Deployment of Real-time Natural Language Processing and Deep Learning Clinical Decision Support in the Electronic Health Record: Pipeline Implementation for an Opioid Misuse Screener in Hospitalized Adults

BACKGROUND

The clinical narrative in electronic health records (EHRs) carries valuable information for predictive analytics; however, its free-text form is difficult to mine and analyze for clinical decision support (CDS). Large-scale clinical natural language processing (NLP) pipelines have focused on data warehouse applications for retrospective research efforts. There remains a paucity of evidence for implementing NLP pipelines at the bedside for health care delivery.

OBJECTIVE

We aimed to detail a hospital-wide, operational pipeline to implement a real-time NLP-driven CDS tool and describe a protocol for an implementation framework with a user-centered design of the CDS tool.

METHODS

The pipeline integrated a previously trained open-source convolutional neural network model for screening opioid misuse that leveraged EHR notes mapped to standardized medical vocabularies in the Unified Medical Language System. A sample of 100 adult encounters were reviewed by a physician informaticist for silent testing of the deep learning algorithm before deployment. An end user interview survey was developed to examine the user acceptability of a best practice alert (BPA) to provide the screening results with recommendations. The planned implementation also included a human-centered design with user feedback on the BPA, an implementation framework with cost-effectiveness, and a noninferiority patient outcome analysis plan.

RESULTS

The pipeline was a reproducible workflow with a shared pseudocode for a cloud service to ingest, process, and store clinical notes as Health Level 7 messages from a major EHR vendor in an elastic cloud computing environment. Feature engineering of the notes used an open-source NLP engine, and the features were fed into the deep learning algorithm, with the results returned as a BPA in the EHR. On-site silent testing of the deep learning algorithm demonstrated a sensitivity of 93% (95% CI 66%-99%) and specificity of 92% (95% CI 84%-96%), similar to published validation studies. Before deployment, approvals were received across hospital committees for inpatient operations. Five interviews were conducted; they informed the development of an educational flyer and further modified the BPA to exclude certain patients and allow the refusal of recommendations. The longest delay in pipeline development was because of cybersecurity approvals, especially because of the exchange of protected health information between the Microsoft (Microsoft Corp) and Epic (Epic Systems Corp) cloud vendors. In silent testing, the resultant pipeline provided a BPA to the bedside within minutes of a provider entering a note in the EHR.

CONCLUSIONS

The components of the real-time NLP pipeline were detailed with open-source tools and pseudocode for other health systems to benchmark. The deployment of medical artificial intelligence systems in routine clinical care presents an important yet unfulfilled opportunity, and our protocol aimed to close the gap in the implementation of artificial intelligence-driven CDS.

TRIAL REGISTRATION

ClinicalTrials.gov NCT05745480; https://www.clinicaltrials.gov/ct2/show/NCT05745480.

Collaborative design and implementation of a clinical decision support system for automated fall-risk identification and referrals in emergency departments

Of the 3 million older adults seeking fall-related emergency care each year, nearly one-third visited the Emergency Department (ED) in the previous 6 months. ED providers have a great opportunity to refer patients for fall prevention services at these initial visits, but lack feasible tools for identifying those at highest-risk. Existing fall screening tools have been poorly adopted due to ED staff/provider burden and lack of workflow integration. To address this, we developed an automated clinical decision support (CDS) system for identifying and referring older adult ED patients at risk of future falls. We engaged an interdisciplinary design team (ED providers, health services researchers, information technology/predictive analytics professionals, and outpatient Falls Clinic staff) to collaboratively develop a system that successfully met user requirements and integrated seamlessly into existing ED workflows. Our rapid-cycle development and evaluation process employed a novel combination of human-centered design, implementation science, and patient experience strategies, facilitating simultaneous design of the CDS tool and intervention implementation strategies. This included defining system requirements, systematically identifying and resolving usability problems, assessing barriers and facilitators to implementation (e.g., data accessibility, lack of time, high patient volumes, appointment availability) from multiple vantage points, and refining protocols for communicating with referred patients at discharge. ED physician, nurse, and patient stakeholders were also engaged through online surveys and user testing. Successful CDS design and implementation required integration of multiple new technologies and processes into existing workflows, necessitating interdisciplinary collaboration from the onset. By using this iterative approach, we were able to design and implement an intervention meeting all project goals. Processes used in this Clinical-IT-Research partnership can be applied to other use cases involving automated risk-stratification, CDS development, and EHR-facilitated care coordination.

Emotion work in the public performances of male-to-female transsexuals

Much research has shown that entering the public sphere is emotionally taxing yet key to male-to-female transsexuals' status passage. Yet, little is known about how transsexuals actively manage their emotions during this important transitional phase. Taking a dramaturgical approach to emotions, we explored how some male-to-female transsexuals managed their emotions in ways that helped generate self-confidence and commitment to their paths. Interviewees engaged in three primary forms of emotion work: (1) preparatory emotion work mitigated anxiety and bolstered confidence, which motivated them to enter public arenas as women; (2) in situ emotion work transformed negative emotions as they arose when performing womanhood in public; and (3) retrospective emotion work reinterpreted past public performances to neutralize negative and accentuate positive emotions.

A cost effective, community based heart health promotion project in England: prospective comparative study

OBJECTIVE

To determine whether a community based coronary heart disease health promotion project, undertaken over four years, was associated with changes in the prevalence in adults of lifestyle risk factors known to affect the development of coronary heart disease, and to estimate whether such an approach was cost effective.

DESIGN

Prospective, comparative study of the effects of a health promotion intervention on coronary heart disease lifestyle risk factors, assessed by postal questionnaire sent to a randomly chosen sample, both at baseline and after four years.

SUBJECTS

Intervention and control populations of adults aged 18-64 in Rotherham, both from areas with a high incidence of coronary heart disease and similar socioeconomic composition.

MAIN OUTCOME MEASURES

Changes in prevalence of lifestyle risk factors between the control and intervention communities from 1991 to 1995. The effect of the intervention on certain lifestyle behaviours was evaluated using multiple logistic regression to model the proportion with a particular behaviour in the study communities as a function of age (18-40 or 41-64 years), sex, the year of observation (1991 or 1995), and area (intervention of control).

RESULTS

6.9% fewer people smoked and 8.7% more drank low fat milk in the intervention area, but no other statistically significant changes between the areas were detected. The estimated cost per life year gained was pounds 31.

CONCLUSIONS

It is possible to have a cost effective impact on coronary heart disease lifestyle risk factors in a population of adults over four years using only modest resources.

The impact of heart health promotion on coronary heart disease lifestyle risk factors in schoolchildren: lessons learnt from a community-based project

A community health promotion project called Action Heart was undertaken in two electoral wards in Rotherham to try to change lifestyles of people. Schools were included within the project. Coronary heart disease lifestyle risk factors were measured at baseline and after a three year period in the intervention area and a similar control area. Lifestyle factors in schoolchildren were measured separately from adults using a different instrument. The post intervention survey of adults and economic evaluation demonstrated that Action Heart had achieved cost-effective estimated health gains. In the schoolchildren however, a mixture of positive and negative risk factor changes in both areas was demonstrated. Significant changes in lifestyle risk factors in schoolchildren were not elicited using this approach. The possible reasons for the lack of impact on lifestyle risk factors in schoolchildren are examined and the implications for further work explored.