SemEHR: A general-purpose semantic search system to surface semantic data from clinical notes for tailored care, trial recruitment, and clinical research

Embedding research recruitment in a community resource e-prescribing system: lessons from an implementation study on Chicago's South Side

OBJECTIVE

The study sought to implement and assess the CommunityRx e-prescribing system to recruit research participants from a predominantly non-Hispanic Black community on Chicago's South Side.

MATERIALS AND METHODS

CommunityRx integrates with electronic medical record systems to generate a personalized list of health-promoting community resources (HealtheRx). Between December 2015 and December 2016, HealtheRxs distributed at outpatient visits to adults with asthma or chronic obstructive pulmonary disease also incentivized participation in a pulmonary research registry. Usual practices for registry recruitment continued in parallel.

RESULTS

Focus groups established acceptability and appropriateness among the target population. Pulmonary research registry recruitment information was included on 13 437 HealtheRxs. Forty-one (90% non-Hispanic Black) patients responded with willingness to participate and 9 (8 non-Hispanic Black) returned a signed consent required to enroll. Usual recruitment practices enrolled 4 registrants (1 non-Hispanic Black).

DISCUSSION

Automating research recruitment using a community e-prescribing system is feasible.

CONCLUSIONS

Implementation of an electronic medical record-integrated, community resource referral tool promotes enrollment of eligible underrepresented research participants; however, enrollment was low.

Medicines in pregnancy

Medicine use in pregnancy is extremely common, but there are significant knowledge gaps surrounding the safety, dosage and long-term effects of drugs used. Pregnant women have been purposively excluded from clinical trials of the majority of treatments for conditions that may occur concurrently with pregnancy. There is minimal information on the pharmacokinetics of many existing treatments and no systematic capture of long-term outcome data to help inform choices. Treatments commonly used in pregnancy are thus often old and untested, not optimised in dose, and prescribed off-label without adequate safety information. In addition, there has been a staggering lack of investment in drug development for obstetric conditions for decades. This is a major public health concern, and pregnancy complications are the leading cause of mortality in children under five years old globally, and health in pregnancy is a major determinant of women's long-term health and wellbeing. There is an acute need for adequate investment and legislation to boost inclusion of pregnant women in clinical studies, capture high-quality information on medication use in pregnancy in general, and encourage new medicinal product development for obstetric conditions.

Using clinical Natural Language Processing for health outcomes research: Overview and actionable suggestions for future advances

The importance of incorporating Natural Language Processing (NLP) methods in clinical informatics research has been increasingly recognized over the past years, and has led to transformative advances. Typically, clinical NLP systems are developed and evaluated on word, sentence, or document level annotations that model specific attributes and features, such as document content (e.g., patient status, or report type), document section types (e.g., current medications, past medical history, or discharge summary), named entities and concepts (e.g., diagnoses, symptoms, or treatments) or semantic attributes (e.g., negation, severity, or temporality). From a clinical perspective, on the other hand, research studies are typically modelled and evaluated on a patient- or population-level, such as predicting how a patient group might respond to specific treatments or patient monitoring over time. While some NLP tasks consider predictions at the individual or group user level, these tasks still constitute a minority. Owing to the discrepancy between scientific objectives of each field, and because of differences in methodological evaluation priorities, there is no clear alignment between these evaluation approaches. Here we provide a broad summary and outline of the challenging issues involved in defining appropriate intrinsic and extrinsic evaluation methods for NLP research that is to be used for clinical outcomes research, and vice versa. A particular focus is placed on mental health research, an area still relatively understudied by the clinical NLP research community, but where NLP methods are of notable relevance. Recent advances in clinical NLP method development have been significant, but we propose more emphasis needs to be placed on rigorous evaluation for the field to advance further. To enable this, we provide actionable suggestions, including a minimal protocol that could be used when reporting clinical NLP method development and its evaluation.