Health Policy. 2023 Jan;127:44-50. doi: 10.1016/j.healthpol.2022.10.010. Epub 2022 Oct 21.

ABSTRACT

BACKGROUND: In line with affordability and equity principles, Medicare-Australia's universal health care program-has measures to contain out-of-pocket (OOP) costs, particularly for lower income households. This study examined the distribution of OOP costs for Medicare-subsidised out-of-hospital services and prescription medicines in Australian households, according to their ability to pay.

METHODS: OOP costs for out-of-hospital services and medicines in 2017-18 were estimated for each household, using 2016 Australian Census data linked to Medicare Benefits Schedule (MBS) and Pharmaceutical Benefit Scheme (PBS) claims. We derived household disposable income by combining income information from the Census linked to income tax and social security data. We quantified OOP costs as a proportion of equivalised household disposable income and calculated Kakwani progressivity indices (K).

RESULTS: Using data from 82% (n = 6,830,365) of all Census private households, OOP costs as a percentage of equivalised household disposable income decreased from 1.16% in the poorest decile to 0.63% in the richest decile for MBS services, and from 1.35% to 0.35% for PBS medicines. The regressive trend was less pronounced for MBS services (K = -0.06), with percentage OOP cost relatively stable between the 2nd and 9th income deciles; while percentage OOP cost decreased with increasing income for PBS medicines (K = -0.24).

CONCLUSION: OOP costs for out-of-hospital Medicare services were mildly regressive while those for prescription medicines were distinctly regressive. Actions to reduce inequity in OOP costs, particularly for medicines, should be considered.

PMID:36456400 | DOI:10.1016/j.healthpol.2022.10.010

Lancet. 2022 Nov;400 Suppl 1:S29. doi: 10.1016/S0140-6736(22)02239-5.

ABSTRACT

BACKGROUND: The Family Nurse Partnership (FNP) is an early home visiting service supporting young mothers. A randomised controlled trial of FNP in England found no effect on short-term primary outcomes or maltreatment in children up to age 7 years, but positive impacts on some educational outcomes. We report preliminary results of a national evaluation of FNP using linked administrative data.

METHODS: We constructed a cohort of all mothers in England aged 13-19 years who gave birth between April 1, 2010, and March 31, 2019, to their firstborn child or children, using linked administrative data from hospital admissions (Hospital Episode Statistics) and education and social care (National Pupil Database). We evaluated differences in a range of policy relevant child and maternal outcomes, comparing mothers who were enrolled in FNP with those who were not, using propensity score matching.

FINDINGS: Of 110 960 mothers in our linked cohort, 26 290 (24%) were enrolled in FNP. FNP mothers were younger, more deprived, and more likely to have adversity or social care histories than mothers not enrolled. Compared with mothers not enrolled in FNP, those in FNP did not have fewer unplanned hospital admissions for injury or maltreatment in children by age 2 years, lower rates of children looked after in out-of-home care by age 7 years, or improved maternal outcomes, but were more likely to achieve a good level of development at school entry. We present findings among subgroups of younger maternal age (13-15 years), increased deprivation according to quintile of Index of Multiple Deprivation, and adversity and social care history. We also present sensitivity analyses that aim to minimise confounding.

INTERPRETATION: Our study supports findings from previous trials of FNP showing little benefit for measured child maltreatment and maternal outcomes, but some evidence of benefit for school readiness. Interpretation of results needs careful consideration of the impact of residual confounding due to unmeasured or undisclosed factors (eg, family violence) linked to targeting of FNP to higher risk mothers, and surveillance bias.

FUNDING: National Institute for Health and Care Research.

PMID:36448115 | DOI:10.1016/S0140-6736(22)02239-5

Accid Anal Prev. 2023 Jan;179:106897. doi: 10.1016/j.aap.2022.106897. Epub 2022 Nov 23.

NO ABSTRACT

PMID:36434986 | DOI:10.1016/j.aap.2022.106897

Int J Environ Res Public Health. 2022 Nov 15;19(22):15012. doi: 10.3390/ijerph192215012.

ABSTRACT

Social media data reveal patterns of knowledge, attitudes, and behaviours of users on a range of topics. This study analysed 4398 tweets gathered between 17 January 2022 and 3 February 2022 related to ecosystem services, using the keyword and hashtag "ecosystem services". The Microsoft Excel plugin, NodeXL was used for social and semantic network analysis. The results reveal a loosely dense network in which information is conveyed slowly, with homogeneous, medium-sized subgroups typical of the community cluster structure. Citizens, NGOs, and governmental administrations emerged as the main gatekeepers of information in the network. Various semantic themes emerged such as the protection of natural capital for the sustainable production of ecosystem services; nature-based solutions to protect human structures and wellbeing against natural hazards; socio-ecological systems as the interaction between human beings and the environment; focus on specific services such as the storage of atmospheric CO2 and the provision of food. In conclusion, the perception of social users of the role of ecosystem services can help policymakers and forest managers to outline and implement efficient forest management strategies and plans.

PMID:36429730 | DOI:10.3390/ijerph192215012

Lancet. 2022 Nov;400 Suppl 1:S29. doi: 10.1016/S0140-6736(22)02239-5.

ABSTRACT

BACKGROUND: The Family Nurse Partnership (FNP) is an early home visiting service supporting young mothers. A randomised controlled trial of FNP in England found no effect on short-term primary outcomes or maltreatment in children up to age 7 years, but positive impacts on some educational outcomes. We report preliminary results of a national evaluation of FNP using linked administrative data.

METHODS: We constructed a cohort of all mothers in England aged 13-19 years who gave birth between April 1, 2010, and March 31, 2019, to their firstborn child or children, using linked administrative data from hospital admissions (Hospital Episode Statistics) and education and social care (National Pupil Database). We evaluated differences in a range of policy relevant child and maternal outcomes, comparing mothers who were enrolled in FNP with those who were not, using propensity score matching.

FINDINGS: Of 110 960 mothers in our linked cohort, 26 290 (24%) were enrolled in FNP. FNP mothers were younger, more deprived, and more likely to have adversity or social care histories than mothers not enrolled. Compared with mothers not enrolled in FNP, those in FNP did not have fewer unplanned hospital admissions for injury or maltreatment in children by age 2 years, lower rates of children looked after in out-of-home care by age 7 years, or improved maternal outcomes, but were more likely to achieve a good level of development at school entry. We present findings among subgroups of younger maternal age (13-15 years), increased deprivation according to quintile of Index of Multiple Deprivation, and adversity and social care history. We also present sensitivity analyses that aim to minimise confounding.

INTERPRETATION: Our study supports findings from previous trials of FNP showing little benefit for measured child maltreatment and maternal outcomes, but some evidence of benefit for school readiness. Interpretation of results needs careful consideration of the impact of residual confounding due to unmeasured or undisclosed factors (eg, family violence) linked to targeting of FNP to higher risk mothers, and surveillance bias.

FUNDING: National Institute for Health and Care Research.

PMID:36426444 | DOI:10.1016/S0140-6736(22)02239-5

BMJ Health Care Inform. 2022 Nov;29(1):e100671. doi: 10.1136/bmjhci-2022-100671.

ABSTRACT

OBJECTIVE: Patients frequently miss their medical appointments. Therefore, short message service (SMS) has been used as a strategy for medical and healthcare service appointment reminders. This systematic review aimed to identify barriers to SMS appointment reminders across African regions.

METHODS: PubMed, Google Scholar, Semantic Scholar and Web of Science were used for searching, and hand searching was done. Original studies written in English, conducted in Africa, and published since 1 December 2018, were included. The standard quality assessment checklist was used for the quality appraisal of the included studies. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses flowchart diagram was used for study selection and screening, and any disagreements were resolved via discussions.

RESULTS: A total of 955 articles were searched, 521 studies were removed due to duplication and 105 studies were assessed for eligibility. Consequently, nine studies met the inclusion criteria. Five out of nine included studies were done by randomised control trials. The barriers that hampered patients, mothers and other parental figures of children when they were notified via SMS of medical and health services were identified. Among the 11 identified barriers, illiteracy, issues of confidentiality, familiarised text messages, inadequate information communication technology infrastructure, being a rural resident and loss of mobile phones occurred in at least two studies.

CONCLUSIONS: SMS is an effective and widely accepted appointment reminder tool. However, it is hampered by numerous barriers. Hence, we gathered summarised information about users' barriers to SMS-based appointment reminders. Therefore, stakeholders should address existing identified barriers for better Mhealth interventions.

PROSPERO REGISTRATION NUMBER: CRD42022296559.

PMID:36423934 | DOI:10.1136/bmjhci-2022-100671

Front Res Metr Anal. 2022 Nov 7;7:982435. doi: 10.3389/frma.2022.982435. eCollection 2022.

ABSTRACT

With the Square Kilometer Array (SKA) project and the new Multi-Purpose Reactor (MPR) soon coming on-line, South Africa and other collaborating countries in Africa will need to make the management, analysis, publication, and curation of "Big Scientific Data" a priority. In addition, the recent draft Open Science policy from the South African Department of Science and Innovation (DSI) requires both Open Access to scholarly publications and research outputs, and an Open Data policy that facilitates equal opportunity of access to research data. The policy also endorses the deposit, discovery and dissemination of data and metadata in a manner consistent with the FAIR principles - making data Findable, Accessible, Interoperable and Re-usable (FAIR). The challenge to achieve Open Science in Africa starts with open access for research publications and the provision of persistent links to the supporting data. With the deluge of research data expected from the new experimental facilities in South Africa, the problem of how to make such data FAIR takes center stage. One promising approach to make such scientific datasets more "Findable" and "Interoperable" is to rely on the Dataset representation of the Schema.org vocabulary which has been endorsed by all the major search engines. The approach adds some semantic markup to Web pages and makes scientific datasets more "Findable" by search engines. This paper does not address all aspects of the Open Science agenda but instead is focused on the management and analysis challenges of the "Big Scientific Data" that will be produced by the SKA project. The paper summarizes the role of the SKA Regional Centers (SRCs) and then discusses the goal of ensuring reproducibility for the SKA data products. Experiments at the new MPR neutron source will also have to conform to the DSI's Open Science policy. The Open Science and FAIR data practices used at the ISIS Neutron source at the Rutherford Appleton Laboratory in the UK are then briefly described. The paper concludes with some remarks about the important role of interdisciplinary teams of research software engineers, data engineers and research librarians in research data management.

PMID:36419537 | PMC:PMC9676438 | DOI:10.3389/frma.2022.982435

Intern Emerg Med. 2022 Nov 19. doi: 10.1007/s11739-022-03151-1. Online ahead of print.

NO ABSTRACT

PMID:36401715 | DOI:10.1007/s11739-022-03151-1

Healthc Inform Res. 2022 Oct;28(4):332-342. doi: 10.4258/hir.2022.28.4.332. Epub 2022 Oct 31.

ABSTRACT

OBJECTIVES: Symptomatic treatment is an essential component in the overall treatment of multiple sclerosis (MS). However, knowledge in this regard is confusing and scattered. Physicians also have challenges in choosing symptomatic treatment based on the patient's condition. To share, update, and reuse this knowledge, the aim of this study was to provide an ontology for MS symptomatic treatment.

METHODS: The Symptomatic Treatment of Multiple Sclerosis Ontology (STMSO) was developed according to Ontology Development 101 and a guideline for developing good ontologies in the biomedical domain. We obtained knowledge and rules through a systematic review and entered this knowledge in the form of classes and subclasses in the ontology. We then mapped the ontology using the Basic Formal Ontology (BFO) and Ontology for General Medical Sciences (OGMS) as reference ontologies. The ontology was built using Protégé Editor in the Web Ontology Language format. Finally, an evaluation was done by experts using criterion-based approaches in terms of accuracy, clarity, consistency, and completeness.

RESULTS: The knowledge extraction phase identified 110 articles related to the ontology in the form of 626 classes, 40 object properties, and 139 rules. Five general classes included "patient," "symptoms," "pharmacological treatment," "treatment plan," and "measurement index." The evaluation in terms of standards for biomedical ontology showed that STMSO was accurate, clear, consistent, and complete.

CONCLUSIONS: STMSO is the first comprehensive semantic representation of the symptomatic treatment of MS and provides a major step toward the development of intelligent clinical decision support systems for symptomatic MS treatment.

PMID:36380430 | DOI:10.4258/hir.2022.28.4.332

BMC Geriatr. 2022 Nov 15;22(1):858. doi: 10.1186/s12877-022-03579-2.

ABSTRACT

BACKGROUND: Routinely collected health administrative data can be used to estimate the prevalence or incidence of dementia at a population level but can be inaccurate. This study aimed to examine the accuracy of hospital and death data for diagnosing dementia compared with a clinical diagnosis in community dwelling older men in Australia.

METHODS: We performed a retrospective analysis of the Concord Health and Ageing in Men Project (CHAMP) in Sydney, Australia. Of the 1705 men aged ≥70 years in the CHAMP study, 1400 had available linked administrative data records from 1 year prior to 1 year post the date of clinical dementia diagnosis. The primary outcome was the accuracy of dementia diagnosis using linked administrative data records compared to clinical dementia diagnosis. The linked data diagnosis was based on hospital and death records for the 1 year pre and post the clinical diagnosis. Clinical dementia diagnosis was a two-stage process with initial screening, followed by clinical assessment for those meeting a validated cut-off. A final clinical diagnosis of dementia based on the Diagnostic and Statistical Manual of Mental Disorders (4th edition) criteria was reached by a consensus panel.

RESULTS: Administrative data identified 28 participants as having dementia, compared to 88 identified through clinical assessment. Administrative data had a sensitivity of 20% (95% CI: 13-30%, 18/88), specificity of 99% (95% CI: 99-100%, 1301/1312), positive predictive value (PPV) of 62% (95% CI: 44-77%), negative predictive value of 95% (95% CI: 94-95%), positive likelihood ratio of 24.4 (95% CI: 11.9-50.0) and negative likelihood ratio of 0.80 (0.72-0.89).

CONCLUSIONS: Administrative hospital and death data has limited accuracy for dementia diagnosis with poor sensitivity and PPV. The prevalence of dementia is likely underestimated using hospital and deaths data.

PMID:36380274 | DOI:10.1186/s12877-022-03579-2

Eur J Haematol. 2023 Mar;110(3):243-252. doi: 10.1111/ejh.13899. Epub 2022 Nov 25.

ABSTRACT

Studies have shown higher survival rates for patients with Hodgkin lymphoma (HL) treated within clinical trials compared to patients treated outside clinical trials. However, endpoints are often limited to overall survival (OS). In this retrospective cohort study, we investigated the effect of trial participation on OS, the incidence of relapse, second cancer, and cardiovascular disease (CVD). The study population consisted of patients with HL, aged between 14 and 51 years at diagnosis, who started their treatment between 1962 and 2002 at three Dutch cancer centres. Patients were either included in the EORTC Lymphoma Group trials (H1-H9) or treated according to standard guidelines at the time. After adjusting for differences in baseline characteristics, trial participation was associated with longer OS (median OS: 29.4 years [95%CI: 27.0-31.6] for treatment inside trials versus 27.4 years [95%CI: 26.0-28.5] for treatment outside trials, p = .046), a lower incidence of relapse (HR = 0.79, 95%CI: 0.63-0.98, p = .036) and a higher incidence of CVD (HR = 1.49, 95%CI: 1.23-1.79, p < .001). The trial effect for CVD was present only for patients treated before 1983. No evidence of differences in the incidence of second cancer was found. Consequently, essential results from clinical trials should be implemented into standard practice without undue delay.

PMID:36369842 | DOI:10.1111/ejh.13899

Sensors (Basel). 2022 Nov 1;22(21):8393. doi: 10.3390/s22218393.

ABSTRACT

Background: The planetary rover is an essential platform for planetary exploration. Visual semantic segmentation is significant in the localization, perception, and path planning of the rover autonomy. Recent advances in computer vision and artificial intelligence brought about new opportunities. A systematic literature review (SLR) can help analyze existing solutions, discover available data, and identify potential gaps. Methods: A rigorous SLR has been conducted, and papers are selected from three databases (IEEE Xplore, Web of Science, and Scopus) from the start of records to May 2022. The 320 candidate studies were found by searching with keywords and bool operators, and they address the semantic terrain segmentation in the navigation vision of planetary rovers. Finally, after four rounds of screening, 30 papers were included with robust inclusion and exclusion criteria as well as quality assessment. Results: 30 studies were included for the review, and sub-research areas include navigation (16 studies), geological analysis (7 studies), exploration efficiency (10 studies), and others (3 studies) (overlaps exist). Five distributions are extendedly depicted (time, study type, geographical location, publisher, and experimental setting), which analyzes the included study from the view of community interests, development status, and reimplementation ability. One key research question and six sub-research questions are discussed to evaluate the current achievements and future gaps. Conclusions: Many promising achievements in accuracy, available data, and real-time performance have been promoted by computer vision and artificial intelligence. However, a solution that satisfies pixel-level segmentation, real-time inference time, and onboard hardware does not exist, and an open, pixel-level annotated, and the real-world data-based dataset is not found. As planetary exploration projects progress worldwide, more promising studies will be proposed, and deep learning will bring more opportunities and contributions to future studies. Contributions: This SLR identifies future gaps and challenges by proposing a methodical, replicable, and transparent survey, which is the first review (also the first SLR) for semantic terrain segmentation in the navigation vision of planetary rovers.

PMID:36366089 | DOI:10.3390/s22218393

Sci Total Environ. 2022 Nov 7:159981. doi: 10.1016/j.scitotenv.2022.159981. Online ahead of print.

ABSTRACT

Plastic pollution control, involving the whole life cycle management of plastic production, consumption, sorting, recycling, and disposal, has become necessary for global sustainable development. Research on public attitudes is vital to understanding whether plastic pollution control policies are being successfully implemented and the degree to which the public is involved. However, few studies have assessed public attitudes toward plastic pollution control from the whole life cycle perspective, especially using big data. Based on China's whole life cycle management policy of plastics, this study collected more than 200,000 relevant comments and user information from Sina Weibo to analyze and evaluate public attitudes and opinions toward plastic pollution control. Spatial-temporal analysis was conducted to discover the regional and temporal differences in public attention. Using a sentiment classification method based on semantic analysis, the emotional tendencies of the public attitudes toward ten subdivided plastic pollution control links were studied. It was found that more people held a positive attitude and paid more attention to reusing and sorting links, while the negative emotions were concentrated on the collection and sorting links. Using a topic modeling method, the negative opinions in various links were revealed, such as lack of supervision and industry standards; over packaging or insufficient packaging; food safety problems caused by the reuse; high costs, poor use and possibly greater waste of substitutes; unclear sorting rules and insufficient supporting measures. Graph theory was applied to display these opinions. Finally, some policy implications derived from the discussions are given.

PMID:36356749 | DOI:10.1016/j.scitotenv.2022.159981

Artif Intell Rev. 2022;55(8):6185-6206. doi: 10.1007/s10462-022-10149-w. Epub 2022 Apr 7.

ABSTRACT

In his seminal paper of 2004, Ulrich Junker proposed the QuickXplain algorithm, which provides a divide-and-conquer computation strategy to find within a given set an irreducible subset with a particular (monotone) property. Beside its original application in the domain of constraint satisfaction problems, the algorithm has since then found widespread adoption in areas as different as model-based diagnosis, recommender systems, verification, or the Semantic Web. This popularity is due to the frequent occurrence of the problem of finding irreducible subsets on the one hand, and to QuickXplain's general applicability and favorable computational complexity on the other hand. However, although (we regularly experience) people are having a hard time understanding QuickXplain and seeing why it works correctly, a proof of correctness of the algorithm has never been published. This is what we account for in this work, by explaining QuickXplain in a novel tried and tested way and by presenting an intelligible formal proof of it. Apart from showing the correctness of the algorithm and excluding the later detection of errors (proof and trust effect), the added value of the availability of a formal proof is, e.g., (i) that the workings of the algorithm often become completely clear only after studying, verifying and comprehending the proof (didactic effect), (ii) that the shown proof methodology can be used as a guidance for proving other recursive algorithms (transfer effect), and (iii) the possibility of providing "gapless" correctness proofs of systems that rely on (results computed by) QuickXplain, such as numerous model-based debuggers (completeness effect).

PMID:36337611 | PMC:PMC9622537 | DOI:10.1007/s10462-022-10149-w

Stud Health Technol Inform. 2022 Nov 3;299:157-162. doi: 10.3233/SHTI220975.

ABSTRACT

Electronic Health Record (EHR) systems currently in use are not designed for widely interoperable longitudinal health data. Therefore, EHR data cannot be properly shared, managed and analyzed. In this article, we propose two approaches to making EHR data more comprehensive and FAIR (Findable, Accessible, Interoperable, and Reusable) and thus more useful for diagnosis and clinical research. Firstly, the data modeling based on the LinkML framework makes the data interoperability more realistic in diverse environments with various experts involved. We show the first results of how diverse health data can be integrated based on an easy-to-understand data model and without loss of available clinical knowledge. Secondly, decentralizing EHRs contributes to the higher availability of comprehensive and consistent EHR data. We propose a technology stack for decentralized EHRs and the reasons behind this proposal. Moreover, the two proposed approaches empower patients because their EHR data can become more available, understandable, and usable for them, and they can share their data according to their needs and preferences. Finally, we explore how the users of the proposed solution could be involved in the process of its validation and adoption.

PMID:36325857 | DOI:10.3233/SHTI220975

Stud Health Technol Inform. 2022 Nov 3;299:44-52. doi: 10.3233/SHTI220962.

ABSTRACT

The advancement of healthcare towards P5 medicine requires communication and cooperation between all actors and institutions involved. Interoperability must go beyond integrating data from different sources and include the understanding of the meaning of the data in the context of concepts and contexts they represent for a specific use case. In other words, we have to advance from data sharing through sharing semantics up to sharing clinical and medical knowledge. According to the Good Modeling Best Practices, we have to start with describing the real-world business system by domain experts using Domain Ontologies before transforming it into an information and communication technology (ICT) system, thereafter specifying the informational components and then transforming the system into an implementable solution. Any representation style - in the system development process acc. to ISO 10746 called system view - is defined by a related ontology, to be distinguished from real-world domain ontologies representing the knowledge spaces of involved disciplines. The system enabling such representational transformation shall also support versioning as well as the management of historical evolutions. One of such systems is the Common Terminology Service Release 2 (CTS2), which is a standard that allows the complete management of terminological contents. The main objective of this work is to present the choices we made to transform an ontology, written in the standard Ontology Web Language (OWL), into the CTS2 objects. We tested our transformation approach with the Alzheimer's Disease Ontology. We managed to map all the elements of the considered ontology to CTS2 terminological resources, except for a subset of elements such as the equivalentClass derived from restrictions on other classes.

PMID:36325845 | DOI:10.3233/SHTI220962

Front Psychol. 2022 Oct 17;13:1005429. doi: 10.3389/fpsyg.2022.1005429. eCollection 2022.

ABSTRACT

An online platform is a setting where users may express their attitude in text or visual content. The doctrine thinking in consumer psychology is that greater perceived product value (e.g., more product features or lower price) gives more positive consumer attitude. Because of different types of platforms, however, online users might form their product/brand attitudes in different ways. We gathered 7,264 lines of online reviews about two famous brands on two types of social media platforms: online text-based forums and live-streaming platforms. The data were collected through a web crawler, and semantic analysis was employed to process the data before hypothesis testing. The findings of this study indicate that users' perception of product features, price levels and brand culture significantly influence user attitude. The more product characteristics communicated on online platforms, the more difficult to formulate a positive user attitude, and users tend to have more positive attitude with higher perceived price. Compared with traditional text-based platforms, contents in live-streaming platforms (e.g., Tik Tok) with less product features, wider culture distance and lower perceived price are favored among users.

PMID:36324787 | PMC:PMC9619103 | DOI:10.3389/fpsyg.2022.1005429

Int J Clin Pract. 2022 Oct 18;2022:6807484. doi: 10.1155/2022/6807484. eCollection 2022.

ABSTRACT

Today, healthcare has become one of the largest and most fast-paced industries due to the rapid development of digital healthcare technologies. The fundamental thing to enhance healthcare services is communicating and linking massive volumes of available healthcare data. However, the key challenge in reaching this ambitious goal is letting the information exchange across heterogeneous sources and methods as well as establishing efficient tools and techniques. Semantic Web (SW) technology can help to tackle these problems. They can enhance knowledge exchange, information management, data interoperability, and decision support in healthcare systems. They can also be utilized to create various e-healthcare systems that aid medical practitioners in making decisions and provide patients with crucial medical information and automated hospital services. This systematic literature review (SLR) on SW in healthcare systems aims to assess and critique previous findings while adhering to appropriate research procedures. We looked at 65 papers and came up with five themes: e-service, disease, information management, frontier technology, and regulatory conditions. In each thematic research area, we presented the contributions of previous literature. We emphasized the topic by responding to five specific research questions. We have finished the SLR study by identifying research gaps and establishing future research goals that will help to minimize the difficulty of adopting SW in healthcare systems and provide new approaches for SW-based medical systems' progress.

PMID:36320897 | PMC:PMC9596238 | DOI:10.1155/2022/6807484

Web Semant. 2022 Oct 13:100760. doi: 10.1016/j.websem.2022.100760. Online ahead of print.

ABSTRACT

In this paper, we present Knowledge4COVID-19, a framework that aims to showcase the power of integrating disparate sources of knowledge to discover adverse drug effects caused by drug-drug interactions among COVID-19 treatments and pre-existing condition drugs. Initially, we focus on constructing the Knowledge4COVID-19 knowledge graph (KG) from the declarative definition of mapping rules using the RDF Mapping Language. Since valuable information about drug treatments, drug-drug interactions, and side effects is present in textual descriptions in scientific databases (e.g., DrugBank) or in scientific literature (e.g., the CORD-19, the Covid-19 Open Research Dataset), the Knowledge4COVID-19 framework implements Natural Language Processing. The Knowledge4COVID-19 framework extracts relevant entities and predicates that enable the fine-grained description of COVID-19 treatments and the potential adverse events that may occur when these treatments are combined with treatments of common comorbidities, e.g., hypertension, diabetes, or asthma. Moreover, on top of the KG, several techniques for the discovery and prediction of interactions and potential adverse effects of drugs have been developed with the aim of suggesting more accurate treatments for treating the virus. We provide services to traverse the KG and visualize the effects that a group of drugs may have on a treatment outcome. Knowledge4COVID-19 was part of the Pan-European hackathon#EUvsVirus in April 2020 and is publicly available as a resource through a GitHub repository and a DOI.

PMID:36268112 | PMC:PMC9558693 | DOI:10.1016/j.websem.2022.100760

J Pathol Inform. 2022 Sep 15;13:100139. doi: 10.1016/j.jpi.2022.100139. eCollection 2022.

ABSTRACT

Exa-scale volumes of medical data have been produced for decades. In most cases, the diagnosis is reported in free text, encoding medical knowledge that is still largely unexploited. In order to allow decoding medical knowledge included in reports, we propose an unsupervised knowledge extraction system combining a rule-based expert system with pre-trained Machine Learning (ML) models, namely the Semantic Knowledge Extractor Tool (SKET). Combining rule-based techniques and pre-trained ML models provides high accuracy results for knowledge extraction. This work demonstrates the viability of unsupervised Natural Language Processing (NLP) techniques to extract critical information from cancer reports, opening opportunities such as data mining for knowledge extraction purposes, precision medicine applications, structured report creation, and multimodal learning. SKET is a practical and unsupervised approach to extracting knowledge from pathology reports, which opens up unprecedented opportunities to exploit textual and multimodal medical information in clinical practice. We also propose SKET eXplained (SKET X), a web-based system providing visual explanations about the algorithmic decisions taken by SKET. SKET X is designed/developed to support pathologists and domain experts in understanding SKET predictions, possibly driving further improvements to the system.

PMID:36268087 | PMC:PMC9577130 | DOI:10.1016/j.jpi.2022.100139