ABSTRACT
Data curation for a hospital-based cancer registry heavily relies on the labor-intensive manual abstraction process by cancer registrars to identify cancer-related information from free-text electronic health records. To streamline this process, a natural language processing system incorporating a hybrid of deep learning-based and rule-based approaches for identifying lung cancer registry-related concepts, along with a symbolic expert system that generates registry coding based on weighted rules, was developed. The system is integrated with the hospital information system at a medical center to provide cancer registrars with a patient journey visualization platform. The embedded system offers a comprehensive view of patient reports annotated with significant registry concepts to facilitate the manual coding process and elevate overall quality. Extensive evaluations, including comparisons with state-of-the-art methods, were conducted using a lung cancer dataset comprising 1428 patients from the medical center. The experimental results illustrate the effectiveness of the developed system, consistently achieving F1-scores of 0.85 and 1.00 across 30 coding items. Registrar feedback highlights the system's reliability as a tool for assisting and auditing the abstraction. By presenting key registry items along the timeline of a patient's reports with accurate code predictions, the system improves the quality of registrar outcomes and reduces the labor resources and time required for data abstraction. Our study highlights advancements in cancer registry coding practices, demonstrating that the proposed hybrid weighted neural-symbolic cancer registry system is reliable and efficient for assisting cancer registrars in the coding workflow and contributing to clinical outcomes.
ABSTRACT
BACKGROUND: The widespread use of electronic health records in the clinical and biomedical fields makes the removal of protected health information (PHI) essential to maintain privacy. However, a significant portion of information is recorded in unstructured textual forms, posing a challenge for deidentification. In multilingual countries, medical records could be written in a mixture of more than one language, referred to as code mixing. Most current clinical natural language processing techniques are designed for monolingual text, and there is a need to address the deidentification of code-mixed text. OBJECTIVE: The aim of this study was to investigate the effectiveness and underlying mechanism of fine-tuned pretrained language models (PLMs) in identifying PHI in the code-mixed context. Additionally, we aimed to evaluate the potential of prompting large language models (LLMs) for recognizing PHI in a zero-shot manner. METHODS: We compiled the first clinical code-mixed deidentification data set consisting of text written in Chinese and English. We explored the effectiveness of fine-tuned PLMs for recognizing PHI in code-mixed content, with a focus on whether PLMs exploit naming regularity and mention coverage to achieve superior performance, by probing the developed models' outputs to examine their decision-making process. Furthermore, we investigated the potential of prompt-based in-context learning of LLMs for recognizing PHI in code-mixed text. RESULTS: The developed methods were evaluated on a code-mixed deidentification corpus of 1700 discharge summaries. We observed that different PHI types had preferences in their occurrences within the different types of language-mixed sentences, and PLMs could effectively recognize PHI by exploiting the learned name regularity. However, the models may exhibit suboptimal results when regularity is weak or mentions contain unknown words that the representations cannot generate well. We also found that the availability of code-mixed training instances is essential for the model's performance. Furthermore, the LLM-based deidentification method was a feasible and appealing approach that can be controlled and enhanced through natural language prompts. CONCLUSIONS: The study contributes to understanding the underlying mechanism of PLMs in addressing the deidentification process in the code-mixed context and highlights the significance of incorporating code-mixed training instances into the model training phase. To support the advancement of research, we created a manipulated subset of the resynthesized data set available for research purposes. Based on the compiled data set, we found that the LLM-based deidentification method is a feasible approach, but carefully crafted prompts are essential to avoid unwanted output. However, the use of such methods in the hospital setting requires careful consideration of data security and privacy concerns. Further research could explore the augmentation of PLMs and LLMs with external knowledge to improve their strength in recognizing rare PHI.
Subject(s)
Artificial Intelligence , Electronic Health Records , Humans , Natural Language Processing , Privacy , ChinaABSTRACT
BACKGROUND: Electronic health records (EHRs) in unstructured formats are valuable sources of information for research in both the clinical and biomedical domains. However, before such records can be used for research purposes, sensitive health information (SHI) must be removed in several cases to protect patient privacy. Rule-based and machine learning-based methods have been shown to be effective in deidentification. However, very few studies investigated the combination of transformer-based language models and rules. OBJECTIVE: The objective of this study is to develop a hybrid deidentification pipeline for Australian EHR text notes using rules and transformers. The study also aims to investigate the impact of pretrained word embedding and transformer-based language models. METHODS: In this study, we present a hybrid deidentification pipeline called OpenDeID, which is developed using an Australian multicenter EHR-based corpus called OpenDeID Corpus. The OpenDeID corpus consists of 2100 pathology reports with 38,414 SHI entities from 1833 patients. The OpenDeID pipeline incorporates a hybrid approach of associative rules, supervised deep learning, and pretrained language models. RESULTS: The OpenDeID achieved a best F1-score of 0.9659 by fine-tuning the Discharge Summary BioBERT model and incorporating various preprocessing and postprocessing rules. The OpenDeID pipeline has been deployed at a large tertiary teaching hospital and has processed over 8000 unstructured EHR text notes in real time. CONCLUSIONS: The OpenDeID pipeline is a hybrid deidentification pipeline to deidentify SHI entities in unstructured EHR text notes. The pipeline has been evaluated on a large multicenter corpus. External validation will be undertaken as part of our future work to evaluate the effectiveness of the OpenDeID pipeline.
Subject(s)
Data Anonymization , Electronic Health Records , Humans , Australia , Algorithms , Hospitals, TeachingABSTRACT
This study presents the outcomes of the shared task competition BioCreative VII (Task 3) focusing on the extraction of medication names from a Twitter user's publicly available tweets (the user's 'timeline'). In general, detecting health-related tweets is notoriously challenging for natural language processing tools. The main challenge, aside from the informality of the language used, is that people tweet about any and all topics, and most of their tweets are not related to health. Thus, finding those tweets in a user's timeline that mention specific health-related concepts such as medications requires addressing extreme imbalance. Task 3 called for detecting tweets in a user's timeline that mentions a medication name and, for each detected mention, extracting its span. The organizers made available a corpus consisting of 182 049 tweets publicly posted by 212 Twitter users with all medication mentions manually annotated. The corpus exhibits the natural distribution of positive tweets, with only 442 tweets (0.2%) mentioning a medication. This task was an opportunity for participants to evaluate methods that are robust to class imbalance beyond the simple lexical match. A total of 65 teams registered, and 16 teams submitted a system run. This study summarizes the corpus created by the organizers and the approaches taken by the participating teams for this challenge. The corpus is freely available at https://biocreative.bioinformatics.udel.edu/tasks/biocreative-vii/track-3/. The methods and the results of the competing systems are analyzed with a focus on the approaches taken for learning from class-imbalanced data.
Subject(s)
Data Mining , Natural Language Processing , Humans , Data Mining/methodsABSTRACT
BACKGROUND: Most previous studies make psychiatric diagnoses based on diagnostic terms. In this study we sought to augment Diagnostic and Statistical Manual of Mental Disorders, 5th Edition (DSM-5) diagnostic criteria with deep neural network models to make psychiatric diagnoses based on psychiatric notes. METHODS: We augmented DSM-5 diagnostic criteria with self-attention-based bidirectional long short-term memory (BiLSTM) models to identify schizophrenia, bipolar, and unipolar depressive disorders. Given that the diagnostic criteria for psychiatric diagnosis include a certain symptom profile and functional impairment, we first extracted psychiatric symptoms and functional features with two approaches, including a lexicon-based approach and a dependency parsing approach. Then, we incorporated free-text discharge notes and extracted features for psychiatric diagnoses with the proposed models. RESULTS: The micro-averaged F1 scores of the two automatic annotation approaches were greater than 0.8. BiLSTM models with self-attention outperformed the rule-based models with DSM-5 criteria in the prediction of schizophrenia and bipolar disorder, while the latter outperformed the former in predicting unipolar depressive disorder. Approaches for augmenting DSM-5 criteria with a self-attention-based BiLSTM outperformed both pure rule-based and pure deep neural network models. In terms of classification of psychiatric diagnoses, we observed that the performance for schizophrenia and bipolar disorder was acceptable. CONCLUSION: This DSM-5-augmented deep neural network models showed good performance in identifying psychiatric diagnoses from psychiatric notes. We conclude that it is possible to establish a model that consults clinical notes to make psychiatric diagnoses comparably to physicians. Further research will be extended to outpatient notes and other psychiatric disorders.
Subject(s)
Bipolar Disorder , Mental Disorders , Schizophrenia , Humans , Diagnostic and Statistical Manual of Mental Disorders , Mental Disorders/diagnosis , Schizophrenia/diagnosis , Bipolar Disorder/diagnosisABSTRACT
Electronic health records (EHRs) at medical institutions provide valuable sources for research in both clinical and biomedical domains. However, before such records can be used for research purposes, protected health information (PHI) mentioned in the unstructured text must be removed. In Taiwan's EHR systems the unstructured EHR texts are usually represented in the mixing of English and Chinese languages, which brings challenges for de-identification. This paper presented the first study, to the best of our knowledge, of the construction of a code-mixed EHR de-identification corpus and the evaluation of different mature entity recognition methods applied for the code-mixed PHI recognition task.
Subject(s)
Confidentiality , Electronic Health Records , Language , Natural Language Processing , TaiwanABSTRACT
BACKGROUND: Identifying and extracting family history information (FHI) from clinical reports are significant for recognizing disease susceptibility. However, FHI is usually described in a narrative manner within patients' electronic health records, which requires the application of natural language processing technologies to automatically extract such information to provide more comprehensive patient-centered information to physicians. OBJECTIVE: This study aimed to overcome the 2 main challenges observed in previous research focusing on FHI extraction. One is the requirement to develop postprocessing rules to infer the member and side information of family mentions. The other is to efficiently utilize intrasentence and intersentence information to assist FHI extraction. METHODS: We formulated the task as a sequential labeling problem and propose an enhanced relation-side scheme that encodes the required family member properties to not only eliminate the need for postprocessing rules but also relieve the insufficient training instance issues. Moreover, an attention-based neural network structure was proposed to exploit cross-sentence information to identify FHI and its attributes requiring cross-sentence inference. RESULTS: The dataset released by the 2019 n2c2/OHNLP family history extraction task was used to evaluate the performance of the proposed methods. We started by comparing the performance of the traditional neural sequence models with the ordinary scheme and enhanced scheme. Next, we studied the effectiveness of the proposed attention-enhanced neural networks by comparing their performance with that of the traditional networks. It was observed that, with the enhanced scheme, the recall of the neural network can be improved, leading to an increase in the F score of 0.024. The proposed neural attention mechanism enhanced both the recall and precision and resulted in an improved F score of 0.807, which was ranked fourth in the shared task. CONCLUSIONS: We presented an attention-based neural network along with an enhanced tag scheme that enables the neural network model to learn and interpret the implicit relationship and side information of the recognized family members across sentences without relying on heuristic rules.
ABSTRACT
Identifying patients eligible for clinical trials using electronic health records (EHRs) is a challenging task usually requiring a comprehensive analysis of information stored in multiple EHRs of a patient. The goal of this study is to investigate different methods and their effectiveness in identifying patients that meet specific eligibility selection criteria based on patients' longitudinal records. An unstructured dataset released by the n2c2 cohort selection for clinical trials track was used, each of which included 2-5 records manually annotated to thirteen pre-defined selection criteria. Unlike the other studies, we formulated the problem as a multiple instance learning (MIL) task and compared the performance with that of the rule-based and the single instance-based classifiers. Our official best run achieved an average micro-F score of 0.8765 which was ranked as one of the top ten results in the track. Further experiments demonstrated that the performance of the MIL-based classifiers consistently yield better performance than their single-instance counterparts in the criteria that require the overall comprehension of the information distributed among all of the patient's EHRs. Rule-based and single instance learning approaches exhibited better performance in criteria that don't require a consideration of several factors across records. This study demonstrated that cohort selection using longitudinal patient records can be formulated as a MIL problem. Our results exhibit that the MIL-based classifiers supplement the rule-based methods and provide better results in comparison to the single instance learning approaches.
Subject(s)
Electronic Health Records , Machine Learning , Cohort Studies , Humans , Motivation , Patient SelectionABSTRACT
The introduction of pre-trained language models in natural language processing (NLP) based on deep learning and the availability of electronic health records (EHRs) presents a great opportunity to transfer the "knowledge" learned from data in the general domain to enable the analysis of unstructured textual data in clinical domains. This study explored the feasibility of applying NLP to a small EHR dataset to investigate the power of transfer learning to facilitate the process of patient screening in psychiatry. A total of 500 patients were randomly selected from a medical center database. Three annotators with clinical experience reviewed the notes to make diagnoses for major/minor depression, bipolar disorder, schizophrenia, and dementia to form a small and highly imbalanced corpus. Several state-of-the-art NLP methods based on deep learning along with pre-trained models based on shallow or deep transfer learning were adapted to develop models to classify the aforementioned diseases. We hypothesized that the models that rely on transferred knowledge would be expected to outperform the models learned from scratch. The experimental results demonstrated that the models with the pre-trained techniques outperformed the models without transferred knowledge by micro-avg. and macro-avg. F-scores of 0.11 and 0.28, respectively. Our results also suggested that the use of the feature dependency strategy to build multi-labeling models instead of problem transformation is superior considering its higher performance and simplicity in the training process.
ABSTRACT
BACKGROUND: Many studies have used Taiwan's National Health Insurance Research database (NHIRD) to conduct psychiatric research. However, the accuracy of the diagnostic codes for psychiatric disorders in NHIRD is not validated, and the symptom profiles are not available either. This study aimed to evaluate the accuracy of diagnostic codes and use text mining to extract symptom profile and functional impairment from electronic health records (EHRs) to overcome the above research limitations. METHODS: A total of 500 discharge notes were randomly selected from a medical center's database. Three annotators reviewed the notes to establish gold standards. The accuracy of diagnostic codes for major psychiatric illness was evaluated. Text mining approaches were applied to extract depressive symptoms and function profiles and to identify patients with major depressive disorder. RESULTS: The accuracy of the diagnostic code for major depressive disorder, schizophrenia, and dementia was acceptable but that of bipolar disorder and minor depression was less satisfactory. The performance of text mining approach to recognize depressive symptoms is satisfactory; however, the recall for functional impairment is lower resulting in lower F-scores of 0.774-0.753. Using the text mining approach to identify major depressive disorder, the recall was 0.85 but precision was only 0.69. CONCLUSIONS: The accuracy of the diagnostic code for major depressive disorder in discharge notes was generally acceptable. This finding supports the utilization of psychiatric diagnoses in claims databases. The application of text mining to EHRs might help in overcoming current limitations in research using claims databases.
Subject(s)
Data Mining/methods , Depressive Disorder, Major/diagnosis , Electronic Health Records/standards , International Classification of Diseases/standards , Adult , Bipolar Disorder/diagnosis , Databases, Factual , Diagnosis-Related Groups , Female , Humans , Male , Schizophrenia/diagnosis , TaiwanABSTRACT
OBJECTIVE: An adverse drug event (ADE) refers to an injury resulting from medical intervention related to a drug including harm caused by drugs or from the usage of drugs. Extracting ADEs from clinical records can help physicians associate adverse events to targeted drugs. MATERIALS AND METHODS: We proposed a cascading architecture to recognize medical concepts including ADEs, drug names, and entities related to drugs. The architecture includes a preprocessing method and an ensemble of conditional random fields (CRFs) and neural network-based models to respectively address the challenges of surrogate string and overlapping annotation boundaries observed in the employed ADEs and medication extraction (ADME) corpus. The effectiveness of applying different pretrained and postprocessed word embeddings for the ADME task was also studied. RESULTS: The empirical results showed that both CRFs and neural network-based models provide promising solution for the ADME task. The neural network-based models particularly outperformed CRFs in concept types involving narrative descriptions. Our best run achieved an overall micro F-score of 0.919 on the employed corpus. Our results also suggested that the Global Vectors for word representation embedding in general domain provides a very strong baseline, which can be further improved by applying the principal component analysis to generate more isotropic vectors. CONCLUSIONS: We have demonstrated that the proposed cascading architecture can handle the problem of overlapped annotations and further improve the overall recall and F-scores because the architecture enables the developed models to exploit more context information and forms an ensemble for creating a stronger recognizer.
Subject(s)
Drug-Related Side Effects and Adverse Reactions , Electronic Health Records , Information Storage and Retrieval/methods , Natural Language Processing , Neural Networks, Computer , Algorithms , Humans , Narration , Terminology as TopicABSTRACT
BACKGROUND: Family history information (FHI) described in unstructured electronic health records (EHRs) is a valuable information source for patient care and scientific researches. Since FHI is usually described in the format of free text, the entire process of FHI extraction consists of various steps including section segmentation, family member and clinical observation extraction, and relation discovery between the extracted members and their observations. The extraction step involves the recognition of FHI concepts along with their properties such as the family side attribute of the family member concept. METHODS: This study focuses on the extraction step and formulates it as a sequence labeling problem. We employed a neural sequence labeling model along with different tag schemes to distinguish family members and their observations. Corresponding to different tag schemes, the identified entities were aggregated and processed by different algorithms to determine the required properties. RESULTS: We studied the effectiveness of encoding required properties in the tag schemes by evaluating their performance on the dataset released by the BioCreative/OHNLP challenge 2018. It was observed that the proposed side scheme along with the developed features and neural network architecture can achieve an overall F1-score of 0.849 on the test set, which ranked second in the FHI entity recognition subtask. CONCLUSIONS: By comparing with the performance of conditional random fields models, the developed neural network-based models performed significantly better. However, our error analysis revealed two challenging issues of the current approach. One is that some properties required cross-sentence inferences. The other is that the current model is not able to distinguish between the narratives describing the family members of the patient and those specifying the relatives of the patient's family members.
Subject(s)
Electronic Health Records , Information Storage and Retrieval/methods , Medical History Taking , Natural Language Processing , Neural Networks, Computer , Algorithms , HumansABSTRACT
BACKGROUND: Nowadays, social media are often being used by general public to create and share public messages related to their health. With the global increase in social media usage, there is a trend of posting information related to adverse drug reactions (ADR). Mining the social media data for this type of information will be helpful for pharmacological post-marketing surveillance and monitoring. Although the concept of using social media to facilitate pharmacovigilance is convincing, construction of automatic ADR detection systems remains a challenge because the corpora compiled from social media tend to be highly imbalanced, posing a major obstacle to the development of classifiers with reliable performance. METHODS: Several methods have been proposed to address the challenge of imbalanced corpora. However, we are not aware of any studies that investigated the effectiveness of the strategies of dealing with the problem of imbalanced data in the context of ADR detection from social media. In light of this, we evaluated a variety of imbalanced techniques and proposed a novel word embedding-based synthetic minority over-sampling technique (WESMOTE), which synthesizes new training examples from the sentence representation based on word embeddings. We compared the performance of all methods on two large imbalanced datasets released for the purpose of detecting ADR posts. RESULTS: In comparison with the state-of-the-art approaches, the classifiers that incorporated imbalanced classification techniques achieved comparable or better F-scores. All of our best performing configurations combined random under-sampling with techniques including the proposed WESMOTE, boosting and ensemble, implying that an integration of these approaches with under-sampling provides a reliable solution for large imbalanced social media datasets. Furthermore, ensemble-based methods like vote-based under-sampling (VUE) and random under-sampling boosting can be alternatives for the hybrid synthetic methods because both methods increase the diversity of the created weak classifiers, leading to better recall and overall F-scores for the minority classes. CONCLUSIONS: Data collected from the social media are usually very large and highly imbalanced. In order to maximize the performance of a classifier trained on such data, applications of imbalanced strategies are required. We considered several practical methods for handling imbalanced Twitter data along with their performance on the binary classification task with respect to ADRs. In conclusion, the following practical insights are gained: 1) When dealing with text classification, the proposed word embedding-based synthetic minority over-sampling technique is more effective than traditional synthetic-based over-sampling methods. 2) In cases where large amounts of training data are available, the imbalanced strategies combined with under-sampling techniques are preferred. 3) Finally, employment of advanced methods does not guarantee better performance than simpler ones such as VUE, which achieved high performance with advantages like faster building time and ease of development.
Subject(s)
Drug-Related Side Effects and Adverse Reactions , Social Media , Awareness , PharmacovigilanceABSTRACT
The detection of MicroRNA (miRNA) mentions in scientific literature facilitates researchers with the ability to find relevant and appropriate literature based on queries formulated using miRNA information. Considering most published biological studies elaborated on signal transduction pathways or genetic regulatory information in the form of figure captions, the extraction of miRNA from both the main content and figure captions of a manuscript is useful in aggregate analysis and comparative analysis of the studies published. In this study, we present a statistical principle-based miRNA recognition and normalization method to identify miRNAs and link them to the identifiers in the Rfam database. As one of the core components in the text mining pipeline of the database miRTarBase, the proposed method combined the advantages of previous works relying on pattern, dictionary and supervised learning and provided an integrated solution for the problem of miRNA identification. Furthermore, the knowledge learned from the training data was organized in a human-interpretable manner to understand the reason why the system considers a span of text as a miRNA mention, and the represented knowledge can be further complemented by domain experts. We studied the ambiguity level of miRNA nomenclature to connect the miRNA mentions to the Rfam database and evaluated the performance of our approach on two datasets: the BioCreative VI Bio-ID corpus and the miRNA interaction corpus by extending the later corpus with additional Rfam normalization information. Our study highlights and also proposes a better understanding of the challenges associated with miRNA identification and normalization in scientific literature and the research gap that needs to be further explored in prospective studies.
Subject(s)
MicroRNAs/metabolism , Publications , Statistics as Topic , Algorithms , Databases, Genetic , Internet , MicroRNAs/genetics , Molecular Sequence AnnotationABSTRACT
The Precision Medicine Initiative is a multicenter effort aiming at formulating personalized treatments leveraging on individual patient data (clinical, genome sequence and functional genomic data) together with the information in large knowledge bases (KBs) that integrate genome annotation, disease association studies, electronic health records and other data types. The biomedical literature provides a rich foundation for populating these KBs, reporting genetic and molecular interactions that provide the scaffold for the cellular regulatory systems and detailing the influence of genetic variants in these interactions. The goal of BioCreative VI Precision Medicine Track was to extract this particular type of information and was organized in two tasks: (i) document triage task, focused on identifying scientific literature containing experimentally verified protein-protein interactions (PPIs) affected by genetic mutations and (ii) relation extraction task, focused on extracting the affected interactions (protein pairs). To assist system developers and task participants, a large-scale corpus of PubMed documents was manually annotated for this task. Ten teams worldwide contributed 22 distinct text-mining models for the document triage task, and six teams worldwide contributed 14 different text-mining systems for the relation extraction task. When comparing the text-mining system predictions with human annotations, for the triage task, the best F-score was 69.06%, the best precision was 62.89%, the best recall was 98.0% and the best average precision was 72.5%. For the relation extraction task, when taking homologous genes into account, the best F-score was 37.73%, the best precision was 46.5% and the best recall was 54.1%. Submitted systems explored a wide range of methods, from traditional rule-based, statistical and machine learning systems to state-of-the-art deep learning methods. Given the level of participation and the individual team results we find the precision medicine track to be successful in engaging the text-mining research community. In the meantime, the track produced a manually annotated corpus of 5509 PubMed documents developed by BioGRID curators and relevant for precision medicine. The data set is freely available to the community, and the specific interactions have been integrated into the BioGRID data set. In addition, this challenge provided the first results of automatically identifying PubMed articles that describe PPI affected by mutations, as well as extracting the affected relations from those articles. Still, much progress is needed for computer-assisted precision medicine text mining to become mainstream. Future work should focus on addressing the remaining technical challenges and incorporating the practical benefits of text-mining tools into real-world precision medicine information-related curation.
Subject(s)
Data Mining/methods , Databases, Protein , Mutation , Precision Medicine/methods , Protein Interaction Maps , Software , Computational Biology/methods , Humans , Mutation/genetics , Mutation/physiology , Protein Interaction Mapping , Protein Interaction Maps/genetics , Protein Interaction Maps/physiologyABSTRACT
BACKGROUND AND OBJECTIVE: Efficiently capturing the severity of positive valence symptoms could aid in risk stratification for adverse outcomes among patients with psychiatric disorders and identify optimal treatment strategies for patient subgroups. Motivated by the success of convolutional neural networks (CNNs) in classification tasks, we studied the application of various CNN architectures and their performance in predicting the severity of positive valence symptoms in patients with psychiatric disorders based on initial psychiatric evaluation records. METHODS: Psychiatric evaluation records contain unstructured text and semi-structured data such as question-answer pairs. For a given record, we tokenise and normalise the semi-structured content. Pre-processed tokenised words are represented as one-hot encoded word vectors. We then apply different configurations of convolutional and max pooling layers to automatically learn important features from various word representations. We conducted a series of experiments to explore the effect of different CNN architectures on the classification of psychiatric records. RESULTS: Our best CNN model achieved a mean absolute error (MAE) of 0.539 and a normalized MAE of 0.785 on the test dataset, which is comparable to the other well-known text classification algorithms studied in this work. Our results also suggest that the normalisation step has a great impact on the performance of the developed models. CONCLUSIONS: We demonstrate that normalisation of the semi-structured contents can improve the MAE among all CNN configurations. Without advanced feature engineering, CNN-based approaches can provide a comparable solution for classifying positive valence symptom severity in initial psychiatric evaluation records. Although word embedding is well known for its ability to capture relatively low-dimensional similarity between words, our experimental results show that pre-trained embeddings do not improve the classification performance. This phenomenon may be due to the inability of word embeddings to capture problem specific contextual semantic information implying the quality of the employing embedding is critical for obtaining an accurate CNN model.
Subject(s)
Diagnosis, Computer-Assisted/methods , Interview, Psychological , Mental Disorders/diagnosis , Neural Networks, Computer , Humans , Interview, Psychological/methods , Risk Assessment/methodsABSTRACT
Recent advances in biological research reveal that the majority of the experiments strive for comprehensive exploration of the biological system rather than targeting specific biological entities. The qualitative and quantitative findings of the investigations are often exclusively available in the form of figures in published papers. There is no denying that such findings have been instrumental in intensive understanding of biological processes and pathways. However, data as such is unacknowledged by machines as the descriptions in the figure captions comprise of sumptuous information in an ambiguous manner. The abbreviated term 'SIN' exemplifies such issue as it may stand for Sindbis virus or the sex-lethal interactor gene (Drosophila melanogaster). To overcome this ambiguity, entities should be identified by linking them to the respective entries in notable biological databases. Among all entity types, the task of identifying species plays a pivotal role in disambiguating related entities in the text. In this study, we present our species identification tool SPRENO (Species Recognition and Normalization), which is established for recognizing organism terms mentioned in figure captions and linking them to the NCBI taxonomy database by exploiting the contextual information from both the figure caption and the corresponding full text. To determine the ID of ambiguous organism mentions, two disambiguation methods have been developed. One is based on the majority rule to select the ID that has been successfully linked to previously mentioned organism terms. The other is a convolutional neural network (CNN) model trained by learning both the context and the distance information of the target organism mention. As a system based on the majority rule, SPRENO was one of the top-ranked systems in the BioCreative VI BioID track and achieved micro F-scores of 0.776 (entity recognition) and 0.755 (entity normalization) on the official test set, respectively. Additionally, the SPRENO-CNN exhibited better precisions with lower recalls and F-scores (0.720/0.711 for entity recognition/normalization). SPRENO is freely available at https://bigodatamining.github.io/software/201801/.Database URL: https://bigodatamining.github.io/software/201801/.
Subject(s)
Classification , Data Mining/methods , Databases, Factual , Neural Networks, Computer , Animals , Drosophila melanogaster , Genes, Insect , Genes, Viral , Sindbis Virus/genetics , Sindbis Virus/metabolismABSTRACT
Evidence has revealed interesting associations of clinical and social parameters with violent behaviors of patients with psychiatric disorders. Men are more violent preceding and during hospitalization, whereas women are more violent than men throughout the 3days following a hospital admission. It has also been proven that mental disorders may be a consistent risk factor for the occurrence of violence. In order to better understand violent behaviors of patients with psychiatric disorders, it is important to investigate both the clinical symptoms and psychosocial factors that accompany violence in these patients. In this study, we utilized a dataset released by the Partners Healthcare and Neuropsychiatric Genome-scale and RDoC Individualized Domains project of Harvard Medical School to develop a unique text mining pipeline that processes unstructured clinical data in order to recognize clinical and social parameters such asage, gender, history of alcohol use, and violent behaviors, and explored the associations between these parameters and violent behaviors of patients with psychiatric disorders. The aim of our work was to demonstrate the feasibility of mining factors that are strongly associated with violent behaviors among psychiatric patients from unstructured psychiatric evaluation records using clinical text mining. Experiment results showed that stimulants, followed by a family history of violent behavior, suicidal behaviors, and financial stress were strongly associated with violent behaviors. Key aspects explicated in this paper include employing our text mining pipeline to extract clinical and social factors linked with violent behaviors, generating association rules to uncover possible associations between these factors and violent behaviors, and lastly the ranking of top rules associated with violent behaviors using statistical analysis and interpretation.
Subject(s)
Mental Disorders/psychology , Violence , Adolescent , Adult , Female , Humans , Male , Risk Factors , Young AdultABSTRACT
Hepatocellular carcinoma (HCC), one of the most common causes of cancer-related deaths, carries a 5-year survival rate of 18%, underscoring the need for robust biomarkers. In spite of the increased availability of HCC related literatures, many of the promising biomarkers reported have not been validated for clinical use. To narrow down the wide range of possible biomarkers for further clinical validation, bioinformaticians need to sort them out using information provided in published works. Biomedical text mining is an automated way to obtain information of interest within the massive collection of biomedical knowledge, thus enabling extraction of data for biomarkers associated with certain diseases. This method can significantly reduce both the time and effort spent on studying important maladies such as liver diseases. Herein, we report a text mining-aided curation pipeline to identify potential biomarkers for liver cancer. The curation pipeline integrates PubMed E-Utilities to collect abstracts from PubMed and recognize several types of named entities by machine learning-based and pattern-based methods. Genes/proteins from evidential sentences were classified as candidate biomarkers using a convolutional neural network. Lastly, extracted biomarkers were ranked depending on several criteria, such as the frequency of keywords and articles and the journal impact factor, and then integrated into a meaningful list for bioinformaticians. Based on the developed pipeline, we constructed MarkerHub, which contains 2128 candidate biomarkers extracted from PubMed publications from 2008 to 2017. Database URL: http://markerhub.iis.sinica.edu.tw.
ABSTRACT
Fully automated text mining (TM) systems promote efficient literature searching, retrieval, and review but are not sufficient to produce ready-to-consume curated documents. These systems are not meant to replace biocurators, but instead to assist them in one or more literature curation steps. To do so, the user interface is an important aspect that needs to be considered for tool adoption. The BioCreative Interactive task (IAT) is a track designed for exploring user-system interactions, promoting development of useful TM tools, and providing a communication channel between the biocuration and the TM communities. In BioCreative V, the IAT track followed a format similar to previous interactive tracks, where the utility and usability of TM tools, as well as the generation of use cases, have been the focal points. The proposed curation tasks are user-centric and formally evaluated by biocurators. In BioCreative V IAT, seven TM systems and 43 biocurators participated. Two levels of user participation were offered to broaden curator involvement and obtain more feedback on usability aspects. The full level participation involved training on the system, curation of a set of documents with and without TM assistance, tracking of time-on-task, and completion of a user survey. The partial level participation was designed to focus on usability aspects of the interface and not the performance per se In this case, biocurators navigated the system by performing pre-designed tasks and then were asked whether they were able to achieve the task and the level of difficulty in completing the task. In this manuscript, we describe the development of the interactive task, from planning to execution and discuss major findings for the systems tested.Database URL: http://www.biocreative.org.