DOI QR코드

DOI QR Code

Use of an Artificial Neural Network to Construct a Model of Predicting Deep Fungal Infection in Lung Cancer Patients

  • Chen, Jian (Department of Laboratory Medicine, The First Affiliated Hospital of Wenzhou Medical University) ;
  • Chen, Jie (Department of Intensive Care Unit, The First Affiliated Hospital of Wenzhou Medical University) ;
  • Ding, Hong-Yan (Department of Laboratory Medicine, The First Affiliated Hospital of Wenzhou Medical University) ;
  • Pan, Qin-Shi (Department of Laboratory Medicine, The First Affiliated Hospital of Wenzhou Medical University) ;
  • Hong, Wan-Dong (Department of Gastroenterology and Hepatology, The First Affiliated Hospital of Wenzhou Medical University) ;
  • Xu, Gang (Department of Laboratory Medicine, The First Affiliated Hospital of Wenzhou Medical University) ;
  • Yu, Fang-You (Department of Laboratory Medicine, The First Affiliated Hospital of Wenzhou Medical University) ;
  • Wang, Yu-Min (Department of Laboratory Medicine, The First Affiliated Hospital of Wenzhou Medical University)
  • Published : 2015.07.13

Abstract

Background: The statistical methods to analyze and predict the related dangerous factors of deep fungal infection in lung cancer patients were several, such as logic regression analysis, meta-analysis, multivariate Cox proportional hazards model analysis, retrospective analysis, and so on, but the results are inconsistent. Materials and Methods: A total of 696 patients with lung cancer were enrolled. The factors were compared employing Student's t-test or the Mann-Whitney test or the Chi-square test and variables that were significantly related to the presence of deep fungal infection selected as candidates for input into the final artificial neural network analysis (ANN) model. The receiver operating characteristic (ROC) and area under curve (AUC) were used to evaluate the performance of the artificial neural network (ANN) model and logistic regression (LR) model. Results: The prevalence of deep fungal infection from lung cancer in this entire study population was 32.04%(223/696), deep fungal infections occur in sputum specimens 44.05%(200/454). The ratio of candida albicans was 86.99% (194/223) in the total fungi. It was demonstrated that older (${\geq}65$ years), use of antibiotics, low serum albumin concentrations (${\leq}37.18g/L$), radiotherapy, surgery, low hemoglobin hyperlipidemia (${\leq}93.67g/L$), long time of hospitalization (${\geq}14$days) were apt to deep fungal infection and the ANN model consisted of the seven factors. The AUC of ANN model($0.829{\pm}0.019$)was higher than that of LR model ($0.756{\pm}0.021$). Conclusions: The artificial neural network model with variables consisting of age, use of antibiotics, serum albumin concentrations, received radiotherapy, received surgery, hemoglobin, time of hospitalization should be useful for predicting the deep fungal infection in lung cancer.

Keywords

Artificial neural network (ANN);predictors;lung cancer;deep fungal infection

Acknowledgement

Supported by : National Natural Science Foundation of China, Wenzhou Municipal Science and Technology Bureau, Zhejiang Provincial Health Department

References

  1. Adams ST, Leveson SH (2012). Clinical prediction rules. BMJ, 344, 8312. https://doi.org/10.1136/bmj.d8312
  2. Balak MN, Gong Y, Riely GJ, et al (2006). Novel D761Y and common secondary T790M mutations in epidermal growth factor receptor-mutant lung adenocarcinomas with acquired resistance to kinase inhibitors. Clin Cancer Res, 12, 6494-501. https://doi.org/10.1158/1078-0432.CCR-06-1570
  3. Bartosch-Harlid A, Andersson B, Aho U, et al (2008). Artificial neural networks in pancreatic disease. Br J Surg, 95, 817-26. https://doi.org/10.1002/bjs.6239
  4. Bereket W, Hemalatha K, Getenet B, et al (2012). Update on bacterial nosocomial infections. Eur Rev Med Pharmacol Sci, 16, 1039-44.
  5. Chen CH, Lai JM, Chou TY, et al (2009). VEGFA upregulates FLJ10540 and modulates migration and invasion of lung cancer via PI3K/AKT pathway. PloS One, 4, 5052. https://doi.org/10.1371/journal.pone.0005052
  6. Chen J, Pan QS, Hong WD, et al (2014). Use of an artificial neural network to predict risk factors of nosocomial infection in lung cancer patients. Asian Pac J Cancer Prev, 15, 5349-53. https://doi.org/10.7314/APJCP.2014.15.13.5349
  7. Gridelli C, Rossi A, Maione P (2003). Treatment of non-small-cell lung cancer: state of the art and development of new biologic agents. Oncogene, 22, 6629-38. https://doi.org/10.1038/sj.onc.1206957
  8. Hong WD, Ji YF, Wang D, et al (2011). Use of artificial neural network to predict esophageal varices in patients with HBV related cirrhosis. Hepat Mon, 11, 544-7.
  9. Jemal A, Murray T, Ward E, et al (2005). Cancer statistics, 2005. CA Cancer J Clin, 55, 10-30. https://doi.org/10.3322/canjclin.55.1.10
  10. Jiang Y, Li JY, Li M, et al (2004). Clinical analysis of nosocomial pulmonary fungal infection in patients with cancer. Ai Zheng, 23, 1707-9.
  11. Moore MA, Ariyaratne Y, Badar F, et al (2010). Cancer epidemiology in South Asia-past, present and future. Asian Pac J Cancer Prev, 11, 49-66.
  12. Ogawa E, Takenaka K, Katakura H, et al (2008). Perimembrane Aurora-A expression is a significant prognostic factor in correlation with proliferative activity in non-small-cell lung cancer (NSCLC). Ann Surg Oncol, 15, 547-54. https://doi.org/10.1245/s10434-007-9653-8
  13. Saftoiu A, Vilmann P, Gorunescu F, et al (2012). Efficacy of an artificial neural network-based approach to endoscopic ultrasound elastography in diagnosis of focal pancreatic masses. Clin Gastroenterol Hepatol, 10, 84-90. https://doi.org/10.1016/j.cgh.2011.09.014
  14. Salim EI, Jazieh AR, Moore MA (2011). Lung cancer incidence in the arab league countries: risk factors and control. Asian Pac J Cancer Prev, 12, 17-34.
  15. Whiting PF, Sterne JA, Westwood ME, et al (2008). Graphical presentation of diagnostic information. BMC Med Res Methodol, 8, 20. https://doi.org/10.1186/1471-2288-8-20
  16. Zheng MH, Seto WK, Shi KQ, et al (2014). Artificial neural network accurately predicts hepatitis B surface antigen seroclearance. PloS one, 9, 99422. https://doi.org/10.1371/journal.pone.0099422

Cited by

  1. Deep Learning in Medical Imaging: General Overview vol.18, pp.4, 2017, https://doi.org/10.3348/kjr.2017.18.4.570
  2. A Study on Diagnostic Assist Systems of Chronic Obstructive Pulmonary Disease from Medical Images by Deep Learning vol.06, pp.01, 2018, https://doi.org/10.4236/jcc.2018.61003