Identifying main finding sentences in clinical case reports

CLIP in medical imaging: A survey

Contrastive Language-Image Pre-training (CLIP), a simple yet effective pre-training paradigm, successfully introduces text supervision to vision models. It has shown promising results across various tasks due to its generalizability and interpretability. The use of CLIP has recently gained increasing interest in the medical imaging domain, serving as a pre-training paradigm for image-text alignment, or a critical component in diverse clinical tasks. With the aim of facilitating a deeper understanding of this promising direction, this survey offers an in-depth exploration of the CLIP within the domain of medical imaging, regarding both refined CLIP pre-training and CLIP-driven applications. In this paper, we (1) first start with a brief introduction to the fundamentals of CLIP methodology; (2) then investigate the adaptation of CLIP pre-training in the medical imaging domain, focusing on how to optimize CLIP given characteristics of medical images and reports; (3) further explore practical utilization of CLIP pre-trained models in various tasks, including classification, dense prediction, and cross-modal tasks; and (4) finally discuss existing limitations of CLIP in the context of medical imaging, and propose forward-looking directions to address the demands of medical imaging domain. Studies featuring technical and practical value are both investigated. We expect this survey will provide researchers with a holistic understanding of the CLIP paradigm and its potential implications. The project page of this survey can also be found on Github.

Extraction of microRNA-target interaction sentences from biomedical literature by deep learning approach

MicroRNA (miRNA)-target interaction (MTI) plays a substantial role in various cell activities, molecular regulations and physiological processes. Published biomedical literature is the carrier of high-confidence MTI knowledge. However, digging out this knowledge in an efficient manner from large-scale published articles remains challenging. To address this issue, we were motivated to construct a deep learning-based model. We applied the pre-trained language models to biomedical text to obtain the representation, and subsequently fed them into a deep neural network with gate mechanism layers and a fully connected layer for the extraction of MTI information sentences. Performances of the proposed models were evaluated using two datasets constructed on the basis of text data obtained from miRTarBase. The validation and test results revealed that incorporating both PubMedBERT and SciBERT for sentence level encoding with the long short-term memory (LSTM)-based deep neural network can yield an outstanding performance, with both F1 and accuracy being higher than 80% on validation data and test data. Additionally, the proposed deep learning method outperformed the following machine learning methods: random forest, support vector machine, logistic regression and bidirectional LSTM. This work would greatly facilitate studies on MTI analysis and regulations. It is anticipated that this work can assist in large-scale screening of miRNAs, thereby revealing their functional roles in various diseases, which is important for the development of highly specific drugs with fewer side effects. Source code and corpus are publicly available at https://github.com/qi29.

A representation and deep learning model for annotating ubiquitylation sentences stating E3 ligase - substrate interaction

Background

Ubiquitylation is an important post-translational modification of proteins that not only plays a central role in cellular coding, but is also closely associated with the development of a variety of diseases. The specific selection of substrate by ligase E3 is the key in ubiquitylation. As various high-throughput analytical techniques continue to be applied to the study of ubiquitylation, a large amount of ubiquitylation site data, and records of E3-substrate interactions continue to be generated. Biomedical literature is an important vehicle for information on E3-substrate interactions in ubiquitylation and related new discoveries, as well as an important channel for researchers to obtain such up to date data. The continuous explosion of ubiquitylation related literature poses a great challenge to researchers in acquiring and analyzing the information. Therefore, automatic annotation of these E3-substrate interaction sentences from the available literature is urgently needed.

Results

In this research, we proposed a model based on representation and attention mechanism based deep learning methods, to automatic annotate E3-substrate interaction sentences in biomedical literature. Focusing on the sentences with E3 protein inside, we applied several natural language processing methods and a Long Short-Term Memory (LSTM)-based deep learning classifier to train the model. Experimental results had proved the effectiveness of our proposed model. And also, the proposed attention mechanism deep learning method outperforms other statistical machine learning methods. We also created a manual corpus of E3-substrate interaction sentences, in which the E3 proteins and substrate proteins are also labeled, in order to construct our model. The corpus and model proposed by our research are definitely able to be very useful and valuable resource for advancement of ubiquitylation-related research.

Conclusion

Having the entire manual corpus of E3-substrate interaction sentences readily available in electronic form will greatly facilitate subsequent text mining and machine learning analyses. Automatic annotating ubiquitylation sentences stating E3 ligase-substrate interaction is significantly benefited from semantic representation and deep learning. The model enables rapid information accessing and can assist in further screening of key ubiquitylation ligase substrates for in-depth studies.

The Impact of Excluding Nonrandomized Studies From Systematic Reviews in Rare Diseases: "The Example of Meta-Analyses Evaluating the Efficacy and Safety of Enzyme Replacement Therapy in Patients With Mucopolysaccharidosis"

Nonrandomized studies are usually excluded from systematic reviews. This could lead to loss of a considerable amount of information on rare diseases. In this article, we explore the impact of excluding nonrandomized studies on the generalizability of meta-analyses results on mucopolysaccharidosis (MPS) disease. A comprehensive search of systematic reviews on MPS patients up to May 2020 was carried out (CRD42020191217). The primary endpoint was the rate of patients excluded from systematic reviews if only randomized studies were considered. Secondary outcomes included the differences in patient and study characteristics between randomized and nonrandomized studies, the methods used to combine data from studies with different designs, and the number of patients excluded from systematic reviews if case reports were not considered. More than 50% of the patients analyzed have been recruited in nonrandomized studies. Patient characteristics, duration of follow-up, and the clinical outcomes evaluated differ between the randomized and nonrandomized studies. There are feasible strategies to combine the data from different randomized and nonrandomized designs. The analyses suggest the relevance of including case reports in the systematic reviews, since the smaller the number of patients in the reference population, the larger the selection bias associated to excluding case reports. Our results recommend including nonrandomized studies in the systematic reviews of MPS to increase the representativeness of the results and to avoid a selection bias. The recommendations obtained from this study should be considered when conducting systematic reviews on rare diseases.

The Value of Case Reports in Systematic Reviews from Rare Diseases. The Example of Enzyme Replacement Therapy (ERT) in Patients with Mucopolysaccharidosis Type II (MPS-II)

BACKGROUND

Case reports are usually excluded from systematic reviews. Patients with rare diseases are more dependent on novel individualized strategies than patients with common diseases. We reviewed and summarized the novelties reported by case reports in mucopolysaccharidosis type II (MPS-II) patients treated with enzyme replacement therapy (ERT).

METHODS

We selected the case reports included in a previous meta-analysis of patients with MPS-II treated with ERT. Later clinical studies evaluating the same topic of those case reports were reported. Our primary aim was to summarize novelties reported in previous case reports. Secondary objectives analyzed the number of novelties evaluated in subsequent clinical studies and the time elapsed between the publication of the case report to the publication of the clinical study.

RESULTS

We identified 11 innovative proposals in case reports that had not been previously considered in clinical studies. Only two (18.2%) were analyzed in subsequent nonrandomized cohort studies. The other nine novelties (81.8%) were analyzed in later case reports (five) or were not included in ulterior studies (four) after more than five years from their first publication.

CONCLUSIONS

Case reports should be included in systematic reviews of rare disease to obtain a comprehensive summary of the state of research and offer valuable information for healthcare practitioners.