Metastatic breast cancer (MBC) continues to be a leading cause of cancer-related deaths among women. This work introduces an innovative non-invasive breast cancer classification model designed to improve the identification of cancer metastases. While this study marks the initial exploration into predicting MBC, additional investigations are essential to validate the occurrence of MBC. Our approach combines the strengths of large language models (LLMs), specifically the bidirectional encoder representations from transformers (BERT) model, with the powerful capabilities of graph neural networks (GNNs) to predict MBC patients based on their histopathology reports. This paper introduces a BERT-GNN approach for metastatic breast cancer prediction (BG-MBC) that integrates graph information derived from the BERT model. In this model, nodes are constructed from patient medical records, while BERT embeddings are employed to vectorise representations of the words in histopathology reports, thereby capturing semantic information crucial for classification by employing three distinct approaches (namely univariate selection, extra trees classifier for feature importance, and Shapley values to identify the features that have the most significant impact). Identifying the most crucial 30 features out of 676 generated as embeddings during model training, our model further enhances its predictive capabilities. The BG-MBC model achieves outstanding accuracy, with a detection rate of 0.98 and an area under curve (AUC) of 0.98, in identifying MBC patients. This remarkable performance is credited to the model\'s utilisation of attention scores generated by the LLM from histopathology reports, effectively capturing pertinent features for classification.

BACKGROUND: Research gaps refer to unanswered questions in the existing body of knowledge, either due to a lack of studies or inconclusive results. Research gaps are essential starting points and motivation in scientific research. Traditional methods for identifying research gaps, such as literature reviews and expert opinions, can be time consuming, labor intensive, and prone to bias. They may also fall short when dealing with rapidly evolving or time-sensitive subjects. Thus, innovative scalable approaches are needed to identify research gaps, systematically assess the literature, and prioritize areas for further study in the topic of interest.
OBJECTIVE: In this paper, we propose a machine learning-based approach for identifying research gaps through the analysis of scientific literature. We used the COVID-19 pandemic as a case study.
METHODS: We conducted an analysis to identify research gaps in COVID-19 literature using the COVID-19 Open Research (CORD-19) data set, which comprises 1,121,433 papers related to the COVID-19 pandemic. Our approach is based on the BERTopic topic modeling technique, which leverages transformers and class-based term frequency-inverse document frequency to create dense clusters allowing for easily interpretable topics. Our BERTopic-based approach involves 3 stages: embedding documents, clustering documents (dimension reduction and clustering), and representing topics (generating candidates and maximizing candidate relevance).
RESULTS: After applying the study selection criteria, we included 33,206 abstracts in the analysis of this study. The final list of research gaps identified 21 different areas, which were grouped into 6 principal topics. These topics were: \"virus of COVID-19,\" \"risk factors of COVID-19,\" \"prevention of COVID-19,\" \"treatment of COVID-19,\" \"health care delivery during COVID-19,\" \"and impact of COVID-19.\" The most prominent topic, observed in over half of the analyzed studies, was \"the impact of COVID-19.\"
CONCLUSIONS: The proposed machine learning-based approach has the potential to identify research gaps in scientific literature. This study is not intended to replace individual literature research within a selected topic. Instead, it can serve as a guide to formulate precise literature search queries in specific areas associated with research questions that previous publications have earmarked for future exploration. Future research should leverage an up-to-date list of studies that are retrieved from the most common databases in the target area. When feasible, full texts or, at minimum, discussion sections should be analyzed rather than limiting their analysis to abstracts. Furthermore, future studies could evaluate more efficient modeling algorithms, especially those combining topic modeling with statistical uncertainty quantification, such as conformal prediction.

UNASSIGNED: Pathology reports contain key information about the patient\'s diagnosis as well as important gross and microscopic findings. These information-rich clinical reports offer an invaluable resource for clinical studies, but data extraction and analysis from such unstructured texts is often manual and tedious. While neural information retrieval systems (typically implemented as deep learning methods for natural language processing) are automatic and flexible, they typically require a large domain-specific text corpus for training, making them infeasible for many medical subdomains. Thus, an automated data extraction method for pathology reports that does not require a large training corpus would be of significant value and utility.
UNASSIGNED: To develop a language model-based neural information retrieval system that can be trained on small datasets and validate it by training it on renal transplant-pathology reports to extract relevant information for two predefined questions: (1) \"What kind of rejection does the patient show?\"; (2) \"What is the grade of interstitial fibrosis and tubular atrophy (IFTA)?\"
UNASSIGNED: Kidney BERT was developed by pre-training Clinical BERT on 3.4K renal transplant pathology reports and 1.5M words. Then, exKidneyBERT was developed by extending Clinical BERT\'s tokenizer with six technical keywords and repeating the pre-training procedure. This extended the model\'s vocabulary. All three models were fine-tuned with information retrieval heads.
UNASSIGNED: The model with extended vocabulary, exKidneyBERT, outperformed Clinical BERT and Kidney BERT in both questions. For rejection, exKidneyBERT achieved an 83.3% overlap ratio for antibody-mediated rejection (ABMR) and 79.2% for T-cell mediated rejection (TCMR). For IFTA, exKidneyBERT had a 95.8% exact match rate.
UNASSIGNED: ExKidneyBERT is a high-performing model for extracting information from renal pathology reports. Additional pre-training of BERT language models on specialized small domains does not necessarily improve performance. Extending the BERT tokenizer\'s vocabulary library is essential for specialized domains to improve performance, especially when pre-training on small corpora.

The Transformer-based approaches to solving natural language processing (NLP) tasks such as BERT and GPT are gaining popularity due to their ability to achieve high performance. These approaches benefit from using enormous data sizes to create pre-trained models and the ability to understand the context of words in a sentence. Their use in the information retrieval domain is thought to increase effectiveness and efficiency. This paper demonstrates a BERT-based method (CASBERT) implementation to build a search tool over data annotated compositely using ontologies. The data was a collection of biosimulation models written using the CellML standard in the Physiome Model Repository (PMR). A biosimulation model structurally consists of basic entities of constants and variables that construct higher-level entities such as components, reactions, and the model. Finding these entities specific to their level is beneficial for various purposes regarding variable reuse, experiment setup, and model audit. Initially, we created embeddings representing compositely-annotated entities for constant and variable search (lowest level entity). Then, these low-level entity embeddings were vertically and efficiently combined to create higher-level entity embeddings to search components, models, images, and simulation setups. Our approach was general, so it can be used to create search tools with other data semantically annotated with ontologies - biosimulation models encoded in the SBML format, for example. Our tool is named Biosimulation Model Search Engine (BMSE).

Scarcity of labels for medical images is a significant barrier for training representation learning approaches based on deep neural networks. This limitation is also present when using imaging data collected during routine clinical care stored in picture archiving communication systems (PACS), as these data rarely have attached the high-quality labels required for medical image computing tasks. However, medical images extracted from PACS are commonly coupled with descriptive radiology reports that contain significant information and could be leveraged to pre-train imaging models, which could serve as starting points for further task-specific fine-tuning. In this work, we perform a head-to-head comparison of three different self-supervised strategies to pre-train the same imaging model on 3D brain computed tomography angiogram (CTA) images, with large vessel occlusion (LVO) detection as the downstream task. These strategies evaluate two natural language processing (NLP) approaches, one to extract 100 explicit radiology concepts (Rad-SpatialNet) and the other to create general-purpose radiology reports embeddings (DistilBERT). In addition, we experiment with learning radiology concepts directly or by using a recent self-supervised learning approach (CLIP) that learns by ranking the distance between language and image vector embeddings. The LVO detection task was selected because it requires 3D imaging data, is clinically important, and requires the algorithm to learn outputs not explicitly stated in the radiology report. Pre-training was performed on an unlabeled dataset containing 1,542 3D CTA - reports pairs. The downstream task was tested on a labeled dataset of 402 subjects for LVO. We find that the pre-training performed with CLIP-based strategies improve the performance of the imaging model to detect LVO compared to a model trained only on the labeled data. The best performance was achieved by pre-training using the explicit radiology concepts and CLIP strategy.

Understanding the diagnostic goal of medical reports is valuable information for understanding patient flows. This work focuses on extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring. We investigate the performance of domain-dependent and general state-of-the-art language models and their alignment with domain expertise. To this end, eXplainable Artificial Intelligence (XAI) techniques are used to acquire insight into the inner workings of the model, which are verified on their trustworthiness. The verified XAI explanations are then compared with explanations from a domain expert, to indirectly determine the reliability of the model. BERTje, a Dutch Bidirectional Encoder Representations from Transformers (BERT) model, outperforms RobBERT and MedRoBERTa.nl in both accuracy and reliability. The latter model (MedRoBERTa.nl) is a domain-specific model, while BERTje is a generic model, showing that domain-specific models are not always superior. Our validation of BERTje in a small prospective study shows promising results for the potential uptake of the model in a practical setting.

UNASSIGNED: Medical notes are narratives that describe the health of the patient in free text format. These notes can be more informative than structured data such as the history of medications or disease conditions. They are routinely collected and can be used to evaluate the patient\'s risk for developing chronic diseases such as dementia. This study investigates different methodologies for transforming routine care notes into dementia risk classifiers and evaluates the generalizability of these classifiers to new patients and new health care institutions.
UNASSIGNED: The notes collected over the relevant history of the patient are lengthy. In this study, TF-ICF is used to select keywords with the highest discriminative ability between at risk dementia patients and healthy controls. The medical notes are then summarized in the form of occurrences of the selected keywords. Two different encodings of the summary are compared. The first encoding consists of the average of the vector embedding of each keyword occurrence as produced by the BERT or Clinical BERT pre-trained language models. The second encoding aggregates the keywords according to UMLS concepts and uses each concept as an exposure variable. For both encodings, misspellings of the selected keywords are also considered in an effort to improve the predictive performance of the classifiers. A neural network is developed over the first encoding and a gradient boosted trees model is applied to the second encoding. Patients from a single health care institution are used to develop all the classifiers which are then evaluated on held-out patients from the same health care institution as well as test patients from two other health care institutions.
UNASSIGNED: The results indicate that it is possible to identify patients at risk for dementia one year ahead of the onset of the disease using medical notes with an AUC of 75% when a gradient boosted trees model is used in conjunction with exposure variables derived from UMLS concepts. However, this performance is not maintained with an embedded feature space and when the classifier is applied to patients from other health care institutions. Moreover, an analysis of the top predictors of the gradient boosted trees model indicates that different features inform the classification depending on whether or not spelling variants of the keywords are included.
UNASSIGNED: The present study demonstrates that medical notes can enable risk prediction models for complex chronic diseases such as dementia. However, additional research efforts are needed to improve the generalizability of these models. These efforts should take into consideration the length and localization of the medical notes; the availability of sufficient training data for each disease condition; and the variabilities resulting from different feature engineering techniques.

The recent success of deep learning neural language models such as Bidirectional Encoder Representations from Transformers (BERT) has brought innovations to computational language research. The present study explores the possibility of using a language model in investigating human language processes, based on the case study of negative polarity items (NPIs). We first conducted an experiment with BERT to examine whether the model successfully captures the hierarchical structural relationship between an NPI and its licensor and whether it may lead to an error analogous to the grammatical illusion shown in the psycholinguistic experiment (Experiment 1). We also investigated whether the language model can capture the fine-grained semantic properties of NPI licensors and discriminate their subtle differences on the scale of licensing strengths (Experiment 2). The results of the two experiments suggest that overall, the neural language model is highly sensitive to both syntactic and semantic constraints in NPI processing. The model\'s processing patterns and sensitivities are shown to be very close to humans, suggesting their role as a research tool or object in the study of language.

The Internet of Things is a paradigm that interconnects several smart devices through the internet to provide ubiquitous services to users. This paradigm and Web 2.0 platforms generate countless amounts of textual data. Thus, a significant challenge in this context is automatically performing text classification. State-of-the-art outcomes have recently been obtained by employing language models trained from scratch on corpora made up from news online to handle text classification better. A language model that we can highlight is BERT (Bidirectional Encoder Representations from Transformers) and also DistilBERT is a pre-trained smaller general-purpose language representation model. In this context, through a case study, we propose performing the text classification task with two previously mentioned models for two languages (English and Brazilian Portuguese) in different datasets. The results show that DistilBERT\'s training time for English and Brazilian Portuguese was about 45% faster than its larger counterpart, it was also 40% smaller, and preserves about 96% of language comprehension skills for balanced datasets.

Building a document-level classifier for COVID-19 on radiology reports could help assist providers in their daily clinical routine, as well as create large numbers of labels for computer vision models. We have developed such a classifier by fine-tuning a BERT-like model initialized from RadBERT, its continuous pre-training on radiology reports that can be used on all radiology-related tasks. RadBERT outperforms all biomedical pre-trainings on this COVID-19 task (P<0.01) and helps our fine-tuned model achieve an 88.9 macro-averaged F1-score, when evaluated on both X-ray and CT reports. To build this model, we rely on a multi-institutional dataset re-sampled and enriched with concurrent lung diseases, helping the model to resist to distribution shifts. In addition, we explore a variety of fine-tuning and hyperparameter optimization techniques that accelerate fine-tuning convergence, stabilize performance, and improve accuracy, especially when data or computational resources are limited. Finally, we provide a set of visualization tools and explainability methods to better understand the performance of the model, and support its practical use in the clinical setting. Our approach offers a ready-to-use COVID-19 classifier and can be applied similarly to other radiology report classification tasks.