Clinical Natural Language Processing in 2014: Foundational Methods Supporting Efficient Healthcare

Optimizing healthcare system by amalgamation of text processing and deep learning: a systematic review

The explosion of clinical textual data has drawn the attention of researchers. Owing to the abundance of clinical data, it is becoming difficult for healthcare professionals to take real-time measures. The tools and methods are lacking when compared to the amount of clinical data generated every day. This review aims to survey the text processing pipeline with deep learning methods such as CNN, RNN, LSTM, and GRU in the healthcare domain and discuss various applications such as clinical concept detection and extraction, medically aware dialogue systems, sentiment analysis of drug reviews shared online, clinical trial matching, and pharmacovigilance. In addition, we highlighted the major challenges in deploying text processing with deep learning to clinical textual data and identified the scope of research in this domain. Furthermore, we have discussed various resources that can be used in the future to optimize the healthcare domain by amalgamating text processing and deep learning.

Classifying the lifestyle status for Alzheimer's disease from clinical notes using deep learning with weak supervision

BACKGROUND

Since no effective therapies exist for Alzheimer's disease (AD), prevention has become more critical through lifestyle status changes and interventions. Analyzing electronic health records (EHRs) of patients with AD can help us better understand lifestyle's effect on AD. However, lifestyle information is typically stored in clinical narratives. Thus, the objective of the study was to compare different natural language processing (NLP) models on classifying the lifestyle statuses (e.g., physical activity and excessive diet) from clinical texts in English.

METHODS

Based on the collected concept unique identifiers (CUIs) associated with the lifestyle status, we extracted all related EHRs for patients with AD from the Clinical Data Repository (CDR) of the University of Minnesota (UMN). We automatically generated labels for the training data by using a rule-based NLP algorithm. We conducted weak supervision for pre-trained Bidirectional Encoder Representations from Transformers (BERT) models and three traditional machine learning models as baseline models on the weakly labeled training corpus. These models include the BERT base model, PubMedBERT (abstracts + full text), PubMedBERT (only abstracts), Unified Medical Language System (UMLS) BERT, Bio BERT, Bio-clinical BERT, logistic regression, support vector machine, and random forest. The rule-based model used for weak supervision was tested on the GSC for comparison. We performed two case studies: physical activity and excessive diet, in order to validate the effectiveness of BERT models in classifying lifestyle status for all models were evaluated and compared on the developed Gold Standard Corpus (GSC) on the two case studies.

RESULTS

The UMLS BERT model achieved the best performance for classifying status of physical activity, with its precision, recall, and F-1 scores of 0.93, 0.93, and 0.92, respectively. Regarding classifying excessive diet, the Bio-clinical BERT model showed the best performance with precision, recall, and F-1 scores of 0.93, 0.93, and 0.93, respectively.

CONCLUSION

The proposed approach leveraging weak supervision could significantly increase the sample size, which is required for training the deep learning models. By comparing with the traditional machine learning models, the study also demonstrates the high performance of BERT models for classifying lifestyle status for Alzheimer's disease in clinical notes.

EXPLORING SENTIMENT AND CARE MANAGEMENT OF HOSPITALIZED PATIENTS DURING FIRST WAVE OF COVID-19 PANDEMIC USING ELECTRONIC NURSING HEALTH RECORDS: DESCRIPTIVE STUDY

BACKGROUND

The COVID-19 pandemic has changed the usual work in many hospitalization units (or wards). Few studies use electronic nursing clinical notes (ENCN) and their unstructured text to identify alterations in patients' feelings and therapeutic procedures of interest.

OBJECTIVE

Analysis of positive/negative sentiments through inspection of the free text of the ENCN; comparison of sentiments of ENCN with/without hospitalized COVID-19 patients; temporal analysis of the sentiments of the patients during the start of the first wave of the COVID-19 pandemic; and identification of the topics in ENCN.

METHODS

This is a descriptive study with analysis of the text content of ENCN. All ENCNs between January and June 2020 at Guadarrama Hospital (Madrid, Spain) extracted from the CGM Selene Electronic Health Records System were included. Two groups of ENCNs were analyzed: one from hospitalized patients in post intensive care units COVID-19, and a second group from hospitalized patients with non COVID-19. A sentiment analysis was performed on the lemmatized text, using the dictionaries NRC, Affin and Bing. A polarity analysis of the sentences was performed using the Bing dictionary, the SO Dictionaries V1.11Spa dictionary as amplifiers and decrementators. Machine learning techniques were applied in order to evaluate the presence of significant differences in the ENCN in groups of COVID-19 or non COVID-19 patients. Finally, a structural analysis of thematic models was performed to study the abstract topics that occur in the ENCN, using Latent Dirichlet Allocation topic modeling.

RESULTS

A total of 37,564 electronic health records were analyzed. Sentiment analysis in ENCN showed that patients with subacute COVID-19 have a higher proportion of positive sentiments compared to non COVID-19. Also, there are significant differences in polarity between both groups (Z=5.532, P<.001) with a polarity in COVID-19 patients of 0.108±0.299 versus a polarity in non COVID-19 patients of 0.09±0.301. Machine learning modeling reported that despite all models presenting high values, it is the neural network that presents the best indicators, over 0.8, and with significant P values between both groups. From Structural Topic Modeling analysis, the final model containing 10 topics was selected. It is noted a high correlation between topics 2, 5 and 8 (pressure ulcer and pharmacotherapy treatment), topics 1, 4, 7 and 9 (incidences related to fever and well-being state, and baseline oxygen saturation) and topics 3, 10 (blood glucose level and pain).

CONCLUSIONS

The ENCN may help in the development and implementation of more effective programs which allows to the COVID-19 pandemic patients a faster come back to a pre-pandemic way of life. Topic modeling could help identify specific clinical problems in patients and better target the care they receive.

CLINICALTRIAL

Assessing the Performance of Clinical Natural Language Processing Systems: Development of an Evaluation Methodology

Background

Clinical natural language processing (cNLP) systems are of crucial importance due to their increasing capability in extracting clinically important information from free text contained in electronic health records (EHRs). The conversion of a nonstructured representation of a patient’s clinical history into a structured format enables medical doctors to generate clinical knowledge at a level that was not possible before. Finally, the interpretation of the insights gained provided by cNLP systems has a great potential in driving decisions about clinical practice. However, carrying out robust evaluations of those cNLP systems is a complex task that is hindered by a lack of standard guidance on how to systematically approach them.

Objective

Our objective was to offer natural language processing (NLP) experts a methodology for the evaluation of cNLP systems to assist them in carrying out this task. By following the proposed phases, the robustness and representativeness of the performance metrics of their own cNLP systems can be assured.

Methods

The proposed evaluation methodology comprised five phases: (1) the definition of the target population, (2) the statistical document collection, (3) the design of the annotation guidelines and annotation project, (4) the external annotations, and (5) the cNLP system performance evaluation. We presented the application of all phases to evaluate the performance of a cNLP system called “EHRead Technology” (developed by Savana, an international medical company), applied in a study on patients with asthma. As part of the evaluation methodology, we introduced the Sample Size Calculator for Evaluations (SLiCE), a software tool that calculates the number of documents needed to achieve a statistically useful and resourceful gold standard.

Results

The application of the proposed evaluation methodology on a real use-case study of patients with asthma revealed the benefit of the different phases for cNLP system evaluations. By using SLiCE to adjust the number of documents needed, a meaningful and resourceful gold standard was created. In the presented use-case, using as little as 519 EHRs, it was possible to evaluate the performance of the cNLP system and obtain performance metrics for the primary variable within the expected CIs.

Conclusions

We showed that our evaluation methodology can offer guidance to NLP experts on how to approach the evaluation of their cNLP systems. By following the five phases, NLP experts can assure the robustness of their evaluation and avoid unnecessary investment of human and financial resources. Besides the theoretical guidance, we offer SLiCE as an easy-to-use, open-source Python library.

Should free-text data in electronic medical records be shared for research? A citizens' jury study in the UK

BACKGROUND

Use of routinely collected patient data for research and service planning is an explicit policy of the UK National Health Service and UK government. Much clinical information is recorded in free-text letters, reports and notes. These text data are generally lost to research, due to the increased privacy risk compared with structured data. We conducted a citizens' jury which asked members of the public whether their medical free-text data should be shared for research for public benefit, to inform an ethical policy.

METHODS

Eighteen citizens took part over 3 days. Jurors heard a range of expert presentations as well as arguments for and against sharing free text, and then questioned presenters and deliberated together. They answered a questionnaire on whether and how free text should be shared for research, gave reasons for and against sharing and suggestions for alleviating their concerns.

RESULTS

Jurors were in favour of sharing medical data and agreed this would benefit health research, but were more cautious about sharing free-text than structured data. They preferred processing of free text where a computer extracted information at scale. Their concerns were lack of transparency in uses of data, and privacy risks. They suggested keeping patients informed about uses of their data, and giving clear pathways to opt out of data sharing.

CONCLUSIONS

Informed citizens suggested a transparent culture of research for the public benefit, and continuous improvement of technology to protect patient privacy, to mitigate their concerns regarding privacy risks of using patient text data.

Trends and Features of the Applications of Natural Language Processing Techniques for Clinical Trials Text Analysis

Natural language processing (NLP) is an effective tool for generating structured information from unstructured data, the one that is commonly found in clinical trial texts. Such interdisciplinary research has gradually grown into a flourishing research field with accumulated scientific outputs available. In this study, bibliographical data collected from Web of Science, PubMed, and Scopus databases from 2001 to 2018 had been investigated with the use of three prominent methods, including performance analysis, science mapping, and, particularly, an automatic text analysis approach named structural topic modeling. Topical trend visualization and test analysis were further employed to quantify the effects of the year of publication on topic proportions. Topical diverse distributions across prolific countries/regions and institutions were also visualized and compared. In addition, scientific collaborations between countries/regions, institutions, and authors were also explored using social network analysis. The findings obtained were essential for facilitating the development of the NLP-enhanced clinical trial texts processing, boosting scientific and technological NLP-enhanced clinical trial research, and facilitating inter-country/region and inter-institution collaborations.

Evaluating the Portability of an NLP System for Processing Echocardiograms: A Retrospective, Multi-site Observational Study

While natural language processing (NLP) of unstructured clinical narratives holds the potential for patient care and clinical research, portability of NLP approaches across multiple sites remains a major challenge. This study investigated the portability of an NLP system developed initially at the Department of Veterans Affairs (VA) to extract 27 key cardiac concepts from free-text or semi-structured echocardiograms from three academic edical centers: Weill Cornell Medicine, Mayo Clinic and Northwestern Medicine. While the NLP system showed high precision and recall easurements for four target concepts (aortic valve regurgitation, left atrium size at end systole, mitral valve regurgitation, tricuspid valve regurgitation) across all sites, we found moderate or poor results for the remaining concepts and the NLP system performance varied between individual sites.

Customization scenarios for de-identification of clinical notes

BACKGROUND

Automated machine-learning systems are able to de-identify electronic medical records, including free-text clinical notes. Use of such systems would greatly boost the amount of data available to researchers, yet their deployment has been limited due to uncertainty about their performance when applied to new datasets.

OBJECTIVE

We present practical options for clinical note de-identification, assessing performance of machine learning systems ranging from off-the-shelf to fully customized.

METHODS

We implement a state-of-the-art machine learning de-identification system, training and testing on pairs of datasets that match the deployment scenarios. We use clinical notes from two i2b2 competition corpora, the Physionet Gold Standard corpus, and parts of the MIMIC-III dataset.

RESULTS

Fully customized systems remove 97-99% of personally identifying information. Performance of off-the-shelf systems varies by dataset, with performance mostly above 90%. Providing a small labeled dataset or large unlabeled dataset allows for fine-tuning that improves performance over off-the-shelf systems.

CONCLUSION

Health organizations should be aware of the levels of customization available when selecting a de-identification deployment solution, in order to choose the one that best matches their resources and target performance level.

Systematic Evaluation of Research Progress on Natural Language Processing in Medicine Over the Past 20 Years: Bibliometric Study on PubMed

BACKGROUND

Natural language processing (NLP) is an important traditional field in computer science, but its application in medical research has faced many challenges. With the extensive digitalization of medical information globally and increasing importance of understanding and mining big data in the medical field, NLP is becoming more crucial.

OBJECTIVE

The goal of the research was to perform a systematic review on the use of NLP in medical research with the aim of understanding the global progress on NLP research outcomes, content, methods, and study groups involved.

METHODS

A systematic review was conducted using the PubMed database as a search platform. All published studies on the application of NLP in medicine (except biomedicine) during the 20 years between 1999 and 2018 were retrieved. The data obtained from these published studies were cleaned and structured. Excel (Microsoft Corp) and VOSviewer (Nees Jan van Eck and Ludo Waltman) were used to perform bibliometric analysis of publication trends, author orders, countries, institutions, collaboration relationships, research hot spots, diseases studied, and research methods.

RESULTS

A total of 3498 articles were obtained during initial screening, and 2336 articles were found to meet the study criteria after manual screening. The number of publications increased every year, with a significant growth after 2012 (number of publications ranged from 148 to a maximum of 302 annually). The United States has occupied the leading position since the inception of the field, with the largest number of articles published. The United States contributed to 63.01% (1472/2336) of all publications, followed by France (5.44%, 127/2336) and the United Kingdom (3.51%, 82/2336). The author with the largest number of articles published was Hongfang Liu (70), while Stéphane Meystre (17) and Hua Xu (33) published the largest number of articles as the first and corresponding authors. Among the first author's affiliation institution, Columbia University published the largest number of articles, accounting for 4.54% (106/2336) of the total. Specifically, approximately one-fifth (17.68%, 413/2336) of the articles involved research on specific diseases, and the subject areas primarily focused on mental illness (16.46%, 68/413), breast cancer (5.81%, 24/413), and pneumonia (4.12%, 17/413).

CONCLUSIONS

NLP is in a period of robust development in the medical field, with an average of approximately 100 publications annually. Electronic medical records were the most used research materials, but social media such as Twitter have become important research materials since 2015. Cancer (24.94%, 103/413) was the most common subject area in NLP-assisted medical research on diseases, with breast cancers (23.30%, 24/103) and lung cancers (14.56%, 15/103) accounting for the highest proportions of studies. Columbia University and the talents trained therein were the most active and prolific research forces on NLP in the medical field.

Natural Language Processing Combined with ICD-9-CM Codes as a Novel Method to Study the Epidemiology of Allergic Drug Reactions

BACKGROUND

Allergic drug reaction epidemiologic data are sparse because it remains difficult to identify true cases in large data sets using manual chart review.

OBJECTIVE

To develop and validate a novel informatics method based on natural language processing (NLP) in combination with International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes that identifies allergic drug reactions in the electronic health record.

METHODS

Previously studied and high-yield ICD-9-CM codes were used to screen for possible allergic drug reactions among all inpatients admitted in 2007 and 2008. A random sample was selected for manual chart review to identify true cases of allergic drug reactions. A rule-based NLP algorithm was then developed to identify allergic drug reactions using free-text clinical notes and discharge summaries from the filtered cases. The performance of using manual chart review of ICD-9-CM codes alone was compared with ICD-9-CM codes in combination with NLP.

RESULTS

Of 3907 cases identified by ICD-9-CM codes, 725 (19%) were randomly selected for manual chart review; 335 were confirmed as allergic drug reactions, resulting in a positive predictive value (PPV) of 46% (range: 18%-79%) when using ICD-9-CM codes alone. Our NLP algorithm in combination with ICD-9-CM codes achieved a PPV of 86% (range: 69%-100%). Among the 335 confirmed positive cases, NLP identified 259 true cases, resulting in a recall/sensitivity of 77% (range: 26%-100%). Among the 390 negative cases, NLP achieved a specificity of 89% (range: 69%-100%).

CONCLUSION

Using NLP with ICD-9-CM codes improved identification of allergic drug reactions. The resulting decrease in manual chart review effort will facilitate large epidemiology studies of this understudied area.

Risk Assessment Tools and Data-Driven Approaches for Predicting and Preventing Suicidal Behavior

Risk assessment of suicidal behavior is a time-consuming but notoriously inaccurate activity for mental health services globally. In the last 50 years a large number of tools have been designed for suicide risk assessment, and tested in a wide variety of populations, but studies show that these tools suffer from low positive predictive values. More recently, advances in research fields such as machine learning and natural language processing applied on large datasets have shown promising results for health care, and may enable an important shift in advancing precision medicine. In this conceptual review, we discuss established risk assessment tools and examples of novel data-driven approaches that have been used for identification of suicidal behavior and risk. We provide a perspective on the strengths and weaknesses of these applications to mental health-related data, and suggest research directions to enable improvement in clinical practice.

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.

From Sour Grapes to Low-Hanging Fruit: A Case Study Demonstrating a Practical Strategy for Natural Language Processing Portability

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.

Clinical Natural Language Processing in languages other than English: opportunities and challenges

Background

Natural language processing applied to clinical text or aimed at a clinical outcome has been thriving in recent years. This paper offers the first broad overview of clinical Natural Language Processing (NLP) for languages other than English. Recent studies are summarized to offer insights and outline opportunities in this area.

Main Body

We envision three groups of intended readers: (1) NLP researchers leveraging experience gained in other languages, (2) NLP researchers faced with establishing clinical text processing in a language other than English, and (3) clinical informatics researchers and practitioners looking for resources in their languages in order to apply NLP techniques and tools to clinical practice and/or investigation. We review work in clinical NLP in languages other than English. We classify these studies into three groups: (i) studies describing the development of new NLP systems or components de novo, (ii) studies describing the adaptation of NLP architectures developed for English to another language, and (iii) studies focusing on a particular clinical application.

Conclusion

We show the advantages and drawbacks of each method, and highlight the appropriate application context. Finally, we identify major challenges and opportunities that will affect the impact of NLP on clinical practice and public health studies in a context that encompasses English as well as other languages.

Capturing the Patient's Perspective: a Review of Advances in Natural Language Processing of Health-Related Text

Background: Natural Language Processing (NLP) methods are increasingly being utilized to mine knowledge from unstructured health-related texts. Recent advances in noisy text processing techniques are enabling researchers and medical domain experts to go beyond the information encapsulated in published texts (e.g., clinical trials and systematic reviews) and structured questionnaires, and obtain perspectives from other unstructured sources such as Electronic Health Records (EHRs) and social media posts. Objectives: To review the recently published literature discussing the application of NLP techniques for mining health-related information from EHRs and social media posts. Methods: Literature review included the research published over the last five years based on searches of PubMed, conference proceedings, and the ACM Digital Library, as well as on relevant publications referenced in papers. We particularly focused on the techniques employed on EHRs and social media data. Results: A set of 62 studies involving EHRs and 87 studies involving social media matched our criteria and were included in this paper. We present the purposes of these studies, outline the key NLP contributions, and discuss the general trends observed in the field, the current state of research, and important outstanding problems. Conclusions: Over the recent years, there has been a continuing transition from lexical and rule-based systems to learning-based approaches, because of the growth of annotated data sets and advances in data science. For EHRs, publicly available annotated data is still scarce and this acts as an obstacle to research progress. On the contrary, research on social media mining has seen a rapid growth, particularly because the large amount of unlabeled data available via this resource compensates for the uncertainty inherent to the data. Effective mechanisms to filter out noise and for mapping social media expressions to standard medical concepts are crucial and latent research problems. Shared tasks and other competitive challenges have been driving factors behind the implementation of open systems, and they are likely to play an imperative role in the development of future systems.

Algorithmic Classification of Five Characteristic Types of Paraphasias

PURPOSE

This study was intended to evaluate a series of algorithms developed to perform automatic classification of paraphasic errors (formal, semantic, mixed, neologistic, and unrelated errors).

METHOD

We analyzed 7,111 paraphasias from the Moss Aphasia Psycholinguistics Project Database (Mirman et al., 2010) and evaluated the classification accuracy of 3 automated tools. First, we used frequency norms from the SUBTLEXus database (Brysbaert & New, 2009) to differentiate nonword errors and real-word productions. Then we implemented a phonological-similarity algorithm to identify phonologically related real-word errors. Last, we assessed the performance of a semantic-similarity criterion that was based on word2vec (Mikolov, Yih, & Zweig, 2013).

RESULTS

Overall, the algorithmic classification replicated human scoring for the major categories of paraphasias studied with high accuracy. The tool that was based on the SUBTLEXus frequency norms was more than 97% accurate in making lexicality judgments. The phonological-similarity criterion was approximately 91% accurate, and the overall classification accuracy of the semantic classifier ranged from 86% to 90%.

CONCLUSION

Overall, the results highlight the potential of tools from the field of natural language processing for the development of highly reliable, cost-effective diagnostic tools suitable for collecting high-quality measurement data for research and clinical purposes.

Aspiring to Unintended Consequences of Natural Language Processing: A Review of Recent Developments in Clinical and Consumer-Generated Text Processing

OBJECTIVES

This paper reviews work over the past two years in Natural Language Processing (NLP) applied to clinical and consumer-generated texts.

METHODS

We included any application or methodological publication that leverages text to facilitate healthcare and address the health-related needs of consumers and populations.

RESULTS

Many important developments in clinical text processing, both foundational and task-oriented, were addressed in community- wide evaluations and discussed in corresponding special issues that are referenced in this review. These focused issues and in-depth reviews of several other active research areas, such as pharmacovigilance and summarization, allowed us to discuss in greater depth disease modeling and predictive analytics using clinical texts, and text analysis in social media for healthcare quality assessment, trends towards online interventions based on rapid analysis of health-related posts, and consumer health question answering, among other issues.

CONCLUSIONS

Our analysis shows that although clinical NLP continues to advance towards practical applications and more NLP methods are used in large-scale live health information applications, more needs to be done to make NLP use in clinical applications a routine widespread reality. Progress in clinical NLP is mirrored by developments in social media text analysis: the research is moving from capturing trends to addressing individual health-related posts, thus showing potential to become a tool for precision medicine and a valuable addition to the standard healthcare quality evaluation tools.

Automatic classification of registered clinical trials towards the Global Burden of Diseases taxonomy of diseases and injuries

BACKGROUND

Clinical trial registries may allow for producing a global mapping of health research. However, health conditions are not described with standardized taxonomies in registries. Previous work analyzed clinical trial registries to improve the retrieval of relevant clinical trials for patients. However, no previous work has classified clinical trials across diseases using a standardized taxonomy allowing a comparison between global health research and global burden across diseases. We developed a knowledge-based classifier of health conditions studied in registered clinical trials towards categories of diseases and injuries from the Global Burden of Diseases (GBD) 2010 study. The classifier relies on the UMLS® knowledge source (Unified Medical Language System®) and on heuristic algorithms for parsing data. It maps trial records to a 28-class grouping of the GBD categories by automatically extracting UMLS concepts from text fields and by projecting concepts between medical terminologies. The classifier allows deriving pathways between the clinical trial record and candidate GBD categories using natural language processing and links between knowledge sources, and selects the relevant GBD classification based on rules of prioritization across the pathways found. We compared automatic and manual classifications for an external test set of 2,763 trials. We automatically classified 109,603 interventional trials registered before February 2014 at WHO ICTRP.

RESULTS

In the external test set, the classifier identified the exact GBD categories for 78 % of the trials. It had very good performance for most of the 28 categories, especially "Neoplasms" (sensitivity 97.4 %, specificity 97.5 %). The sensitivity was moderate for trials not relevant to any GBD category (53 %) and low for trials of injuries (16 %). For the 109,603 trials registered at WHO ICTRP, the classifier did not assign any GBD category to 20.5 % of trials while the most common GBD categories were "Neoplasms" (22.8 %) and "Diabetes" (8.9 %).

CONCLUSIONS

We developed and validated a knowledge-based classifier allowing for automatically identifying the diseases studied in registered trials by using the taxonomy from the GBD 2010 study. This tool is freely available to the research community and can be used for large-scale public health studies.