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.
References
[1]
Lugtenberg M, Burgers JS, Clancy C, Westert GP, Schneider EC (2011) Current guidelines have limited applicability to patients with comorbid conditions: a systematic analysis of evidence-based guidelines. PLoS One 6: e25987.
[2]
Shi HY, Lee HH, Tsai MH, Chiu CC, Uen YH, et al. (2011) Long-term outcomes of laparoscopic cholecystectomy: a prospective piecewise linear regression analysis. Surg Endosc 25: 2132–2140.
[3]
Tao M, Teng Y, Shao H, Wu P, Mills EJ (2011) Knowledge, perceptions and information about hormone therapy (HT) among menopausal women: a systematic review and meta-synthesis. PLoS One 6: e24661.
Sampson DL, Parker TJ, Upton Z, Hurst CP (2011) A comparison of methods for classifying clinical samples based on proteomics data: a case study for statistical and machine learning approaches. PLoS One 6: e24973.
[6]
Furey TS, Cristianini N, Duffy N, Bednarski DW, Schummer M, et al. (2000) Support vector machine classification and validation of cancer tissue samples using microarray expression data. Bioinformatics 16: 906–914.
[7]
Rasmussen CE, Williams CKI (2006) Gaussian Processes for Machine Learning. MIT Press, Cambridge, MA.
[8]
Kapoor A, Grauman K, Urtasun R, Darrell T (2010) Gaussian processes for object categorization. Int J Comput Vis 88: 169–188.
[9]
Lancichinetti A, Radicchi F, Ramasco JJ, Fortunato S (2011) Finding statistically significant communities in networks. PLoS One 6: e18961.
[10]
Zou J, Han Y, So SS (2008) Overview of artificial neural networks. Methods Mol Biol 458: 15–23.
[11]
Das A, Ben-Menachem T, Cooper GS, Chak A, Sivak MV Jr, et al. (2003) Prediction of outcome in acute lower gastrointestinal haemorrhage based on an artificial neural network: internal and external validation of a predictive model. Lancet 362: 1261–1266.
[12]
Thakur V, Schlachta CM, Jayaraman S (2011) Minilaparoscopic versus conventional laparoscopic cholecystectomy a systematic review and meta-analysis. Ann Surg 253: 244–258.
[13]
Shi HY, Lee KT, Lee HH, Uen YH, Tsai JT, et al. (2009) Post-cholecystectomy quality of life: a prospective multicenter cohort study of its associations with preoperative functional status and patient demographics. J Gastrointest Surg 13: 1651–1658.
[14]
Gholipour C, Fakhree MB, Shalchi RA, Abbasi M (2009) Prediction of conversion of laparoscopic cholecystectomy to open surgery with artificial neural networks. BMC Surg 9: 13.
[15]
Liew PL, Lee YC, Lin YC, Lee TS, Lee WJ, et al. (2007) Comparison of artificial neural networks with logistic regression in prediction of gallbladder disease among obese patients. Dig Liver Dis 39: 356–362.
[16]
Eldar S, Siegelmann HT, Buzaglo D, Matter I, Cohen A, et al. (2002) Conversion of laparoscopic cholecystectomy to open cholecystectomy in acute cholecystitis: artificial neural networks improve the prediction of conversion. World J Surg 26: 79–85.
[17]
Hsu CE, Lee KT, Chang CS, Chiu HC, Chao FT, et al. (2010) Cholecystectomy prevalence and treatment cost: an 8-year study in Taiwan. Surg Endosc 24: 3127–3133.
[18]
Shi HY, Lee KT, Lee HH, Uen YH, Chiu CC (2011) Response shift effect on gastrointestinal quality of life index after laparoscopic cholecystectomy. Qual Life Res 20: 335–341.
[19]
Shi HY, Chang JK, Wong CY, Wang JW, Tu YK, et al. (2010) Responsiveness and minimal important differences after revision total hip arthroplasty. BMC Musculoskelet Disord 11: 261.
[20]
Ware JE, Kosinski M, Bayliss MS, McHorney CA, Rogers WH, et al. (1995) Comparison of methods for the scoring and statistical analysis of SF-36 health profile and summary measures: summary of results from the Medical Outcomes Study. Med Care 33: AS264–279.
[21]
Rumelhart DE, Hinton GE, Williams RJ (1986) Learning internal representations by error propagation. In Rumelhart, D. E. & McCleland, J. L. (Ed.) Cambridge, MA: MIT Press, pp. 318–362.
[22]
Chen CF, Ho WH, Chou HY, Yang SM, Chen IT, et al. (2011) Long-term prediction of emergency department revenue and visitor volume using autoregressive integrated moving average model. Comput Math Methods Med 2011: 395690.
[23]
Piaggi P, Lippi C, Fierabracci P, Maffei M, Calderone A, et al. (2010) Artificial neural networks in the outcome prediction of adjustable gastric banding in obese women. PLoS One 5: e13624.
[24]
Segal ME, Goodman PH, Goldstein R, Hauck W, Whyte J, et al. (2006) The accuracy of artificial neural networks in predicting long-term outcome after traumatic brain injury. J Head Trauma Rehabil 21: 298–314.
[25]
Salvatore S, Serati M, Siesto G, Cattoni E, Zanirato M, et al. (2011) Correlation between anatomical findings and symptoms in women with pelvic organ prolapse using an artificial neural network analysis. Int Urogynecol J 22: 453–459.
[26]
Tetko IV, Livingstone DJ, Luik AI (1995) Neural network studies. 1. Comparison of Overfitting and Overtraining. J Chem Inf Comput Sci 35,826–833.
[27]
Quintana JM, Arostegui I, Oribe V, López de Tejada I, Barrios B, et al. (2005) Influence of age and gender on quality-of-life outcomes after cholecystectomy. Qual Life Res 14: 815–825.
[28]
Buddingh KT, Nieuwenhuijs VB (2011) The critical view of safety and routine intraoperative cholangiography complement each other as safety measures during cholecystectomy. J Gastrointest Surg 15: 1069–1070.
[29]
Noble H, Whitley E, Norton S, Thompson M (2011) A study of preoperative factors associated with a poor outcome following laparoscopic bile duct exploration. Surg Endosc 25: 130–139.
[30]
Joseph S, Moore BT, Sorensen GB, Earley JW, Tang F, et al. (2011) Single-incision laparoscopic cholecystectomy: a comparison with the gold standard. Surg Endosc 25: 3008–3015.
[31]
Ho WH, Chou JH, Guo CY (2010) Parameter identification of chaotic systems using improved differential evolution algorithm. Nonlinear Dynamics 61, 29–41.
