NimbleMiner: An Open-Source Nursing-Sensitive Natural Language Processing System Based on Word Embedding.

This study develops and evaluates an open-source software (called NimbleMiner) that allows clinicians to interact with word embedding models with a goal of creating lexicons of similar terms. As a case study, the system was used to identify similar terms for patient fall history from homecare visit notes (N = 1 149 586) extracted from a large US homecare agency. Several experiments with parameters of word embedding models were conducted to identify the most time-effective and high-quality model. Models with larger word window width sizes (n = 10) that present users with about 50 top potentially similar terms for each (true) term validated by the user were most effective. NimbleMiner can assist in building a thorough vocabulary of fall history terms in about 2 hours. For domains like nursing, this approach could offer a valuable tool for rapid lexicon enrichment and discovery.

Extracting Alcohol and Substance Abuse Status from Clinical Notes: The Added Value of Nursing Data.

We applied an open source natural language processing (NLP) system "NimbleMiner" to identify clinical notes with mentions of alcohol and substance abuse. NimbleMiner allows users to rapidly discover clinical vocabularies (using word embedding model) and then implement machine learning for text classification. We used a large inpatient dataset with over 50,000 intensive care unit admissions (MIMIC II). Clinical notes included physician-written discharge summaries (n = 51,201) and nursing notes (n = 412,343). We first used physician-written discharge summaries to train the system's algorithm and then added nursing notes to the physician-written discharge summaries and evaluated algorithms prediction accuracy. Adding nursing notes to the physician-written discharge summaries resulted in almost two-fold vocabulary expansion. NimbleMiner slightly outperformed other state-of-the-art NLP systems (average F-score = .84), while requiring significantly less time for the algorithms development.: Our findings underline the importance of nursing data for the analysis of electronic patient records.

Identifying Diabetes in Clinical Notes in Hebrew: A Novel Text Classification Approach Based on Word Embedding.

NimbleMiner is a word embedding-based, language-agnostic natural language processing system for clinical text classification. Previously, NimbleMiner was applied in English and this study applied NimbleMiner on a large sample of inpatient clinical notes in Hebrew to identify instances of diabetes mellitus. The study data included 521,278 clinical notes (one admission and one discharge note per patient) for 268,664 hospital admissions to medical-surgical units of a large hospital in Israel. NimbleMiner achieved overall good performance (F-score =.94) when tested on a gold standard human annotated dataset of 800 clinical notes. We found 15% more patients with diabetes mentioned in the clinical notes compared with diagnoses data. Our findings about underreporting of diabetes in the coded diagnoses data highlight the urgent need for tools and algorithms that will help busy providers identify a range of useful information, like having a diabetes.

Mining fall-related information in clinical notes: Comparison of rule-based and novel word embedding-based machine learning approaches.

BACKGROUND: Natural language processing (NLP) of health-related data is still an expertise demanding, and resource expensive process. We created a novel, open source rapid clinical text mining system called NimbleMiner. NimbleMiner combines several machine learning techniques (word embedding models and positive only labels learning) to facilitate the process in which a human rapidly performs text mining of clinical narratives, while being aided by the machine learning components. OBJECTIVE: This manuscript describes the general system architecture and user Interface and presents results of a case study aimed at classifying fall-related information (including fall history, fall prevention interventions, and fall risk) in homecare visit notes. METHODS: We extracted a corpus of homecare visit notes (n = 1,149,586) for 89,459 patients from a large US-based homecare agency. We used a gold standard testing dataset of 750 notes annotated by two human reviewers to compare the NimbleMiner's ability to classify documents regarding whether they contain fall-related information with a previously developed rule-based NLP system. RESULTS: NimbleMiner outperformed the rule-based system in almost all domains. The overall F- score was 85.8% compared to 81% by the rule based-system with the best performance for identifying general fall history (F = 89% vs. F = 85.1% rule-based), followed by fall risk (F = 87% vs. F = 78.7% rule-based), fall prevention interventions (F = 88.1% vs. F = 78.2% rule-based) and fall within 2 days of the note date (F = 83.1% vs. F = 80.6% rule-based). The rule-based system achieved slightly better performance for fall within 2 weeks of the note date (F = 81.9% vs. F = 84% rule-based). DISCUSSION & CONCLUSIONS: NimbleMiner outperformed other systems aimed at fall information classification, including our previously developed rule-based approach. These promising results indicate that clinical text mining can be implemented without the need for large labeled datasets necessary for other types of machine learning. This is critical for domains with little NLP developments, like nursing or allied health professions.