Mining clinical phrases from nursing notes to discover risk factors of patient deterioration. (March 2020)

• Record Type: Journal Article
• Authors: Korach, Zfania Tom; Yang, Jie; Rossetti, Sarah Collins; Cato, Kenrick D.; Kang, Min-Jeoung; Knaplund, Christopher; Schnock, Kumiko O.; Garcia, Jose P.; Jia, Haomiao; Schwartz, Jessica M.; Zhou, Li
• Is Part Of: International journal of medical informatics. Volume 135(2020)
• Publication Date: 2020-03
• Subjects: ICU intensive care unit -- RR rapid response -- EHR electronic health record -- NLP natural language processing -- RR Rapid response -- BoW bag-of-words -- BoNG bag-of-N-grams -- ML machine-learning -- QPM Quality Phrase Mining -- IR information-retrieval -- PoS part-of-speech -- CRF conditional-random fields -- NER named-entity recognition -- SMEs subject matter experts -- IRR inter-rater reliability -- AP average precision -- SD standard deviation -- HR hazard ratio; Data mining -- Nursing informatics -- Hospital Rapid response team -- Unsupervised machine learning; Medical informatics -- Periodicals; Information science -- Periodicals; Computers -- Periodicals; Medical technology -- Periodicals; Medical Informatics -- Periodicals; Technology, Medical -- Periodicals; Computers; Information science; Medical informatics; Medical technology; Electronic journals; Periodicals; Electronic journals; 610.285
• DOI: 10.1016/j.ijmedinf.2019.104053
• Languages: English
• ISSNs: 1386-5056

Abstract

Graphical abstract: Highlights: Nursing notes convey important signals about patient conditions and clinical outcomes. Unsupervised machine learning can identify phrases representing clinical entities. These phrases are useful for outcome prediction and risk factor identification. Abstract: Objective: Early identification and treatment of patient deterioration is crucial to improving clinical outcomes. To act, hospital rapid response (RR) teams often rely on nurses' clinical judgement typically documented narratively in the electronic health record (EHR). We developed a data-driven, unsupervised method to discover potential risk factors of RR events from nursing notes. Methods: We applied multiple natural language processing methods, including language modelling, word embeddings, and two phrase mining methods (TextRank and NC-Value), to identify quality phrases that represent clinical entities from unannotated nursing notes. TextRank was used to determine the important word-sequences in each note. NC-Value was then used to globally rank the locally-important sequences across the whole corpus. We evaluated our method both on its accuracy compared to human judgement and on the ability of the mined phrases to predict a clinical outcome, RR event hazard. Results: When applied to 61, 740 hospital encounters with 1, 067 RR events and 778, 955 notes, our method achieved an average precision of 0.590 to 0.764 (when excluding numeric tokens). Time-dependent covariates Cox model using the phrases achieved a concordance index of 0.739. Clustering the phrases revealed clinical concepts significantly associated with RR event hazard. Discussion: Our findings demonstrate that our minimal-annotation, unsurprised method can rapidly mine quality phrases from a large amount of nursing notes, and these identified phrases are useful for downstream tasks, such as clinical outcome predication and risk factor identification.