FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386799605> ?p ?o ?g. }

• W4386799605 endingPage "454" @default.
• W4386799605 startingPage "451" @default.
• W4386799605 abstract "Ebbert et al1Ebbert J.O. Khan R.G. Leibovich B.C. Health care transformations merging traditional and digital medical practices.Mayo Clinic Proceedings: Digital Health. 2023; 1: 63-66Abstract Full Text Full Text PDF Google Scholar present an excellent assessment of models for collaboration between traditional and digital care providers with astute observations regarding the primary care landscape, where the greatest potential for direct competition and market disruption exists, and specialty care is where we will focus. Here, traditional providers hold an advantage over their digital counterparts by providing full diagnostic and management services, whereas digital providers must refer to multiple elements. As the authors state, opportunities exist for collaboration, but first there need to be models in place for equitable reimbursement. Regulations surrounding data transfer and health care provision may present further barriers. In the United States, barriers exist for data transfer and health care delivery between states, which may hinder patient access to digital providers, particularly in less populated rural states where financial incentives to operate may be lower. Like the United States, the UK health care regulatory framework is a patchwork of data protection and health care legislation. In the United Kingdom, the National Health Service digital provides the framework for digital transformation (DT): developing digital products and data services, working with health care providers and technology companies, and committing >$150 million to developing and testing artificial intelligence (AI) in pathology, radiology, and other specialties. Individual providers may develop or implement the technology and services they require. We view the future of digital providers in specialty care as providing innovative products and services to traditional providers to enhance care. Using the authors’ example of inflammatory bowel disease, approaching half of patients with Crohn disease in the United States use biologic therapy,2Yu H. MacIsaac D. Wong J.J. et al.Market share and costs of biologic therapies for inflammatory bowel disease in the USA.Aliment Pharmacol Ther. 2018; 47: 364-370https://doi.org/10.1111/apt.14430Crossref PubMed Scopus (121) Google Scholar often requiring intravenous administration, which may complicate care provision in a health care environment, and may complicate care provision by digital providers. Digital providers might, as suggested by Ebbert et al,1Ebbert J.O. Khan R.G. Leibovich B.C. Health care transformations merging traditional and digital medical practices.Mayo Clinic Proceedings: Digital Health. 2023; 1: 63-66Abstract Full Text Full Text PDF Google Scholar provide dietary advice and application-based support, but we would view these as outsourced services delivered on behalf of the traditional provider. A digital provider might also develop AI to improve efficiency and disease detection in endoscopy or medical imaging. We use hepatology and rare liver diseases as demonstrative examples for our argument. Digital transformation generates impact in hepatology both through broader application in health care, for example, efficiency gains from electronic health care records, referral portals, or robotic process automation, and by the application of digital technology specifically to liver disease (Figure 1). Rare liver disease lends itself to DT, and particularly to AI, in developing novel tools in diagnosis and management. Increasing disease burden and mortality3Liver disease profiles March 2023 update. Office for Health Improvement and Disparities.https://www.gov.uk/government/statistics/liver-disease-profiles-march-2023-update/liver-disease-profiles-march-2023-update#:∼:text=the%20fingertips%20platform.-,Main%20findings,in%20the%20past%2020%20yearsDate accessed: September 7, 2023Google Scholar with incompletely elucidated pathogenesis of important liver diseases indicate significant unmet needs, whereas the huge volumes of demographic characteristics, biochemical, radiological, and histological data routinely collected in these patients mean that the data volumes required for AI development are likely acquirable. Artificial intelligence in the form of machine learning (ML) and deep learning (DL) is opening new frontiers in disease diagnosis, risk stratification, and management. The current focus in hepatology is on common liver diseases such as metabolic-associated fatty liver disease, but there are examples of technology being developed or adapted for rarer liver diseases. Artificial intelligence in radiology has 2 categories: radiomics, using ML where a mathematical equation or series of equations are applied to images under close supervision, and DL systems, where convolutional neural networks extract information without the need for preprogramming. Digital companies are exploiting this technology to create innovative products such as Ferriscan (Resonance Health Limited), magnetic resonance cholangiopancreatography (MRCP+, Perspectum), and LiverMultiScan (Perspectum). Ferriscan uses radiomics to quantify liver iron. Magnetic resonance images produced using a standardized protocol are transferred electronically to the digital provider, who applies a proprietary algorithm to accurately quantify liver iron content, with the result conveyed to the referrer. This has now replaced liver biopsy (with its associated risk and expense) in patients suspected of iron overload,4European Association for the Study of the LiverEASL clinical practice guidelines on haemochromatosis.J Hepatol. 2022; 77: 479-502https://doi.org/10.1016/j.jhep.2022.03.033Abstract Full Text Full Text PDF PubMed Scopus (28) Google Scholar thereby reducing costs for traditional providers both in diagnosis and the avoidance of unnecessary venesections, providing a clear incentive for collaboration. In primary sclerosing cholangitis, radiological features may have prognostic value: early arterial peribiliary enhancement has been linked to higher risk scores and a poorer prognosis.5Mulinacci G. Cristoferi L. Palermo A. et al.Risk stratification in primary sclerosing cholangitis.Minerva Gastroenterol (Torino). 2023; 69: 84-94https://doi.org/10.23736/S2724-5985.20.02821-4Crossref Scopus (0) Google Scholar Quantitative MRCP+ is an imaging tool able to create three dimensional quantitative models of the biliary and pancreatic systems, such as volumetric analysis, automatic detection of regions of variation, and number, length, and severity of strictures.6Goldfinger M.H. Ridgway G.R. Ferreira C. et al.Quantitative MRCP imaging: accuracy, repeatability, reproducibility, and cohort-derived normative ranges.J Magn Reson Imaging. 2020; 52: 807-820https://doi.org/10.1002/jmri.27113Crossref Scopus (21) Google Scholar The MRCP+ correlates well with validated risk scoring systems and could improve diagnosis and prognostic models in primary sclerosing cholangitis. There has been some research into the use of multiparametric magnetic resonance imaging (LiverMultiScan) in autoimmune hepatitis (AIH) to produce iron-corrected T1 relaxation (cT1) maps, indicating areas of inflammation and fibrosis. There is evidence that a higher cT1 at diagnosis correlates with the risk of loss of biochemical remission and could therefore have prognostic value.7Heneghan M.A. Shumbayawonda E. Dennis A. et al.Quantitative magnetic resonance imaging to aid clinical decision making in autoimmune hepatitis.EClinicalmedicine. 2022; 46101325https://doi.org/10.1016/j.eclinm.2022.101325Abstract Full Text Full Text PDF Scopus (5) Google Scholar In the future, DL may be able to extract data from medical imaging with as yet unrealized diagnostic or prognostic value across a range of liver diseases. Digital pathology is a rapidly growing area in the diagnosis of liver disease. Two forms exist: whole slide imaging and computational pathology (CPATH). Whole slide imaging uses a digital scanner to digitalize the entire histological specimen. When ML or DL is applied to whole slide imaging, it is termed CPATH. In diseases such as AIH where liver biopsy is essential in diagnosis, CPATH could be used to identify hereto unrecognized morphological features in AIH subtypes, which may aid diagnosis and differentiation between AIH and its mimics, such as drug-induced liver injury. Prognostic markers may be identified, allowing an application for CPATH in risk stratification and predicting future relapse. Future digital pathology companies might use proprietary algorithms to produce validated risk stratification or prognosis as seen in radiology. The use of AI for routine tasks and diagnoses will likely reduce costs and address workforce issues prevalent in pathology departments. Whole slide imaging allows easier and faster sharing of data between pathologists and referral to tertiary pathology providers. Its use remains uncommon though, particularly outside larger centers, partly owing to the availability and expense of the necessary digital scanning equipment. Developments in big data and AI show promise in the detection and management of rare liver diseases. Allowing data linkage between electronic health care records in primary and secondary care could be used to create disease databases and identify new disease cases or eligible candidates for clinical trials. In primary biliary cholangitis, it has been shown that de novo cases and patients unknown to specialty care can be identified through the application of novel ontologies to primary care datasets.8Pericleous M. Kelly C. Odin J.A. et al.Clinical ontologies improve case finding of primary biliary cholangitis in UK primary and secondary care.Dig Dis Sci. 2020; 65: 3143-3158https://doi.org/10.1007/s10620-019-06039-xCrossref Scopus (1) Google Scholar The large datasets needed to develop and validate AI technology are often held by traditional health care organizations. They reasonably view the data they hold as a commodity. This can be leveraged in collaborative arrangements with digital companies. An AI company called Deepmind accessed patient data at 1 organization in exchange for free use of its Streams application with technical support.9Lawrence N.R. Bradley S.H. Big data and the NHS - we have the -technology, but we need patient and professional engagement.Future Healthc J. 2018; 5: 229-230https://doi.org/10.7861/futurehosp.5-3-229Crossref Google Scholar The models described by Ebbert et al1Ebbert J.O. Khan R.G. Leibovich B.C. Health care transformations merging traditional and digital medical practices.Mayo Clinic Proceedings: Digital Health. 2023; 1: 63-66Abstract Full Text Full Text PDF Google Scholar on the basis of referral between digital and traditional providers to complement the strengths of each have merit and work for less complex care, but the barriers described by the authors are significant. We have discussed a more transactional landscape of service provision and collaboration: digital providers delivering services or licensing technology to traditional providers, and pecuniary reimbursement and anonymized patient data passing in the opposite direction. These relationships appear more mutually beneficial than multiple referrals between 2 providers delivering aspects of care for the same disease and provide more scope to work at scale within existing regulatory frameworks. If the hurdles can be overcome, the patient benefits realized through these collaborations could be transformative." @default.
• W4386799605 created "2023-09-17" @default.
• W4386799605 creator A5035431541 @default.
• W4386799605 creator A5061679437 @default.
• W4386799605 creator A5067057750 @default.
• W4386799605 date "2023-12-01" @default.
• W4386799605 modified "2023-10-06" @default.
• W4386799605 title "A Snapshot of Digital Transformation in Hepatology and Rare Liver Disease Related Health Care: A UK Perspective" @default.
• W4386799605 cites W2770190609 @default.
• W4386799605 cites W2955681701 @default.
• W4386799605 cites W2999430353 @default.
• W4386799605 cites W3009400189 @default.
• W4386799605 cites W4220750533 @default.
• W4386799605 cites W4282003446 @default.
• W4386799605 doi "https://doi.org/10.1016/j.mcpdig.2023.08.003" @default.
• W4386799605 hasPublicationYear "2023" @default.
• W4386799605 type Work @default.
• W4386799605 citedByCount "0" @default.
• W4386799605 crossrefType "journal-article" @default.
• W4386799605 hasAuthorship W4386799605A5035431541 @default.
• W4386799605 hasAuthorship W4386799605A5061679437 @default.
• W4386799605 hasAuthorship W4386799605A5067057750 @default.
• W4386799605 hasBestOaLocation W43867996051 @default.
• W4386799605 hasConcept C111919701 @default.
• W4386799605 hasConcept C126322002 @default.
• W4386799605 hasConcept C12713177 @default.
• W4386799605 hasConcept C154945302 @default.
• W4386799605 hasConcept C160735492 @default.
• W4386799605 hasConcept C17744445 @default.
• W4386799605 hasConcept C199539241 @default.
• W4386799605 hasConcept C2777075537 @default.
• W4386799605 hasConcept C2779134260 @default.
• W4386799605 hasConcept C41008148 @default.
• W4386799605 hasConcept C41260117 @default.
• W4386799605 hasConcept C512399662 @default.
• W4386799605 hasConcept C55282118 @default.
• W4386799605 hasConcept C71924100 @default.
• W4386799605 hasConceptScore W4386799605C111919701 @default.
• W4386799605 hasConceptScore W4386799605C126322002 @default.
• W4386799605 hasConceptScore W4386799605C12713177 @default.
• W4386799605 hasConceptScore W4386799605C154945302 @default.
• W4386799605 hasConceptScore W4386799605C160735492 @default.
• W4386799605 hasConceptScore W4386799605C17744445 @default.
• W4386799605 hasConceptScore W4386799605C199539241 @default.
• W4386799605 hasConceptScore W4386799605C2777075537 @default.
• W4386799605 hasConceptScore W4386799605C2779134260 @default.
• W4386799605 hasConceptScore W4386799605C41008148 @default.
• W4386799605 hasConceptScore W4386799605C41260117 @default.
• W4386799605 hasConceptScore W4386799605C512399662 @default.
• W4386799605 hasConceptScore W4386799605C55282118 @default.
• W4386799605 hasConceptScore W4386799605C71924100 @default.
• W4386799605 hasIssue "4" @default.
• W4386799605 hasLocation W43867996051 @default.
• W4386799605 hasOpenAccess W4386799605 @default.
• W4386799605 hasPrimaryLocation W43867996051 @default.
• W4386799605 hasRelatedWork W1994263673 @default.
• W4386799605 hasRelatedWork W2030064918 @default.
• W4386799605 hasRelatedWork W2094665023 @default.
• W4386799605 hasRelatedWork W2234872707 @default.
• W4386799605 hasRelatedWork W2257083003 @default.
• W4386799605 hasRelatedWork W2810162999 @default.
• W4386799605 hasRelatedWork W2891664938 @default.
• W4386799605 hasRelatedWork W2992527292 @default.
• W4386799605 hasRelatedWork W3132164478 @default.
• W4386799605 hasRelatedWork W379263722 @default.
• W4386799605 hasVolume "1" @default.
• W4386799605 isParatext "false" @default.
• W4386799605 isRetracted "false" @default.
• W4386799605 workType "article" @default.