Dataset Information

Comparisons of prediction models of quality of life after laparoscopic cholecystectomy: a longitudinal prospective study.

ABSTRACT:

Background

Few studies of laparoscopic cholecystectomy (LC) outcome have used longitudinal data for more than two years. Moreover, no studies have considered group differences in factors other than outcome such as age and nonsurgical treatment. Additionally, almost all published articles agree that the essential issue of the internal validity (reproducibility) of the artificial neural network (ANN), support vector machine (SVM), Gaussian process regression (GPR) and multiple linear regression (MLR) models has not been adequately addressed. This study proposed to validate the use of these models for predicting quality of life (QOL) after LC and to compare the predictive capability of ANNs with that of SVM, GPR and MLR.

Methodology/principal findings

A total of 400 LC patients completed the SF-36 and the Gastrointestinal Quality of Life Index at baseline and at 2 years postoperatively. The criteria for evaluating the accuracy of the system models were mean square error (MSE) and mean absolute percentage error (MAPE). A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the variables in order of importance. Compared to SVM, GPR and MLR models, the ANN model generally had smaller MSE and MAPE values in the training data set and test data set. Most ANN models had MAPE values ranging from 4.20% to 8.60%, and most had high prediction accuracy. The global sensitivity analysis also showed that preoperative functional status was the best parameter for predicting QOL after LC.

Conclusions/significance

Compared with SVM, GPR and MLR models, the ANN model in this study was more accurate in predicting patient-reported QOL and had higher overall performance indices. Further studies of this model may consider the effect of a more detailed database that includes complications and clinical examination findings as well as more detailed outcome data.

SUBMITTER: Shi HY

PROVIDER: S-EPMC3532431 | biostudies-literature | 2012

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Comparisons of prediction models of quality of life after laparoscopic cholecystectomy: a longitudinal prospective study.

Shi Hon-Yi HY Lee Hao-Hsien HH Tsai Jinn-Tsong JT Ho Wen-Hsien WH Chen Chieh-Fan CF Lee King-Teh KT Chiu Chong-Chi CC

PloS one 20121228 12

<h4>Background</h4>Few studies of laparoscopic cholecystectomy (LC) outcome have used longitudinal data for more than two years. Moreover, no studies have considered group differences in factors other than outcome such as age and nonsurgical treatment. Additionally, almost all published articles agree that the essential issue of the internal validity (reproducibility) of the artificial neural network (ANN), support vector machine (SVM), Gaussian process regression (GPR) and multiple linear regre ...[more]

PMID: 23284677

Similar Datasets

Project description:Extracorporeal life support (ECLS) provides emergency pulmonary and cardiac assistance for patients in respiratory or cardiac failure. Most studies evaluate the success of ECLS based on patients' survival rate. However, the trajectory of health status and quality of life (QOL) should also be important considerations. The study's aim was to explore changes in health status and QOL in adult patients weaned from ECLS who survived to hospital discharge over a one-year period.A prospective longitudinal study was conducted from April 2012 to September 2014. A convenience sample of patients who had undergone ECLS was followed for one-year after hospital discharge. Heath status was measured with a physical activity scale, the Centre for Epidemiologic Studies Depression scale, and a social support scale; we assessed quality of life with the physical and mental component summary scales of the Short-Form 36 Health Survey. Changes in depression, social support, physical activity and QOL were analysed with generalized estimating equations at 3-month intervals; participants' QOL at 12 months after discharge was compared with the general population.A total of 231 patients received ECLS during the study period. Sixty-five patients survived to hospital discharge (28% survival rate); 32 participants completed the study. Data showed scores for physical activity increased significantly over time (p < .001), while depression and social support significantly decreased (p < .05 and p < .001, respectively). Participants with veno-venous ECLS had higher scores for depression than participants with veno-arterial ECLS (p < .05). PCS scores significantly increased at 9, and 12 months after discharge (p < .05 and p < .001, respectively). There was no significant change in MCS scores.This was a preliminary study of patients with ECLS following hospital discharge over a one-year period. One year following hospital discharge survivors of ECLS continued to experience physical complications and some continued to have depressive symptoms; the level of social support was significantly lower after hospital discharge. Healthcare professionals should understand the trajectory of health status and QOL after discharge, which can help developing evidence-based interventions and improve QOL for survivors of ECLS.

Dataset Information

Comparisons of prediction models of quality of life after laparoscopic cholecystectomy: a longitudinal prospective study.

Background

Methodology/principal findings

Conclusions/significance

Publications

Comparisons of prediction models of quality of life after laparoscopic cholecystectomy: a longitudinal prospective study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure