Predicting mortality in patients with cirrhosis of liver with application of neural network technology

Journal of Gastroenterology and Hepatology (Australia) - Tập 18 Số 9 - Trang 1054-1060 - 2003
Rupa Banerjee1, Ananya Das2, Uday C. Ghoshal3, Madhumita Sinha4
1Department of Gastroenterology, Pushpawati Singhania Research Institute for Liver, Kidney and Digestive Diseases, Raebareli Road, Lucknow 226014, India.
2Departments of Gastroenterology, Pushpawati Singhania Research Institute for Liver, Kidney and Digestive Diseases, New Delhi,
3Sanjay Gandhi Postgraduate Institute of Medical Sciences, Lucknow and
4Max Health Care, New Delhi, India

Tóm tắt

AbstractBackground:  Prediction of mortality from cirrhosis is important in planning optimal timing of liver transplantation and other interventions. We evaluated the role of the Artificial Neural Network (ANN), which uses non‐linear statistics for pattern recognition in predicting one‐year liver disease‐related mortality using information available during initial clinical evaluation.Methods:  The ANN was constructed using software with data from a training set (n = 46) selected at random from a cohort of adult cirrhotics (n = 92). After training, validation was performed in the remaining patients (n = 46) whose outcome in terms of one‐year mortality was unknown to the network. The performance of ANN was compared to those of a logistic regression model (LRM) and Child‐Pugh's score (CPS). Death (related to cirrhosis/its complications) within one year of inclusion was the outcome variable. The ANN was also tested in an external validation sample (EVS, n = 62) from another hospital.Results:  Patients in the EVS were younger (mean age, 41 vs 45 years), infrequently of alcoholic etiology (5% vs 49%), had less severe disease (mean CPS 6.6 vs 10.8), and had lower one‐year mortality (13 vs 46%). In the internal validation sample, ANN's accuracy was 91%, sensitivity 90% and specificity 92% in prediction of one‐year mortality; area under the receiver‐operating characteristic (ROC) curve was 0.94. The performance of the LRM (accuracy 74%) and the CPS (accuracy 55%) was significantly worse than ANN (P < 0.05, McNemar's test). Despite differences in the characteristics of the two groups, the ANN performed fairly well in the EVS (accuracy of 90%, area under curve 0.85).Conclusions:  ANN can accurately predict one‐year mortality in cirrhosis and is superior to CPS and LRM.

Từ khóa


Tài liệu tham khảo

Institute of Medicine., 1999, Organ Procurement and Transplantation: Assessing Current Policies and the Potential Impact of the DHHS Final Rule, 57

10.1053/jhep.2001.22481

10.1002/hep.1840100102

10.1016/0016-5085(92)91449-E

10.1002/hep.1840030602

10.1136/gut.27.11.1377

10.1002/hep.1840140614

10.1016/S0140-6736(95)91746-2

10.1016/S0140-6736(95)91804-3

International Hepatology Informatics Group., 1994, Diseases of the Liver and Biliary Tract: Standardization of Nomenclature, Diagnostic Criteria and Prognosis

Ray G, 2000, Etiological spectrum of chronic liver disease in Eastern India, Trop. Gastroenterol., 21, 60

Mailliard ME, 2001, Harrison's Principles of Internal Medicine, 1752

10.7326/0003-4819-122-5-199503010-00007

10.1161/01.CIR.96.6.1798

10.1148/radiology.143.1.7063747

10.1097/00005373-200102000-00018

10.1053/jhep.2001.22172

Lapuerta P, 1997, Neural networks as predictors of outcomes in alcoholic patients with severe liver disease, Hepatology, 302, 6

10.1016/S0196-0644(05)80056-3

10.7326/0003-4819-120-2-199401150-00007

Thông tin
Thông tin xuất bản

Journal of Gastroenterology and Hepatology (Australia)

Tập 18 Số 9

1054-1060

Thông tin tác giả