Author(s)

Chuangui Cao^1,2, Chengcheng Han^1,2, Qiang Lin^1,2*

¹School of Mathematics and Computer Science, Northwest Minzu University, Lanzhou, China.
²Key Laboratory of Streaming Data Computing Technologies and Application, Northwest Minzu University, Lanzhou, China.

Mining rich semantic information hidden in heterogeneous information network is one of the important tasks of data mining. Generally, a nuclear medicine text consists of the description of disease (i.e., lesions) and diagnostic results. However, how to construct a computer-aided diagnostic model with a large number of medical texts is a challenging task. To automatically diagnose diseases with SPECT imaging, in this work, we create a knowledge-based diagnostic model by exploring the association between a disease and its properties. Firstly, an overview of nuclear medicine and data mining is presented. Second, the method of preprocessing textual nuclear medicine diagnostic reports is proposed. Last, the created diagnostic modes based on random forest and SVM are proposed. Experimental evaluation conducted real-world data of diagnostic reports of SPECT imaging demonstrates that our diagnostic models are workable and effective to automatically identify diseases with textual diagnostic reports.

Text Classification, Nuclear Medicine, SPECT Imaging, Diagnostic Model, Random Forest, SVM

Cao, C. , Han, C. and Lin, Q. (2021) Creating Knowledge-Based Diagnostic Models by Mining Textual Diagnostic Reports of SPECT Scans. Journal of Computer and Communications, 9, 10-19. doi: 10.4236/jcc.2021.95002.