Browsing by Author "Hattingh, Retha"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    The accuracy of radiology speech recognition reports in a multilingual South African teaching hospital
    (BioMed Central, 2015-03) Du Toit, Jacqueline; Hattingh, Retha; Pitcher, Richard
    Background: Speech recognition (SR) technology, the process whereby spoken words are converted to digital text, has been used in radiology reporting since 1981. It was initially anticipated that SR would dominate radiology reporting, with claims of up to 99% accuracy, reduced turnaround times and significant cost savings. However, expectations have not yet been realised. The limited data available suggest SR reports have significantly higher levels of inaccuracy than traditional dictation transcription (DT) reports, as well as incurring greater aggregate costs. There has been little work on the clinical significance of such errors, however, and little is known of the impact of reporter seniority on the generation of errors, or the influence of system familiarity on reducing error rates. Furthermore, there have been conflicting findings on the accuracy of SR amongst users with English as first- and second-language respectively. Methods: The aim of the study was to compare the accuracy of SR and DT reports in a resource-limited setting. The first 300 SR and the first 300 DT reports generated during March 2010 were retrieved from the hospital’s PACS, and reviewed by a single observer. Text errors were identified, and then classified as either clinically significant or insignificant based on their potential impact on patient management. In addition, a follow-up analysis was conducted exactly 4 years later. Results: Of the original 300 SR reports analysed, 25.6% contained errors, with 9.6% being clinically significant. Only 9.3% of the DT reports contained errors, 2.3% having potential clinical impact. Both the overall difference in SR and DT error rates, and the difference in ‘clinically significant’ error rates (9.6% vs. 2.3%) were statistically significant. In the follow-up study, the overall SR error rate was strikingly similar at 24.3%, 6% being clinically significant. Radiologists with second-language English were more likely to generate reports containing errors, but level of seniority had no bearing. Conclusion: SR technology consistently increased inaccuracies in Tygerberg Hospital (TBH) radiology reports, thereby potentially compromising patient care. Awareness of increased error rates in SR reports, particularly amongst those transcribing in a second-language, is important for effective implementation of SR in a multilingual healthcare environment.
  • Thumbnail Image
    Item
    Mammography reporting at Tygerberg Hospital, Cape Town, South Africa
    (Health & Medical Publishing Group, 2014-07) Pitcher, Richard; Lotz, Jan; Ackermann, Christelle; Bagadia, Asif; Davis, Razaan; Du Plessis, Anne-Marie; Griffith-Richards, Stephanie; Hattingh, Retha; Wagener, Georg; Apffelstaedt, Justus; Dalmayer, Lisa; Baatjes, Karin
    In their recent article, Apffelstaedt et al.[1] analysed 16 105 mammograms performed at Tygerberg Hospital (TBH), Cape Town, South Africa (SA), between 2003 and 2012. The summary reported that ‘mammograms were read by experienced breast surgeons’, while the discussion stated: ‘A further noteworthy fact is that this TBH series was based exclusively on mammography interpretation by surgeons with a special interest in breast health.’ The suggestion that mammograms were exclusively interpreted by breast surgeons does not reflect the mammography workflow at our institution.
  • Thumbnail Image
    Item
    Results of a pilot programme of mammographic breast cancer screening in the Western Cape
    (Health & Medical Publishing Group, 2014-04) Apffelstaedt, Justus P.; Hattingh, Retha; Baatjes, Karin; Wessels, Natalie
    Background. Mammographic screening programmes are now established in developing countries. We present an analysis of the first screening programme in sub-Saharan Africa. Methods. Women aged ≥40 years were identified at three primary healthcare centres in the Western Cape Province, South Africa, and after giving informed consent underwent mammography at a mobile unit. After a single reading, patients with American College of Radiology Breast Imaging Reporting and Data System (BIRADS) 3 - 5 lesions were referred to a tertiary centre for further management. Results. Between 1 February 2011 and 31 August 2012, 2 712 screening mammograms were performed. A total of 261 screening mammograms were reported as BIRADS 3 - 5 (recall rate 9.6%). Upon review of the 250 available screening mammograms, 58 (23%) were rated benign or no abnormalities (BIRADS 1 and 2) and no further action was taken. In 32 women, tissue was acquired (biopsy rate for the series 1.2%); 10 cancers were diagnosed (biopsy malignancy rate 31%). For the entire series of 2 712 screening mammograms, the cancer diagnosis rate was 3.7/1 000 examinations. Of 10 cancers diagnosed at screening, 5 were TNM clinical stage 0, 2 stage I and 3 stage II. Conclusions. The low cancer detection rate achieved, and the technical and multiple administrative problems experienced do not justify installation of a screening programme using the model utilised in this series.