Development of the lung cancer diagnostic system / 南方医科大学学报

ABSTRACT

<p><b>OBJECTIVE</b>To develop a lung cancer diagnosis system.</p><p><b>METHODS</b>A retrospective analysis was conducted in 1883 patients with primary lung cancer or benign pulmonary diseases (pneumonia, tuberculosis, or pneumonia pseudotumor). SPSS11.5 software was used for data processing. For the relevant factors, a non-factor Logistic regression analysis was used followed by establishment of the regression model. Microsoft Visual Studio 2005 system development platform and VB.Net corresponding language were used to develop the lung cancer diagnosis system.</p><p><b>RESULTS</b>The non-factor multi-factor regression model showed a goodness-of-fit (R2) of the model of 0.806, with a diagnostic accuracy for benign lung diseases of 92.8%, a diagnostic accuracy for lung cancer of 89.0%, and an overall accuracy of 90.8%.</p><p><b>CONCLUSION</b>The model system for early clinical diagnosis of lung cancer has been established.</p>