Development and evaluation of a text analytics algorithm for automated application of national COVID-19 shielding criteria in rheumatology patients.

INTRODUCTION: At the beginning of the COVID-19 pandemic, the UK's Scientific Committee issued extreme social distancing measures, termed 'shielding', aimed at a subpopulation deemed extremely clinically vulnerable to infection. National guidance for risk stratification was based on patients' age, comorbidities and immunosuppressive therapies, including biologics that are not captured in primary care records. This process required considerable clinician time to manually review outpatient letters. Our aim was to develop and evaluate an automated shielding algorithm by text-mining outpatient letter diagnoses and medications, reducing the need for future manual review. METHODS: Rheumatology outpatient letters from a large UK foundation trust were retrieved. Free-text diagnoses were processed using Intelligent Medical Objects software (Concept Tagger), which used interface terminology for each condition mapped to Systematized Medical Nomenclature for Medicine-Clinical Terminology (SNOMED-CT) codes. We developed the Medication Concept Recognition tool (Named Entity Recognition) to retrieve medications' type, dose, duration and status (active/past) at the time of the letter. Age, diagnosis and medication variables were then combined to calculate a shielding score based on the most recent letter. The algorithm's performance was evaluated using clinical review as the gold standard. The time taken to deploy the developed algorithm on a larger patient subset was measured. RESULTS: In total, 5942 free-text diagnoses were extracted and mapped to SNOMED-CT, with 13 665 free-text medications (n=803 patients). The automated algorithm demonstrated a sensitivity of 80% (95% CI: 75%, 85%) and specificity of 92% (95% CI: 90%, 94%). Positive likelihood ratio was 10 (95% CI: 8, 14), negative likelihood ratio was 0.21 (95% CI: 0.16, 0.28) and F1 score was 0.81. Evaluation of mismatches revealed that the algorithm performed correctly against the gold standard in most cases. The developed algorithm was then deployed on records from an additional 15 865 patients, which took 18 hours for data extraction and 1 hour to deploy. DISCUSSION: An automated algorithm for risk stratification has several advantages including reducing clinician time for manual review to allow more time for direct care, improving efficiency and increasing transparency in individual patient communication. It has the potential to be adapted for future public health initiatives that require prompt automated review of hospital outpatient letters.

Extracting Drug Names and Associated Attributes From Discharge Summaries: Text Mining Study.

BACKGROUND: Drug prescriptions are often recorded in free-text clinical narratives; making this information available in a structured form is important to support many health-related tasks. Although several natural language processing (NLP) methods have been proposed to extract such information, many challenges remain. OBJECTIVE: This study evaluates the feasibility of using NLP and deep learning approaches for extracting and linking drug names and associated attributes identified in clinical free-text notes and presents an extensive error analysis of different methods. This study initiated with the participation in the 2018 National NLP Clinical Challenges (n2c2) shared task on adverse drug events and medication extraction. METHODS: The proposed system (DrugEx) consists of a named entity recognizer (NER) to identify drugs and associated attributes and a relation extraction (RE) method to identify the relations between them. For NER, we explored deep learning-based approaches (ie, bidirectional long-short term memory with conditional random fields [BiLSTM-CRFs]) with various embeddings (ie, word embedding, character embedding [CE], and semantic-feature embedding) to investigate how different embeddings influence the performance. A rule-based method was implemented for RE and compared with a context-aware long-short term memory (LSTM) model. The methods were trained and evaluated using the 2018 n2c2 shared task data. RESULTS: The experiments showed that the best model (BiLSTM-CRFs with pretrained word embeddings [PWE] and CE) achieved lenient micro F-scores of 0.921 for NER, 0.927 for RE, and 0.855 for the end-to-end system. NER, which relies on the pretrained word and semantic embeddings, performed better on most individual entity types, but NER with PWE and CE had the highest classification efficiency among the proposed approaches. Extracting relations using the rule-based method achieved higher accuracy than the context-aware LSTM for most relations. Interestingly, the LSTM model performed notably better in the reason-drug relations, the most challenging relation type. CONCLUSIONS: The proposed end-to-end system achieved encouraging results and demonstrated the feasibility of using deep learning methods to extract medication information from free-text data.

Data and systems for medication-related text classification and concept normalization from Twitter: insights from the Social Media Mining for Health (SMM4H)-2017 shared task.

Objective: We executed the Social Media Mining for Health (SMM4H) 2017 shared tasks to enable the community-driven development and large-scale evaluation of automatic text processing methods for the classification and normalization of health-related text from social media. An additional objective was to publicly release manually annotated data. Materials and Methods: We organized 3 independent subtasks: automatic classification of self-reports of 1) adverse drug reactions (ADRs) and 2) medication consumption, from medication-mentioning tweets, and 3) normalization of ADR expressions. Training data consisted of 15 717 annotated tweets for (1), 10 260 for (2), and 6650 ADR phrases and identifiers for (3); and exhibited typical properties of social-media-based health-related texts. Systems were evaluated using 9961, 7513, and 2500 instances for the 3 subtasks, respectively. We evaluated performances of classes of methods and ensembles of system combinations following the shared tasks. Results: Among 55 system runs, the best system scores for the 3 subtasks were 0.435 (ADR class F1-score) for subtask-1, 0.693 (micro-averaged F1-score over two classes) for subtask-2, and 88.5% (accuracy) for subtask-3. Ensembles of system combinations obtained best scores of 0.476, 0.702, and 88.7%, outperforming individual systems. Discussion: Among individual systems, support vector machines and convolutional neural networks showed high performance. Performance gains achieved by ensembles of system combinations suggest that such strategies may be suitable for operational systems relying on difficult text classification tasks (eg, subtask-1). Conclusions: Data imbalance and lack of context remain challenges for natural language processing of social media text. Annotated data from the shared task have been made available as reference standards for future studies (http://dx.doi.org/10.17632/rxwfb3tysd.1).

Erratum: Author Correction: Frequent discussion of insomnia and weight gain with glucocorticoid therapy: an analysis of Twitter posts.

[This corrects the article DOI: 10.1038/s41746-017-0007-z.].

Frequent discussion of insomnia and weight gain with glucocorticoid therapy: An analysis of Twitter posts.

In recent years, social media websites have been suggested as a novel, vast source of data which may be useful for deriving drug safety information. Despite this, there are few published reports of drug safety profiles derived in this way. The aims of this study were to detect and quantify glucocorticoid-related adverse events using a computerised system for automated detection of suspected adverse drug reactions (ADR) from narrative text in Twitter, and to compare the frequency of specific ADR mentions within Twitter to the frequency and patterns of spontaneous ADR reporting to a national drug regulatory body. Of 159,297 tweets mentioning either prednisolone or prednisone between 1st October 2012 and 30th June 2015, 20,206 tweets were deemed to contain information resembling an ADR. The top AE MedDRA® Preferred Terms were 'insomnia' and 'weight increased', both recognised non-serious but common side effects. These were proportionally over-reported in Twitter when compared to spontaneous reports in the UK regulator's ADR reporting scheme. Serious glucocorticoid related AEs were reported less frequently. Pharmacovigilance using Twitter data has the potential to be a valuable, supplementary source of drug safety information. In particular, it can illustrate which drug side effects patients discuss most commonly, potentially because of important impacts on quality of life. This information could help clinicians to inform patients about frequent and relevant non-serious side effects as well as more serious side effects.

#WhyWeTweetMH: Understanding Why People Use Twitter to Discuss Mental Health Problems.

BACKGROUND: Use of the social media website Twitter is highly prevalent and has led to a plethora of Web-based social and health-related data available for use by researchers. As such, researchers are increasingly using data from social media to retrieve and analyze mental health-related content. However, there is limited evidence regarding why people use this emerging platform to discuss mental health problems in the first place. OBJECTIVES: The aim of this study was to explore the reasons why individuals discuss mental health on the social media website Twitter. The study was the first of its kind to implement a study-specific hashtag for research; therefore, we also examined how feasible it was to circulate and analyze a study-specific hashtag for mental health research. METHODS: Text mining methods using the Twitter Streaming Application Programming Interface (API) and Twitter Search API were used to collect and organize tweets from the hashtag #WhyWeTweetMH, circulated between September 2015 and November 2015. Tweets were analyzed thematically to understand the key reasons for discussing mental health using the Twitter platform. RESULTS: Four overarching themes were derived from the 132 tweets collected: (1) sense of community; (2) raising awareness and combatting stigma; (3) safe space for expression; and (4) coping and empowerment. In addition, 11 associated subthemes were also identified. CONCLUSIONS: The themes derived from the content of the tweets highlight the perceived therapeutic benefits of Twitter through the provision of support and information and the potential for self-management strategies. The ability to use Twitter to combat stigma and raise awareness of mental health problems indicates the societal benefits that can be facilitated via the platform. The number of tweets and themes identified demonstrates the feasibility of implementing study-specific hashtags to explore research questions in the field of mental health and can be used as a basis for other health-related research.