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.

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).

Patient-centered care via health information technology: a qualitative study with experts from Israel and the U.S.

Although patient-centered care (PCC) is one of the cornerstones of modern healthcare, the role that health information technology (HIT) plays in supporting PCC remains unclear. In this qualitative study, we interviewed academic and clinical experts from the US and Israel to understand to what extent current HIT systems are supportive of PCC and how PCC should be supported by HIT in the future. A maximum variation sampling approach was used to identify nine experts in both HIT and PCC from clinical and academic settings in Israel and the US.

Mining social media data to assess the risk of skin and soft tissue infections from allergen immunotherapy.

Background: Allergen immunotherapy (AIT) treatment for allergic rhinitis and asthma is used by 2.6 million Americans annually. Clinical and sterility testing studies identify no risk of contamination or infection from extracts prepared using recommended aseptic techniques, but regulatory concerns persist.

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.

Improving patient prioritization during hospital-homecare transition: A pilot study of a clinical decision support tool.

Patient admission to homecare is a complex process. Medicare policy requires that all patients receive a first home visit within 48 hr after the referral is received at the homecare agency. For unstable or high risk patients, waiting 48 hr to be seen by homecare nurses may not be safe.

Nonpainful wide-area compression inhibits experimental pain.

Compression therapy, a well-recognized treatment for lymphoedema and venous disorders, pressurizes limbs and generates massive non-noxious afferent sensory barrages. The aim of this study was to study whether such afferent activity has an analgesic effect when applied on the lower limbs, hypothesizing that larger compression areas will induce stronger analgesic effects, and whether this effect correlates with conditioned pain modulation (CPM). Thirty young healthy subjects received painful heat and pressure stimuli (47°C for 30 seconds, forearm; 300 kPa for 15 seconds, wrist) before and during 3 compression protocols of either SMALL (up to ankles), MEDIUM (up to knees), or LARGE (up to hips) compression areas.