LIVIVO - Das Suchportal für Lebenswissenschaften

switch to English language
Erweiterte Suche

Suchergebnis

Treffer 1 - 10 von insgesamt 139

Suchoptionen

  1. Artikel ; Online: Curtis P. Langlotz, MD, PhD, President, Radiological Society of North America, 2024.

    Eng, John

    Radiology

    2023  Band 310, Heft 1, Seite(n) e249001

    Mesh-Begriff(e) Humans ; Radiography ; Radiology ; North America
    Sprache Englisch
    Erscheinungsdatum 2023-12-14
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ZDB-ID 80324-8
    ISSN 1527-1315 ; 0033-8419
    ISSN (online) 1527-1315
    ISSN 0033-8419
    DOI 10.1148/radiol.249001
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

  2. Buch: Radiologie compact

    Eng, John

    37 Tabellen

    (US-ART, US-American radiology toolbooks)

    1999  

    Verfasserangabe hrsg. von John Eng. Übers. von Kirsten Holsteg
    Serientitel US-ART, US-American radiology toolbooks
    Schlagwörter Radiologische Diagnostik
    Schlagwörter Diagnostische Radiologie ; Strahlendiagnostik
    Sprache Deutsch
    Umfang XVI, 357 S. : Ill., graph. Darst.
    Verlag Thieme
    Erscheinungsort Stuttgart u.a.
    Dokumenttyp Buch
    Anmerkung Aus d. Engl. übers.
    HBZ-ID HT010502929
    ISBN 3-13-117431-5 ; 978-3-13-117431-4
    Datenquelle Katalog ZB MED Medizin, Gesundheit

    Kategorien

  3. Buch: Manual of radiology

    Eng, John

    acute problems and essential procedures

    1997  

    Verfasserangabe ed. John Eng
    Schlagwörter Radiography / handbooks ; Radiography / methods / handbooks
    Sprache Englisch
    Umfang XV, 351 S. : Ill., graph. Darst.
    Verlag Lippincott-Raven
    Erscheinungsort Philadelphia u.a.
    Erscheinungsland Vereinigte Staaten
    Dokumenttyp Buch
    HBZ-ID HT007568939
    ISBN 0-397-51768-8 ; 978-0-397-51768-8
    Datenquelle Katalog ZB MED Medizin, Gesundheit

    Kategorien

  4. Artikel ; Online: External Validation of Deep Learning Algorithms for Radiologic Diagnosis: A Systematic Review.

    Yu, Alice C / Mohajer, Bahram / Eng, John

    Radiology. Artificial intelligence

    2022  Band 4, Heft 3, Seite(n) e210064

    Abstract: Purpose: To assess generalizability of published deep learning (DL) algorithms for radiologic diagnosis.: Materials and methods: In this systematic review, the PubMed database was searched for peer-reviewed studies of DL algorithms for image-based ... ...

    Abstract Purpose: To assess generalizability of published deep learning (DL) algorithms for radiologic diagnosis.
    Materials and methods: In this systematic review, the PubMed database was searched for peer-reviewed studies of DL algorithms for image-based radiologic diagnosis that included external validation, published from January 1, 2015, through April 1, 2021. Studies using nonimaging features or incorporating non-DL methods for feature extraction or classification were excluded. Two reviewers independently evaluated studies for inclusion, and any discrepancies were resolved by consensus. Internal and external performance measures and pertinent study characteristics were extracted, and relationships among these data were examined using nonparametric statistics.
    Results: Eighty-three studies reporting 86 algorithms were included. The vast majority (70 of 86, 81%) reported at least some decrease in external performance compared with internal performance, with nearly half (42 of 86, 49%) reporting at least a modest decrease (≥0.05 on the unit scale) and nearly a quarter (21 of 86, 24%) reporting a substantial decrease (≥0.10 on the unit scale). No study characteristics were found to be associated with the difference between internal and external performance.
    Conclusion: Among published external validation studies of DL algorithms for image-based radiologic diagnosis, the vast majority demonstrated diminished algorithm performance on the external dataset, with some reporting a substantial performance decrease.
    Sprache Englisch
    Erscheinungsdatum 2022-05-04
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ISSN 2638-6100
    ISSN (online) 2638-6100
    DOI 10.1148/ryai.210064
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

  5. Artikel ; Online: One Algorithm May Not Fit All: How Selection Bias Affects Machine Learning Performance.

    Yu, Alice C / Eng, John

    Radiographics : a review publication of the Radiological Society of North America, Inc

    2020  Band 40, Heft 7, Seite(n) 1932–1937

    Abstract: Machine learning (ML) algorithms have demonstrated high diagnostic accuracy in identifying and categorizing disease on radiologic images. Despite the results of initial research studies that report ML algorithm diagnostic accuracy similar to or exceeding ...

    Abstract Machine learning (ML) algorithms have demonstrated high diagnostic accuracy in identifying and categorizing disease on radiologic images. Despite the results of initial research studies that report ML algorithm diagnostic accuracy similar to or exceeding that of radiologists, the results are less impressive when the algorithms are installed at new hospitals and are presented with new images. This phenomenon is potentially the result of selection bias in the data that were used to develop the ML algorithm. Selection bias has long been described by clinical epidemiologists as a key consideration when designing a clinical research study, but this concept has largely been unaddressed in the medical imaging ML literature. The authors discuss the importance of selection bias and its relevance to ML algorithm development to prepare the radiologist to critically evaluate ML literature for potential selection bias and understand how it might affect the applicability of ML algorithms in real clinical environments.
    Sprache Englisch
    Erscheinungsdatum 2020-09-25
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ZDB-ID 603172-9
    ISSN 1527-1323 ; 0271-5333
    ISSN (online) 1527-1323
    ISSN 0271-5333
    DOI 10.1148/rg.2020200040
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

  6. Artikel ; Online: Imaging Publications in the COVID-19 Pandemic: Applying New Research Results to Clinical Practice.

    Eng, John / Bluemke, David A

    Radiology

    2020  Band 297, Heft 1, Seite(n) E228–E231

    Mesh-Begriff(e) Betacoronavirus ; COVID-19 ; Coronavirus Infections/diagnostic imaging ; Epidemiologic Research Design ; Humans ; Pandemics ; Pneumonia, Viral/diagnostic imaging ; Predictive Value of Tests ; Publications/standards ; Radiology/organization & administration ; SARS-CoV-2 ; Tomography, X-Ray Computed
    Schlagwörter covid19
    Sprache Englisch
    Erscheinungsdatum 2020-04-23
    Erscheinungsland United States
    Dokumenttyp Journal Article ; Review
    ZDB-ID 80324-8
    ISSN 1527-1315 ; 0033-8419
    ISSN (online) 1527-1315
    ISSN 0033-8419
    DOI 10.1148/radiol.2020201724
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

  7. Artikel ; Online: Receiver operating characteristic analysis: utility, reality, covariates, and the future.

    Eng, John

    Academic radiology

    2013  Band 20, Heft 7, Seite(n) 795–797

    Mesh-Begriff(e) Humans ; ROC Curve ; Radiology
    Sprache Englisch
    Erscheinungsdatum 2013-07
    Erscheinungsland United States
    Dokumenttyp Editorial ; Introductory Journal Article
    ZDB-ID 1355509-1
    ISSN 1878-4046 ; 1076-6332
    ISSN (online) 1878-4046
    ISSN 1076-6332
    DOI 10.1016/j.acra.2013.05.001
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

  8. Artikel ; Online: Sampling the latest work in receiver operating characteristic analysis: what does it mean?

    Eng, John

    Academic radiology

    2012  Band 19, Heft 12, Seite(n) 1449–1451

    Mesh-Begriff(e) History, 20th Century ; History, 21st Century ; Humans ; ROC Curve ; Radiology/history ; Radiology/methods ; Sensitivity and Specificity
    Sprache Englisch
    Erscheinungsdatum 2012-12
    Erscheinungsland United States
    Dokumenttyp Biography ; Editorial ; Historical Article ; Introductory Journal Article
    ZDB-ID 1355509-1
    ISSN 1878-4046 ; 1076-6332
    ISSN (online) 1878-4046
    ISSN 1076-6332
    DOI 10.1016/j.acra.2012.09.019
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

  9. Artikel ; Online: Teaching receiver operating characteristic analysis: an interactive laboratory exercise.

    Eng, John

    Academic radiology

    2012  Band 19, Heft 12, Seite(n) 1452–1456

    Abstract: Rationale and objectives: Despite its fundamental importance in the evaluation of diagnostic tests, receiver operating characteristic (ROC) analysis is not easily understood. The purpose of this project was to create a learning experience that resulted ... ...

    Abstract Rationale and objectives: Despite its fundamental importance in the evaluation of diagnostic tests, receiver operating characteristic (ROC) analysis is not easily understood. The purpose of this project was to create a learning experience that resulted in an intuitive understanding of the basic principles of ROC analysis.
    Materials and methods: An interactive laboratory exercise was developed for a class about radiology testing taught within a clinical epidemiology course between 2000 and 2009. The physician students in the course were clinical fellows from various medical specialties who were enrolled in a graduate degree program in clinical investigation. For the exercise, the class was divided into six groups. Each group interpreted radiographs from a set of 50 exams of the peripheral skeleton to determine the presence or absence of an acute fracture. Data from the class were pooled and given to each student. Students calculated the area under the ROC curve (AUC) corresponding to overall class performance. A binormal ROC curve was also fitted to the data from each class year.
    Results: The laboratory exercise was conducted for 8 years with approximately 20-30 students per year. The mean AUC over the eight laboratory classes was 0.72 with a standard deviation of 0.08 (range, 0.60-0.85).
    Conclusion: With some simplifications in design, an observer study can be conducted in a laboratory classroom setting. Participatory data collection promotes the intuitive understanding of ROC analysis principles.
    Mesh-Begriff(e) Area Under Curve ; Humans ; Internship and Residency ; ROC Curve ; Radiographic Image Interpretation, Computer-Assisted ; Radiology/education ; Sensitivity and Specificity ; Teaching/methods
    Sprache Englisch
    Erscheinungsdatum 2012-12
    Erscheinungsland United States
    Dokumenttyp Journal Article
    ZDB-ID 1355509-1
    ISSN 1878-4046 ; 1076-6332
    ISSN (online) 1878-4046
    ISSN 1076-6332
    DOI 10.1016/j.acra.2012.09.003
    Datenquelle MEDical Literature Analysis and Retrieval System OnLINE

    Zusatzmaterialien

    Kategorien

  10. Buch ; Online: Contrast-induced nephropathy

    Eng, John

    comparative effects of different contrast media

    (Comparative effectiveness review ; number 155 ; AHRQ publication ; no. 15(16)-EHC022-EF)

    2015  

    Abstract: OBJECTIVES: To evaluate the comparative effects of different types of contrast media with respect to the risk of developing contrast-induced nephropathy (CIN) by synthesizing the current literature. DATA SOURCES: We searched for original studies in ... ...

    Körperschaft United States. / Agency for Healthcare Research and Quality,
    Johns Hopkins University. / Evidence-based Practice Center,
    Effective Health Care Program (U.S.)
    Verfasserangabe investigators, John Eng, Rathan M. Subramaniam, Renee F. Wilson, Sharon Turban, Michael J. Choi, Allen Zhang, Catalina Suarez-Cuervo, Cheryl Sherrod, Susan Hutfless, Emmanuel E. Iyoha, Eric B. Bass
    Serientitel Comparative effectiveness review ; number 155
    AHRQ publication ; no. 15(16)-EHC022-EF
    Abstract OBJECTIVES: To evaluate the comparative effects of different types of contrast media with respect to the risk of developing contrast-induced nephropathy (CIN) by synthesizing the current literature. DATA SOURCES: We searched for original studies in MEDLINE(r), Embase(r), and the Cochrane Library through October 1, 2014. We also searched for studies in ClinicalTrials.gov and the Scopus database. METHODS: Two reviewers independently reviewed each article to identify randomized controlled trials (RCTs) that reported on CIN-related outcomes in patients after receiving low-osmolar contrast media (LOCM) or iso-osmolar contrast media (IOCM). We included head-to-head comparisons of one LOCM versus another LOCM or of LOCM versus IOCM. (Only 1 IOCM is currently available in the United States.) For each study, one reviewer extracted the data and a second reviewer verified the accuracy. Both reviewers assessed the risk of bias for each study. Together, the reviewers graded the strength of evidence for the comparisons and outcomes of interest. We quantitatively pooled the results of studies that were sufficiently similar, using a 25-percent relative risk reduction as the threshold for a minimally important difference. RESULTS: We identified five RCTs that compared two or more LOCMs, including two studies of intra-arterial administration, two studies of intravenous administration, and one study examining both routes. We identified 25 RCTs that compared IOCM with LOCM, including 18 studies of intra-arterial administration and 7 studies of intravenous administration. No study comparing LOCMs reported a statistically significant or clinically important difference between study arms, and the overall analysis did not suggest that any one LOCM was superior to another. In a meta-analysis, we found a borderline significant reduction in short-term CIN risk with IOCM compared with a diverse group of LOCMs (pooled relative risk, 0.80; 95% confidence interval [CI], 0.65 to 0.99, p=0.045). When the analysis was stratified by route of administration, the aggregate pooled relative risk was 0.80 (95% CI, 0.64 to 1.01) for intra-arterial and 0.84 (95% CI, 0.42 to 1.71) for intravenous. In studies that investigated IOCM versus LOCM, the outcomes of mortality, cardiovascular outcomes, need for renal replacement therapy, and imaging quality or diagnostic accuracy showed no significant difference between groups. One study comparing different LOCMs investigated the outcomes of death and adverse events, and found no difference between groups. CONCLUSIONS: We found low strength of evidence that the risk of CIN did not differ between LOCMs, and moderate strength of evidence that IOCM had a slightly lower risk of CIN than LOCM. The lower risk was not clinically important and just reached statistical significance.
    Mesh-Begriff(e) Acute Kidney Injury/chemically induced ; Contrast Media/adverse effects ; Comparative Effectiveness Research
    Sprache Englisch
    Umfang 1 online resource (1 PDF file (various pagings)) :, illustrations.
    Dokumenttyp Buch ; Online
    Datenquelle Katalog der US National Library of Medicine (NLM)

    Zusatzmaterialien

    Kategorien

Zum Seitenanfang