Evaluating and extending the Informed Consent Ontology for representing permissions from the clinical domain

The purpose of this study was to evaluate, revise, and extend the Informed Consent Ontology (ICO) for expressing clinical permissions, including reuse of residual clinical biospecimens and health data. This study followed a formative evaluation design and used a bottom-up modeling approach. Data were collected from the literature on US federal regulations and a study of clinical consent forms. Eleven federal regulations and fifteen permission-sentences from clinical consent forms were iteratively modeled to identify entities and their relationships, followed by community reflection and negotiation based on a series of predetermined evaluation questions. ICO included fifty-two classes and twelve object properties necessary when modeling, demonstrating appropriateness of extending ICO for the clinical domain. Twenty-six additional classes were imported into ICO from other ontologies, and twelve new classes were recommended for development. This work addresses a critical gap in formally representing permissions clinical permissions, including reuse of residual clinical biospecimens and health data. It makes missing content available to the OBO Foundry, enabling use alongside other widely-adopted biomedical ontologies. ICO serves as a machine-interpretable and interoperable tool for responsible reuse of residual clinical biospecimens and health data at scale.

An Intelligent Literature Review: an Inductive Approach to define Machine Learning Applications in the clinical domain

Big data analytics utilizes different analytics techniques to transform large volume and diversified big dataset. The analytics uses various computational methods such as different Machine Learning (ML) in convert raw data to valuable insights. The ML assist individuals to perform work activities quicker and better, and empower decision-makers in system use. Since academics and industry practitioners have growing interests on ML, how different applications of ML in specific problem domains have been explored, but not in a holistic manner from the past literature. This paper aims to promote the utilization of intelligent literature review for researchers by introducing a step-by-step framework on a case providing the code template. We offer an intelligent literature review to obtain in-depth analytical insight of ML applications in the clinical domain to: a) develop the intelligent literature framework using traditional literature and Latent Dirichlet Allocation (LDA) topic modeling, b) analyze research documents using traditional systematic literature review revealing ML applications, and c) identify topics from documents using LDA topic modeling. We used a PRISMA framework for the traditional literature review, reviewed four databases (e.g. IEEE, PubMed, Scopus, and Google Scholar), which are published between 2016 and 2021 (September). The framework comprises two stages – Traditional systematic literature review and LDA topic modeling. The intelligent literature review framework reviewed 305 research documents in a transparent, reliable, and faster way.

Algorithm-based advice taking and clinical judgement: impact of advice distance and algorithm information

Evidence-based algorithms can improve both lay and professional judgements and decisions, yet they remain underutilised. Research on advice taking established that humans tend to discount advice – especially when it contradicts their own judgement (“egocentric advice discounting”) – but this can be mitigated by knowledge about the advisor’s past performance. Advice discounting has typically been investigated using tasks with outcomes of low importance (e.g., general knowledge questions), and students as participants. Using the judge-advisor framework, we tested whether the principles of advice discounting apply in the clinical domain. We used realistic patient scenarios, algorithmic advice from a validated cancer risk calculator, and General Practitioners (GPs) as participants. GPs could update their risk estimates after receiving algorithmic advice. Half of them received information about the algorithm’s derivation, validation, and accuracy. We measured Weight of Advice and found that, on average, GPs weighed their estimates and the algorithm equally – but not always: they retained their initial estimates 29% of the time, and fully updated them 27% of the time. Updating did not depend on whether GPs were informed about the algorithm. We found a weak negative quadratic relationship between estimate updating and advice distance: although GPs integrate algorithmic advice on average, they may somewhat discount it, if it is very different from their own estimate. These results present a more complex picture than simple egocentric discounting of advice. They cast a more optimistic view of advice taking, where experts weigh algorithmic advice and their own judgement equally and move towards the advice even when it contradicts their own initial estimates.

Using the diagnostic odds ratio to select multivariate sequential patterns in order to build an interpretable pattern-based classifier in a clinical domain (Preprint)

BACKGROUND It is important to exploit all available data on patients in settings such as Intensive Care Burn Units (ICBUs), where several variables are recorded over time. It is possible to take advantage of the multivariate patterns that model the evolution of patients in order to predict their survival. However, pattern discovery algorithms generate a large number of patterns, of which only some are relevant for classification. The interpretability of the model is, moreover, an essential property in the clinical domain. OBJECTIVE We propose to use the Diagnostic Odds Ratio (DOR) to select the multivariate sequential patterns used in the classification in a clinical domain, rather than employing frequency properties. This makes it possible to employ a terminology closer to the language of clinicians, in which a pattern is considered to be a risk factor or to have a protection factor. METHODS We employ data obtained from the ICBU at the University Hospital of Getafe, where six temporal variables for 465 patients were registered every day during 5 days, and to model the evolution of these clinical variables we use multivariate sequential patterns. We compare four ways in which to employ the DOR for pattern selection: 1) We use it as a threshold in order to select patterns with a minimum DOR; 2) We select patterns whose differential DORs are higher than a threshold as regards their extensions; 3) We select patterns whose DOR confidence intervals do not overlap; and 4) We propose the combination of threshold and non-overlapping confidence intervals in order to select the most discriminative patterns. As a baseline, we compare our proposals with Jumping Emerging Patterns (JEPs), one of the most frequently used techniques for pattern selection that utilize frequency properties. RESULTS We have compared the number and length of the patterns eventually selected, classification performance, and pattern and model interpretability. We show that discretization has a great impact on the accuracy of the classification model, but that a trade off must be found between classification accuracy and the physicians' capacity to interpret the patterns obtained. We have, therefore, opted to use expert discretization without losing too much accuracy. We have also identified that the experiments combining threshold and non-overlapping confidence intervals (Option 4) obtained the fewest number of patterns but also with the smallest size, thus implying the loss of an acceptable accuracy as regards clinician interpretation. CONCLUSIONS A method for the classification of patients’ survival can benefit from the use of sequential patterns, since these patterns consider knowledge about the temporal evolution of the variables in the case of ICBU. We have proved that the DOR can be used in several ways, and that it is a suitable measure with which to select discriminative and interpretable quality patterns.

Semantic Textual Similarity in Japanese Clinical Domain Texts Using BERT

Background Semantic textual similarity (STS) captures the degree of semantic similarity between texts. It plays an important role in many natural language processing applications such as text summarization, question answering, machine translation, information retrieval, dialog systems, plagiarism detection, and query ranking. STS has been widely studied in the general English domain. However, there exists few resources for STS tasks in the clinical domain and in languages other than English, such as Japanese. Objective The objective of this study is to capture semantic similarity between Japanese clinical texts (Japanese clinical STS) by creating a Japanese dataset that is publicly available. Materials We created two datasets for Japanese clinical STS: (1) Japanese case reports (CR dataset) and (2) Japanese electronic medical records (EMR dataset). The CR dataset was created from publicly available case reports extracted from the CiNii database. The EMR dataset was created from Japanese electronic medical records. Methods We used an approach based on bidirectional encoder representations from transformers (BERT) to capture the semantic similarity between the clinical domain texts. BERT is a popular approach for transfer learning and has been proven to be effective in achieving high accuracy for small datasets. We implemented two Japanese pretrained BERT models: a general Japanese BERT and a clinical Japanese BERT. The general Japanese BERT is pretrained on Japanese Wikipedia texts while the clinical Japanese BERT is pretrained on Japanese clinical texts. Results The BERT models performed well in capturing semantic similarity in our datasets. The general Japanese BERT outperformed the clinical Japanese BERT and achieved a high correlation with human score (0.904 in the CR dataset and 0.875 in the EMR dataset). It was unexpected that the general Japanese BERT outperformed the clinical Japanese BERT on clinical domain dataset. This could be due to the fact that the general Japanese BERT is pretrained on a wide range of texts compared with the clinical Japanese BERT.

FAIRifying Clinical Studies Metadata: A Registry for the Biomedical Research

The data produced during a research project are too often collected for the sole purpose of the study, therefore hindering profitable reuse in similar contexts. The growing need to counteract this trend has recently led to the formalization of the FAIR principles that aim to make (meta)data Findable, Accessible, Interoperable and Reusable, for humans and machines. Since their introduction, efforts are ongoing to encourage FAIR principles adoption and to implement solutions based on them. This paper reports on the FAIR-compliant registry we developed to collect and serve metadata describing clinical trials. The design of the registry is based on the FAIR Data Point (FDP) specifications, the state-of-the-art reference for FAIRified metadata sharing. To map the metadata relevant to our use case, we have extended the DCAT-based semantic model of the FDP adopting well-established ontologies in the biomedical and clinical domain, like the Semanticscience Integrated Ontology (SIO). Current implementation is based on the Molgenis software and provides both a user interface and a REST API for metadata discovering. At present the registry is being loaded with the metadata of the 18 clinical studies included in the ‘I FAIR Program’, a project finalised to the dissemination of FAIR best practices among the clinical researchers in Sardinia (Italy). After a testing phase, the registry will be publicly available, while the new model and the source code will be released open source.

DeIDNER Corpus: Annotation of Clinical Discharge Summary Notes for Named Entity Recognition Using BRAT Tool

Named Entity Recognition (NER) aims to identify and classify entities into predefined categories is a critical pre-processing task in Natural Language Processing (NLP) pipeline. Readily available off-the-shelf NER algorithms or programs are trained on a general corpus and often need to be retrained when applied on a different domain. The end model’s performance depends on the quality of named entities generated by these NER models used in the NLP task. To improve NER model accuracy, researchers build domain-specific corpora for both model training and evaluation. However, in the clinical domain, there is a dearth of training data because of privacy reasons, forcing many studies to use NER models that are trained in the non-clinical domain to generate NER feature-set. Thus, influencing the performance of the downstream NLP tasks like information extraction and de-identification. In this paper, our objective is to create a high quality annotated clinical corpus for training NER models that can be easily generalizable and can be used in a downstream de-identification task to generate named entities feature-set.

Sex as a Prognostic Factor in Systematic Reviews: Challenges and Lessons Learned

Sex is a common baseline factor collected in studies that has the potential to be a prognostic factor (PF) in several clinical areas. In recent years, research on sex as a PF has increased; however, this influx of new studies frequently shows conflicting results across the same treatment or disease state. Thus, systematic reviews (SRs) addressing sex as a PF may help us to better understand diseases and further personalize healthcare. We wrote this article to offer insights into the challenges we encountered when conducting SRs on sex as a PF and suggestions on how to overcome these obstacles, regardless of the clinical domain. When carrying out a PF SR with sex as the index factor, it is important to keep in mind the modifications that must be made in various SR stages, such as modifying the PF section of CHARMS-PF, adjusting certain sections of QUIPS and extracting data on the sex and gender terms used throughout the studies. In this paper, we provide an overview of the lessons learned from carrying out our reviews on sex as a PF in different disciplines and now call on researchers, funding agencies and journals to realize the importance of studying sex as a PF.