Medical Text Mining Research Articles

Enhanced Precision in Chinese Medical Text Mining Using the ALBERT+Bi-LSTM+CRF Model

Medical texts are rich in specialized knowledge and medical information. As the medical and healthcare sectors are becoming more digitized, many medical texts must be effectively harnessed to derive insights and patterns. Thus, great attention is directed to this emerging research area. Generally, natural language processing (NLP) algorithms are employed to extract comprehensive information from unstructured medical texts, aiming to construct a graphical database for medical knowledge. One of the needs is to optimize model sizes while maintaining the precision of the BART algorithm. A novel carefully designed algorithm, called ALBERT+Bi-LSTM+CRF, is introduced. In this way, both enhanced efficiency and scalability are attained. When entities are extracted, the constructed algorithm achieves 91.8%, 92.5%, and 94.3% for the F-score, precision, and recall, respectively. The proposed algorithm also achieves remarkable outcomes in extracting relations, with 88.3%, 88.1%, and 88.4% for the F-score, precision, and recall, respectively. This further underscores its practicality in the graphical construction of medical knowledge.

Integrated Application of LLM Model and Knowledge Graph in Medical Text Mining and Knowledge Extraction

Integrated Application of LLM Model and Knowledge Graph in Medical Text Mining and Knowledge Extraction

Forecasting Financial Time Series Using Deep Learning Networks: Evidence from Long-Short Term Memory and Gated Recurrent Unit

The ability to predict the stock market and analyze market trends is invaluable to researchers and anyone interested in investing. However, this task is a challenging problem due to a large number of parameters and unpredictable noise that may affect the stock price. To overcome this issue, researchers have employed numerous approaches such as Moving Average (MA), Support Vector Machine (SVM), and Neural Networks. With technological advances, deep learning methods have become popular in processing time-series data. In this paper, we compare two recently introduced deep learning models, namely a Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), in forecasting daily movements of the Standard & Poor (S&P 500) index using the daily closing price of this index from 14/5/1991 to 14/5/2021. Results show that both models are effective and accurate in stock market prediction. In this case study, the mean squared error (MSE) and mean absolute error (MAE) for the GRU model are slightly lower than the LSTM model; hence, GRU outperformed the LSTM model despite its simpler structure. The results of this study are applicable in various instances where it is challenging to identify patterns among large volumes of unstructured data, such as medical data analysis, text mining, and financial time series modeling.

DrNote: An open medical annotation service.

In the context of clinical trials and medical research medical text mining can provide broader insights for various research scenarios by tapping additional text data sources and extracting relevant information that is often exclusively present in unstructured fashion. Although various works for data like electronic health reports are available for English texts, only limited work on tools for non-English text resources has been published that offers immediate practicality in terms of flexibility and initial setup. We introduce DrNote, an open source text annotation service for medical text processing. Our work provides an entire annotation pipeline with its focus on a fast yet effective and easy to use software implementation. Further, the software allows its users to define a custom annotation scope by filtering only for relevant entities that should be included in its knowledge base. The approach is based on OpenTapioca and combines the publicly available datasets from WikiData and Wikipedia, and thus, performs entity linking tasks. In contrast to other related work our service can easily be built upon any language-specific Wikipedia dataset in order to be trained on a specific target language. We provide a public demo instance of our DrNote annotation service at https://drnote.misit-augsburg.de/.

Negation and uncertainty detection in clinical texts written in Spanish: a deep learning-based approach.

Detecting negation and uncertainty is crucial for medical text mining applications; otherwise, extracted information can be incorrectly identified as real or factual events. Although several approaches have been proposed to detect negation and uncertainty in clinical texts, most efforts have focused on the English language. Most proposals developed for Spanish have focused mainly on negation detection and do not deal with uncertainty. In this paper, we propose a deep learning-based approach for both negation and uncertainty detection in clinical texts written in Spanish. The proposed approach explores two deep learning methods to achieve this goal: (i) Bidirectional Long-Short Term Memory with a Conditional Random Field layer (BiLSTM-CRF) and (ii) Bidirectional Encoder Representation for Transformers (BERT). The approach was evaluated using NUBES and IULA, two public corpora for the Spanish language. The results obtained showed an F-score of 92% and 80% in the scope recognition task for negation and uncertainty, respectively. We also present the results of a validation process conducted using a real-life annotated dataset from clinical notes belonging to cancer patients. The proposed approach shows the feasibility of deep learning-based methods to detect negation and uncertainty in Spanish clinical texts. Experiments also highlighted that this approach improves performance in the scope recognition task compared to other proposals in the biomedical domain.

Intelligent cloud assistance for healthcare sectors

E-healthcare systems have been measured by the drastically facilitating healthcare monitoring, earlier intervention and disease modelling and proof-based medical consultancy using medical image feature extraction and text mining. Due to certain resource constraints encountered in wearable devices, it is essential to outsource frequently generated healthcare information of individuals to cloud systems. Regrettably, handling both computation and storage to some un-trusted entity is a sequence of privacy and security crisis. The prevailing approaches significantly concentrate on finely tuning privacy preservation statistical medical text analysis and access, which is barely considered as a dynamic fluctuation of health condition and analysis of medical image. In this work, an effectual and secure privacy preservation dynamic medical modelling scheme has been anticipated as a healthcare service with cloud-based e-healthcare solution that offers automated functions to notify nearby hospitals in providing immediate proper treatment for medical emergencies.

A combinatorial optimization approach for multi-label associative classification

Mining associations between variables corresponding to multiple class labels (or outcomes) is prevalent in various applied domains, such as medical diagnosis, text mining, e-commence, and social behavior analysis. While most associative classification algorithms have been developed to discover association rules of binary variables for single-label classification problem, there are limited methods designed for the problem, called multi-label classification, that accounts for multi-labels. In this study, we consider the multi-label classification problem as a multi-class classification problem and formulate it as a 0–1 integer optimization model. We then leverage combinatorial optimization and association rule techniques to solve this hard problem. More specifically, we propose a ranking metric for selecting and aggregating stronger rules to form an optimal multi-label classifier. The computational results for multiple real applications show that our algorithm is able to identify significant association rules between key variables and multiple labels, and in turn achieves a competitive classification performance compared to state-of-the-art machine learning methods such as logistic regression, decision trees, and random forest. Moreover, we design a user-interface tool interfaced with the developed algorithm and demonstrate a medical diagnosis problem to predict multiple high-risk subgroups during emergency care in practice.

Causality Mining in Natural Languages Using Machine and Deep Learning Techniques: A Survey

The era of big textual corpora and machine learning technologies have paved the way for researchers in numerous data mining fields. Among them, causality mining (CM) from textual data has become a significant area of concern and has more attention from researchers. Causality (cause-effect relations) serves as an essential category of relationships, which plays a significant role in question answering, future events predication, discourse comprehension, decision making, future scenario generation, medical text mining, behavior prediction, and textual prediction entailment. While, decades of development techniques for CM are still prone to performance enhancement, especially for ambiguous and implicitly expressed causalities. The ineffectiveness of the early attempts is mainly due to small, ambiguous, heterogeneous, and domain-specific datasets constructed by manually linguistic and syntactic rules. Many researchers have deployed shallow machine learning (ML) and deep learning (DL) techniques to deal with such datasets, and they achieved satisfactory performance. In this survey, an effort has been made to address a comprehensive review of some state-of-the-art shallow ML and DL approaches in CM. We present a detailed taxonomy of CM and discuss popular ML and DL approaches with their comparative weaknesses and strengths, applications, popular datasets, and frameworks. Lastly, the future research challenges are discussed with illustrations of how to transform them into productive future research directions.

Automated classification of BI-RADS in textual mammography reports

The main purpose of this paper is to process key information in medical text records and also classifypatients, per different levels of breast imaging-reporting and data system (BI-RADS). The BI-RADS is a scheme for thestandardization of breast imaging reports. Therefore, medical text mining is employed to classify mammography reportssupported BI-RADS. In this research, a new method is proposed for automated BI-RADS classifications extraction fromtextual reports and improves the therapeutic procedures. At first, a mammography lexicon is employed for choosingkeywords from medical text reports. Word2vec and term frequency inverse document frequency (TFIDF) techniques areused for extracting features, finally, they are combined with the hospital information system (HIS) reports and calledWith-HIS. The different classifiers like multiclass support vector machine (SVM), naïve Bayesian (NB), extreme gradientboosting (XGBoost), and multilevel fuzzy min-max neural network (MLF) are used so as to compare the accuracy ofWith-HIS and without HIS (called Without-HIS). The results are confirmed that using HIS beside the proposed approach(Word2vec +TFIDF) encompasses a significant effect on the accuracy of medical text classification. Accuracy within theproposed method with MLF classifier is 0.89% but Without-HIS is 0.85%.

A Medical Decision Support System for the Differential Diagnosis Based on Medical Information Text Mining

Aristidis Ilias1, Andreas Kanavos1* and Maria Adamopoulos2 Author Affiliations 1Department of Computer Engineering & Informatics, University of Patras, Greece 2School of Medicine, University of Patras, Greece Received: September 11, 2020 | Published: October 02, 2020 Corresponding author: Andreas Kanavos, Department of Computer Engineering & Informatics, University of Patras, Greece DOI: 10.26717/BJSTR.2020.30.005020

Automated Spelling Correction for Clinical Text Mining in Russian.

The main goal of this paper is to develop a spell checker module for clinical text in Russian. The described approach combines string distance measure algorithms with technics of machine learning embedding methods. Our overall precision is 0.86, lexical precision - 0.975 and error precision is 0.74. We develop spell checker as a part of medical text mining tool regarding the problems of misspelling, negation, experiencer and temporality detection.

Overexpression of miR-17 is correlated with liver metastasis in colorectal cancer.

Background:Colorectal cancer (CRC) is the second leading cause of cancer-related deaths in men and women. The presence of systemic disease, with metastatic spread to distant sites such as the liver, considerably reduces the survival rate in CRC. Cancer stem cells contribute to the metastatic potential of CRC. However, the mechanism underlying metastasis in CRC remains unclear. Thus, this study aimed to examine the expression of microRNAs (miRNAs) in CRC stem cells in cases of liver metastases and assess their correlation with clinicopathological features.Methods:miRNAs showing high expression in liver metastases and primary lesions were selected through data mining of gene expression omnibus datasets, and miRNAs characteristic of stem cells were selected through COREMINE medical text mining. Subsequently, paired formalin-fixed paraffin-embedded tissue samples of primary CRC and liver metastasis from 30 patients were examined for the expression of miRNAs common to these lists (hsa-miR-20a, hsa-miR-26b, hsa-miR-146a, hsa-miR-17, hsa-miR-451, hsa-miR-23a, and hsa-miR-29a) using quantitative real-time polymerase chain reaction. Further, miRNA expression was compared between liver metastases and the primary tumor in each patient and the factors associated with differential expression were analyzed.Results:hsa-miR-17 was significantly upregulated in liver metastases (P < .05), but no significant difference in the expression of hsa-miR-26b, hsa-miR-146a, hsa-miR-451, hsa-miR-23a, and hsa-miR-29a was observed between primary tumors and liver metastases. The higher expression of hsa-miR-17 in liver metastases was associated with the administration of neoadjuvant chemotherapy and tumor differentiation (P < .05) but was not associated with age, sex, tumor location, or lymphatic metastasis.Conclusions:High expression of miR-17 may contribute to liver metastasis in CRC. Therefore, an in-depth understanding of its downstream pathways could help in elucidating the mechanisms underlying liver metastases in CRC. However, additional studies are warranted to validate these findings.

PMO: A knowledge representation model towards precision medicine.

With the rapid development of biomedical technology, amounts of data in the field of precision medicine (PM) are growing exponentially. Valuable knowledge is included in scattered data in which meaningful biomedical entities and their semantic relationships are buried. Therefore, it is necessary to develop a knowledge representation model like ontology to formally represent the relationships among diseases, phenotypes, genes, mutations, drugs, etc. and achieve effective integration of heterogeneous data. On basis of existing work, our study focus on solving the following issues: (i) Selecting the primary entities in PM domain; (ii) collecting and integrating biomedical vocabularies related to the above entities; (iii) defining and normalizing semantic relationships among these entities. We proposed a semi-automated method which improved the original Ontology Development 101 method to build the Precision Medicine Ontology (PMO), including defining the scope of the PMO according to the definition of PM, collecting terms from different biomedical resources, integrating and normalizing the terms by a combination of machine and manual work, defining the annotation properties, reusing existing ontologies and taxonomies, defining semantic relationships, evaluating PMO and creating the PMO website. Finally, the Precision Medicine Vocabulary (PMV) contains 4.53 million terms collected from 62 biomedical vocabularies, and the PMO includes eleven branches of PM concepts such as disease, chemical and drug, phenotype, gene, mutation, gene product and cell, described by 93 semantic relationships among them. PMO is an open, extensible ontology of PM, all of the terms and relationships in which could be obtained from the PMO website (http://www.phoc.org.cn/pmo/). Compared to existing project, our work has brought a broader and deeper coverage of mutation, gene and gene product, which enriches the semantic type and vocabulary in PM domain and benefits all users in terms of medical literature annotation, text mining and knowledge base construction.

A Survey Techniques Used for Prediction of Heart Attack with Machine Learning and Medical Text Mining

Heart attack is one of the most critical heart disease in the world and affects human life very badly. In heart attack, the heart is unable to push the required amount of blood to other parts of the body. Accurate and on time diagnosis of heart attack is important for heart failure prevention and treatment. The diagnosis of such condition through traditional medical history has been considered as not reliable in many aspects. To classify the healthy people and people with heart attack causes and related problems, noninvasive-based methods such as machine learning are reliable and efficient. In the proposed study, we developed a machine-learning-based diagnosis system for heart attack prediction by using heart disease dataset. We used popular machine learning algorithms for performance evaluation metrics such as classification accuracy, sensitivity and correlation coefficient. The proposed system can easily predict and classify people with heart attack possibilities from healthy people.

Scientific Challenge in eHealth: MAPPATHON, a Metadata Mapping Challenge.

Scientific challenges based on benchmark data enable the comparison and evaluation of different algorithms and take place regularly in scientific disciplines like medical image processing, text mining or genetics. The idea of a challenge is rarely applied within the eHealth community. Mappathon is a metadata mapping challenge that asks for methods to find corresponding data elements within similar datasets and to correlate data elements among each other.

Mapping anatomical related entities to human body parts based on wikipedia in discharge summaries

*Background Consisting of dictated free-text documents such as discharge summaries, medical narratives are widely used in medical natural language processing. Relationships between anatomical entities and human body parts are crucial for building medical text mining applications. To achieve this, we establish a mapping system consisting of a Wikipedia-based scoring algorithm and a named entity normalization method (NEN). The mapping system makes full use of information available on Wikipedia, which is a comprehensive Internet medical knowledge base. We also built a new ontology, Tree of Human Body Parts (THBP), from core anatomical parts by referring to anatomical experts and Unified Medical Language Systems (UMLS) to make the mapping system efficacious for clinical treatments.*Result The gold standard is derived from 50 discharge summaries from our previous work, in which 2,224 anatomical entities are included. The F1-measure of the baseline system is 70.20%, while our algorithm based on Wikipedia achieves 86.67% with the assistance of NEN.*Conclusions We construct a framework to map anatomical entities to THBP ontology using normalization and a scoring algorithm based on Wikipedia. The proposed framework is proven to be much more effective and efficient than the main baseline system.

SBLC: a hybrid model for disease named entity recognition based on semantic bidirectional LSTMs and conditional random fields

BackgroundDisease named entity recognition (NER) is a fundamental step in information processing of medical texts. However, disease NER involves complex issues such as descriptive modifiers in actual practice. The accurate identification of disease NER is a still an open and essential research problem in medical information extraction and text mining tasks.MethodsA hybrid model named Semantics Bidirectional LSTM and CRF (SBLC) for disease named entity recognition task is proposed. The model leverages word embeddings, Bidirectional Long Short Term Memory networks and Conditional Random Fields. A publically available NCBI disease dataset is applied to evaluate the model through comparing with nine state-of-the-art baseline methods including cTAKES, MetaMap, DNorm, C-Bi-LSTM-CRF, TaggerOne and DNER.ResultsThe results show that the SBLC model achieves an F1 score of 0.862 and outperforms the other methods. In addition, the model does not rely on external domain dictionaries, thus it can be more conveniently applied in many aspects of medical text processing.ConclusionsAccording to performance comparison, the proposed SBLC model achieved the best performance, demonstrating its effectiveness in disease named entity recognition.

Medical data mining in sentiment analysis based on optimized swarm search feature selection.

In this paper, we propose a novel technique termed as optimized swarm search-based feature selection (OS-FS), which is a swarm-type of searching function that selects an ideal subset of features for enhanced classification accuracy. In terms of gaining insights from unstructured medical based texts, sentiment prediction is becoming an increasingly crucial machine learning technique. In fact, due to its robustness and accuracy, it recently gained popularity in the medical industries. Medical text mining is well known as a fundamental data analytic for sentiment prediction. To form a high-dimensional sparse matrix, a popular preprocessing step in text mining is employed to transform medical text strings to word vectors. However, such a sparse matrix poses problems to the induction of accurate sentiment prediction model. The swarm search in our proposed OS-FS can be optimized by a new feature evaluation technique called clustering-by-coefficient-of-variation. In order to find a subset of features from all the original features from the sparse matrix, this type of feature selection has been a commonly utilized dimensionality reduction technique, and has the capability to improve accuracy of the prediction model. We implement this method based on a case scenario where 279 medical articles related to 'meaningful use functionalities on health care quality, safety, and efficiency' from a systematic review of previous medical IT literature. For this medical text mining, a multi-class of sentiments, positive, mixed-positive, neutral and negative is recognized from the document contents. Our experimental results demonstrate the superiority of OS-FS over traditional feature selection methods in literature.

A Survey of Current Work in Medical Text Mining---Data Source Perspective

This paper discusses the application of text mining in medical field at home and abroad based on overview and analysis of current literature data. Foreign researchers have specific text mining tools, and they use it in the search engine data and electronic medical record. In addition, it is also used to predict side effects between drugs. In China, text mining based on medical literature data occupies a large part. On the one hand, they can monitor the self disclosure of health information. On the other hand, they explore whether online information can help individuals get out of the disease. With the development of information technology, text mining will become more and more widely applied in the medical field in the future.

BioCreative V track 4: a shared task for the extraction of causal network information using the Biological Expression Language.

Automatic extraction of biological network information is one of the most desired and most complex tasks in biological and medical text mining. Track 4 at BioCreative V attempts to approach this complexity using fragments of large-scale manually curated biological networks, represented in Biological Expression Language (BEL), as training and test data. BEL is an advanced knowledge representation format which has been designed to be both human readable and machine processable. The specific goal of track 4 was to evaluate text mining systems capable of automatically constructing BEL statements from given evidence text, and of retrieving evidence text for given BEL statements. Given the complexity of the task, we designed an evaluation methodology which gives credit to partially correct statements. We identified various levels of information expressed by BEL statements, such as entities, functions, relations, and introduced an evaluation framework which rewards systems capable of delivering useful BEL fragments at each of these levels. The aim of this evaluation method is to help identify the characteristics of the systems which, if combined, would be most useful for achieving the overall goal of automatically constructing causal biological networks from text.