Fernando Campos

A Machine Learning Approach to Clinical Terms Normalization.

We propose a machine learning approach for semantic recognition and normalization of clinical term descriptions. Clinical terms considered here are noisy descriptions in Spanish language written by health care professionals in our electronic health record system. These description terms contain clinical findings, family history, suspected disease, among other categories of concepts. Descriptions are usually very short texts presenting high lexical variability containing synonymy, acronyms, abbreviations and typographical errors. Mapping description terms to normalized descriptions requires medical expertise which makes it difficult to develop a rule-based knowledge engineering approach. In order to build a training dataset we use those descriptions that have been previously matched by terminologists to the hospital thesaurus database. We generate a set of feature vectors based on pairs of descriptions involving their individual and joint characteristics. We propose an unsupervised learning approach to discover term equivalence classes including synonyms, abbreviations, acronyms and frequent typographical errors. We evaluate different combinations of features to train MaxEnt and XGBoost models. Our system achieves an F1 score of 89% on the Hospital Italiano de Buenos Aires (HIBA) problem list.

Design, Implementation and Evaluation of an Architecture based on the CDA R2 Document Repository to Provide Support to the Contingency Plan.

The pervasive use of electronic records in healthcare increases the dependency on technology due to the lack of physical backup for the records. Downtime in the Electronic Health Record system is unavoidable, due to software, infrastructure and power failures as well as natural disasters, so there is a need to develop a contingency plan ensuring patient care continuity and minimizing risks for health care delivery. To mitigate these risks, two applications were developed allowing healthcare delivery providers to retrieve clinical information using the Clinical Document Architecture Release 2 (CDA R2) document repository as the information source. In this paper we describe the strategy, implementation and results; and provide an evaluation of effectiveness.