Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 5 de 5
Filter
Add more filters










Database
Publication year range
1.
Sci Rep ; 12(1): 21302, 2022 Dec 09.
Article in English | MEDLINE | ID: mdl-36494393

ABSTRACT

Statistical learning algorithms strongly rely on an oversimplified assumption for optimal performance, that is, source (training) and target (testing) data are independent and identically distributed. Variation in human tissue, physician labeling and physical imaging parameters (PIPs) in the generative process, yield medical image datasets with statistics that render this central assumption false. When deploying models, new examples are often out of distribution with respect to training data, thus, training robust dependable and predictive models is still a challenge in medical imaging with significant accuracy drops common for deployed models. This statistical variation between training and testing data is referred to as domain shift (DS).To the best of our knowledge we provide the first empirical evidence that variation in PIPs between test and train medical image datasets is a significant driver of DS and model generalization error is correlated with this variance. We show significant covariate shift occurs due to a selection bias in sampling from a small area of PIP space for both inter and intra-hospital regimes. In order to show this, we control for population shift, prevalence shift, data selection biases and annotation biases to investigate the sole effect of the physical generation process on model generalization for a proxy task of age group estimation on a combined 44 k image mammogram dataset collected from five hospitals.We hypothesize that training data should be sampled evenly from PIP space to produce the most robust models and hope this study provides motivation to retain medical image generation metadata that is almost always discarded or redacted in open source datasets. This metadata measured with standard international units can provide a universal regularizing anchor between distributions generated across the world for all current and future imaging modalities.


Subject(s)
Algorithms , Diagnostic Imaging , Humans
2.
Orv Hetil ; 163(14): 535-543, 2022 04 03.
Article in Hungarian | MEDLINE | ID: mdl-35377853

ABSTRACT

Due to various factors, the chances of infectious disease emergence or re-emergence have increased in the 21st century, thus, the likelihood of new emerging pandemics has also increased. The COVID-19 pandemic, which appeared in 2019, has highlighted that certain new and re-emerging infectious diseases - in the case of lack or delay in effective measures - can spread very rapidly. The main tool for the fight against infectious diseases is immunization through vaccination. While focusing on the personal health, public health, economic and societal benefits of a lifelong immunization strategy, especially in light of the aging society, the goal of this paper is to present the benefits of vaccines. In order to increase the added value of vaccinations it is recommended to create a lifelong immunization strategy.


Subject(s)
COVID-19 , Vaccines , Humans , Pandemics , Vaccination
3.
Orv Hetil ; 162(47): 1876-1884, 2021 11 21.
Article in Hungarian | MEDLINE | ID: mdl-34801981

ABSTRACT

Összefoglaló. Bevezetés és célkituzés: Az egészségügyi intézmények digitalizációs fejlesztése kapcsán célszeru egy digitális szervezeti stratégia megalkotása a betegbiztonsági és kiberbiztonsági szempontok figyelembevételével. E tanulmány célja az egészségügyi intézményi digitalizáció betegbiztonságra gyakorolt hatásainak átfogó szakirodalmi megismerése és a nemzetközi szakirodalmi közlések tapasztalatai alapján összeállított, a hazai gyakorlatban használható intézményi stratégiai javaslat megalkotása és bemutatása. Módszer: A szerzok irodalomkutatást végeztek, angol és német nyelvu közleményeket kerestek több adatbázisban. A közlemények tartalmát elore meghatározott szempontok szerint gyujtötték. Eredmények: A szerzok 39 közleményt értékeltek, 12 közleményt részletesen mutatnak be. A digitalizációs fejlesztések gyakorlati tapasztalatait és veszélyeit tárgyalják. Az ajánlások foként stratégiai és kiberbiztonsági szempontokat, oktatás- és kompetenciafejlesztést javasolnak. Következtetés: A szerzok hazai egészségügyi intézmények számára javasolják betegbiztonsági és kiberbiztonsági szempontokat figyelembe vevo digitalizációs fejlesztési stratégia megalkotását, amellyel a betegellátással foglalkozók szakmai szempontjainak érvényesülését segítik. Orv Hetil. 2021; 162(47): 1876-1884. INTRODUCTION AND OBJECTIVE: In connection with the digitalisation development of healthcare institutions, it is desirable to create a digital organizational strategy, which takes into account patient safety and cyber security aspects. The aim of this study is to familiarize doctors with the comprehensive study of the effects of the digitalisation of healthcare institutions on patient safety and to create and present an institutional strategic proposal, which has been compiled based on the experience of international literature publications. METHOD: A study of the relevant literature was conducted, searching through publications in English and German in several databases. The content of the publications was collected according to pre-defined criteria. RESULTS: 39 articles were evaluated out of which 12 are presented in detail. The practical experiences and risks of the digitalisation developments are discussed. The recommendations principally suggest strategic and cyber security aspects, education and competency improvement. CONCLUSION: The creation of a digitalisation development strategy, which considers patient safety and cyber security aspects, should be considered also in Hungarian healthcare institutions. This strategy would also help the justification and realization of the professional priorities of healthcare providers. Orv Hetil. 2021; 162(47): 1876-1884.


Subject(s)
Delivery of Health Care , Patient Safety , Humans , Hungary
4.
Sci Rep ; 11(1): 5943, 2021 03 15.
Article in English | MEDLINE | ID: mdl-33723282

ABSTRACT

Mobile phones have been used to monitor mobility changes during the COVID-19 pandemic but surprisingly few studies addressed in detail the implementation of practical applications involving whole populations. We report a method of generating a "mobility-index" and a "stay-at-home/resting-index" based on aggregated anonymous Call Detail Records of almost all subscribers in Hungary, which tracks all phones, examining their strengths and weaknesses, comparing it with Community Mobility Reports from Google, limited to smartphone data. The impact of policy changes, such as school closures, could be identified with sufficient granularity to capture a rush to shops prior to imposition of restrictions. Anecdotal reports of large scale movement of Hungarians to holiday homes were confirmed. At the national level, our results correlated well with Google mobility data, but there were some differences at weekends and national holidays, which can be explained by methodological differences. Mobile phones offer a means to analyse population movement but there are several technical and privacy issues. Overcoming these, our method is a practical and inexpensive way forward, achieving high levels of accuracy and resolution, especially where uptake of smartphones is modest, although it is not an alternative to smartphone-based solutions used for contact tracing and quarantine monitoring.


Subject(s)
Big Data , COVID-19/epidemiology , Computers, Handheld , SARS-CoV-2 , Social Mobility/statistics & numerical data , COVID-19/prevention & control , COVID-19/virology , Contact Tracing , Geography, Medical , Humans , Hungary/epidemiology , Public Health Surveillance
5.
Orv Hetil ; 161(36): 1498-1505, 2020 09.
Article in Hungarian | MEDLINE | ID: mdl-32886624

ABSTRACT

In recent years, due to the value of health data and the specificities of health processes, data breaches have become increasingly important. In addition to the general data protection rules of the European Union, aspects of general information security, including technology and human behaviour, have been reassessed. In this article, we present the importance of blackmail (ransomware) virus attacks in the health sector. According to international data, especially in the US, one of the most important methods of institutional attacks will be the extortion attack in the coming years, and this is expected to increase in importance, especially in health care where sensitive and valuable data are truly life-giving. Because of the encryption of data and the blocking of core processes, blackmail viruses can also have a significant impact on the effectiveness of therapy and healthcare. In addition to presenting the current international situation, the article also outlines the most important steps that can be taken by those involved in daily patient's care to ensure continuity of patient care. Orv Hetil. 2020; 161(36): 1498-1505.


Subject(s)
Computer Security , Crime , Health Information Systems , Humans
SELECTION OF CITATIONS
SEARCH DETAIL
...