ABSTRACT
The rapid increase of medical literature poses a significant challenge for physicians, who have repeatedly reported to struggle to keep up to date with developments in research. This gap is one of the main challenges in integrating recent advances in clinical research with day-to-day practice. Thus, the need for clinical decision support (CDS) search systems that can retrieve highly relevant medical literature given a clinical note describing a patient has emerged. However, clinical notes are inherently noisy, thus not being fit to be used as queries as-is. In this work, we present a convolutional neural model aimed at improving clinical notes representation, making them suitable for document retrieval. The system is designed to predict, for each clinical note term, its importance in relevant documents. The approach was evaluated on the 2016 TREC CDS dataset, where it achieved a 37% improvement in infNDCG over state-of-the-art query reduction methods and a 27% improvement over the best known method for the task.
- Saeid Balaneshin-kordan and Alexander Kotov. 2016. Optimization method for weighting explicit and latent concepts in clinical decision support queries. In ICTIR. Google ScholarDigital Library
- Michael Bendersky, Donald Metzler, and W Bruce Croft. 2011. Parameterized concept weighting in verbose queries SIGIR. ACM. Google ScholarDigital Library
- Steven Bethard, Guergana Savova, Wei-Te Chen, Leon Derczynski, James Pustejovsky, and Marc Verhagen. 2016. Semeval-2016 task 12: Clinical tempeval. SemEval (2016).Google Scholar
- Yoon Kim. 2014. Convolutional neural networks for sentence classification. arXiv:1408.5882 (2014).Google Scholar
- Diederik Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv:1412.6980 (2014).Google Scholar
- Giridhar Kumaran and Vitor R Carvalho. 2009. Reducing long queries using query quality predictors SIGIR. Google ScholarDigital Library
- André Mourao, Flávio Martins, and Joao Magalhaes. 2014. NovaSearch at TREC 2014 clinical decision support track TREC.Google Scholar
- Eitan Naveh, Tal Katz-Navon, and Zvi Stern. 2015. Resident physicians' clinical training and error rate: the roles of autonomy, consultation, and familiarity with the literature. Advances in Health Sciences Education 1 (2015), 59--71.Google ScholarCross Ref
- Heung-Seon Oh and Yuchul Jung. 2015. Cluster-based query expansion using external collections in medical information retrieval. Journal of Biomedical Informatics (2015). Google ScholarDigital Library
- Jeffrey Pennington, Richard Socher, and Christopher D. Manning. 2014. GloVe: Global Vectors for Word Representation. In EMNLP.Google Scholar
- Kirk Roberts. 2016. Assessing the Corpus Size vs Similarity Trade-off for Word Embeddings in Clinical NLP ClinicalNLP workshop at COLING 2016.Google Scholar
- Kirk Roberts, Dina Demner-Fushman, Ellen M Voorhees, and William R Hersh. 2017. Overview of the TREC 2016 Clinical Decision Support Track. TREC.Google Scholar
- Aliaksei Severyn and Alessandro Moschitti. 2015. Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks SIGIR. Google ScholarDigital Library
- Luca Soldaini, Arman Cohan, Andrew Yates, Nazli Goharian, and Ophir Frieder. 2015. Retrieving medical literature for clinical decision support ECIR.Google Scholar
- Luca Soldaini and Nazli Goharian. 2016. QuickUMLS: a fast, unsupervised approach for medical concept extraction MedIR Workshop at SIGIR.Google Scholar
- Luca Soldaini, Andrew Yates, and Nazli Goharian. 2017. Learning to Reformulate Long Queries for Clinical Decision Support. JASIST (2017).Google Scholar
- Emine Yilmaz, Evangelos Kanoulas, and Javed A Aslam. 2008. A simple and efficient sampling method for estimating AP and NDCG SIGIR. Google ScholarDigital Library
- Hualong Zhang and Liting Liu. 2017. NKU at TREC 2016: Clinical Decision Support Track. (2017).Google Scholar
Index Terms
- Denoising Clinical Notes for Medical Literature Retrieval with Convolutional Neural Model
Recommendations
A Review of Analytics and Clinical Informatics in Health Care
Federal investment in health information technology has incentivized the adoption of electronic health record systems by physicians and health care organizations; the result has been a massive rise in the collection of patient data in electronic form (...
Medical Specialists Retrieval System Using Unified Medical Language System
ICMHI '17: Proceedings of the 1st International Conference on Medical and Health Informatics 2017A large number of doctors and wide range of medical specialties can cause confusion in choosing the right medical specialist. This research aims to build a medical specialists retrieval system that corresponds with the user's disease. To make the system ...
Comments