal, Harjit ;
Lim, Joseph K. ;
Ansari, Naheed ;
Coca, Steven G. ;
Parikh, Chirag R. .
HEPATOLOGY, 2013, 57 (02) :753-762
[5]   Albumin in decompensated cirrhosis: new concepts and perspectives [J].
Bernardi, Mauro ;
Angeli, Paolo ;
Claria, Joan ;
Moreau, Richard ;
Gines, Pere ;
Jalan, Rajiv ;
Caraceni, Paolo ;
Fernandez, Javier ;
Gerbes, Alexander L. ;
O'Brien, Alastair J. ;
Trebicka, Jonel ;
Thevenot, Thierry ;
Arroyo, Vicente .
GUT, 2020, 69 (06) :1127-1138
[6]   Evidence-based incorporation of serum sodium concentration into MELD [J].
Biggins, Scott W. ;
Kim, W. Ray ;
Terrault, Norah A. ;
Saab, Sammy ;
Balan, Vijay ;
Schiano, Thomas ;
Benson, Joanne ;
Therneau, Terry ;
Kremers, Walter ;
Wiesner, Russell ;
Kamath, Patrick ;
Klintmalm, Goran .
GASTROENTEROLOGY, 2006, 130 (06) :1652-1660
[7]   Acute kidney injury spectrum in patients with chronic liver disease: Where do we stand? [J].
Chancharoenthana, Wiwat ;
Leelahavanichkul, Asada .
WORLD JOURNAL OF GASTROENTEROLOGY, 2019, 25 (28) :3684-3703
[8]   Serum lipid and lipoprotein patterns in patients with liver cirrhosis and chronic active hepatitis [J].
Cicognani, C ;
Malavolti, M ;
MorselliLabate, AM ;
Zamboni, L ;
Sama, C ;
Barbara, L .
ARCHIVES OF INTERNAL MEDICINE, 1997, 157 (07) :792-796
[9]   Natural history and prognostic indicators of survival in cirrhosis: A systematic review of 118 studies [J].
D'Amico, G ;
Garcia-Tsao, G ;
Pagliaro, L .
JOURNAL OF HEPATOLOGY, 2006, 44 (01) :217-231
[10]   Competing risks and prognostic stages of cirrhosis: a 25-year inception cohort study of 494 patients [J].
D'Amico, G. ;
Pasta, L. ;
Morabito, A. ;
D'Amico, M. ;
Caltagirone, M. ;
Malizia, G. ;
Tine, F. ;
Giannuoli, G. ;
Traina, M. ;
Vizzini, G. ;
Politi, F. ;
Luca, A. ;
Virdone, R. ;
Licata, A. ;
Pagliaro, L. .
ALIMENTARY PHARMACOLOGY & THERAPEUTICS, 2014, 39 (10) :1180-1193