Search

Summary: Current studies in early cancer detection based on liquid biopsy data often rely on off-the-shelf models and face challenges with heterogeneous data, as well as manually designed data preprocessing pipelines with different parameter settings. To address those challenges, we present AutoCancer, an automated, multimodal, and interpretable transformer-based framework. This framework integrates feature selection, neural architecture search, and hyperparameter optimization into a unified optimization problem with Bayesian optimization. Comprehensive experiments demonstrate that AutoCancer achieves accurate performance in specific cancer types and pan-cancer analysis, outperforming existing methods across three cohorts. We further demonstrated the interpretability of AutoCancer by identifying key gene mutations associated with non-small cell lung cancer to pinpoint crucial factors at different stages and subtypes. The robustness of AutoCancer, coupled with its strong interpretability, underscores its potential for clinical applications in early cancer detection.

Graph Neural Networks are employed to encode molecular graph representations, but structural information and chemical functions are largely missing. Here, the authors develop hierarchical molecular graph self-supervised learning as a framework to learn molecule representation for property prediction.

Abstract Background In biomedical research, chemical and disease relation extraction from unstructured biomedical literature is an essential task. Effective context understanding and knowledge integration are two main research problems in this task. Most work of relation extraction focuses on classification for entity mention pairs. Inspired by the effectiveness of machine reading comprehension (RC) in the respect of context understanding, solving biomedical relation extraction with the RC framework at both intra-sentential and inter-sentential levels is a new topic worthy to be explored. Except for the unstructured biomedical text, many structured knowledge bases (KBs) provide valuable guidance for biomedical relation extraction. Utilizing knowledge in the RC framework is also worthy to be investigated. We propose a knowledge-enhanced reading comprehension (KRC) framework to leverage reading comprehension and prior knowledge for biomedical relation extraction. First, we generate questions for each relation, which reformulates the relation extraction task to a question answering task. Second, based on the RC framework, we integrate knowledge representation through an efficient knowledge-enhanced attention interaction mechanism to guide the biomedical relation extraction. Results The proposed model was evaluated on the BioCreative V CDR dataset and CHR dataset. Experiments show that our model achieved a competitive document-level F1 of 71.18% and 93.3%, respectively, compared with other methods. Conclusion Result analysis reveals that open-domain reading comprehension data and knowledge representation can help improve biomedical relation extraction in our proposed KRC framework. Our work can encourage more research on bridging reading comprehension and biomedical relation extraction and promote the biomedical relation extraction.

Abstract Background Biomedical named entity recognition (NER) is a fundamental task of biomedical text mining that finds the boundaries of entity mentions in biomedical text and determines their entity type. To accelerate the development of biomedical NER techniques in Spanish, the PharmaCoNER organizers launched a competition to recognize pharmacological substances, compounds, and proteins. Biomedical NER is usually recognized as a sequence labeling task, and almost all state-of-the-art sequence labeling methods ignore the meaning of different entity types. In this paper, we investigate some methods to introduce the meaning of entity types in deep learning methods for biomedical NER and apply them to the PharmaCoNER 2019 challenge. The meaning of each entity type is represented by its definition information. Material and method We investigate how to use entity definition information in the following two methods: (1) SQuad-style machine reading comprehension (MRC) methods that treat entity definition information as query and biomedical text as context and predict answer spans as entities. (2) Span-level one-pass (SOne) methods that predict entity spans of one type by one type and introduce entity type meaning, which is represented by entity definition information. All models are trained and tested on the PharmaCoNER 2019 corpus, and their performance is evaluated by strict micro-average precision, recall, and F1-score. Results Entity definition information brings improvements to both SQuad-style MRC and SOne methods by about 0.003 in micro-averaged F1-score. The SQuad-style MRC model using entity definition information as query achieves the best performance with a micro-averaged precision of 0.9225, a recall of 0.9050, and an F1-score of 0.9137, respectively. It outperforms the best model of the PharmaCoNER 2019 challenge by 0.0032 in F1-score. Compared with the state-of-the-art model without using manually-crafted features, our model obtains a 1% improvement in F1-score, which is significant. These results indicate that entity definition information is useful for deep learning methods on biomedical NER. Conclusion Our entity definition information enhanced models achieve the state-of-the-art micro-average F1 score of 0.9137, which implies that entity definition information has a positive impact on biomedical NER detection. In the future, we will explore more entity definition information from knowledge graph.

Abstract Objective Relation extraction (RE) is a fundamental task of natural language processing, which always draws plenty of attention from researchers, especially RE at the document-level. We aim to explore an effective novel method for document-level medical relation extraction. Methods We propose a novel edge-oriented graph neural network based on document structure and external knowledge for document-level medical RE, called SKEoG. This network has the ability to take full advantage of document structure and external knowledge. Results We evaluate SKEoG on two public datasets, that is, Chemical-Disease Relation (CDR) dataset and Chemical Reactions dataset (CHR) dataset, by comparing it with other state-of-the-art methods. SKEoG achieves the highest F1-score of 70.7 on the CDR dataset and F1-score of 91.4 on the CHR dataset. Conclusion The proposed SKEoG method achieves new state-of-the-art performance. Both document structure and external knowledge can bring performance improvement in the EoG framework. Selecting proper methods for knowledge node representation is also very important.

Abstract Background Drug repurposing is to find new indications of approved drugs, which is essential for investigating new uses for approved or investigational drug efficiency. The active gene annotation corpus (named AGAC) is annotated by human experts, which was developed to support knowledge discovery for drug repurposing. The AGAC track of the BioNLP Open Shared Tasks using this corpus is organized by EMNLP-BioNLP 2019, where the “Selective annotation” attribution makes AGAC track more challenging than other traditional sequence labeling tasks. In this work, we show our methods for trigger word detection (Task 1) and its thematic role identification (Task 2) in the AGAC track. As a step forward to drug repurposing research, our work can also be applied to large-scale automatic extraction of medical text knowledge. Methods To meet the challenges of the two tasks, we consider Task 1 as the medical name entity recognition (NER), which cultivates molecular phenomena related to gene mutation. And we regard Task 2 as a relation extraction task, which captures the thematic roles between entities. In this work, we exploit pre-trained biomedical language representation models (e.g., BioBERT) in the information extraction pipeline for mutation-disease knowledge collection from PubMed. Moreover, we design the fine-tuning framework by using a multi-task learning technique and extra features. We further investigate different approaches to consolidate and transfer the knowledge from varying sources and illustrate the performance of our model on the AGAC corpus. Our approach is based on fine-tuned BERT, BioBERT, NCBI BERT, and ClinicalBERT using multi-task learning. Further experiments show the effectiveness of knowledge transformation and the ensemble integration of models of two tasks. We conduct a performance comparison of various algorithms. We also do an ablation study on the development set of Task 1 to examine the effectiveness of each component of our method. Results Compared with competitor methods, our model obtained the highest Precision (0.63), Recall (0.56), and F-score value (0.60) in Task 1, which ranks first place. It outperformed the baseline method provided by the organizers by 0.10 in F-score. The model shared the same encoding layers for the named entity recognition and relation extraction parts. And we obtained a second high F-score (0.25) in Task 2 with a simple but effective framework. Conclusions Experimental results on the benchmark annotation of genes with active mutation-centric function changes corpus show that integrating pre-trained biomedical language representation models (i.e., BERT, NCBI BERT, ClinicalBERT, BioBERT) into a pipe of information extraction methods with multi-task learning can improve the ability to collect mutation-disease knowledge from PubMed.

IntroductionStudies have shown that suicide is closely related to various social factors. However, due to the restriction in the data scale, our understanding of these social factors is still limited. We propose a conceptual framework for understanding social determinants of suicide at the national level and investigate the relationships between structural determinants (i.e., gender, employment statuses, and occupation) and suicide outcomes (i.e., types of suicide, places of suicide, suicide methods, and warning signs) in South Korea.MethodsWe linked a national-level suicide registry from the Korea Psychological Autopsy Center with the Social Determinants of Health framework proposed by the World Health Organization's Commission on Social Determinants of Health.ResultsFirst, male and female suicide victims have clear differences in their typical suicide methods (fire vs. drug overdose), primary warning signs (verbal vs. mood), and places of death (suburb vs. home). Second, employees accounted for the largest proportion of murder-suicides (>30%). The proportion of students was much higher for joint suicides than for individual suicides and murder-suicides. Third, among individuals choosing pesticides as their suicide method, over 50% were primary workers. In terms of drug overdoses, professionals and laborers accounted for the largest percentage; the former also constituted the largest proportion in the method of jumping from heights.ConclusionA clear connection exists between the investigated structural factors and various suicide outcomes, with gender, social class, and occupation all impacting suicide.

Abstract Background Text Matching (TM) is a fundamental task of natural language processing widely used in many application systems such as information retrieval, automatic question answering, machine translation, dialogue system, reading comprehension, etc. In recent years, a large number of deep learning neural networks have been applied to TM, and have refreshed benchmarks of TM repeatedly. Among the deep learning neural networks, convolutional neural network (CNN) is one of the most popular networks, which suffers from difficulties in dealing with small samples and keeping relative structures of features. In this paper, we propose a novel deep learning architecture based on capsule network for TM, called CapsTM, where capsule network is a new type of neural network architecture proposed to address some of the short comings of CNN and shows great potential in many tasks. Methods CapsTM is a five-layer neural network, including an input layer, a representation layer, an aggregation layer, a capsule layer and a prediction layer. In CapsTM, two pieces of text are first individually converted into sequences of embeddings and are further transformed by a highway network in the input layer. Then, Bidirectional Long Short-Term Memory (BiLSTM) is used to represent each piece of text and attention-based interaction matrix is used to represent interactive information of the two pieces of text in the representation layer. Subsequently, the two kinds of representations are fused together by BiLSTM in the aggregation layer, and are further represented with capsules (vectors) in the capsule layer. Finally, the prediction layer is a connected network used for classification. CapsTM is an extension of ESIM by adding a capsule layer before the prediction layer. Results We construct a corpus of Chinese medical question matching, which contains 36,360 question pairs. This corpus is randomly split into three parts: a training set of 32,360 question pairs, a development set of 2000 question pairs and a test set of 2000 question pairs. On this corpus, we conduct a series of experiments to evaluate the proposed CapsTM and compare it with other state-of-the-art methods. CapsTM achieves the highest F-score of 0.8666. Conclusion The experimental results demonstrate that CapsTM is effective for Chinese medical question matching and outperforms other state-of-the-art methods for comparison.

Abstract Background Semantic textual similarity (STS) is a fundamental natural language processing (NLP) task which can be widely used in many NLP applications such as Question Answer (QA), Information Retrieval (IR), etc. It is a typical regression problem, and almost all STS systems either use distributed representation or one-hot representation to model sentence pairs. Methods In this paper, we proposed a novel framework based on a gated network to fuse distributed representation and one-hot representation of sentence pairs. Some current state-of-the-art distributed representation methods, including Convolutional Neural Network (CNN), Bi-directional Long Short Term Memory networks (Bi-LSTM) and Bidirectional Encoder Representations from Transformers (BERT), were used in our framework, and a system based on this framework was developed for a shared task regarding clinical STS organized by BioCreative/OHNLP in 2018. Results Compared with the systems only using distributed representation or one-hot representation, our method achieved much higher Pearson correlation. Among all distributed representations, BERT performed best. The highest Person correlation of our system was 0.8541, higher than the best official one of the BioCreative/OHNLP clinical STS shared task in 2018 (0.8328) by 0.0213. Conclusions Distributed representation and one-hot representation are complementary to each other and can be fused by gated network.

Abstract Background Family history (FH) information, including family members, side of family of family members (i.e., maternal or paternal), living status of family members, observations (diseases) of family members, etc., is very important in the decision-making process of disorder diagnosis and treatment. However FH information cannot be used directly by computers as it is always embedded in unstructured text in electronic health records (EHRs). In order to extract FH information form clinical text, there is a need of natural language processing (NLP). In the BioCreative/OHNLP2018 challenge, there is a task regarding FH extraction (i.e., task1), including two subtasks: (1) entity identification, identifying family members and their observations (diseases) mentioned in clinical text; (2) family history extraction, extracting side of family of family members, living status of family members, and observations of family members. For this task, we propose a system based on deep joint learning methods to extract FH information. Our system achieves the highest F1- scores of 0.8901 on subtask1 and 0.6359 on subtask2, respectively.

With the rapid growth of information technology, the necessity for processing substantial amounts of health data using advanced information technologies is increasing. A large amount of valuable data exists in natural text such as diagnosis text, discharge summaries, online health discussions, and eligibility criteria of clinical trials. Health natural language processing, as an interdisciplinary field of natural language processing and health care, plays a substantial role in a wide scope of both methodology development and applications. This editorial shares the most recent methodology innovations of health natural language processing and applications in the medical domain published in this JMIR Medical Informatics special theme issue entitled "Health Natural Language Processing: Methodology Development and Applications".

Abstract Background Ontology has attracted substantial attention from both academia and industry. Handling uncertainty reasoning is important in researching ontology. For example, when a patient is suffering from cirrhosis, the appearance of abdominal vein varices is four times more likely than the presence of bitter taste. Such medical knowledge is crucial for decision-making in various medical applications but is missing from existing medical ontologies. In this paper, we aim to discover medical knowledge probabilities from electronic medical record (EMR) texts to enrich ontologies. First, we build an ontology by identifying meaningful entity mentions from EMRs. Then, we propose a symptom-dependency-aware naïve Bayes classifier (SDNB) that is based on the assumption that there is a level of dependency among symptoms. To ensure the accuracy of the diagnostic classification, we incorporate the probability of a disease into the ontology via innovative approaches. Results We conduct a series of experiments to evaluate whether the proposed method can discover meaningful and accurate probabilities for medical knowledge. Based on over 30,000 deidentified medical records, we explore 336 abdominal diseases and 81 related symptoms. Among these 336 gastrointestinal diseases, the probabilities of 31 diseases are obtained via our method. These 31 probabilities of diseases and 189 conditional probabilities between diseases and the symptoms are added into the generated ontology. Conclusion In this paper, we propose a medical knowledge probability discovery method that is based on the analysis and extraction of EMR text data for enriching a medical ontology with probability information. The experimental results demonstrate that the proposed method can effectively identify accurate medical knowledge probability information from EMR data. In addition, the proposed method can efficiently and accurately calculate the probability of a patient suffering from a specified disease, thereby demonstrating the advantage of combining an ontology and a symptom-dependency-aware naïve Bayes classifier.

Abstract Background Chinese word segmentation (CWS) and part-of-speech (POS) tagging are two fundamental tasks of Chinese text processing. They are usually preliminary steps for lots of Chinese natural language processing (NLP) tasks. There have been a large number of studies on CWS and POS tagging in various domains, however, few studies have been proposed for CWS and POS tagging in the clinical domain as it is not easy to determine granularity of words. Methods In this paper, we investigated CWS and POS tagging for Chinese clinical text at a fine-granularity level, and manually annotated a corpus. On the corpus, we compared two state-of-the-art methods, i.e., conditional random fields (CRF) and bidirectional long short-term memory (BiLSTM) with a CRF layer. In order to validate the plausibility of the fine-grained annotation, we further investigated the effect of CWS and POS tagging on Chinese clinical named entity recognition (NER) on another independent corpus. Results When only CWS was considered, CRF achieved higher precision, recall and F-measure than BiLSTM-CRF. When both CWS and POS tagging were considered, CRF also gained an advantage over BiLSTM. CRF outperformed BiLSTM-CRF by 0.14% in F-measure on CWS and by 0.34% in F-measure on POS tagging. The CWS information brought a greatest improvement of 0.34% in F-measure, while the CWS&POS information brought a greatest improvement of 0.74% in F-measure. Conclusions Our proposed fine-grained CWS and POS tagging corpus is reliable and meaningful as the output of the CWS and POS tagging systems developed on this corpus improved the performance of a Chinese clinical NER system on another independent corpus.

Abstract Background Clinical entity recognition as a fundamental task of clinical text processing has been attracted a great deal of attention during the last decade. However, most studies focus on clinical text in English rather than other languages. Recently, a few researchers have began to study entity recognition in Chinese clinical text. Methods In this paper, a novel deep neural network, called attention-based CNN-LSTM-CRF, is proposed to recognize entities in Chinese clinical text. Attention-based CNN-LSTM-CRF is an extension of LSTM-CRF by introducing a CNN (convolutional neural network) layer after the input layer to capture local context information of words of interest and an attention layer before the CRF layer to select relevant words in the same sentence. Results In order to evaluate the proposed method, we compare it with other two currently popular methods, CRF (conditional random field) and LSTM-CRF, on two benchmark datasets. One of the datasets is publically available and only contains contiguous clinical entities, and the other one is constructed by us and contains contiguous and discontiguous clinical entities. Experimental results show that attention-based CNN-LSTM-CRF outperforms CRF and LSTM-CRF. Conclusions CNN and attention mechanism are individually beneficial to LSTM-CRF-based Chinese clinical entity recognition system, no matter whether contiguous clinical entities are considered. The conribution of attention mechanism is greater than CNN.

Abstract Efficient representations of drugs provide important support for healthcare analytics, such as drug–drug interaction (DDI) prediction and drug–drug similarity (DDS) computation. However, incomplete annotated data and drug feature sparseness create substantial barriers for drug representation learning, making it difficult to accurately identify new drug properties prior to public release. To alleviate these deficiencies, we propose KMR, a knowledge-oriented feature-driven method which can learn drug related knowledge with an accurate representation. We conduct series of experiments on real-world medical datasets to demonstrate that KMR is capable of drug representation learning. KMR can support to discover meaningful DDI with an accuracy rate of 92.19%, demonstrating that techniques developed in KMR significantly improve the prediction quality for new drugs not seen at training. Experimental results also indicate that KMR can identify DDS with an accuracy rate of 88.7% by facilitating drug knowledge, outperforming existing state-of-the-art drug similarity measures.

Abstract Background The goal of temporal indexing is to select an occurred time or time interval for each medical entity in clinical notes, so that all medical entities can be indexed on a united timeline, which could assist the understanding of clinical notes and the further application of medical entities. Some temporal relation shared tasks for the medical entity in English clinical notes have been organized in the past few years, such as the 2012 i2b2 NLP challenge, 2015 and 2016 clinical TempEval challenges. In these tasks, many heuristics rule-based and machine learning-based systems have been developed. In recent years, the deep neural network models have shown great potential on many problems including the relation classification. Methods In this paper, we propose a recurrent convolutional neural network (RNN-CNN) model for the temporal indexing task, which consists of four layers: input layer – generates representation for each context word of medical entities or temporal expressions; LSTM (long-short term memory) layer – learns the context information of each word in a sentence and outputs a new word representation sequence; CNN layer – extracts meaningful features from a sentence and outputs a new representation for medical entity or temporal expression; Output layer – takes the representations of medical entity, temporal expression and relation features as input and classifies the temporal relation. Finally, the time or time interval for each medical entity can be directly selected according to the probability of each temporal relation predicted by above model. Results To investigate the performance of our RNN-CNN model for the temporal indexing task, several baseline methods were also employed, such as the rule-based, support vector machine (SVM), convolutional neural network (CNN) and recurrent neural network (RNN) methods. Experiments conducted on a manually annotated corpus (including 563 clinical notes with 12,611 medical entities and 4006 temporal expressions) show that RNN-CNN model achieves the best F1-score of 75.97% for temporal relation classification and the best accuracy of 71.96% for temporal indexing. Conclusions Neural network methods perform much better than the traditional rule-based and SVM-based method, which can capture more semantic information from the context of medical entities and temporal expressions. Besides, all our methods perform much better for the accurate time indexing than the time interval indexing, so how to improve the performance for time interval indexing will be the main focus in our future work.

Abstract Background Entropy has become increasingly popular in computer science and information theory because it can be used to measure the predictability and redundancy of knowledge bases, especially ontologies. However, current entropy applications that evaluate ontologies consider only single-point connectivity rather than path connectivity, and they assign equal weights to each entity and path. Results We propose an Entropy-Aware Path-Based (EAPB) metric for ontology quality by considering the path information between different vertices and textual information included in the path to calculate the connectivity path of the whole network and dynamic weights between different nodes. The information obtained from structure-based embedding and text-based embedding is multiplied by the connectivity matrix of the entropy computation. EAPB is analytically evaluated against the state-of-the-art criteria. We have performed empirical analysis on real-world medical ontologies and a synthetic ontology based on the following three aspects: ontology statistical information (data quantity), entropy evaluation (data quality), and a case study (ontology structure and text visualization). These aspects mutually demonstrate the reliability of the proposed metric. The experimental results show that the proposed EAPB can effectively evaluate ontologies, especially those in the medical informatics field. Conclusions We leverage path information and textual information to enrich the network representational learning and aid in entropy computation. The analytics and assessments of semantic web can benefit from the structure information but also the text information. We believe that EAPB is helpful for managing ontology development and evaluation projects. Our results are reproducible and we will release the source code and ontology of this work after publication. (Source code and ontology: https://github.com/AnonymousResearcher1/ontologyEvaluate).

Abstract Background Extracting relationships between chemicals and diseases from unstructured literature have attracted plenty of attention since the relationships are very useful for a large number of biomedical applications such as drug repositioning and pharmacovigilance. A number of machine learning methods have been proposed for chemical-induced disease (CID) extraction due to some publicly available annotated corpora. Most of them suffer from time-consuming feature engineering except deep learning methods. In this paper, we propose a novel document-level deep learning method, called recurrent piecewise convolutional neural networks (RPCNN), for CID extraction. Results Experimental results on a benchmark dataset, the CDR (Chemical-induced Disease Relation) dataset of the BioCreative V challenge for CID extraction show that the highest precision, recall and F-score of our RPCNN-based CID extraction system are 65.24, 77.21 and 70.77%, which is competitive with other state-of-the-art systems. Conclusions A novel deep learning method is proposed for document-level CID extraction, where domain knowledge, piecewise strategy, attention mechanism, and multi-instance learning are combined together. The effectiveness of the method is proved by experiments conducted on a benchmark dataset.

Abstract Background Most state-of-the-art biomedical entity normalization systems, such as rule-based systems, merely rely on morphological information of entity mentions, but rarely consider their semantic information. In this paper, we introduce a novel convolutional neural network (CNN) architecture that regards biomedical entity normalization as a ranking problem and benefits from semantic information of biomedical entities. Results The CNN-based ranking method first generates candidates using handcrafted rules, and then ranks the candidates according to their semantic information modeled by CNN as well as their morphological information. Experiments on two benchmark datasets for biomedical entity normalization show that our proposed CNN-based ranking method outperforms traditional rule-based method with state-of-the-art performance. Conclusions We propose a CNN architecture that regards biomedical entity normalization as a ranking problem. Comparison results show that semantic information is beneficial to biomedical entity normalization and can be well combined with morphological information in our CNN architecture for further improvement.

Abstract Background Entity recognition is one of the most primary steps for text analysis and has long attracted considerable attention from researchers. In the clinical domain, various types of entities, such as clinical entities and protected health information (PHI), widely exist in clinical texts. Recognizing these entities has become a hot topic in clinical natural language processing (NLP), and a large number of traditional machine learning methods, such as support vector machine and conditional random field, have been deployed to recognize entities from clinical texts in the past few years. In recent years, recurrent neural network (RNN), one of deep learning methods that has shown great potential on many problems including named entity recognition, also has been gradually used for entity recognition from clinical texts. Methods In this paper, we comprehensively investigate the performance of LSTM (long-short term memory), a representative variant of RNN, on clinical entity recognition and protected health information recognition. The LSTM model consists of three layers: input layer – generates representation of each word of a sentence; LSTM layer – outputs another word representation sequence that captures the context information of each word in this sentence; Inference layer – makes tagging decisions according to the output of LSTM layer, that is, outputting a label sequence. Results Experiments conducted on corpora of the 2010, 2012 and 2014 i2b2 NLP challenges show that LSTM achieves highest micro-average F1-scores of 85.81% on the 2010 i2b2 medical concept extraction, 92.29% on the 2012 i2b2 clinical event detection, and 94.37% on the 2014 i2b2 de-identification, which is considerably competitive with other state-of-the-art systems. Conclusions LSTM that requires no hand-crafted feature has great potential on entity recognition from clinical texts. It outperforms traditional machine learning methods that suffer from fussy feature engineering. A possible future direction is how to integrate knowledge bases widely existing in the clinical domain into LSTM, which is a case of our future work. Moreover, how to use LSTM to recognize entities in specific formats is also another possible future direction.

Time series prediction has been widely applied to the finance industry in applications such as stock market price and commodity price forecasting. Machine learning methods have been widely used in financial time series prediction in recent years. How to label financial time series data to determine the prediction accuracy of machine learning models and subsequently determine final investment returns is a hot topic. Existing labeling methods of financial time series mainly label data by comparing the current data with those of a short time period in the future. However, financial time series data are typically non-linear with obvious short-term randomness. Therefore, these labeling methods have not captured the continuous trend features of financial time series data, leading to a difference between their labeling results and real market trends. In this paper, a new labeling method called “continuous trend labeling” is proposed to address the above problem. In the feature preprocessing stage, this paper proposed a new method that can avoid the problem of look-ahead bias in traditional data standardization or normalization processes. Then, a detailed logical explanation was given, the definition of continuous trend labeling was proposed and also an automatic labeling algorithm was given to extract the continuous trend features of financial time series data. Experiments on the Shanghai Composite Index and Shenzhen Component Index and some stocks of China showed that our labeling method is a much better state-of-the-art labeling method in terms of classification accuracy and some other classification evaluation metrics. The results of the paper also proved that deep learning models such as LSTM and GRU are more suitable for dealing with the prediction of financial time series data.

Semantic features are very important for machine learning-based drug name recognition (DNR) systems. The semantic features used in most DNR systems are based on drug dictionaries manually constructed by experts. Building large-scale drug dictionaries is a time-consuming task and adding new drugs to existing drug dictionaries immediately after they are developed is also a challenge. In recent years, word embeddings that contain rich latent semantic information of words have been widely used to improve the performance of various natural language processing tasks. However, they have not been used in DNR systems. Compared to the semantic features based on drug dictionaries, the advantage of word embeddings lies in that learning them is unsupervised. In this paper, we investigate the effect of semantic features based on word embeddings on DNR and compare them with semantic features based on three drug dictionaries. We propose a conditional random fields (CRF)-based system for DNR. The skip-gram model, an unsupervised algorithm, is used to induce word embeddings on about 17.3 GigaByte (GB) unlabeled biomedical texts collected from MEDLINE (National Library of Medicine, Bethesda, MD, USA). The system is evaluated on the drug-drug interaction extraction (DDIExtraction) 2013 corpus. Experimental results show that word embeddings significantly improve the performance of the DNR system and they are competitive with semantic features based on drug dictionaries. F-score is improved by 2.92 percentage points when word embeddings are added into the baseline system. It is comparative with the improvements from semantic features based on drug dictionaries. Furthermore, word embeddings are complementary to the semantic features based on drug dictionaries. When both word embeddings and semantic features based on drug dictionaries are added, the system achieves the best performance with an F-score of 78.37%, which outperforms the best system of the DDIExtraction 2013 challenge by 6.87 percentage points.

Drug name recognition (DNR), which seeks to recognize drug mentions in unstructured medical texts and classify them into pre-defined categories, is a fundamental task of medical information extraction, and is a key component of many medical relation extraction systems and applications. A large number of efforts have been devoted to DNR, and great progress has been made in DNR in the last several decades. We present here a comprehensive review of studies on DNR from various aspects such as the challenges of DNR, the existing approaches and resources for DNR, and possible directions.