30
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: not found
      • Article: not found

      Human–computer collaboration for skin cancer recognition

      Read this article at

      ScienceOpenPublisherPubMed
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Related collections

          Most cited references21

          • Record: found
          • Abstract: found
          • Article: not found

          Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: a systematic review.

          Developers of health care software have attributed improvements in patient care to these applications. As with any health care intervention, such claims require confirmation in clinical trials. To review controlled trials assessing the effects of computerized clinical decision support systems (CDSSs) and to identify study characteristics predicting benefit. We updated our earlier reviews by searching the MEDLINE, EMBASE, Cochrane Library, Inspec, and ISI databases and consulting reference lists through September 2004. Authors of 64 primary studies confirmed data or provided additional information. We included randomized and nonrandomized controlled trials that evaluated the effect of a CDSS compared with care provided without a CDSS on practitioner performance or patient outcomes. Teams of 2 reviewers independently abstracted data on methods, setting, CDSS and patient characteristics, and outcomes. One hundred studies met our inclusion criteria. The number and methodologic quality of studies improved over time. The CDSS improved practitioner performance in 62 (64%) of the 97 studies assessing this outcome, including 4 (40%) of 10 diagnostic systems, 16 (76%) of 21 reminder systems, 23 (62%) of 37 disease management systems, and 19 (66%) of 29 drug-dosing or prescribing systems. Fifty-two trials assessed 1 or more patient outcomes, of which 7 trials (13%) reported improvements. Improved practitioner performance was associated with CDSSs that automatically prompted users compared with requiring users to activate the system (success in 73% of trials vs 47%; P = .02) and studies in which the authors also developed the CDSS software compared with studies in which the authors were not the developers (74% success vs 28%; respectively, P = .001). Many CDSSs improve practitioner performance. To date, the effects on patient outcomes remain understudied and, when studied, inconsistent.
            Bookmark
            • Record: found
            • Abstract: found
            • Article: not found

            Virtual health care in the era of COVID-19

            Patients are under lockdown and health workers are at risk of infection. Paul Webster reports on how telemedicine is being embraced like never before. In the face of a surge in cases of coronavirus disease 2019 (COVID-19), physicians and health systems worldwide are racing to adopt virtualised treatment approaches that obviate the need for physical meetings between patients and health providers. But many doctors are watching warily. “I'd estimate that the majority of patient consultations in the United States are now happening virtually”, says Ray Dorsey, director of the Center for Health and Technology at the University of Rochester Medical Center (Rochester, NY, USA). “There has been something like a ten-fold increase in the last couple of weeks. It's as big a transformation as any ever before in the history of US health care. But the real question is whether these measures will stay in place after the pandemic subsides?” In shifting towards virtualised care in response to COVID-19, health-care planners worldwide are drawing from China's experiences. In China, patients were advised to seek physicians' help online rather than in person after the pandemic first emerged in Wuhan in December, says Yanwu Xu, principal health architect for Baidu Health, one of China's largest internet corporations, and one of three companies contracted by the Chinese Government to implement virtual care technologies. © 2020 TPG/Getty Images 2020 Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active. Speaking to The Lancet from Beijing, Xu, who is a member of WHO's Digital Health Technical Advisory Group, and a researcher at the Chinese Academy of Sciences' Ningbo Institute of Materials Technology & Engineering, explained that China's virtual care transformation was unleashed when the country's national health insurance agency agreed to pay for virtual care consultations because the hospitals and clinics were full. “For the first time, Chinese physicians have really embraced virtual care”, says Xu. “Thanks to these technologies physicians can consult with upwards of a hundred patients a day, which is a very significant increase in the daily caseloads they handled in person in the past.” Following China's example, on March 30, at the direction of US President Donald Trump, the Centers for Medicare & Medicaid Services (CMS), which oversees the nation's major public health programmes, issued what it termed “an unprecedented array of temporary regulatory waivers and new rules to equip the American healthcare system with maximum flexibility to respond to the 2019 Novel Coronavirus (COVID-19) pandemic”. In a press release, the CMS explained that its new measures will allow for more than 80 additional services to be furnished via telehealth. “During the public health emergencies, individuals can use interactive apps with audio and video capabilities to visit with their clinician for an even broader range of services. Providers also can evaluate beneficiaries who have audio phones only. These temporary changes will ensure that patients have access to physicians and other providers while remaining safely at home.” Eric Topol, director of the Scripps Research Translational Institute in La Jolla (CA, USA), praises these efforts, but laments that they have been so long coming. “This is a very big moment for virtual health care. But, of course, there isn't a lot of readiness. There are so many ways to monitor people's health that we aren't doing at any scale, in large part due to interstate regulatory barriers that have meant we are in no way ready for this moment.” Similar steps to sweep aside regulatory and hegemonic professional barriers are being taken in Canada, according to Sandy Buchman, president of the Canadian Medical Association. “As we confront [COVID-19], we're racing to implement virtual health-care technologies as quickly as we can. The scale and pace of change is unprecedented for Canadian health care.” Topol warns that the sudden rush to virtualisation risks diminishing the quality of clinical care. “It's inexpensive and expedient, but it'll never be the same as a physical examination with all of its human qualities of judgment and communication. But with COVID, this is a trade-off we have to accept.” Similar developments are sweeping health care in the UK, says Trisha Greenhalgh, co-director of the Interdisciplinary Research In Health Sciences Unit at Oxford University (Oxford, UK). “We have a research project that has been tracking the use of video conferencing in Scotland over the past 6 months, and in the space of the last 2 weeks we've seen [a] 1000% increase in use”, said Greenhalgh. “It's incredible. [COVID-19] has done what we couldn't do until now, because, suddenly, it's not just the patient who might die—now it's the doctor who might die. So the doctors are highly motivated. The risk–benefit ratio for virtual health care has massively shifted and all the red tape has suddenly been cut.” In Italy, although all 20 regions had implemented national telemedicine guidelines as of 2018, hospital managers have been largely caught off guard by the explosion in digital demand, says Elena Sini, information officer for GVM Care & Research, a network of nine private hospitals in northern Italy. Many Italian hospitals lack the necessary hardware and technical resources, she noted in a March 23 webinar. “Burnout is also a concern for IT staff, so set up some psychological support for IT staff”, she advises. Sini reported a lack of hardware due to broken supply chains and insufficient bandwidth capacities as the demand increased by about 90% on fixed landlines and 40% on mobile networks in Italy. “We have to ramp up telemedicine capabilities, but for most hospitals in Italy this is an issue. We just don't have the capabilities to deliver.” Speaking alongside Sini, Henning Schneider, chief information officer for Asklepios Kliniken, one of Germany's largest private hospital networks, said the COVID-19 pandemic is highlighting a need for intensified IT collaboration between German hospitals. In New Delhi, India, Anurag Agrawal, director of the Council of Scientific and Industrial Research's Institute of Genomics and Integrative Biology, says Indian health-care providers have become similarly preoccupied with virtual health care while the country is in near-total lockdown. “Suddenly, after years of resistance to virtual health care, our physicians keenly want it”, said Agrawal. “[COVID-19] is breaching the barriers to virtual health care faster than anything in history.” Access to virtual health care is far easier within India's publicly financed health-care systems than among private providers, Agrawal notes. However, as India's response to COVID-19 escalates, many private physicians are providing virtual consultations for free. “That could change if the lockdown runs longer”, Agrawal explains. “Meanwhile, the national and state governments will need some time to ramp this up, and the lockdown is buying us time.” To expedite the transformation, he adds, the Indian Government is copying China's tactics by releasing a set of newly developed applications that use instant messaging platforms, such as WhatsApp, to enable a suite of virtual health-care services, including public messaging about behavioural modifications, epidemiological tracing, and access to virtual health-care providers. “The Chinese had a national advantage with their WeChat messaging platform, which is better-suited to hosting virtual health-care apps than WhatsApp is.” Like Topol, Agrawal warns that virtual health care comes with a trade-off in the quality of patient care. “Physicians, too, we should keep in mind, benefit from the in-person consultations as much as patients”, he suggests. “We may mourn that.” African health-care providers have yet to join the global rush en masse, observes Chris Seebregts, chief executive of Jembi Health Systems, a Cape Town-based non-governmental organisation that advises health-system strategists in digital technologies in Cameroon, Ethiopia, Kenya, Malawi, Mozambique, South Africa, South Sudan, and Uganda. “Digital health technologies are being adopted at a huge rate now here in South Africa in response to [COVID-19]”, Seebregts said via video conference from Cape Town, “but we're not seeing much adoption yet elsewhere in Africa. [COVID-19] may accelerate it, but it's too soon to say.” With mobile phone use now globally ubiquitous, technological barriers to the adoption of virtual health care are easily surmountable, even in the most resource-scarce settings, notes Alex Jadad, founder of the Centre for Global eHealth Innovation at the University of Toronto, ON, Canada, where he is the director of the Institute for Global Health Equity and Innovation. “Whether I'm deep in Malawi or deep in the Amazon, all I need is a mobile phone and a connection that allows me to talk to a clinician. That's all it takes for a clinical encounter. These are god-like tools for medicine. There's no need for us to wait for any more sophisticated infrastructure than that”, says Jadad, who is advising on virtual health-care adoption strategies for health groups in Colombia. “The regulatory barriers that have held virtual health care back for all these decades were never justifiable”, Jadad avers. “[COVID-19] is an opportunity to blow all these barriers away. And the question now is ‘how far are we willing to go?’” © 2020 Catherine Lai/AFP/Getty Images 2020 Since January 2020 Elsevier has created a COVID-19 resource centre with free information in English and Mandarin on the novel coronavirus COVID-19. The COVID-19 resource centre is hosted on Elsevier Connect, the company's public news and information website. Elsevier hereby grants permission to make all its COVID-19-related research that is available on the COVID-19 resource centre - including this research content - immediately available in PubMed Central and other publicly funded repositories, such as the WHO COVID database with rights for unrestricted research re-use and analyses in any form or by any means with acknowledgement of the original source. These permissions are granted for free by Elsevier for as long as the COVID-19 resource centre remains active.
              Bookmark
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions

              Training of neural networks for automated diagnosis of pigmented skin lesions is hampered by the small size and lack of diversity of available datasets of dermatoscopic images. We tackle this problem by releasing the HAM10000 (“Human Against Machine with 10000 training images”) dataset. We collected dermatoscopic images from different populations acquired and stored by different modalities. Given this diversity we had to apply different acquisition and cleaning methods and developed semi-automatic workflows utilizing specifically trained neural networks. The final dataset consists of 10015 dermatoscopic images which are released as a training set for academic machine learning purposes and are publicly available through the ISIC archive. This benchmark dataset can be used for machine learning and for comparisons with human experts. Cases include a representative collection of all important diagnostic categories in the realm of pigmented lesions. More than 50% of lesions have been confirmed by pathology, while the ground truth for the rest of the cases was either follow-up, expert consensus, or confirmation by in-vivo confocal microscopy.
                Bookmark

                Author and article information

                Journal
                Nature Medicine
                Nat Med
                Springer Science and Business Media LLC
                1078-8956
                1546-170X
                June 22 2020
                Article
                10.1038/s41591-020-0942-0
                32572267
                fe8a84a1-c471-4886-be7d-dc287733833f
                © 2020

                Free to read

                http://www.springer.com/tdm

                http://www.springer.com/tdm

                History

                Comments

                Comment on this article