National Natural Language Processing Research Articles

Question Answering for Electronic Health Records: Scoping Review of Datasets and Models.

Question answering (QA) systems for patient-related data can assist both clinicians and patients. They can, for example, assist clinicians in decision-making and enable patients to have a better understanding of their medical history. Substantial amounts of patient data are stored in electronic health records (EHRs), making EHR QA an important research area. Because of the differences in data format and modality, this differs greatly from other medical QA tasks that use medical websites or scientific papers to retrieve answers, making it critical to research EHR QA. This study aims to provide a methodological review of existing works on QA for EHRs. The objectives of this study were to identify the existing EHR QA datasets and analyze them, study the state-of-the-art methodologies used in this task, compare the different evaluation metrics used by these state-of-the-art models, and finally elicit the various challenges and the ongoing issues in EHR QA. We searched for articles from January 1, 2005, to September 30, 2023, in 4 digital sources, including Google Scholar, ACL Anthology, ACM Digital Library, and PubMed, to collect relevant publications on EHR QA. Our systematic screening process followed PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. A total of 4111 papers were identified for our study, and after screening based on our inclusion criteria, we obtained 47 papers for further study. The selected studies were then classified into 2 non-mutually exclusive categories depending on their scope: "EHR QA datasets" and "EHR QA models." A systematic screening process obtained 47 papers on EHR QA for final review. Out of the 47 papers, 53% (n=25) were about EHR QA datasets, and 79% (n=37) papers were about EHR QA models. It was observed that QA on EHRs is relatively new and unexplored. Most of the works are fairly recent. In addition, it was observed that emrQA is by far the most popular EHR QA dataset, both in terms of citations and usage in other papers. We have classified the EHR QA datasets based on their modality, and we have inferred that Medical Information Mart for Intensive Care (MIMIC-III) and the National Natural Language Processing Clinical Challenges datasets (ie, n2c2 datasets) are the most popular EHR databases and corpuses used in EHR QA. Furthermore, we identified the different models used in EHR QA along with the evaluation metrics used for these models. EHR QA research faces multiple challenges, such as the limited availability of clinical annotations, concept normalization in EHR QA, and challenges faced in generating realistic EHR QA datasets. There are still many gaps in research that motivate further work. This study will assist future researchers in focusing on areas of EHR QA that have possible future research directions.

A deep learning approach for medication disposition and corresponding attributes extraction

ObjectiveThis article summarizes our approach to extracting medication and corresponding attributes from clinical notes, which is the focus of track 1 of the 2022 National Natural Language Processing (NLP) Clinical Challenges(n2c2) shared task. MethodsThe dataset was prepared using Contextualized Medication Event Dataset (CMED), including 500 notes from 296 patients. Our system consisted of three components: medication named entity recognition (NER), event classification (EC), and context classification (CC). These three components were built using transformer models with slightly different architecture and input text engineering. A zero-shot learning solution for CC was also explored. ResultsOur best performance systems achieved micro-average F1 scores of 0.973, 0.911, and 0.909 for the NER, EC, and CC, respectively. ConclusionIn this study, we implemented a deep learning-based NLP system and demonstrated that our approach of (1) utilizing special tokens helps our model to distinguish multiple medications mentions in the same context; (2) aggregating multiple events of a single medication into multiple labels improves our model’s performance.

Benchmarking Effectiveness and Efficiency of Deep Learning Models for Semantic Textual Similarity in the Clinical Domain: Validation Study.

BackgroundSemantic textual similarity (STS) measures the degree of relatedness between sentence pairs. The Open Health Natural Language Processing (OHNLP) Consortium released an expertly annotated STS data set and called for the National Natural Language Processing Clinical Challenges. This work describes our entry, an ensemble model that leverages a range of deep learning (DL) models. Our team from the National Library of Medicine obtained a Pearson correlation of 0.8967 in an official test set during 2019 National Natural Language Processing Clinical Challenges/Open Health Natural Language Processing shared task and achieved a second rank.ObjectiveAlthough our models strongly correlate with manual annotations, annotator-level correlation was only moderate (weighted Cohen κ=0.60). We are cautious of the potential use of DL models in production systems and argue that it is more critical to evaluate the models in-depth, especially those with extremely high correlations. In this study, we benchmark the effectiveness and efficiency of top-ranked DL models. We quantify their robustness and inference times to validate their usefulness in real-time applications.MethodsWe benchmarked five DL models, which are the top-ranked systems for STS tasks: Convolutional Neural Network, BioSentVec, BioBERT, BlueBERT, and ClinicalBERT. We evaluated a random forest model as an additional baseline. For each model, we repeated the experiment 10 times, using the official training and testing sets. We reported 95% CI of the Wilcoxon rank-sum test on the average Pearson correlation (official evaluation metric) and running time. We further evaluated Spearman correlation, R², and mean squared error as additional measures.ResultsUsing only the official training set, all models obtained highly effective results. BioSentVec and BioBERT achieved the highest average Pearson correlations (0.8497 and 0.8481, respectively). BioSentVec also had the highest results in 3 of 4 effectiveness measures, followed by BioBERT. However, their robustness to sentence pairs of different similarity levels varies significantly. A particular observation is that BERT models made the most errors (a mean squared error of over 2.5) on highly similar sentence pairs. They cannot capture highly similar sentence pairs effectively when they have different negation terms or word orders. In addition, time efficiency is dramatically different from the effectiveness results. On average, the BERT models were approximately 20 times and 50 times slower than the Convolutional Neural Network and BioSentVec models, respectively. This results in challenges for real-time applications.ConclusionsDespite the excitement of further improving Pearson correlations in this data set, our results highlight that evaluations of the effectiveness and efficiency of STS models are critical. In future, we suggest more evaluations on the generalization capability and user-level testing of the models. We call for community efforts to create more biomedical and clinical STS data sets from different perspectives to reflect the multifaceted notion of sentence-relatedness.

Extracting Family History Information From Electronic Health Records: Natural Language Processing Analysis.

BackgroundThe prognosis, diagnosis, and treatment of many genetic disorders and familial diseases significantly improve if the family history (FH) of a patient is known. Such information is often written in the free text of clinical notes.ObjectiveThe aim of this study is to develop automated methods that enable access to FH data through natural language processing.MethodsWe performed information extraction by using transformers to extract disease mentions from notes. We also experimented with rule-based methods for extracting family member (FM) information from text and coreference resolution techniques. We evaluated different transfer learning strategies to improve the annotation of diseases. We provided a thorough error analysis of the contributing factors that affect such information extraction systems.ResultsOur experiments showed that the combination of domain-adaptive pretraining and intermediate-task pretraining achieved an F1 score of 81.63% for the extraction of diseases and FMs from notes when it was tested on a public shared task data set from the National Natural Language Processing Clinical Challenges (N2C2), providing a statistically significant improvement over the baseline (P<.001). In comparison, in the 2019 N2C2/Open Health Natural Language Processing Shared Task, the median F1 score of all 17 participating teams was 76.59%.ConclusionsOur approach, which leverages a state-of-the-art named entity recognition model for disease mention detection coupled with a hybrid method for FM mention detection, achieved an effectiveness that was close to that of the top 3 systems participating in the 2019 N2C2 FH extraction challenge, with only the top system convincingly outperforming our approach in terms of precision.

A Hybrid Model for Family History Information Identification and Relation Extraction: Development and Evaluation of an End-to-End Information Extraction System.

BackgroundFamily history information is important to assess the risk of inherited medical conditions. Natural language processing has the potential to extract this information from unstructured free-text notes to improve patient care and decision making. We describe the end-to-end information extraction system the Medical University of South Carolina team developed when participating in the 2019 National Natural Language Processing Clinical Challenge (n2c2)/Open Health Natural Language Processing (OHNLP) shared task.ObjectiveThis task involves identifying mentions of family members and observations in electronic health record text notes and recognizing the 2 types of relations (family member-living status relations and family member-observation relations). Our system aims to achieve a high level of performance by integrating heuristics and advanced information extraction methods. Our efforts also include improving the performance of 2 subtasks by exploiting additional labeled data and clinical text-based embedding models.MethodsWe present a hybrid method that combines machine learning and rule-based approaches. We implemented an end-to-end system with multiple information extraction and attribute classification components. For entity identification, we trained bidirectional long short-term memory deep learning models. These models incorporated static word embeddings and context-dependent embeddings. We created a voting ensemble that combined the predictions of all individual models. For relation extraction, we trained 2 relation extraction models. The first model determined the living status of each family member. The second model identified observations associated with each family member. We implemented online gradient descent models to extract related entity pairs. As part of postchallenge efforts, we used the BioCreative/OHNLP 2018 corpus and trained new models with the union of these 2 datasets. We also pretrained language models using clinical notes from the Medical Information Mart for Intensive Care (MIMIC-III) clinical database.ResultsThe voting ensemble achieved better performance than individual classifiers. In the entity identification task, our top-performing system reached a precision of 78.90% and a recall of 83.84%. Our natural language processing system for entity identification took 3rd place out of 17 teams in the challenge. We ranked 4th out of 9 teams in the relation extraction task. Our system substantially benefited from the combination of the 2 datasets. Compared to our official submission with F1 scores of 81.30% and 64.94% for entity identification and relation extraction, respectively, the revised system yielded significantly better performance (P<.05) with F1 scores of 86.02% and 72.48%, respectively.ConclusionsWe demonstrated that a hybrid model could be used to successfully extract family history information recorded in unstructured free-text notes. In this study, our approach to entity identification as a sequence labeling problem produced satisfactory results. Our postchallenge efforts significantly improved performance by leveraging additional labeled data and using word vector representations learned from large collections of clinical notes.

Using Character-Level and Entity-Level Representations to Enhance Bidirectional Encoder Representation From Transformers-Based Clinical Semantic Textual Similarity Model: ClinicalSTS Modeling Study.

BackgroundWith the popularity of electronic health records (EHRs), the quality of health care has been improved. However, there are also some problems caused by EHRs, such as the growing use of copy-and-paste and templates, resulting in EHRs of low quality in content. In order to minimize data redundancy in different documents, Harvard Medical School and Mayo Clinic organized a national natural language processing (NLP) clinical challenge (n2c2) on clinical semantic textual similarity (ClinicalSTS) in 2019. The task of this challenge is to compute the semantic similarity among clinical text snippets.ObjectiveIn this study, we aim to investigate novel methods to model ClinicalSTS and analyze the results.MethodsWe propose a semantically enhanced text matching model for the 2019 n2c2/Open Health NLP (OHNLP) challenge on ClinicalSTS. The model includes 3 representation modules to encode clinical text snippet pairs at different levels: (1) character-level representation module based on convolutional neural network (CNN) to tackle the out-of-vocabulary problem in NLP; (2) sentence-level representation module that adopts a pretrained language model bidirectional encoder representation from transformers (BERT) to encode clinical text snippet pairs; and (3) entity-level representation module to model clinical entity information in clinical text snippets. In the case of entity-level representation, we compare 2 methods. One encodes entities by the entity-type label sequence corresponding to text snippet (called entity I), whereas the other encodes entities by their representation in MeSH, a knowledge graph in the medical domain (called entity II).ResultsWe conduct experiments on the ClinicalSTS corpus of the 2019 n2c2/OHNLP challenge for model performance evaluation. The model only using BERT for text snippet pair encoding achieved a Pearson correlation coefficient (PCC) of 0.848. When character-level representation and entity-level representation are individually added into our model, the PCC increased to 0.857 and 0.854 (entity I)/0.859 (entity II), respectively. When both character-level representation and entity-level representation are added into our model, the PCC further increased to 0.861 (entity I) and 0.868 (entity II).ConclusionsExperimental results show that both character-level information and entity-level information can effectively enhance the BERT-based STS model.

Extraction of Family History Information From Clinical Notes: Deep Learning and Heuristics Approach

BackgroundElectronic health records store large amounts of patient clinical data. Despite efforts to structure patient data, clinical notes containing rich patient information remain stored as free text, greatly limiting its exploitation. This includes family history, which is highly relevant for applications such as diagnosis and prognosis.ObjectiveThis study aims to develop automatic strategies for annotating family history information in clinical notes, focusing not only on the extraction of relevant entities such as family members and disease mentions but also on the extraction of relations between the identified entities.MethodsThis study extends a previous contribution for the 2019 track on family history extraction from national natural language processing clinical challenges by improving a previously developed rule-based engine, using deep learning (DL) approaches for the extraction of entities from clinical notes, and combining both approaches in a hybrid end-to-end system capable of successfully extracting family member and observation entities and the relations between those entities. Furthermore, this study analyzes the impact of factors such as the use of external resources and different types of embeddings in the performance of DL models.ResultsThe approaches developed were evaluated in a first task regarding entity extraction and in a second task concerning relation extraction. The proposed DL approach improved observation extraction, obtaining F1 scores of 0.8688 and 0.7907 in the training and test sets, respectively. However, DL approaches have limitations in the extraction of family members. The rule-based engine was adjusted to have higher generalizing capability and achieved family member extraction F1 scores of 0.8823 and 0.8092 in the training and test sets, respectively. The resulting hybrid system obtained F1 scores of 0.8743 and 0.7979 in the training and test sets, respectively. For the second task, the original evaluator was adjusted to perform a more exact evaluation than the original one, and the hybrid system obtained F1 scores of 0.6480 and 0.5082 in the training and test sets, respectively.ConclusionsWe evaluated the impact of several factors on the performance of DL models, and we present an end-to-end system for extracting family history information from clinical notes, which can help in the structuring and reuse of this type of information. The final hybrid solution is provided in a publicly available code repository.

Cohort Selection for Clinical Trials From Longitudinal Patient Records: Text Mining Approach.

BackgroundClinical trials are an important step in introducing new interventions into clinical practice by generating data on their safety and efficacy. Clinical trials need to ensure that participants are similar so that the findings can be attributed to the interventions studied and not to some other factors. Therefore, each clinical trial defines eligibility criteria, which describe characteristics that must be shared by the participants. Unfortunately, the complexities of eligibility criteria may not allow them to be translated directly into readily executable database queries. Instead, they may require careful analysis of the narrative sections of medical records. Manual screening of medical records is time consuming, thus negatively affecting the timeliness of the recruitment process.ObjectiveTrack 1 of the 2018 National Natural Language Processing Clinical Challenge focused on the task of cohort selection for clinical trials, aiming to answer the following question: Can natural language processing be applied to narrative medical records to identify patients who meet eligibility criteria for clinical trials? The task required the participating systems to analyze longitudinal patient records to determine if the corresponding patients met the given eligibility criteria. We aimed to describe a system developed to address this task.MethodsOur system consisted of 13 classifiers, one for each eligibility criterion. All classifiers used a bag-of-words document representation model. To prevent the loss of relevant contextual information associated with such representation, a pattern-matching approach was used to extract context-sensitive features. They were embedded back into the text as lexically distinguishable tokens, which were consequently featured in the bag-of-words representation. Supervised machine learning was chosen wherever a sufficient number of both positive and negative instances was available to learn from. A rule-based approach focusing on a small set of relevant features was chosen for the remaining criteria.ResultsThe system was evaluated using microaveraged F measure. Overall, 4 machine algorithms, including support vector machine, logistic regression, naïve Bayesian classifier, and gradient tree boosting (GTB), were evaluated on the training data using 10–fold cross-validation. Overall, GTB demonstrated the most consistent performance. Its performance peaked when oversampling was used to balance the training data. The final evaluation was performed on previously unseen test data. On average, the F measure of 89.04% was comparable to 3 of the top ranked performances in the shared task (91.11%, 90.28%, and 90.21%). With an F measure of 88.14%, we significantly outperformed these systems (81.03%, 78.50%, and 70.81%) in identifying patients with advanced coronary artery disease.ConclusionsThe holdout evaluation provides evidence that our system was able to identify eligible patients for the given clinical trial with high accuracy. Our approach demonstrates how rule-based knowledge infusion can improve the performance of machine learning algorithms even when trained on a relatively small dataset.

Cohort selection for clinical trials using hierarchical neural network.

Cohort selection for clinical trials is a key step for clinical research. We proposed a hierarchical neural network to determine whether a patient satisfied selection criteria or not. We designed a hierarchical neural network (denoted as CNN-Highway-LSTM or LSTM-Highway-LSTM) for the track 1 of the national natural language processing (NLP) clinical challenge (n2c2) on cohort selection for clinical trials in 2018. The neural network is composed of 5 components: (1) sentence representation using convolutional neural network (CNN) or long short-term memory (LSTM) network; (2) a highway network to adjust information flow; (3) a self-attention neural network to reweight sentences; (4) document representation using LSTM, which takes sentence representations in chronological order as input; (5) a fully connected neural network to determine whether each criterion is met or not. We compared the proposed method with its variants, including the methods only using the first component to represent documents directly and the fully connected neural network for classification (denoted as CNN-only or LSTM-only) and the methods without using the highway network (denoted as CNN-LSTM or LSTM-LSTM). The performance of all methods was measured by micro-averaged precision, recall, and F1 score. The micro-averaged F1 scores of CNN-only, LSTM-only, CNN-LSTM, LSTM-LSTM, CNN-Highway-LSTM, and LSTM-Highway-LSTM were 85.24%, 84.25%, 87.27%, 88.68%, 88.48%, and 90.21%, respectively. The highest micro-averaged F1 score is higher than our submitted 1 of 88.55%, which is 1 of the top-ranked results in the challenge. The results indicate that the proposed method is effective for cohort selection for clinical trials. Although the proposed method achieved promising results, some mistakes were caused by word ambiguity, negation, number analysis and incomplete dictionary. Moreover, imbalanced data was another challenge that needs to be tackled in the future. In this article, we proposed a hierarchical neural network for cohort selection. Experimental results show that this method is good at selecting cohort.