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

Abstract

<b>Background:</b> The statistical methods to analyze and predict the related dangerous factors of deep fungalinfection in lung cancer patients were several, such as logic regression analysis, meta-analysis, multivariate Coxproportional hazards model analysis, retrospective analysis, and so on, but the results are inconsistent. Materialsand <br/><b>Methods</b>: A total of 696 patients with lung cancer were enrolled. The factors were compared employingStudent’s t-test or the Mann-Whitney test or the Chi-square test and variables that were significantly relatedto the presence of deep fungal infection selected as candidates for input into the final artificial neural networkanalysis (ANN) model. The receiver operating characteristic (ROC) and area under curve (AUC) were used toevaluate the performance of the artificial neural network (ANN) model and logistic regression (LR) model. <br/><b>Results</b>: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 (≥65 years), use of antibiotics, low serum albuminconcentrations (≤37.18g /L), radiotherapy, surgery, low hemoglobin hyperlipidemia (≤93.67g /L), long time ofhospitalization (≥14days) were apt to deep fungal infection and the ANN model consisted of the seven factors.The AUC of ANN model(0.829±0.019)was higher than that of LR model (0.756±0.021). <br/><b>Conclusions</b>: The artificialneural network model with variables consisting of age, use of antibiotics, serum albumin concentrations, receivedradiotherapy, received surgery, hemoglobin, time of hospitalization should be useful for predicting the deepfungal infection in lung cancer.