id	author	title	date	pages	extension	mime	words	sentences	flesch	summary	cache	txt
work_slbvbdfjyzhnfkl3t2tfdiqp7a	Dario Antonelli	Analysis of diabetic patients through their examination history	2013	22	.pdf	application/pdf	6845	605	58	paper proposes a data analysis framework based on a multiple-level clustering technique to identify the examination pathways commonly followed by Keywords: data mining, cluster analysis, patient examination history, a large collection of raw examination data, the framework allows the identification of clusters containing patients with a similar examination history. The multiple-level strategy adopted in this study exploits the DBSCAN algorithm to select the dataset part analyzed at each iteration and locally cluster The proposed framework to analyse the patient examination history contains four main steps: (i) data collection, (ii) data transformation, (iii) cluster Figure 1: The proposed framework for the cluster analysis of patient examination data the similarity between patient examination histories, while Section 4.2.2 describes how the DBSCAN parameters and the number of clustering levels Second-level clusters collect patients that are tested using an increasing number of examinations to	./cache/work_slbvbdfjyzhnfkl3t2tfdiqp7a.pdf	./txt/work_slbvbdfjyzhnfkl3t2tfdiqp7a.txt