Faculty Bibliography

BACKGROUND:Although clinical decision support (CDS) alerts are effective reminders of best practices, their effectiveness is blunted by clinicians who fail to respond to an overabundance of inappropriate alerts. An electronic health record (EHR)-integrated machine learning (ML) algorithm is a potentially powerful tool to increase the signal-to-noise ratio of CDS alerts and positively impact the clinician's interaction with these alerts in general. OBJECTIVE:This study aimed to describe the development and implementation of an ML-based signal-to-noise optimization system (SmartCDS) to increase the signal of alerts by decreasing the volume of low-value herpes zoster (shingles) vaccination alerts. METHODS:We built and deployed SmartCDS, which builds personalized user activity profiles to suppress shingles vaccination alerts unlikely to yield a clinician's interaction. We extracted all records of shingles alerts from January 2017 to March 2019 from our EHR system, including 327,737 encounters, 780 providers, and 144,438 patients. RESULTS:During the 6 weeks of pilot deployment, the SmartCDS system suppressed an average of 43.67% (15,425/35,315) potential shingles alerts (appointments) and maintained stable counts of weekly shingles vaccination orders (326.3 with system active vs 331.3 in the control group; P=.38) and weekly user-alert interactions (1118.3 with system active vs 1166.3 in the control group; P=.20). CONCLUSIONS:All key statistics remained stable while the system was turned on. Although the results are promising, the characteristics of the system can be subject to future data shifts, which require automated logging and monitoring. We demonstrated that an automated, ML-based method and data architecture to suppress alerts are feasible without detriment to overall order rates. This work is the first alert suppression ML-based model deployed in practice and serves as foundational work in encounter-level customization of alert display to maximize effectiveness.

INTRODUCTION AND AIMS/OBJECTIVE:This article examines the feasibility of leveraging Twitter to detect posts authored by people who use opioids (PWUO) or content related to opioid use disorder (OUD), and manually develop a multidimensional taxonomy of relevant tweets. DESIGN AND METHODS/METHODS:Twitter messages were collected between June and October 2017 (n = 23 827) and evaluated using an inductive coding approach. Content was then manually classified into two axes (n = 17 420): (i) user experience regarding accessing, using, or recovery from illicit opioids; and (ii) content categories (e.g. policies, medical information, jokes/sarcasm). RESULTS:The most prevalent categories consisted of jokes or sarcastic comments pertaining to OUD, PWUOs or hypothetically using illicit opioids (63%), informational content about treatments for OUD, overdose prevention or accessing self-help groups (20%), and commentary about government opioid policy or news related to opioids (17%). Posts by PWUOs centered on identifying illicit sources for procuring opioids (i.e. online, drug dealers; 49%), symptoms and/or strategies to quell opioid withdrawal symptoms (21%), and combining illicit opioid use with other substances, such as cocaine or benzodiazepines (17%). State and public health experts infrequently posted content pertaining to OUD (1%). DISCUSSION AND CONCLUSIONS/CONCLUSIONS:Twitter offers a feasible approach to identify PWUO. Further research is needed to evaluate the efficacy of Twitter to disseminate evidence-based content and facilitate linkage to treatment and harm reduction services.

The trend of e-cigarette use among teens is ever increasing. Here we show the dysbiotic oral microbial ecology in e-cigarette users influencing the local host immune environment compared with non-smoker controls and cigarette smokers. Using 16S rRNA high-throughput sequencing, we evaluated 119 human participants, 40 in each of the three cohorts, and found significantly altered beta-diversity in e-cigarette users (p = 0.006) when compared with never smokers or tobacco cigarette smokers. The abundance of Porphyromonas and Veillonella (p = 0.008) was higher among vapers. Interleukin (IL)-6 and IL-1β were highly elevated in e-cigarette users when compared with non-users. Epithelial cell-exposed e-cigarette aerosols were more susceptible for infection. In vitro infection model of premalignant Leuk-1 and malignant cell lines exposed to e-cigarette aerosol and challenged by Porphyromonas gingivalis and Fusobacterium nucleatum resulted in elevated inflammatory response. Our findings for the first time demonstrate that e-cigarette users are more prone to infection.

[This corrects the article DOI: 10.1371/journal.pone.0215571.].

BACKGROUND:Because of the strong link between childhood obesity and adulthood obesity comorbidities, and the difficulty in decreasing body mass index (BMI) later in life, effective strategies are needed to address this condition in early childhood. The ability to predict obesity before age five could be a useful tool, allowing prevention strategies to focus on high risk children. The few existing prediction models for obesity in childhood have primarily employed data from longitudinal cohort studies, relying on difficult to collect data that are not readily available to all practitioners. Instead, we utilized real-world unaugmented electronic health record (EHR) data from the first two years of life to predict obesity status at age five, an approach not yet taken in pediatric obesity research. METHODS AND FINDINGS/RESULTS:We trained a variety of machine learning algorithms to perform both binary classification and regression. Following previous studies demonstrating different obesity determinants for boys and girls, we similarly developed separate models for both groups. In each of the separate models for boys and girls we found that weight for length z-score, BMI between 19 and 24 months, and the last BMI measure recorded before age two were the most important features for prediction. The best performing models were able to predict obesity with an Area Under the Receiver Operator Characteristic Curve (AUC) of 81.7% for girls and 76.1% for boys. CONCLUSIONS:We were able to predict obesity at age five using EHR data with an AUC comparable to cohort-based studies, reducing the need for investment in additional data collection. Our results suggest that machine learning approaches for predicting future childhood obesity using EHR data could improve the ability of clinicians and researchers to drive future policy, intervention design, and the decision-making process in a clinical setting.

Conventional text classification models make a bag-of-words assumption reducing text into word occurrence counts per document. Recent algorithms such as word2vec are capable of learning semantic meaning and similarity between words in an entirely unsupervised manner using a contextual window and doing so much faster than previous methods. Each word is projected into vector space such that similar meaning words such as "strong" and "powerful" are projected into the same general Euclidean space. Open questions about these embeddings include their utility across classification tasks and the optimal properties and source of documents to construct broadly functional embeddings. In this work, we demonstrate the usefulness of pre-trained embeddings for classification in our task and demonstrate that custom word embeddings, built in the domain and for the tasks, can improve performance over word embeddings learnt on more general data including news articles or Wikipedia.

Natural Language Processing (NLP) holds potential for patient care and clinical research, but a gap exists between promise and reality. While some studies have demonstrated portability of NLP systems across multiple sites, challenges remain. Strategies to mitigate these challenges can strive for complex NLP problems using advanced methods (hard-to-reach fruit), or focus on simple NLP problems using practical methods (low-hanging fruit). This paper investigates a practical strategy for NLP portability using extraction of left ventricular ejection fraction (LVEF) as a use case. We used a tool developed at the Department of Veterans Affair (VA) to extract the LVEF values from free-text echocardiograms in the MIMIC-III database. The approach showed an accuracy of 98.4%, sensitivity of 99.4%, a positive predictive value of 98.7%, and F-score of 99.0%. This experience, in which a simple NLP solution proved highly portable with excellent performance, illustrates the point that simple NLP applications may be easier to disseminate and adapt, and in the short term may prove more useful, than complex applications.