Benchmarking for biomedical natural language processing tasks with a domain specific ALBERT

Transformer models in biomedicine

Deep neural networks (DNN) have fundamentally revolutionized the artificial intelligence (AI) field. The transformer model is a type of DNN that was originally used for the natural language processing tasks and has since gained more and more attention for processing various kinds of sequential data, including biological sequences and structured electronic health records. Along with this development, transformer-based models such as BioBERT, MedBERT, and MassGenie have been trained and deployed by researchers to answer various scientific questions originating in the biomedical domain. In this paper, we review the development and application of transformer models for analyzing various biomedical-related datasets such as biomedical textual data, protein sequences, medical structured-longitudinal data, and biomedical images as well as graphs. Also, we look at explainable AI strategies that help to comprehend the predictions of transformer-based models. Finally, we discuss the limitations and challenges of current models, and point out emerging novel research directions.

Oversampling effect in pretraining for bidirectional encoder representations from transformers (BERT) to localize medical BERT and enhance biomedical BERT

BACKGROUND

Pretraining large-scale neural language models on raw texts has made a significant contribution to improving transfer learning in natural language processing. With the introduction of transformer-based language models, such as bidirectional encoder representations from transformers (BERT), the performance of information extraction from free text has improved significantly in both the general and medical domains. However, it is difficult to train specific BERT models to perform well in domains for which few databases of a high quality and large size are publicly available.

OBJECTIVE

We hypothesized that this problem could be addressed by oversampling a domain-specific corpus and using it for pretraining with a larger corpus in a balanced manner. In the present study, we verified our hypothesis by developing pretraining models using our method and evaluating their performance.

METHODS

Our proposed method was based on the simultaneous pretraining of models with knowledge from distinct domains after oversampling. We conducted three experiments in which we generated (1) English biomedical BERT from a small biomedical corpus, (2) Japanese medical BERT from a small medical corpus, and (3) enhanced biomedical BERT pretrained with complete PubMed abstracts in a balanced manner. We then compared their performance with those of conventional models.

RESULTS

Our English BERT pretrained using both general and small medical domain corpora performed sufficiently well for practical use on the biomedical language understanding evaluation (BLUE) benchmark. Moreover, our proposed method was more effective than the conventional methods for each biomedical corpus of the same corpus size in the general domain. Our Japanese medical BERT outperformed the other BERT models built using a conventional method for almost all the medical tasks. The model demonstrated the same trend as that of the first experiment in English. Further, our enhanced biomedical BERT model, which was not pretrained on clinical notes, achieved superior clinical and biomedical scores on the BLUE benchmark with an increase of 0.3 points in the clinical score and 0.5 points in the biomedical score. These scores were above those of the models trained without our proposed method.

CONCLUSIONS

Well-balanced pretraining using oversampling instances derived from a corpus appropriate for the target task allowed us to construct a high-performance BERT model.

Language model and its interpretability in biomedicine: A scoping review

With advancements in large language models, artificial intelligence (AI) is undergoing a paradigm shift where AI models can be repurposed with minimal effort across various downstream tasks. This provides great promise in learning generally useful representations from biomedical corpora, at scale, which would empower AI solutions in healthcare and biomedical research. Nonetheless, our understanding of how they work, when they fail, and what they are capable of remains underexplored due to their emergent properties. Consequently, there is a need to comprehensively examine the use of language models in biomedicine. This review aims to summarize existing studies of language models in biomedicine and identify topics ripe for future research, along with the technical and analytical challenges w.r.t. interpretability. We expect this review to help researchers and practitioners better understand the landscape of language models in biomedicine and what methods are available to enhance the interpretability of their models.

Question answering systems for health professionals at the point of care-a systematic review

OBJECTIVES

Question answering (QA) systems have the potential to improve the quality of clinical care by providing health professionals with the latest and most relevant evidence. However, QA systems have not been widely adopted. This systematic review aims to characterize current medical QA systems, assess their suitability for healthcare, and identify areas of improvement.

MATERIALS AND METHODS

We searched PubMed, IEEE Xplore, ACM Digital Library, ACL Anthology, and forward and backward citations on February 7, 2023. We included peer-reviewed journal and conference papers describing the design and evaluation of biomedical QA systems. Two reviewers screened titles, abstracts, and full-text articles. We conducted a narrative synthesis and risk of bias assessment for each study. We assessed the utility of biomedical QA systems.

RESULTS

We included 79 studies and identified themes, including question realism, answer reliability, answer utility, clinical specialism, systems, usability, and evaluation methods. Clinicians' questions used to train and evaluate QA systems were restricted to certain sources, types and complexity levels. No system communicated confidence levels in the answers or sources. Many studies suffered from high risks of bias and applicability concerns. Only 8 studies completely satisfied any criterion for clinical utility, and only 7 reported user evaluations. Most systems were built with limited input from clinicians.

DISCUSSION

While machine learning methods have led to increased accuracy, most studies imperfectly reflected real-world healthcare information needs. Key research priorities include developing more realistic healthcare QA datasets and considering the reliability of answer sources, rather than merely focusing on accuracy.

Standigm ASK™: knowledge graph and artificial intelligence platform applied to target discovery in idiopathic pulmonary fibrosis

Standigm ASK™ revolutionizes healthcare by addressing the critical challenge of identifying pivotal target genes in disease mechanisms-a fundamental aspect of drug development success. Standigm ASK™ integrates a unique combination of a heterogeneous knowledge graph (KG) database and an attention-based neural network model, providing interpretable subgraph evidence. Empowering users through an interactive interface, Standigm ASK™ facilitates the exploration of predicted results. Applying Standigm ASK™ to idiopathic pulmonary fibrosis (IPF), a complex lung disease, we focused on genes (AMFR, MDFIC and NR5A2) identified through KG evidence. In vitro experiments demonstrated their relevance, as TGFβ treatment induced gene expression changes associated with epithelial-mesenchymal transition characteristics. Gene knockdown reversed these changes, identifying AMFR, MDFIC and NR5A2 as potential therapeutic targets for IPF. In summary, Standigm ASK™ emerges as an innovative KG and artificial intelligence platform driving insights in drug target discovery, exemplified by the identification and validation of therapeutic targets for IPF.

A review of research on eligibility criteria for clinical trials

The purpose of this paper is to systematically sort out and analyze the cutting-edge research on the eligibility criteria of clinical trials. Eligibility criteria are important prerequisites for the success of clinical trials. It directly affects the final results of the clinical trials. Inappropriate eligibility criteria will lead to insufficient recruitment, which is an important reason for the eventual failure of many clinical trials. We have investigated the research status of eligibility criteria for clinical trials on academic platforms such as arXiv and NIH. We have classified and sorted out all the papers we found, so that readers can understand the frontier research in this field. Eligibility criteria are the most important part of a clinical trial study. The ultimate goal of research in this field is to formulate more scientific and reasonable eligibility criteria and speed up the clinical trial process. The global research on the eligibility criteria of clinical trials is mainly divided into four main aspects: natural language processing, patient pre-screening, standard evaluation, and clinical trial query. Compared with the past, people are now using new technologies to study eligibility criteria from a new perspective (big data). In the research process, complex disease concepts, how to choose a suitable dataset, how to prove the validity and scientific of the research results, are challenges faced by researchers (especially for computer-related researchers). Future research will focus on the selection and improvement of artificial intelligence algorithms related to clinical trials and related practical applications such as databases, knowledge graphs, and dictionaries.

Integrating domain knowledge for biomedical text analysis into deep learning: A survey

The past decade has witnessed an explosion of textual information in the biomedical field. Biomedical texts provide a basis for healthcare delivery, knowledge discovery, and decision-making. Over the same period, deep learning has achieved remarkable performance in biomedical natural language processing, however, its development has been limited by well-annotated datasets and interpretability. To solve this, researchers have considered combining domain knowledge (such as biomedical knowledge graph) with biomedical data, which has become a promising means of introducing more information into biomedical datasets and following evidence-based medicine. This paper comprehensively reviews more than 150 recent literature studies on incorporating domain knowledge into deep learning models to facilitate typical biomedical text analysis tasks, including information extraction, text classification, and text generation. We eventually discuss various challenges and future directions.

Benchmark datasets driving artificial intelligence development fail to capture the needs of medical professionals

Publicly accessible benchmarks that allow for assessing and comparing model performances are important drivers of progress in artificial intelligence (AI). While recent advances in AI capabilities hold the potential to transform medical practice by assisting and augmenting the cognitive processes of healthcare professionals, the coverage of clinically relevant tasks by AI benchmarks is largely unclear. Furthermore, there is a lack of systematized meta-information that allows clinical AI researchers to quickly determine accessibility, scope, content and other characteristics of datasets and benchmark datasets relevant to the clinical domain. To address these issues, we curated and released a comprehensive catalogue of datasets and benchmarks pertaining to the broad domain of clinical and biomedical natural language processing (NLP), based on a systematic review of literature and. A total of 450 NLP datasets were manually systematized and annotated with rich metadata, such as targeted tasks, clinical applicability, data types, performance metrics, accessibility and licensing information, and availability of data splits. We then compared tasks covered by AI benchmark datasets with relevant tasks that medical practitioners reported as highly desirable targets for automation in a previous empirical study. Our analysis indicates that AI benchmarks of direct clinical relevance are scarce and fail to cover most work activities that clinicians want to see addressed. In particular, tasks associated with routine documentation and patient data administration workflows are not represented despite significant associated workloads. Thus, currently available AI benchmarks are improperly aligned with desired targets for AI automation in clinical settings, and novel benchmarks should be created to fill these gaps.

Multi-label classification of symptom terms from free-text bilingual adverse drug reaction reports using natural language processing

Allergic reactions to medication range from mild to severe or even life-threatening. Proper documentation of patient allergy information is critical for safe prescription, avoiding drug interactions, and reducing healthcare costs. Allergy information is regularly obtained during the medical interview, but is often poorly documented in electronic health records (EHRs). While many EHRs allow for structured adverse drug reaction (ADR) reporting, a free-text entry is still common. The resulting information is neither interoperable nor easily reusable for other applications, such as clinical decision support systems and prescription alerts. Current approaches require pharmacists to review and code ADRs documented by healthcare professionals. Recently, the effectiveness of machine algorithms in natural language processing (NLP) has been widely demonstrated. Our study aims to develop and evaluate different NLP algorithms that can encode unstructured ADRs stored in EHRs into institutional symptom terms. Our dataset consists of 79,712 pharmacist-reviewed drug allergy records. We evaluated three NLP techniques: Naive Bayes—Support Vector Machine (NB-SVM), Universal Language Model Fine-tuning (ULMFiT), and Bidirectional Encoder Representations from Transformers (BERT). We tested different general-domain pre-trained BERT models, including mBERT, XLM-RoBERTa, and WanchanBERTa, as well as our domain-specific AllergyRoBERTa, which was pre-trained from scratch on our corpus. Overall, BERT models had the highest performance. NB-SVM outperformed ULMFiT and BERT for several symptom terms that are not frequently coded. The ensemble model achieved an exact match ratio of 95.33%, a F₁ score of 98.88%, and a mean average precision of 97.07% for the 36 most frequently coded symptom terms. The model was then further developed into a symptom term suggestion system and achieved a Krippendorff’s alpha agreement coefficient of 0.7081 in prospective testing with pharmacists. Some degree of automation could both accelerate the availability of allergy information and reduce the efforts for human coding.