Showing papers by "Sarvnaz Karimi published in 2017"

Automatic Diagnosis Coding of Radiology Reports: A Comparison of Deep Learning and Conventional Classification Methods

Abstract: Diagnosis autocoding services and research intend to both improve the productivity of clinical coders and the accuracy of the coding. It is an important step in data analysis for funding and reimbursement, as well as health services planning and resource allocation. We investigate the applicability of deep learning at autocoding of radiology reports using International Classification of Diseases (ICD). Deep learning methods are known to require large training data. Our goal is to explore how to use these methods when the training data is sparse, skewed and relatively small, and how their effectiveness compares to conventional methods. We identify optimal parameters that could be used in setting up a convolutional neural network for autocoding with comparable results to that of conventional methods.

Medication and Adverse Event Extraction from Noisy Text

Abstract: We investigate the problem of extracting mentions of medications and adverse drug events using sequence labelling and nonsequence labelling methods. We experiment with three different methods on two different datasets, one from a patient forum with noisy text and one containing narrative patient records. An analysis of the output from these methods are reported to identify what types of named entities are best identified using these methods and, more specifically, how well the discontinuous and overlapping entities that are prevalent in our forum dataset are identified. Our findings can guide studies to choose different methods based on the complexity of the named entities involved, in particular in text mining for pharmacovigilance.

CSIRO at 2017 TREC Precision Medicine Track.

Abstract: TREC Precision Medicine track focuses on search tasks tailored for oncologists. Given a cancer patient, the proposed systems must find clinical trials that match the patient, as well as the relevant information from biomedical literature (PubMed abstracts 2019 baseline). In our experiments, we compare BM25 and Divergence from Randomness (DFR) baselines and report results obtained with multiple learning-torank models. Some of our submitted runs score in top ten runs reported by the organisers.