Biomedical named entity recognition (Bio-NER) is a fundamental task in handling biomedical text terms, such as RNA, protein, cell type, cell line, and DNA. Bio-NER is one of the most elementary and core tasks in biomedical knowledge discovery from texts. The system described here is developed by using the BioNLP/NLPBA 2004 shared task. Experiments are conducted on a training and evaluation set provided by the task organizers. Our results show that, compared with a baseline having a 70.09% F1 score, the RNN Jordan- and Elman-type algorithms have F1 scores of approximately 60.53% and 58.80%, respectively. When we use CRF as a machine learning algorithm, CCA, GloVe, and Word2Vec have F1 scores of 72.73%, 72.74%, and 72.82%, respectively. By using the word embedding constructed through the unsupervised learning, the time and cost required to construct the learning data can be saved.

Screening test using CA-125 is the most common test for detecting ovarian cancer. However, the level of CA-125 is diverse by variable condition other than ovarian cancer. It has led to misdiagnosis of ovarian cancer. In this paper, we explore the 16 serum biomarker for finding alternative biomarker combination to reduce misdiagnosis. For experiment, we use the serum samples that contain 101 cancer and 92 healthy samples. We perform two major tasks: Marker selection and Classification. For optimal marker selection, we use genetic algorithm, random forest, T-test and logistic regression. For classification, we compare linear discriminative analysis, K-nearest neighbor and logistic regression. The final results show that the logistic regression gives high performance for both tasks, and HE4-ELISA, PDGF-AA, Prolactin, TTR is the best biomarker combination for detecting ovarian cancer. We find the combination which contains TTR and Prolactin gives high performance for cancer detection. Early detection of ovarian cancer can reduce high mortality rates. Finding a combination of multiple biomarkers for diagnostic tests with high sensitivity and specificity is very important.

Recently, with the development of Speech to Text, which converts voice to text, and machine translation, technologies for simultaneously translating the captions of video into other languages have been developed. Using this, YouTube, a video-sharing site, provides captions in many languages. Currently, the automatic caption system extracts voice data when uploading a video and provides a subtitle file converted into text. This method creates subtitles suitable for the running time. However, when extracting subtitles from video using Speech to Text, it is impossible to accurately translate the sentence because all sentences are generated without periods. Since the generated subtitles are separated by time units rather than sentence units, and are translated, it is very difficult to understand the translation result as a whole. In this paper, we propose a method to divide text into sentences and generate period marks to improve the accuracy of automatic translation of English subtitles. For this study, we use the 27,826 sentence subtitles provided by Stanford University’s courses as data. Since this lecture video provides complete sentence caption data, it can be used as training data by transforming the subtitles into general YouTube-like caption data. We build a model with the training data using the LSTM-RNN (Long-Short Term Memory – Recurrent Neural Networks) and predict the position of the period mark, resulting in prediction accuracy of 70.84%. Our research will provide people with more accurate translations of subtitles. In addition, we expect that language barriers in online education will be more easily broken by achieving more accurate translations of numerous video lectures in English.

This study was designed to analyze urinary proteins associated with ovarian cancer (OC) and investigate the potential urinary biomarker panel to predict malignancy in women with pelvic masses. We analyzed 23 biomarkers in urine samples obtained from 295 patients with pelvic masses scheduled for surgery. The concentration of urinary biomarkers was quantitatively assessed by the xMAP bead-based multiplexed immunoassay. To identify the performance of each biomarker in predicting cancer over benign tumors, we used a repeated leave-group-out cross-validation strategy. The prediction models using multimarkers were evaluated to develop a urinary ovarian cancer panel. After the exclusion of 12 borderline tumors, the urinary concentration of 17 biomarkers exhibited significant differences between 158 OCs and 125 benign tumors. Human epididymis protein 4 (HE4), vascular cell adhesion molecule (VCAM), and transthyretin (TTR) were the top three biomarkers representing a higher concentration in OC. HE4 demonstrated the highest performance in all samples withOC(mean area under the receiver operating characteristic curve (AUC) 0.822, 95% CI: 0.772–0.869), whereas TTR showed the highest efficacy in early-stage OC (AUC 0.789, 95% CI: 0.714–0.856). Overall, HE4 was the most informative biomarker, followed by creatinine, carcinoembryonic antigen (CEA), neural cell adhesion molecule (NCAM), and TTR using the least absolute shrinkage and selection operator (LASSO) regression models. A multimarker panel consisting of HE4, creatinine, CEA, and TTR presented the best performance with 93.7% sensitivity (SN) at 70.6% specificity (SP) to predict OC over the benign tumor. This panel performed well regardless of disease status and demonstrated an improved performance by including menopausal status. In conclusion, the urinary biomarker panel with HE4, creatinine, CEA, and TTR provided promising efficacy in predicting OC over benign tumors in women with pelvic masses. It was also a non-invasive and easily available diagnostic tool.

Malaria must be diagnosed quickly and accurately at the initial infection stage and treated early to cure it properly. The malaria diagnosis method using a microscope requires much labor and time of a skilled expert and the diagnosis results vary gre

Purpose: In this paper, the problem of a nonlinear model – specifically the hidden unit conditional random fields (HUCRFs) model, which has binary stochastic hidden units between the data and the labels – exhibiting unstable performance depending on the hyperparameter under consideration. Design/methodology/approach: There are three main optimization search methods for hyperparameter tuning: manual search, grid search and random search. This study shows that HUCRFs’ unstable performance depends on the hyperparameter values used and its performance is based on tuning that draws on grid and random searches. All experiments conducted used the n-gram features – specifically, unigram, bigram, and trigram. Findings: Naturally, selecting a list of hyperparameter values based on a researchers’ experience to find a set in which the best performance is exhibited is better than finding it from a probability distribution. Realistically, however, it is impossible to calculate using the parameters in all combinations. The present research indicates that the random search method has a better performance compared with the grid search method while requiring shorter computation time and a reduced cost. Originality/value: In this paper, the issues affecting the performance of HUCRF, a nonlinear model with performance that varies depending on the hyperparameters, but performs better than CRF, has been examined.