Diagnosis of pancreatic carcinoma based on combined measurement of multiple serum tumor markers using artificial neural network analysis

Background Artificial neural network (ANN) has demonstrated the ability to assimilate information from multiple sources to enable the detection of subtle and complex patterns. In this research, we evaluated an ANN model in the diagnosis of pancreatic cancer using multiple serum markers. Methods In this retrospective analysis, 913 serum specimens collected at the Department of General Surgery of Beijing Friendship Hospital were analyzed for carbohydrate antigen 19‐9 (CA19‐9), carbohydrate antigen 125 (CA125), and carcinoembryonic antigen (CEA). The three tumor marker values were used as inputs into an ANN and randomized into a training set of 658 (70.31% were malignant) and a test set of the remaining 255 samples (70.69% were malignant). The samples were also evaluated using a Logistic regression (LR) model. Results The ANN‐derived composite index was superior to each of the serum tumor markers alone and the Logistic regression model. The areas under receiver operating characteristic curves (AUROC) was 0.905 (95% confidence Interval (CI) 0.868‐0.942) for ANN, 0.812 (95% CI 0.762‐0.863) for the Logistic regression model, 0.845 (95% CI 0.798‐0.893) for CA19‐9, 0.795 (95% CI 0.738‐0.851) for CA125, and 0.800 (95% CI 0.746‐0.854) for CEA. ANN analysis of multiple markers yielded a high level of diagnostic accuracy (83.53%) compared to LR (74.90%). Conclusion The performance of ANN model in the diagnosis of pancreatic cancer is better than the single tumor marker and LR model.

[1]  Geoffrey J. Gordon,et al.  Artificial Intelligence in Medicine: 17th Conference on Artificial Intelligence in Medicine, AIME 2019, Poznan, Poland, June 26–29, 2019, Proceedings , 2019, Lecture Notes in Computer Science.

[2]  K Yamauchi,et al.  Evaluation of a neural network classifier for pancreatic masses based on CT findings. , 1997, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[3]  T. Mattfeldt,et al.  Classification of spatial textures in benign and cancerous glandular tissues by stereology and stochastic geometry using artificial neural networks , 2000, Journal of microscopy.

[4]  H. Cammann,et al.  A [‐2]proPSA‐based artificial neural network significantly improves differentiation between prostate cancer and benign prostatic diseases , 2009, The Prostate.

[5]  Hong Qin,et al.  Design and Analysis of Optimization Methods for Subdivision Surface Fitting , 2007, IEEE Transactions on Visualization and Computer Graphics.

[6]  J. Winter,et al.  Biomarkers in Pancreatic Cancer: Diagnostic, Prognostic, and Predictive , 2012, Cancer journal.

[7]  K. Gunavathi,et al.  Lung cancer classification using neural networks for CT images , 2014, Comput. Methods Programs Biomed..

[8]  N. Duraker,et al.  CEA, CA 19‐9, and CA 125 in the differential diagnosis of benign and malignant pancreatic diseases with or without jaundice , 2007, Journal of surgical oncology.

[9]  Adnan Khashman,et al.  A Modified Backpropagation Learning Algorithm With Added Emotional Coefficients , 2008, IEEE Transactions on Neural Networks.

[10]  A. Jemal,et al.  Cancer Statistics, 2010 , 2010, CA: a cancer journal for clinicians.

[11]  Chun-Lang Chang,et al.  The study that applies artificial intelligence and logistic regression for assistance in differential diagnostic of pancreatic cancer , 2009, Expert Syst. Appl..

[12]  Kurt Miller,et al.  Artificial neural networks and prostate cancer—tools for diagnosis and management , 2013, Nature Reviews Urology.

[13]  Zuqiang Liu,et al.  CA125 is Superior to CA19-9 in Predicting the Resectability of Pancreatic Cancer , 2013, Journal of Gastrointestinal Surgery.

[14]  Robert Grützmann,et al.  Preoperative CEA and CA 19-9 are prognostic markers for survival after curative resection for ductal adenocarcinoma of the pancreas - a retrospective tumor marker prognostic study. , 2013, International journal of surgery.

[15]  N. Dubrawsky.  Cancer statistics , 1989, CA: a cancer journal for clinicians.

[16]  K. Hsieh,et al.  The novel application of artificial neural network on bioelectrical impedance analysis to assess the body composition in elderly , 2013, Nutrition Journal.

[17]  Noboru Yanai,et al.  Prognosis of non-surgically treated, clinical stage I lung cancer patients in Japan. , 2002, Lung cancer.

[18]  Andrija Milojević,et al.  Artificial neural networks based early clinical prediction of mortality after spontaneous intracerebral hemorrhage , 2012, Acta Neurologica Belgica.

[19]  Yupei Zhao,et al.  Combined detection of serum tumor markers for differential diagnosis of solid lesions located at the pancreatic head. , 2007, Hepatobiliary & pancreatic diseases international : HBPD INT.

[20]  N. Tangri,et al.  Predicting technique survival in peritoneal dialysis patients: comparing artificial neural networks and logistic regression , 2008, Nephrology, dialysis, transplantation : official publication of the European Dialysis and Transplant Association - European Renal Association.

[21]  M. Lowery,et al.  Postresection surveillance for pancreatic cancer performance status, imaging, and serum markers. , 2012, Cancer journal.

[22]  Yang Qing,et al.  An Artificial Neural Network Approach to the Predictive Modeling of Tensile Force during Renal Suturing , 2012, Annals of Biomedical Engineering.

[23]  S. Steinberg,et al.  Evaluation of the utility of a radioimmunoassay for serum CA 19-9 levels in patients before and after treatment of carcinoma of the pancreas. , 1988, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[24]  L. Spelt,et al.  Artificial neural networks--a method for prediction of survival following liver resection for colorectal cancer metastases. , 2013, European journal of surgical oncology : the journal of the European Society of Surgical Oncology and the British Association of Surgical Oncology.

[25]  Y. Matsuno,et al.  Co-Expression of Mesothelin and CA125 Correlates With Unfavorable Patient Outcome in Pancreatic Ductal Adenocarcinoma , 2011, Pancreas.

[26]  S. Hanash,et al.  A Compendium of Potential Biomarkers of Pancreatic Cancer , 2009, PLoS medicine.

[27]  Wen-Hsien Ho,et al.  Mortality Predicted Accuracy for Hepatocellular Carcinoma Patients with Hepatic Resection Using Artificial Neural Network , 2013, TheScientificWorldJournal.

[28]  Jing Zhang,et al.  Performance comparison of artificial neural network and logistic regression model for differentiating lung nodules on CT scans , 2012, Expert Syst. Appl..

[29]  R. Abrams,et al.  Postresection CA 19-9 predicts overall survival in patients with pancreatic cancer treated with adjuvant chemoradiation: a prospective validation by RTOG 9704. , 2008, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[30]  T. Slavici,et al.  Artificial intelligence techniques: An efficient new approach to challenge the assessment of complex clinical fields such as airway clearance techniques in patients with cystic fibrosis? , 2013, Journal of rehabilitation medicine.

[31]  Daniel W Chan,et al.  Combining multiple serum tumor markers improves detection of stage I epithelial ovarian cancer. , 2007, Gynecologic oncology.

[32]  J. Greenleaf,et al.  Neural network analysis of EUS images to differentiate between pancreatic malignancy and pancreatitis. , 2001, Gastrointestinal endoscopy.

[33]  Hong-Mei Yu,et al.  Tumor biomarkers: help or mislead in the diagnosis of xanthogranulomatous cholecystitis?‐‐analysis of serum CA 19‐9, carcinoembryonic antigen, and CA 12‐5 , 2013, Chinese medical journal.

[34]  E. Montgomery,et al.  Mucin 16 (cancer antigen 125) expression in human tissues and cell lines and correlation with clinical outcome in adenocarcinomas of the pancreas, esophagus, stomach, and colon. , 2012, Human pathology.

[35]  J. Nilsson,et al.  Artificial neural networks predict survival from pancreatic cancer after radical surgery. , 2013, American journal of surgery.

[36]  J. Nilsson,et al.  Artificial neural networks in pancreatic disease , 2008, The British journal of surgery.

[37]  Hon-Yi Shi,et al.  In-hospital mortality after traumatic brain injury surgery: a nationwide population-based comparison of mortality predictors used in artificial neural network and logistic regression models. , 2013, Journal of neurosurgery.