Analysis of the effect of sentiment analysis on extracting adverse drug reactions from tweets and forum posts.

OBJECTIVE: The abundance of text available in social media and health related forums along with the rich expression of public opinion have recently attracted the interest of the public health community to use these sources for pharmacovigilance. Based on the intuition that patients post about Adverse Drug Reactions (ADRs) expressing negative sentiments, we investigate the effect of sentiment analysis features in locating ADR mentions. METHODS: We enrich the feature space of a state-of-the-art ADR identification method with sentiment analysis features. Using a corpus of posts from the DailyStrength forum and tweets annotated for ADR and indication mentions, we evaluate the extent to which sentiment analysis features help in locating ADR mentions and distinguishing them from indication mentions. RESULTS: Evaluation results show that sentiment analysis features marginally improve ADR identification in tweets and health related forum posts. Adding sentiment analysis features achieved a statistically significant F-measure increase from 72.14% to 73.22% in the Twitter part of an existing corpus using its original train/test split. Using stratified 10×10-fold cross-validation, statistically significant F-measure increases were shown in the DailyStrength part of the corpus, from 79.57% to 80.14%, and in the Twitter part of the corpus, from 66.91% to 69.16%. Moreover, sentiment analysis features are shown to reduce the number of ADRs being recognized as indications. CONCLUSION: This study shows that adding sentiment analysis features can marginally improve the performance of even a state-of-the-art ADR identification method. This improvement can be of use to pharmacovigilance practice, due to the rapidly increasing popularity of social media and health forums.

Marfan Syndrome Associated With Acute Myocardial Infarction in the First Trimester of Pregnancy.

Marfan syndrome (MFS) is a rare hereditary connective tissue disorder with autosomal dominant inheritance associated with an increased risk of cardiovascular complications due to connective tissue fragility. Acute myocardial infarction during pregnancy is also a rare event associated with poor maternal and fetal outcomes. Herein, we report a case of a 30-year-old pregnant woman with a known history of MFS. The patient had been treated surgically for an ascending aorta aneurysm and mechanical prosthetic aortic valve repair. She presented at 12 weeks of gestation with severe chest pain, which proved to be acute myocardial infarction. This is believed to be the first case of this complex medical condition presented in the first trimester of pregnancy.

Giant Borderline Phyllodes Tumor of the Breast: A Case Report.

Borderline phyllodes tumor is a rare and benign form of breast cancer with malignant potential. According to the World Health Organization (WHO), phyllodes tumor is classified into three categories: benign, borderline, and malignant. The treatment of phyllodes tumor is wide focal excision combined with radiotherapy and chemotherapy in certain cases. Herein, we report a 47-year-old female who presented with a giant borderline mass approximately 19.5 x 16.9 x 9.3 cm in size. From medical history, we noticed that the mass begun to develop during puberty. Wide focal excision of the tumor and immediate implant-based reconstruction with free nipple graft was performed, with the tumor specimen measuring 16.5 x 14.2 x 8.7 cm. Histological examination reported a borderline phyllodes tumor, and in this case, the patient did not undergo adjuvant treatment.

An unusual case of cervical diverticulum identified by presence of 3 cavities at diagnostic hysteroscopy.

Herein is presented the case report of a patient who had severe dysmenorrhea since menarche, known right unicornuate uterus with a left rudimentary horn, and recurrent hematometra. Previous hysteroscopic drainage of the hematometra temporarily alleviated the symptoms. At subsequent hysteroscopy, 3 cavities were identified, 2 corresponding to the uterine horns and the other to a cervical diverticulum. Hysteroscopic metroplasty with drainage of the rudimentary horn hematometra provided long-term relief of the symptoms. The diagnosis was verified at diagnostic laparoscopy.

A method for discovering and inferring appropriate eligibility criteria in clinical trial protocols without labeled data.

BACKGROUND: We consider the user task of designing clinical trial protocols and propose a method that discovers and outputs the most appropriate eligibility criteria from a potentially huge set of candidates. Each document d in our collection D is a clinical trial protocol which itself contains a set of eligibility criteria. Given a small set of sample documentsD',|D'|≪|D|, a user has initially identified as relevant e.g., via a user query interface, our scoring method automatically suggests eligibility criteria from D, D ⊃ D', by ranking them according to how appropriate they are to the clinical trial protocol currently being designed. The appropriateness is measured by the degree to which they are consistent with the user-supplied sample documents D'. METHOD: We propose a novel three-step method called LDALR which views documents as a mixture of latent topics. First, we infer the latent topics in the sample documents using Latent Dirichlet Allocation (LDA). Next, we use logistic regression models to compute the probability that a given candidate criterion belongs to a particular topic. Lastly, we score each criterion by computing its expected value, the probability-weighted sum of the topic proportions inferred from the set of sample documents. Intuitively, the greater the probability that a candidate criterion belongs to the topics that are dominant in the samples, the higher its expected value or score. RESULTS: Our experiments have shown that LDALR is 8 and 9 times better (resp., for inclusion and exclusion criteria) than randomly choosing from a set of candidates obtained from relevant documents. In user simulation experiments using LDALR, we were able to automatically construct eligibility criteria that are on the average 75% and 70% (resp., for inclusion and exclusion criteria) similar to the correct eligibility criteria. CONCLUSIONS: We have proposed LDALR, a practical method for discovering and inferring appropriate eligibility criteria in clinical trial protocols without labeled data. Results from our experiments suggest that LDALR models can be used to effectively find appropriate eligibility criteria from a large repository of clinical trial protocols.

Splenic Rupture in an Elective Cesarean Section: A Possible Iatrogenic Event.

A rare case of an unexpected iatrogenic splenic rupture during a cesarean section is reported. The trauma was recognized early and treated conservatively without delay; thus, further complications were avoided. A 28-year-old woman with a history of previous cesarean sections was submitted for an elective cesarean section. Intra-operatively, minor bleeding from the left abdomen was noted and eventually assigned to an inferior pole splenic trauma treated conservatively without splenectomy. Although unclear, the injury was considered iatrogenic, probably due to the abdominal pressure for fetal delivery and the anatomy of the splenocolic ligament. This case highlights the clinical suspicion that is required despite routine surgical procedures for the early diagnosis of an unexpected splenic rupture when minor bleeding occurs intra-operatively from the upper abdomen. Early recognition and prompt treatment are of paramount importance for the safety of the fetus and the patient.

Giant Ulcerated Fibroepithelial Stromal Polyp of the Vulva: A Case Report.

Fibroepithelial stromal polyps (FEPs) are benign skin tumors or lesions of mesenchymal and ectodermal origin, also referred to as acrochordons. Herein, we report the case of a 45-year-old woman with a large ulcerated fibroepithelial stromal polyp extending from the right labium of the vulva. No known predisposing factor was recorded to justify the presence and rapid growth of the polyp. Antibiotic treatment was given due to inflammation, and magnetic resonance imaging was useful in establishing a diagnosis. A wide surgical excision was performed, and a histopathological examination confirmed the initial diagnosis, revealing no nuclear atypia or mitoses. The patient recovered well, and follow-up after one year showed no evidence of complications or recurrence.

ASCOT: a text mining-based web-service for efficient search and assisted creation of clinical trials.

Clinical trials are mandatory protocols describing medical research on humans and among the most valuable sources of medical practice evidence. Searching for trials relevant to some query is laborious due to the immense number of existing protocols. Apart from search, writing new trials includes composing detailed eligibility criteria, which might be time-consuming, especially for new researchers. In this paper we present ASCOT, an efficient search application customised for clinical trials. ASCOT uses text mining and data mining methods to enrich clinical trials with metadata, that in turn serve as effective tools to narrow down search. In addition, ASCOT integrates a component for recommending eligibility criteria based on a set of selected protocols.

Bottom-Up Natural Language Processing Based Evaluation of the Fitness of UMLS as a Semantic Source for a Computer Interpretable Guidelines Ontology.

BACKGROUND: CIGs languages consist of approach specific concepts. More widely used concepts, such as those in UMLS are not typically used. OBJECTIVE: An evaluation of UMLS concept sufficiency for CIG definition. METHOD: A popular guideline is mapped to UMLS concepts with NLP. Results are reviewed to evaluate gaps, and appropriateness. RESULTS: A significant number of the guideline text mapped to UMLS concepts. CONCLUSIONS: The approach has shown promise and highlighted further challenges.

A behaviour biometrics dataset for user identification and authentication.

As e-Commerce continues to shift our shopping preference from the physical to online marketplace, we leave behind digital traces of our personally identifiable details. For example, the merchant keeps record of your name and address; the payment processor stores your transaction details including account or card information, and every website you visit stores other information such as your device address and type. Cybercriminals constantly steal and use some of this information to commit identity fraud, ultimately leading to devastating consequences to the victims; but also, to the card issuers and payment processors with whom the financial liability most often lies. To this end, we recognise that data is generally compromised in this digital age, and personal data such as card number, password, personal identification number and account details can be easily stolen and used by someone else. However, there is a plethora of data relating to a person's behaviour biometrics that are almost impossible to steal, such as the way they type on a keyboard, move the cursor, or whether they normally do so via a mouse, touchpad or trackball. This data, commonly called keystroke, mouse and touchscreen dynamics, can be used to create a unique profile for the legitimate card owner, that can be utilised as an additional layer of user authentication during online card payments. Machine learning is a powerful technique for analysing such data to gain knowledge; and has been widely used successfully in many sectors for profiling e.g., genome classification in molecular biology and genetics where predictions are made for one or more forms of biochemical activity along the genome. Similar techniques are applicable in the financial sector to detect anomaly in user keyboard and mouse behaviour when entering card details online, such that they can be used to distinguish between a legitimate and an illegitimate card owner. In this article, a behaviour biometrics (i.e., keystroke and mouse dynamics) dataset, collected from 88 individuals, is presented. The dataset holds a total of 1760 instances categorised into two classes (i.e., legitimate and illegitimate card owners' behaviour). The data was collected to facilitate an academic start-up project (called CyberSignature1) which received funding from Innovate UK, under the Cyber Security Academic Startup Accelerator Programme. The dataset could be helpful to researchers who apply machine learning to develop applications using keystroke and mouse dynamics e.g., in cybersecurity to prevent identity theft. The dataset, entitled 'Behaviour Biometrics Dataset', is freely available on the Mendeley Data repository.

Personalised Accelerometer Cut-point Prediction for Older Adults' Movement Behaviours using a Machine Learning approach.

BACKGROUND AND OBJECTIVES: Body-worn accelerometers are the most popular method for objectively assessing physical activity in older adults. Many studies have developed generic accelerometer cut-points for defining activity intensity in metabolic equivalents for older adults. However, methodological diversity in current studies has led to a great deal of variation in the resulting cut-points, even when using data from the same accelerometer. In addition, the generic cut-point approach assumes that 'one size fits all' which is rarely the case in real life. This study proposes a machine learning method for personalising activity intensity cut-points for older adults. METHODS: Firstly, raw accelerometry data was collected from 33 older adults who performed set activities whilst wearing two accelerometer devices: GENEActive (wrist worn) and ActiGraph (hip worn). ROC analysis was applied to generate personalised cut-point for each data sample based on a device. Four cut-points have been considered: Sensitivity optimised Sedentary Behaviour; Specificity optimised Moderate to Vigorous Physical Activity; Youden optimised Sedentary Behaviour; and Youden optimised Moderate to Vigorous Physical Activity. Then, an additive regression algorithm trained on biodata features, that concern the individual characteristics of participants, was used to predict the cut-points. As the model output is a numeric cut-point value (and not discrete), evaluation was based on two error metrics, Mean Absolute Error and Root Mean Square Error. Standard Error of estimation was also calculated to measure the accuracy of prediction (goodness of fit) and this was used for performance comparison between our approach and the state-of-the-art. Hold-out and 10-Fold cross validation methods were used for performance validation and comparison. RESULTS: The results show that our personalised approach performed consistently better than the state-of-the-art with 10-Fold cross validation on all four cut-points considered for both devices. For the ActiGraph device, the Standard Error of estimation from our approach was lower by 0.33 (Youden optimised Sedentary Behaviour), 9.50 (Sensitivity optimised Sedentary Behaviour), 0.64 (Youden optimised Moderate to Vigorous Physical Activity) and 22.11 (Specificity optimised Moderate to Vigorous Physical Activity). Likewise, the Standard Error of estimation from our approach was lower for the GENEActiv device by 2.29 (Youden optimised Sedentary Behaviour), 41.65 (Sensitivity optimised Sedentary Behaviour), 4.31 (Youden optimised Moderate to Vigorous Physical Activity) and 347.15 (Specificity optimised Moderate to Vigorous Physical Activity). CONCLUSIONS: personalised cut-point can be predicted without prior knowledge of accelerometry data. The results are very promising especially when we consider that our method predicts cut-points without prior knowledge of accelerometry data, unlike the state-of-the-art. More data is required to expand the scope of the experiments presented in this paper.

Malignant transformation of ovarian mature cystic teratoma in a postmenopausal woman presented as acute abdomen.

Malignant transformation of mature cystic teratomas is uncommon but present in clinical practice. Especially in postmenopausal women, the clinical manifestation of a mature teratoma with undiagnosed malignant transformation as acute abdomen is extremely rare. In these cases, total hysterectomy with bilateral salpingo-oophorectomy is the treatment choice since the chance of malignancy is high. The prognosis is good if the cyst is not ruptured, is completely excised and the cancer does not extend beyond the capsule. In any other case, the prognosis is unfavorable since recurrence is common and the tumor is chemoresistant.

Efficient treatment of outliers and class imbalance for diabetes prediction.

Learning from outliers and imbalanced data remains one of the major difficulties for machine learning classifiers. Among the numerous techniques dedicated to tackle this problem, data preprocessing solutions are known to be efficient and easy to implement. In this paper, we propose a selective data preprocessing approach that embeds knowledge of the outlier instances into artificially generated subset to achieve an even distribution. The Synthetic Minority Oversampling TEchnique (SMOTE) was used to balance the training data by introducing artificial minority instances. However, this was not before the outliers were identified and oversampled (irrespective of class). The aim is to balance the training dataset while controlling the effect of outliers. The experiments prove that such selective oversampling empowers SMOTE, ultimately leading to improved classification performance.

Structuring Clinical Decision Support Rules for Drug Safety Using Natural Language Processing.

Drug safety is an important aspect in healthcare, resulting in a number of inadvertent events, which may harm the patients. IT based Clinical Decision Support (CDS), integrated in electronic-prescription or Electronic Health Records (EHR) systems, can provide a means for checking prescriptions for errors. This requires expressing prescription guidelines in a way that can be interpreted by IT systems. The paper uses Natural Language Processing (NLP), to interpret drug guidelines by the UK NICE BNF offered in free text. The employed NLP component, MetaMap, identifies the concepts in the instructions and interprets their semantic meaning. The UMLS semantic types that correspond to these concepts are then processed, in order to understand the concepts that are needed to be implemented in software engineering for a CDS engine.

Large carcinoid tumor of the appendix during pregnancy.

Diagnosis of acute appendicitis is considered more difficult in pregnant than in non-pregnant women. The appendicial carcinoid tumor is a lesion that most frequently is discovered incidentally in the removed organ. We report a rare case of an unruptured acute appendicitis during pregnancy, which proved to be a large carcinoid tumor.

Boosting drug named entity recognition using an aggregate classifier.

OBJECTIVE: Drug named entity recognition (NER) is a critical step for complex biomedical NLP tasks such as the extraction of pharmacogenomic, pharmacodynamic and pharmacokinetic parameters. Large quantities of high quality training data are almost always a prerequisite for employing supervised machine-learning techniques to achieve high classification performance. However, the human labour needed to produce and maintain such resources is a significant limitation. In this study, we improve the performance of drug NER without relying exclusively on manual annotations. METHODS: We perform drug NER using either a small gold-standard corpus (120 abstracts) or no corpus at all. In our approach, we develop a voting system to combine a number of heterogeneous models, based on dictionary knowledge, gold-standard corpora and silver annotations, to enhance performance. To improve recall, we employed genetic programming to evolve 11 regular-expression patterns that capture common drug suffixes and used them as an extra means for recognition. MATERIALS: Our approach uses a dictionary of drug names, i.e. DrugBank, a small manually annotated corpus, i.e. the pharmacokinetic corpus, and a part of the UKPMC database, as raw biomedical text. Gold-standard and silver annotated data are used to train maximum entropy and multinomial logistic regression classifiers. RESULTS: Aggregating drug NER methods, based on gold-standard annotations, dictionary knowledge and patterns, improved the performance on models trained on gold-standard annotations, only, achieving a maximum F-score of 95%. In addition, combining models trained on silver annotations, dictionary knowledge and patterns are shown to achieve comparable performance to models trained exclusively on gold-standard data. The main reason appears to be the morphological similarities shared among drug names. CONCLUSION: We conclude that gold-standard data are not a hard requirement for drug NER. Combining heterogeneous models build on dictionary knowledge can achieve similar or comparable classification performance with that of the best performing model trained on gold-standard annotations.

Umbilical cord length and parity--the Greek experience.

OBJECTIVES: To investigate the relationship between parity and cord length, with respect to peripartum characteristics. STUDY DESIGN: Parity, cord length, placental and birth weight were the studied variables in a sample of 534 parturients with singleton fetuses. Parturients were divided into four groups: primiparous (para-1), secundiparous (para-2), tetriparous (para-3) and multiparous (para >3). Oneway ANOVA and post-hoc tests were applied for the comparison of mean cord length between the four groups of parity. General Linear Model was applied for the detection of covariates. RESULTS: ANOVA yielded significant differences between the four groups. Mean cord length was significantly higher in women of parity >or=3 than in women with lower parity. Although both placental and birth weight were correlated with cord length, application of GLM showed that only birth weight could act as a covariate for the length differences between parity groups. CONCLUSIONS: Cord length appears to increase with advancing parity, the cut-off point being between the second and the third labor. We suggest that intrapartum monitoring should be performed in all multiparous parturients, because of their propensity for longer cords, and thus for related complications.

Heterotopic triplet pregnancy after in vitro fertilization with favorable outcome of the intrauterine twin pregnancy subsequent to surgical treatment of the tubal pregnancy.

Heterotopic triplet pregnancy is an exceptionally rare medical condition. The broad use of assisted reproductive technologies has contributed to the increase of ectopic and subsequently heterotopic pregnancy rate, masking a life-threatening condition for the gravid and the intrauterine pregnancy. We describe a case of a woman with heterotopic triplets at 9(+4) gestational week following transfer of three embryos obtained by in vitro fertilization techniques. The ectopic tubal pregnancy was ruptured and salpingectomy was performed by laparotomy. The intrauterine pregnancy progressed to the delivery by cesarean section of two healthy twins at 36(+2) gestational age. Heterotopic triplets with tubal ectopic are a special diagnostic and therapeutic challenge for the obstetrician. High index of suspicion and timely treatment by laparotomy or laparoscopy can preserve the intrauterine gestation with a successful outcome of the pregnancy.

Deploying and sharing U-Compare workflows as web services.

BACKGROUND: U-Compare is a text mining platform that allows the construction, evaluation and comparison of text mining workflows. U-Compare contains a large library of components that are tuned to the biomedical domain. Users can rapidly develop biomedical text mining workflows by mixing and matching U-Compare's components. Workflows developed using U-Compare can be exported and sent to other users who, in turn, can import and re-use them. However, the resulting workflows are standalone applications, i.e., software tools that run and are accessible only via a local machine, and that can only be run with the U-Compare platform. RESULTS: We address the above issues by extending U-Compare to convert standalone workflows into web services automatically, via a two-click process. The resulting web services can be registered on a central server and made publicly available. Alternatively, users can make web services available on their own servers, after installing the web application framework, which is part of the extension to U-Compare. We have performed a user-oriented evaluation of the proposed extension, by asking users who have tested the enhanced functionality of U-Compare to complete questionnaires that assess its functionality, reliability, usability, efficiency and maintainability. The results obtained reveal that the new functionality is well received by users. CONCLUSIONS: The web services produced by U-Compare are built on top of open standards, i.e., REST and SOAP protocols, and therefore, they are decoupled from the underlying platform. Exported workflows can be integrated with any application that supports these open standards. We demonstrate how the newly extended U-Compare enhances the cross-platform interoperability of workflows, by seamlessly importing a number of text mining workflow web services exported from U-Compare into Taverna, i.e., a generic scientific workflow construction platform.