کشف الگوهای پنهان موجود در داده‌های بیماران مبتلا به سل

Background: Having precisely analyzed the data of patients with specific diseases we can obtain the patterns and knowledge of these disease or even specific characteristics of patients. A hypothesis is usually considered in medical studies when some data are gathered prospectively to prove or deny this hypothesis, but in many cases there may be relationships between the data of the patients which have never been attended and no hypothesis has been considered. Thus, in this study available hidden patterns in the data of patients with tuberculosis have been discovered. Methods: Data of the study included 600 patients with tuberculosis who had referred to Masih Daneshvari hospital of Tehran. Data were gathered by reading patients files and observing clinical tests of patients from hospital data system. APPIRIORI data mining technique and WEKA tool of data mining were utilized to discover the associative relationships of the data. Results: Hypertension diseases, diabetes insipidus and ischemic heart disease have had the most frequency in patients with tuberculosis. Patients with diabetes insipidus or night sweats had also experienced chronic cough. Patients who have had weight loss and had BK+ test one result, had also experienced chronic cough. Patients who have been coughing up blood and had BK+ sputum tests (3), had also experienced chronic cough. Male patients who had night sweats, had also experienced weight loss. Patients who have had weight loss and fever, had also experienced night sweats. Conclusion: Discovered rules can be considered as primary hypothesis for the upcoming studies especially those of clinical trials, In addition to this, physicians can use these rules to analyze the clinical condition of patients.