Mining medical data: a case study of endometriosis

Ultrasound guided aspiration of ovarian endometrioma had been tried as an alternative therapeutic modality in patients whose desire to avoid surgery or surgical approach is contraindicated since 1991. Cyst puncture can reduce tumor volume and destruct the cyst wall, alleviate sticking circumstances and enhance the chance of recovery. But simple aspiration without other treatments results in high recurrence rate (28.5 % to 100 %). In order to reduce recurrence after aspiration, ultrasound-guided aspiration with instillation of tetracycline, methotrexate, and recombinant interleukin-2 has been combined and proven to be effective with the recurrence rates of 46.9 %, 18.1 %, and 40 % respectively. Noma et al. (2001) reported that conduct of ethanol instillation for more than 10 min particularly for a case with a single endometrial cyst is considered most effective from the standpoint of recurrence (14.9 %). Our goal is to analyze patients with recurrent pelvic cyst who underwent surgical intervention. The research data are based on clinical diagnosis, symptoms and medical intervention classification, and the cyst numbers are defined as forecast project target. The decision tree, methodology of data mining technology, is used to find the meaningful characteristic as well as each other mutually connection. The experimental result can help the clinical faculty doctors to better diagnose and provide treatment reference for future patients.