Entity Matching: A Case Study in the Medical Domain

In this paper, we propose a simple and effective solution for the entity matching problem involving data records of healthcare professionals. Our method depends on three attributes that are available in most data sources in the medical domain: name, specialty and address. We apply a blocking technique to avoid comparisons, three matchers for conciliating the data records and a rule-based heuristic to combine the matchers. We performed experiments involving data from three Brazilian Web sources of healthcare professionals. Our results show that our solution is able to avoid unnecessary comparisons and provides good results.