Semantic annotation of consumer health questions

CHQ- SocioEmo: Identifying Social and Emotional Support Needs in Consumer-Health Questions

General public, often called consumers, are increasingly seeking health information online. To be satisfactory, answers to health-related questions often have to go beyond informational needs. Automated approaches to consumer health question answering should be able to recognize the need for social and emotional support. Recently, large scale datasets have addressed the issue of medical question answering and highlighted the challenges associated with question classification from the standpoint of informational needs. However, there is a lack of annotated datasets for the non-informational needs. We introduce a new dataset for non-informational support needs, called CHQ-SocioEmo. The Dataset of Consumer Health Questions was collected from a community question answering forum and annotated with basic emotions and social support needs. This is the first publicly available resource for understanding non-informational support needs in consumer health-related questions online. We benchmark the corpus against multiple state-of-the-art classification models to demonstrate the dataset's effectiveness.

The Hmong Medical Corpus: a biomedical corpus for a minority language

Biomedical communication is an area that increasingly benefits from natural language processing (NLP) work. Biomedical named entity recognition (NER) in particular provides a foundation for advanced NLP applications, such as automated medical question-answering and translation services. However, while a large body of biomedical documents are available in an array of languages, most work in biomedical NER remains in English, with the remainder in official national or regional languages. Minority languages so far remain an underexplored area. The Hmong language, a minority language with sizable populations in several countries and without official status anywhere, represents an exceptional challenge for effective communication in medical contexts. Taking advantage of the large number of government-produced medical information documents in Hmong, we have developed the first named entity-annotated biomedical corpus for a resource-poor minority language. The Hmong Medical Corpus contains 100,535 tokens with 4554 named entities (NEs) of three UMLS semantic types: diseases/syndromes, signs/symptoms, and body parts/organs/organ components. Furthermore, a subset of the corpus is annotated for word position and parts of speech, representing the first such gold-standard dataset publicly available for Hmong. The methodology presented provides a readily reproducible approach for the creation of biomedical NE-annotated corpora for other resource-poor languages.

Classifying unstructured electronic consult messages to understand primary care physician specialty information needs

OBJECTIVE

Electronic consultation (eConsult) content reflects important information about referring clinician needs across an organization, but is challenging to extract. The objective of this work was to develop machine learning models for classifying eConsult questions for question type and question content. Another objective of this work was to investigate the ability to solve this task with constrained expert time resources.

MATERIALS AND METHODS

Our data source is the San Francisco Health Network eConsult system, with over 700 000 deidentified questions from the years 2008-2017, from gastroenterology, urology, and neurology specialties. We develop classifiers based on Bidirectional Encoder Representations from Transformers, experimenting with multitask learning to learn when information can be shared across classifiers. We produce learning curves to understand when we may be able to reduce the amount of human labeling required.

RESULTS

Multitask learning shows benefits only in the neurology-urology pair where they shared substantial similarities in the distribution of question types. Continued pretraining of models in new domains is highly effective. In the neurology-urology pair, near-peak performance is achieved with only 10% of the urology training data given all of the neurology data.

DISCUSSION

Sharing information across classifier types shows little benefit, whereas sharing classifier components across specialties can help if they are similar in the balance of procedural versus cognitive patient care.

CONCLUSION

We can accurately classify eConsult content with enough labeled data, but only in special cases do methods for reducing labeling effort apply. Future work should explore new learning paradigms to further reduce labeling effort.

An automated method to enrich consumer health vocabularies using GloVe word embeddings and an auxiliary lexical resource

BACKGROUND

Clear language makes communication easier between any two parties. A layman may have difficulty communicating with a professional due to not understanding the specialized terms common to the domain. In healthcare, it is rare to find a layman knowledgeable in medical terminology which can lead to poor understanding of their condition and/or treatment. To bridge this gap, several professional vocabularies and ontologies have been created to map laymen medical terms to professional medical terms and vice versa.

OBJECTIVE

Many of the presented vocabularies are built manually or semi-automatically requiring large investments of time and human effort and consequently the slow growth of these vocabularies. In this paper, we present an automatic method to enrich laymen's vocabularies that has the benefit of being able to be applied to vocabularies in any domain.

METHODS

Our entirely automatic approach uses machine learning, specifically Global Vectors for Word Embeddings (GloVe), on a corpus collected from a social media healthcare platform to extend and enhance consumer health vocabularies. Our approach further improves the consumer health vocabularies by incorporating synonyms and hyponyms from the WordNet ontology. The basic GloVe and our novel algorithms incorporating WordNet were evaluated using two laymen datasets from the National Library of Medicine (NLM), Open-Access Consumer Health Vocabulary (OAC CHV) and MedlinePlus Healthcare Vocabulary.

RESULTS

The results show that GloVe was able to find new laymen terms with an F-score of 48.44%. Furthermore, our enhanced GloVe approach outperformed basic GloVe with an average F-score of 61%, a relative improvement of 25%. Furthermore, the enhanced GloVe showed a statistical significance over the two ground truth datasets with P < 0.001.

CONCLUSIONS

This paper presents an automatic approach to enrich consumer health vocabularies using the GloVe word embeddings and an auxiliary lexical source, WordNet. Our approach was evaluated used healthcare text downloaded from MedHelp.org, a healthcare social media platform using two standard laymen vocabularies, OAC CHV, and MedlinePlus. We used the WordNet ontology to expand the healthcare corpus by including synonyms, hyponyms, and hypernyms for each layman term occurrence in the corpus. Given a seed term selected from a concept in the ontology, we measured our algorithms' ability to automatically extract synonyms for those terms that appeared in the ground truth concept. We found that enhanced GloVe outperformed GloVe with a relative improvement of 25% in the F-score.

Dataset search in biodiversity research: Do metadata in data repositories reflect scholarly information needs?

The increasing amount of publicly available research data provides the opportunity to link and integrate data in order to create and prove novel hypotheses, to repeat experiments or to compare recent data to data collected at a different time or place. However, recent studies have shown that retrieving relevant data for data reuse is a time-consuming task in daily research practice. In this study, we explore what hampers dataset retrieval in biodiversity research, a field that produces a large amount of heterogeneous data. In particular, we focus on scholarly search interests and metadata, the primary source of data in a dataset retrieval system. We show that existing metadata currently poorly reflect information needs and therefore are the biggest obstacle in retrieving relevant data. Our findings indicate that for data seekers in the biodiversity domain environments, materials and chemicals, species, biological and chemical processes, locations, data parameters and data types are important information categories. These interests are well covered in metadata elements of domain-specific standards. However, instead of utilizing these standards, large data repositories tend to use metadata standards with domain-independent metadata fields that cover search interests only to some extent. A second problem are arbitrary keywords utilized in descriptive fields such as title, description or subject. Keywords support scholars in a full text search only if the provided terms syntactically match or their semantic relationship to terms used in a user query is known.

Consumer health information and question answering: helping consumers find answers to their health-related information needs

OBJECTIVE

Consumers increasingly turn to the internet in search of health-related information; and they want their questions answered with short and precise passages, rather than needing to analyze lists of relevant documents returned by search engines and reading each document to find an answer. We aim to answer consumer health questions with information from reliable sources.

MATERIALS AND METHODS

We combine knowledge-based, traditional machine and deep learning approaches to understand consumers' questions and select the best answers from consumer-oriented sources. We evaluate the end-to-end system and its components on simple questions generated in a pilot development of MedlinePlus Alexa skill, as well as the short and long real-life questions submitted to the National Library of Medicine by consumers.

RESULTS

Our system achieves 78.7% mean average precision and 87.9% mean reciprocal rank on simple Alexa questions, and 44.5% mean average precision and 51.6% mean reciprocal rank on real-life questions submitted by National Library of Medicine consumers.

DISCUSSION

The ensemble of deep learning, domain knowledge, and traditional approaches recognizes question type and focus well in the simple questions, but it leaves room for improvement on the real-life consumers' questions. Information retrieval approaches alone are sufficient for finding answers to simple Alexa questions. Answering real-life questions, however, benefits from a combination of information retrieval and inference approaches.

CONCLUSION

A pilot practical implementation of research needed to help consumers find reliable answers to their health-related questions demonstrates that for most questions the reliable answers exist and can be found automatically with acceptable accuracy.

Multidimensional Feature Classification of the Health Information Needs of Patients With Hypertension in an Online Health Community Through Analysis of 1000 Patient Question Records: Observational Study

Background

With the rapid development of online health communities, increasing numbers of patients and families are seeking health information on the internet.

Objective

This study aimed to discuss how to fully reveal the health information needs expressed by patients with hypertension in their questions in a web-based environment and how to use the internet to help patients with hypertension receive personalized health education.

Methods

This study randomly selected 1000 text records from the question data of patients with hypertension from 2008 to 2018 collected from Good Doctor Online and constructed a classification system through literature research and content analysis. This paper identified the background characteristics and questioning intention of each patient with hypertension based on the patient’s question and used co-occurrence network analysis and the k-means clustering method to explore the features of the health information needs of patients with hypertension.

Results

The classification system for the health information needs of patients with hypertension included the following nine dimensions: drugs (355 names), symptoms and signs (395 names), tests and examinations (545 names), demographic data (526 kinds), diseases (80 names), risk factors (37 names), emotions (43 kinds), lifestyles (6 kinds), and questions (49 kinds). There were several characteristics of the explored web-based health information needs of patients with hypertension. First, more than 49% of patients described features, such as drugs, symptoms and signs, tests and examinations, demographic data, and diseases. Second, patients with hypertension were most concerned about treatment (778/1000, 77.80%), followed by diagnosis (323/1000, 32.30%). Third, 65.80% (658/1000) of patients asked physicians several questions at the same time. Moreover, 28.30% (283/1000) of patients were very concerned about how to adjust the medication, and they asked other treatment-related questions at the same time, including drug side effects, whether to take the drugs, how to treat the disease, etc. Furthermore, 17.60% (176/1000) of patients consulted physicians about the causes of clinical findings, including the relationship between the clinical findings and a disease, the treatment of a disease, and medications and examinations. Fourth, by k-means clustering, the questioning intentions of patients with hypertension were classified into the following seven categories: “how to adjust medication,” “what to do,” “how to treat,” “phenomenon explanation,” “test and examination,” “disease diagnosis,” and “disease prognosis.”

Conclusions

In a web-based environment, the health information needs expressed by Chinese patients with hypertension to physicians are common and distinct, that is, patients with different background features ask relatively common questions to physicians. The classification system constructed in this study can provide guidance to health information service providers for the construction of web-based health resources, as well as guidance for patient education, which could help solve the problem of information asymmetry in communication between physicians and patients.

Patient Questions and Physician Responses in a Chinese Health Q&A Website: Content Analysis

Background

Since the turn of this century, the internet has become an invaluable resource for people seeking health information and answers to health-related queries. Health question and answer websites have grown in popularity in recent years as a means for patients to obtain health information from medical professionals. For patients suffering from chronic illnesses, it is vital that health care providers become better acquainted with patients’ information needs and learn how they express them in text format.

Objective

The aims of this study were to: (1) explore whether patients can accurately and adequately express their information needs on health question and answer websites, (2) identify what types of problems are of most concern to those suffering from chronic illnesses, and (3) determine the relationship between question characteristics and the number of answers received.

Methods

Questions were collected from a leading Chinese health question and answer website called “All questions will be answered” in January 2018. We focused on questions relating to diabetes and hepatitis, including those that were free and those that were financially rewarded. Content analysis was completed on a total of 7068 (diabetes) and 6685 (hepatitis) textual questions. Correlations between the characteristics of questions (number of words per question, value of reward) and the number of answers received were evaluated using linear regression analysis.

Results

The majority of patients are able to accurately express their problem in text format, while some patients may require minor social support. The questions posted were related to three main topics: (1) prevention and examination, (2) diagnosis, and (3) treatment. Patients with diabetes were most concerned with the treatment received, whereas patients with hepatitis focused on the diagnosis results. The number of words per question and the value of the reward were negatively correlated with the number of answers. The number of words per question and the value of the reward were negatively correlated with the number of answers.

Conclusions

This study provides valuable insights into the ability of patients suffering from chronic illnesses to make an understandable request on health question and answer websites. Health topics relating to diabetes and hepatitis were classified to address the health information needs of chronically ill patients. Furthermore, identification of the factors affecting the number of answers received per question can help users of these websites to better frame their questions to obtain more valuable answers.

A question-entailment approach to question answering

BACKGROUND

One of the challenges in large-scale information retrieval (IR) is developing fine-grained and domain-specific methods to answer natural language questions. Despite the availability of numerous sources and datasets for answer retrieval, Question Answering (QA) remains a challenging problem due to the difficulty of the question understanding and answer extraction tasks. One of the promising tracks investigated in QA is mapping new questions to formerly answered questions that are "similar".

RESULTS

We propose a novel QA approach based on Recognizing Question Entailment (RQE) and we describe the QA system and resources that we built and evaluated on real medical questions. First, we compare logistic regression and deep learning methods for RQE using different kinds of datasets including textual inference, question similarity, and entailment in both the open and clinical domains. Second, we combine IR models with the best RQE method to select entailed questions and rank the retrieved answers. To study the end-to-end QA approach, we built the MedQuAD collection of 47,457 question-answer pairs from trusted medical sources which we introduce and share in the scope of this paper. Following the evaluation process used in TREC 2017 LiveQA, we find that our approach exceeds the best results of the medical task with a 29.8% increase over the best official score.

CONCLUSIONS

The evaluation results support the relevance of question entailment for QA and highlight the effectiveness of combining IR and RQE for future QA efforts. Our findings also show that relying on a restricted set of reliable answer sources can bring a substantial improvement in medical QA.

On the Role of Question Summarization and Information Source Restriction in Consumer Health Question Answering

Despite the recent developments in commercial Question Answering (QA) systems, medical QA remains a challenging task. In this paper, we study the factors behind the complexity of consumer health questions and potential improvement tracks. In particular, we study the impact of information source quality and question conciseness through three experiments. First, an evaluation of a QA method based on a Question-Answer collection created from trusted NIH resources, which outperformed the best results of the medical LiveQA challenge with an average score of 0.711. Then, an evaluation of the same approach using paraphrases and summaries of the test questions, which achieved an average score of 1.125. Our results provide an empirical evidence supporting the key role of summarization and reliable information sources in building efficient CHQA systems. The latter finding on restricting information sources is particularly intriguing as it contradicts the popular tendency ofrelying on big data for medical QA.