Search

Background: Infertility is a significant problem of humanity. In vitro fertilisation is one of the most effective and frequently applied ART methods. The effectiveness IVF depends on the assessment and selection of gametes and embryo with the highest developmental potential. The subjective nature of morphological assessment of oocytes and embryos is still one of the main reasons for seeking effective and objective methods for assessing quality in automatic manner. The most promising methods to automatic classification of oocytes and embryos are based on image analysis aided by machine learning techniques. The special attention is paid on deep neural networks that can be used as classifiers solving the problem of automatic assessment of the oocytes/embryos.Methods: This paper deals with semantic segmentation of human oocyte images using deep neural networks in order to develop new version of the predefined neural networks. Deep semantic oocyte segmentation networks can be seen as medically oriented predefined networks understanding the content of the image. The research presented in the paper is focused on the performance comparison of different types of convolutional neural networks for semantic oocyte segmentation. In the case study, the merits and limitations of the selected deep neural networks are analysed.Results: 71 deep neural models were analysed. The best score was obtained for one of the variants of DeepLab-v3-ResNet-18 model, when the training accuracy (Acc) reached about 85% for training patterns and 79% for validation ones. The weighted intersection over union (wIoU) and global accuracy (gAcc) for test patterns were calculated, as well. The obtained values of these quality measures were 0,897 and 0.93, respectively.Conclusion: The obtained results prove that the proposed approach can be applied to create deep neural models for semantic oocyte segmentation with the high accuracy guaranteeing their usage as the predefined networks in other tasks. [ABSTRACT FROM AUTHOR]

Background: Prescription medication (PM) misuse/abuse has emerged as a national crisis in the United States, and social media has been suggested as a potential resource for performing active monitoring. However, automating a social media-based monitoring system is challenging-requiring advanced natural language processing (NLP) and machine learning methods. In this paper, we describe the development and evaluation of automatic text classification models for detecting self-reports of PM abuse from Twitter.Methods: We experimented with state-of-the-art bi-directional transformer-based language models, which utilize tweet-level representations that enable transfer learning (e.g., BERT, RoBERTa, XLNet, AlBERT, and DistilBERT), proposed fusion-based approaches, and compared the developed models with several traditional machine learning, including deep learning, approaches. Using a public dataset, we evaluated the performances of the classifiers on their abilities to classify the non-majority "abuse/misuse" class.Results: Our proposed fusion-based model performs significantly better than the best traditional model (F1-score [95% CI]: 0.67 [0.64-0.69] vs. 0.45 [0.42-0.48]). We illustrate, via experimentation using varying training set sizes, that the transformer-based models are more stable and require less annotated data compared to the other models. The significant improvements achieved by our best-performing classification model over past approaches makes it suitable for automated continuous monitoring of nonmedical PM use from Twitter.Conclusions: BERT, BERT-like and fusion-based models outperform traditional machine learning and deep learning models, achieving substantial improvements over many years of past research on the topic of prescription medication misuse/abuse classification from social media, which had been shown to be a complex task due to the unique ways in which information about nonmedical use is presented. Several challenges associated with the lack of context and the nature of social media language need to be overcome to further improve BERT and BERT-like models. These experimental driven challenges are represented as potential future research directions. [ABSTRACT FROM AUTHOR]

Background: It is a major challenge of computational biology to provide a comprehensive functional classification of all known proteins. Most existing methods seek recurrent patterns in known proteins based on manually-validated alignments of known protein families. Such methods can achieve high sensitivity, but are limited by the necessary manual labor. This makes our current view of the protein world incomplete and biased. This paper concerns ProtoNet, a automatic unsupervised global clustering system that generates a hierarchical tree of over 1,000,000 proteins, based solely on sequence similarity. Results: In this paper we show that ProtoNet correctly captures functional and structural aspects of the protein world. Furthermore, a novel feature is an automatic procedure that reduces the tree to 12% its original size. This procedure utilizes only parameters intrinsic to the clustering process. Despite the substantial reduction in size, the system's predictive power concerning biological functions is hardly affected. We then carry out an automatic comparison with existing functional protein annotations. Consequently, 78% of the clusters in the compressed tree (5,300 clusters) get assigned a biological function with a high confidence. The clustering and compression processes are unsupervised, and robust. Conclusions: We present an automatically generated unbiased method that provides a hierarchical classification of all currently known proteins. [ABSTRACT FROM AUTHOR]

Background: Major depressive disorder (MDD) has a high incidence and an unknown mechanism. There are no objective and sensitive indicators for clinical diagnosis. Objective: This study explored specific electrophysiological indicators and their role in the clinical diagnosis of MDD using machine learning. Methods: Forty first-episode and drug-naïve patients with MDD and forty healthy controls (HCs) were recruited. EEG data were collected from all subjects in the resting state with eyes closed for 10 min. The severity of MDD was assessed by the Hamilton Depression Rating Scale (HAMD-17). Machine learning analysis was used to identify the patients with MDD. Results: Compared to the HC group, the relative power of the low delta and theta bands was significantly higher in the right occipital region, and the relative power of the alpha band in the entire posterior occipital region was significantly lower in the MDD group. In the MDD group, the alpha band scalp functional connectivity was overall lower, while the scalp functional connectivity in the gamma band was significantly higher than that in the HC group. In the feature set of the relative power of the ROI in each band, the highest accuracy of 88.2% was achieved using the KNN classifier while using PCA feature selection. In the explanatory model using SHAP values, the top-ranking influence feature is the relative power of the alpha band in the left parietal region. Conclusions: Our findings reveal that the abnormal EEG neural oscillations may reflect an imbalance of excitation, inhibition and hyperactivity in the cerebral cortex in first-episode and drug-naïve patients with MDD. The relative power of the alpha band in the left parietal region is expected to be an objective electrophysiological indicator of MDD. [ABSTRACT FROM AUTHOR]

Current animal protection laws require replacement of animal experiments with alternative methods, whenever such methods are suitable to reach the intended scientific objective. However, searching for alternative methods in the scientific literature is a time-consuming task that requires careful screening of an enormously large number of experimental biomedical publications. The identification of potentially relevant methods, e.g. organ or cell culture models, or computer simulations, can be supported with text mining tools specifically built for this purpose. Such tools are trained (or fine tuned) on relevant data sets labeled by human experts. We developed the GoldHamster corpus, composed of 1,600 PubMed (Medline) articles (titles and abstracts), in which we manually identified the used experimental model according to a set of eight labels, namely: "in vivo", "organs", "primary cells", "immortal cell lines", "invertebrates", "humans", "in silico" and "other" (models). We recruited 13 annotators with expertise in the biomedical domain and assigned each article to two individuals. Four additional rounds of annotation aimed at improving the quality of the annotations with disagreements in the first round. Furthermore, we conducted various machine learning experiments based on supervised learning to evaluate the corpus for our classification task. We obtained more than 7,000 document-level annotations for the above labels. After the first round of annotation, the inter-annotator agreement (kappa coefficient) varied among labels, and ranged from 0.42 (for "others") to 0.82 (for "invertebrates"), with an overall score of 0.62. All disagreements were resolved in the subsequent rounds of annotation. The best-performing machine learning experiment used the PubMedBERT pre-trained model with fine-tuning to our corpus, which gained an overall f-score of 0.83. We obtained a corpus with high agreement for all labels, and our evaluation demonstrated that our corpus is suitable for training reliable predictive models for automatic classification of biomedical literature according to the used experimental models. Our SMAFIRA - "Smart feature-based interactive" - search tool (https://smafira.bf3r.de) will employ this classifier for supporting the retrieval of alternative methods to animal experiments. The corpus is available for download (https://doi.org/10.5281/zenodo.7152295), as well as the source code (https://github.com/mariananeves/goldhamster) and the model (https://huggingface.co/SMAFIRA/goldhamster). [ABSTRACT FROM AUTHOR]

Background: Systematic reviews (SRs) are recognized as reliable evidence, which enables evidence-based medicine to be applied to clinical practice. However, owing to the significant efforts required for an SR, its creation is time-consuming, which often leads to out-of-date results. To support SR tasks, tools for automating these SR tasks have been considered; however, applying a general natural language processing model to domain-specific articles and insufficient text data for training poses challenges. Methods: The research objective is to automate the classification of included articles using the Bidirectional Encoder Representations from Transformers (BERT) algorithm. In particular, srBERT models based on the BERT algorithm are pre-trained using abstracts of articles from two types of datasets, and the resulting model is then fine-tuned using the article titles. The performances of our proposed models are compared with those of existing general machine-learning models. Results: Our results indicate that the proposed srBERTmy model, pre-trained with abstracts of articles and a generated vocabulary, achieved state-of-the-art performance in both classification and relation-extraction tasks; for the first task, it achieved an accuracy of 94.35% (89.38%), F1 score of 66.12 (78.64), and area under the receiver operating characteristic curve of 0.77 (0.9) on the original and (generated) datasets, respectively. In the second task, the model achieved an accuracy of 93.5% with a loss of 27%, thereby outperforming the other evaluated models, including the original BERT model. Conclusions: Our research shows the possibility of automatic article classification using machine-learning approaches to support SR tasks and its broad applicability. However, because the performance of our model depends on the size and class ratio of the training dataset, it is important to secure a dataset of sufficient quality, which may pose challenges. [ABSTRACT FROM AUTHOR]

Purpose: A real-time automatic cataract-grading algorithm based on cataract video is proposed.Materials and Methods: In this retrospective study, we set the video of the eye lens section as the research target. A method is proposed to use YOLOv3 to assist in positioning, to automatically identify the position of the lens and classify the cataract after color space conversion. The data set is a cataract video file of 38 people's 76 eyes collected by a slit lamp. Data were collected using five random manner, the method aims to reduce the influence on the collection algorithm accuracy. The video length is within 10 s, and the classified picture data are extracted from the video file. A total of 1520 images are extracted from the image data set, and the data set is divided into training set, validation set and test set according to the ratio of 7:2:1.Results: We verified it on the 76-segment clinical data test set and achieved the accuracy of 0.9400, with the AUC of 0.9880, and the F1 of 0.9388. In addition, because of the color space recognition method, the detection per frame can be completed within 29 microseconds and thus the detection efficiency has been improved significantly.Conclusion: With the efficiency and effectiveness of this algorithm, the lens scan video is used as the research object, which improves the accuracy of the screening. It is closer to the actual cataract diagnosis and treatment process, and can effectively improve the cataract inspection ability of non-ophthalmologists. For cataract screening in poor areas, the accessibility of ophthalmology medical care is also increased. [ABSTRACT FROM AUTHOR]

Background: Systematized Nomenclature of Medicine - Clinical Terms (SNOMED CT) has been designed as standard clinical terminology for annotating Electronic Health Records (EHRs). EHRs textual information is used to classify patients' diseases into an International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) category (usually by an expert). Improving the accuracy of classification is the main purpose of using ontologies and OWL representations at the core of classification systems. In the last few years some ontologies and OWL representations for representing ICD-10-CM categories have been developed. However, they were not designed to be the basis for an automatic classification tool nor do they model ICD-10-CM inclusion terms as Web Ontology Language (OWL) axioms, which enables automatic classification. In this context we have developed Dione, an OWL representation of ICD-10-CM. Results: Dione is the first OWL representation of ICD-10-CM, which is logically consistent, whose axioms define the ICD-10-CM inclusion terms by means of a methodology based on SNOMED CT/ICD-10-CM mappings. The ICD-10-CM exclusions are handled with these mappings. Dione currently contains 391,669 classes, 391,720 entity annotation axioms and 11,795 owl:equivalentClass axioms which have been constructed using 104,646 relationships extracted from the SNOMED CT/ICD-10-CM and BioPortal mappings included in Dione using the owl:intersectionOf and the owl:someValuesFrom statements. The resulting OWL representation has been classified and its consistency tested with the ELK reasoner. We have also taken three clinical records from the Virgen de la Victoria Hospital (Málaga, Spain) which have been manually annotated using SNOMED CT. These annotations have been included as instances to be classified by the reasoner. The classified instances show that Dione could be a promising ICD-10-CM OWL representation to support the classification of patients' diseases. Conclusions: Dione is a first step towards the automatic classification of patients' diseases by using SNOMED CT annotations embedded in Electronic Health Records (EHRs). The purpose of Dione is to standardise and formalise a medical terminology, thereby enabling new kinds of tools and new sets of functionalities to be developed. This in turn assists health specialists by providing classified information from EHRs and enables the automatic annotation of patients' diseases with ICD-10-CM codes. [ABSTRACT FROM AUTHOR]

Background: To improve the quality, quantity, and speed of implementation, careful monitoring of the implementation process is required. However, some health organizations have such limited capacity to collect, organize, and synthesize information relevant to its decision to implement an evidence-based program, the preparation steps necessary for successful program adoption, the fidelity of program delivery, and the sustainment of this program over time. When a large health system implements an evidence-based program across multiple sites, a trained intermediary or broker may provide such monitoring and feedback, but this task is labor intensive and not easily scaled up for large numbers of sites. We present a novel approach to producing an automated system of monitoring implementation stage entrances and exits based on a computational analysis of communication log notes generated by implementation brokers. Potentially discriminating keywords are identified using the definitions of the stages and experts' coding of a portion of the log notes. A machine learning algorithm produces a decision rule to classify remaining, unclassified log notes.Results: We applied this procedure to log notes in the implementation trial of multidimensional treatment foster care in the California 40-county implementation trial (CAL-40) project, using the stages of implementation completion (SIC) measure. We found that a semi-supervised non-negative matrix factorization method accurately identified most stage transitions. Another computational model was built for determining the start and the end of each stage.Conclusions: This automated system demonstrated feasibility in this proof of concept challenge. We provide suggestions on how such a system can be used to improve the speed, quality, quantity, and sustainment of implementation. The innovative methods presented here are not intended to replace the expertise and judgement of an expert rater already in place. Rather, these can be used when human monitoring and feedback is too expensive to use or maintain. These methods rely on digitized text that already exists or can be collected with minimal to no intrusiveness and can signal when additional attention or remediation is required during implementation. Thus, resources can be allocated according to need rather than universally applied, or worse, not applied at all due to their cost. [ABSTRACT FROM AUTHOR]

Background: Diffusion-weighted imaging (DWI) and perfusion-weighted imaging (PWI) abnormalities in patients with multiple sclerosis (MS) are currently measured by a complex combination of separate procedures. Therefore, the purpose of this study was to provide a reliable method for reducing analysis complexity and obtaining reproducible results. Methods: We implemented a semi-automated measuring system in which different well-known software components for magnetic resonance imaging (MRI) analysis are integrated to obtain reliable measurements of DWI and PWI disturbances in MS. Results: We generated the Diffusion/Perfusion Project (DPP) Suite, in which a series of external software programs are managed and harmonically and hierarchically incorporated by in-house developed Matlab software to perform the following processes: 1) image pre-processing, including imaging data anonymization and conversion from DICOM to Nifti format; 2) co-registration of 2D and 3D non-enhanced and Gd-enhanced T1-weighted images in fluid-attenuated inversion recovery (FLAIR) space; 3) lesion segmentation and classification, in which FLAIR lesions are at first segmented and then categorized according to their presumed evolution; 4) co-registration of segmented FLAIR lesion in T1 space to obtain the FLAIR lesion mask in the T1 space; 5) normal appearing tissue segmentation, in which T1 lesion mask is used to segment basal ganglia/thalami, normal appearing grey matter (NAGM) and normal appearing white matter (NAWM); 6) DWI and PWI map generation; 7) co-registration of basal ganglia/thalami, NAGM, NAWM, DWI and PWI maps in previously segmented FLAIR space; 8) data analysis. All these steps are automatic, except for lesion segmentation and classification. Conclusion: We developed a promising method to limit misclassifications and user errors, providing clinical researchers with a practical and reproducible tool to measure DWI and PWI changes in MS. [ABSTRACT FROM AUTHOR]

Background: Laserscanning recently has become a powerful and common method for plant parameterization and plant growth observation on nearly every scale range. However, 3D measurements with high accuracy, spatial resolution and speed result in a multitude of points that require processing and analysis. The primary objective of this research has been to establish a reliable and fast technique for high throughput phenotyping using differentiation, segmentation and classification of single plants by a fully automated system. In this report, we introduce a technique for automated classification of point clouds of plants and present the applicability for plant parameterization. Results: A surface feature histogram based approach from the field of robotics was adapted to close-up laserscans of plants. Local geometric point features describe class characteristics, which were used to distinguish among different plant organs. This approach has been proven and tested on several plant species. Grapevine stems and leaves were classified with an accuracy of up to 98%. The proposed method was successfully transferred to 3D-laserscans of wheat plants for yield estimation. Wheat ears were separated with an accuracy of 96% from other plant organs. Subsequently, the ear volume was calculated and correlated to the ear weight, the kernel weights and the number of kernels. Furthermore the impact of the data resolution was evaluated considering point to point distances between 0.3 and 4.0 mm with respect to the classification accuracy. Conclusion: We introduced an approach using surface feature histograms for automated plant organ parameterization. Highly reliable classification results of about 96% for the separation of grapevine and wheat organs have been obtained. This approach was found to be independent of the point to point distance and applicable to multiple plant species. Its reliability, flexibility and its high order of automation make this method well suited for the demands of high throughput phenotyping. Highlights: • Automatic classification of plant organs using geometrical surface information • Transfer of analysis methods for low resolution point clouds to close-up laser measurements of plants • Analysis of 3D-data requirements for automated plant organ classification [ABSTRACT FROM AUTHOR]

Background: Formal classification of a large collection of protein structures aids the understanding of evolutionary relationships among them. Classifications involving manual steps, such as SCOP and CATH, face the challenge of increasing volume of available structures. Automatic methods such as FSSP or Dali Domain Dictionary, yield divergent classifications, for reasons not yet fully investigated. One possible reason is that the pairwise similarity scores used in automatic classification do not adequately reflect the judgments made in manual classification. Another possibility is the difference between manual and automatic classification procedures. We explore the degree to which these two factors might affect the final classification. Results: We use DALI, SHEBA and VAST pairwise scores on the SCOP C class domains, to investigate a variety of hierarchical clustering procedures. The constructed dendrogram is cut in a variety of ways to produce a partition, which is compared to the SCOP fold classification. Ward's method dendrograms led to partitions closest to the SCOP fold classification. Dendrogram- or tree-cutting strategies fell into four categories according to the similarity of resulting partitions to the SCOP fold partition. Two strategies which optimize similarity to SCOP, gave an average of 72% true positives rate (TPR), at a 1% false positive rate. Cutting the largest size cluster at each step gave an average of 61% TPR which was one of the best strategies not making use of prior knowledge of SCOP. Cutting the longest branch at each step produced one of the worst strategies. We also developed a method to detect irreducible differences between the best possible automatic partitions and SCOP, regardless of the cutting strategy. These differences are substantial. Visual examination of hard-to-classify proteins confirms our previous finding, that global structural similarity of domains is not the only criterion used in the SCOP classification. Conclusion: Different clustering procedures give rise to different levels of agreement between automatic and manual protein classifications. None of the tested procedures completely eliminates the divergence between automatic and manual protein classifications. Achieving full agreement between these two approaches would apparently require additional information. [ABSTRACT FROM AUTHOR]

Background: Inference of remote homology between proteins is very challenging and remains a prerogative of an expert. Thus a significant drawback to the use of evolutionary-based protein structure classifications is the difficulty in assigning new proteins to unique positions in the classification scheme with automatic methods. To address this issue, we have developed an algorithm to map protein domains to an existing structural classification scheme and have applied it to the SCOP database. Results: The general strategy employed by this algorithm is to combine the results of several existing sequence and structure comparison tools applied to a query protein of known structure in order to find the homologs already classified in SCOP database and thus determine classification assignments. The algorithm is able to map domains within newly solved structures to the appropriate SCOP superfamily level with ~95% accuracy. Examples of correctly mapped remote homologs are discussed. The algorithm is also capable of identifying potential evolutionary relationships not specified in the SCOP database, thus helping to make it better. The strategy of the mapping algorithm is not limited to SCOP and can be applied to any other evolutionary-based classification scheme as well. SCOPmap is available for download. Conclusion: The SCOPmap program is useful for assigning domains in newly solved structures to appropriate superfamilies and for identifying evolutionary links between different superfamilies. [ABSTRACT FROM AUTHOR]

Background: Recent studies have shown that long non-coding RNAs (lncRNAs) play a crucial role in the induction of cancer through epigenetic regulation, transcriptional regulation, post-transcriptional regulation and other aspects, thus participating in various biological processes such as cell proliferation, differentiation and apoptosis. As a new nova of anti-tumor therapy, immunotherapy has been shown to be effective in many tumors of which PD-1/PD-L1 monoclonal antibodies has been proofed to increase overall survival rate in advanced gastric cancer (GC). Microsatellite instability (MSI) was known as a biomarker of response to PD-1/PD-L1 monoclonal antibodies therapy. The aim of this study was to identify lncRNAs signatures able to classify MSI status and create a predictive model associated with MSI for GC patients. Methods: Using the data of Stomach adenocarcinoma from The Cancer Genome Atlas (TCGA), we developed and validated a lncRNAs model for automatic MSI classification using a machine learning technology – support vector machine (SVM). The C-index was adopted to evaluate its accuracy. The prognostic values of overall survival (OS) and disease-free survival (DFS) were also assessed in this model. Results: Using the SVM, a lncRNAs model was established consisting of 16 lncRNA features. In the training cohort with 94 GC patients, accuracy was confirmed with AUC 0.976 (95% CI, 0.952 to 0.999). Veracity was also confirmed in the validation cohort (40 GC patients) with AUC 0.950 (0.889 to 0.999). High predicted score was correlated with better DFS in the patients with stage I-III and lower OS with stage I-IV. Conclusion: This study identify 16 LncRNAs signatures able to classify MSI status. The correlation between lncRNAs and MSI status indicates the potential roles of lncRNAs interacting in immunotherapy for GC patients. The pathway of these lncRNAs which might be a target in PD-1/PD-L1 immunotherapy are needed to be further study. [ABSTRACT FROM AUTHOR]