Design and architecture of the CARA infrastructure for visualising and benchmarking patient data from general practice.

OBJECTIVE: Collaborate, Analyse, Research and Audit (CARA) project set out to provide an infrastructure to enable Irish general practitioners (GPs) to use their routinely collected patient management software (PMS) data to better understand their patient population, disease management and prescribing through data dashboards. This paper explains the design and development of the CARA infrastructure. METHODS: The first exemplar dashboard was developed with GPs and focused on antibiotic prescribing to develop and showcase the proposed infrastructure. The data integration process involved extracting, loading and transforming de-identified patient data into data models which connect to the interactive dashboards for GPs to visualise, compare and audit their data. RESULTS: The architecture of the CARA infrastructure includes two main sections: extract, load and transform process (ELT, de-identified patient data into data models) and a Representational State Transfer Application Programming Interface (REST API) (which provides the security barrier between the data models and their visualisation on the CARA dashboard). CARAconnect was created to facilitate the extraction and de-identification of patient data from the practice database. DISCUSSION: The CARA infrastructure allows seamless connectivity with and compatibility with the main PMS in Irish general practice and provides a reproducible template to access and visualise patient data. CARA includes two dashboards, a practice overview and a topic-specific dashboard (example focused on antibiotic prescribing), which includes an audit tool, filters (within practice) and between-practice comparisons. CONCLUSION: CARA supports evidence-based decision-making by providing GPs with valuable insights through interactive data dashboards to optimise patient care, identify potential areas for improvement and benchmark their performance against other practices.Supplementary file 1. Graphical abstract.

Collaboration to reduce antibiotic use and resistance and identify opportunities for improvement and awareness (CARA).

INTRODUCTION: CARA is a five-year Health Research Board (HRB) project. Superbugs cause resistant infections that are difficult to treat and pose a serious threat to human health. Providing tools to explore the prescription of antibiotics by GPs may help identify gaps where improvements can be made. CARA's aim is to combine, link and visualise data on infections, prescribing and other healthcare information. METHODS: The CARA team is creating a dashboard to provide GPs with a tool to visualise their own practice data and compare this with other GPs in Ireland. Anonymous patient data can be uploaded and visualised to show details, current trends and changes in infections and prescribing. The CARA platform will also provide easy options to generate audit reports. RESULTS: After registration, a tool for anonymous data upload will be provided. Through this uploader, data will be used to create instant graphs and overviews as well as comparisons with other GP practices. With selection options, graphical presentations can be further explored or audits generated. Currently, few GPs are involved in the development of the dashboard to ensure it will be efficient. Examples of the dashboard will be shown at the conference. DISCUSSION: The CARA project will provide GPs with a tool to access, analyse and understand their patient data. GPs will have secure accounts accessible through the CARA website to allow easy anonymous data upload in a few steps. The dashboard will show comparisons of their prescribing with other (unknown) practices, identify areas for improvement and conduct audit reports.

Boundary heat diffusion classifier for a semi-supervised learning in a multilayer network embedding.

The scarcity of high-quality annotations in many application scenarios has recently led to an increasing interest in devising learning techniques that combine unlabeled data with labeled data in a network. In this work, we focus on the label propagation problem in multilayer networks. Our approach is inspired by the heat diffusion model, which shows usefulness in machine learning problems such as classification and dimensionality reduction. We propose a novel boundary-based heat diffusion algorithm that guarantees a closed-form solution with an efficient implementation. We experimentally validated our method on synthetic networks and five real-world multilayer network datasets representing scientific coauthorship, spreading drug adoption among physicians, two bibliographic networks, and a movie network. The results demonstrate the benefits of the proposed algorithm, where our boundary-based heat diffusion dominates the performance of the state-of-the-art methods.

Synergy Between Embedding and Protein Functional Association Networks for Drug Label Prediction Using Harmonic Function.

Semi-Supervised Learning (SSL)is an approach to machine learning that makes use of unlabeled data for training with a small amount of labeled data. In the context of molecular biology and pharmacology, one can take advantage of unlabeled data. For instance, to identify drugs and targets where a few genes are known to be associated with a specific target for drugs and considered as labeled data. Labeling the genes requires laboratory verification and validation. This process is usually very time consuming and expensive. Thus, it is useful to estimate the functional role of drugs from unlabeled data using computational methods. To develop such a model, we used openly available data resources to create (i)drugs and genes, (ii)genes and disease, bipartite graphs. We constructed the genetic embedding graph from the two bipartite graphs using Tensor Factorization methods. We integrated the genetic embedding graph with the publicly available protein functional association network. Our results show the usefulness of the integration by effectively predicting drug labels.

Corona citizens' science project-repeated surveys of the Irish response to COVID-19 and subsequent lockdown and restrictive measures.

BACKGROUND: Worldwide, many people have been affected by COVID-19, a novel respiratory illness, caused by a new type of coronavirus SARS-CoV2. The COVID-19 outbreak is considered a pandemic and has created a number of challenges for the general population, patients, and healthcare professionals. Lockdowns have been implemented to slow down the spread of the virus with the expectation that these restrictions will limit the number of cases, and hence the number of hospitalizations and ICU admissions. However, these restrictions, and in particular lockdowns, impact on the life of everyone living in Ireland. AIM: To record how the COVID-19 pandemic and subsequent restrictive measures impacted on people's activities, work, schooling, and childcare. METHODS: The Corona Citizens' Science Project was set up as a population-wide survey. A questionnaire was designed, and the survey was first launched on the 8th of April 2020. An overview of results was released in the press days later. Data was collected in four waves: April 8, April 22, May 6, and June 17, 2020. Each wave had core questions allowing to compare each wave, and wave-specific questions, to understand current impact of changing measures. RESULTS: Over four waves, 152,259 responses were collected. The mean age of respondents was 47 with about 10% over the age of 65. Around 75% were female and 85% had a higher degree. Nearly 70% of the respondents were in employment, and around 13% were retired. Up to 20% of the respondents were essential workers, and 10% of respondents indicated they were in receipt of the COVID-19 pandemic unemployment payment. Around 10% of the people who responded were living alone. The number of people talked to the previous day was on average 2.3 in the first survey; during the lockdown, this went up over time, and in the last survey, the mean was 3.9. The percentage of respondents who did not talk to anyone the previous day decreased from 40 to 22% over the waves. In the first wave, about 6% of respondents reported having had flu-like symptoms in the last 14 days, which declined to 3.3%, 2.5%, and 2.0% in waves 2, 3, and 4 respectively. Similarly, over the four waves, the respondents who indicated that someone they lived with had flu-like symptoms declined from 17 to 12%, 9%, and 11%. Throughout the four waves, nearly one third of people reported one or more underlying conditions. CONCLUSIONS: As a result of the COVID-19 pandemic, a number of restrictive measures, in particular lockdown, were implemented in Ireland to protect populations and healthcare systems. To record some of the major impacts on society, we launched a Corona Citizens Science Project, with the aim to support decision-making. This report provides detail of its findings.

Discovering Links Between Side Effects and Drugs Using a Diffusion Based Method.

Identifying the unintended effects of drugs (side effects) is a very important issue in pharmacological studies. The laboratory verification of associations between drugs and side effects requires costly, time-intensive research. Thus, an approach to predicting drug side effects based on known side effects, using a computational model, is highly desirable. To provide such a model, we used openly available data resources to model drugs and side effects as a bipartite graph. The drug-drug network is constructed using the word2vec model where the edges between drugs represent the semantic similarity between them. We integrated the bipartite graph and the semantic similarity graph using a matrix factorization method and a diffusion based model. Our results show the effectiveness of this integration by computing weighted (i.e., ranked) predictions of initially unknown links between side effects and drugs.

Linked data and online classifications to organise mined patterns in patient data.

In this paper, we investigate the use of web data resources in medicine, especially through medical classifications made available using the principles of Linked Data, to support the interpretation of patterns mined from patient care trajectories. Interpreting such patterns is naturally a challenge for an analyst, as it requires going through large amounts of results and access to sufficient background knowledge. We employ linked data, especially as exposed through the BioPortal system, to create a navigation structure within the patterns obtained form sequential pattern mining. We show how this approach provides a flexible way to explore data about trajectories of diagnoses and treatments according to different medical classifications.

Where to Publish and Find Ontologies? A Survey of Ontology Libraries.

One of the key promises of the Semantic Web is its potential to enable and facilitate data interoperability. The ability of data providers and application developers to share and reuse ontologies is a critical component of this data interoperability: if different applications and data sources use the same set of well defined terms for describing their domain and data, it will be much easier for them to "talk" to one another. Ontology libraries are the systems that collect ontologies from different sources and facilitate the tasks of finding, exploring, and using these ontologies. Thus ontology libraries can serve as a link in enabling diverse users and applications to discover, evaluate, use, and publish ontologies. In this paper, we provide a survey of the growing-and surprisingly diverse-landscape of ontology libraries. We highlight how the varying scope and intended use of the libraries a ects their features, content, and potential exploitation in applications. From reviewing eleven ontology libraries, we identify a core set of questions that ontology practitioners and users should consider in choosing an ontology library for finding ontologies or publishing their own. We also discuss the research challenges that emerge from this survey, for the developers of ontology libraries to address.

Decision support and knowledge management in oncology using hierarchical classification.

This paper presents the KASIMIR research project for the management of decision protocols in oncology. A decision protocol is a kind of decision tree implemented in an object-based representation formalism. A reasoner based on such a formalism and on hierarchical classification is coupled with a knowledge editor. This association provides an assistance for editing and maintenance of protocols, enabling the detection of errors and the comparison between versions of the protocol. In this way, a management of protocols takes fully advantage of the underlying knowledge representation and reasoning tools. This straightforward use of the protocol may be insufficient in some situations. Then, the protocol may have to be adapted for these situations. A study of protocol adaptation is presented. In particular a reasoner based on a combination of hierarchical classification and fuzzy logic is introduced.