Data extraction from machine-translated versus original language randomized trial reports: a comparative study
Open accessThe DOI matches its Crossref record; 5 of the 5 references it cites were found in a registry or an index.
Abstract
BACKGROUND: Google Translate offers free Web-based translation, but it is unknown whether its translation accuracy is sufficient to use in systematic reviews to mitigate concerns about language bias. METHODS: We compared data extraction from non-English language studies with extraction from translations by Google Translate of 10 studies in each of five languages (Chinese, French, German, Japanese and Spanish). Fluent speakers double-extracted original-language articles. Researchers who did not speak the given language double-extracted translated articles along with 10 additional English language trials. Using the original language extractions as a gold standard, we estimated the probability and odds ratio of correctly extracting items from translated articles compared with English, adjusting for reviewer and language. RESULTS: Translation required about 30 minutes per article and extraction of translated articles required additional extraction time. The likelihood of correct extractions was greater for study design and intervention domain items than for outcome descriptions and, particularly, study results. Translated Spanish articles yielded the highest percentage of items (93%) that were correctly extracted more than half the time (followed by German and Japanese 89%, French 85%, and Chinese 78%) but Chinese articles yielded the highest percentage of items (41%) that were correctly extracted >98% of the time (followed by Spanish 30%, French 26%, German 22%, and Japanese 19%). In general, extractors' confidence in translations was not associated with their accuracy. CONCLUSIONS: Translation by Google Translate generally required few resources. Based on our analysis of translations from five languages, using machine translation has the potential to reduce language bias in systematic reviews; however, pending additional empirical data, reviewers should be cautious about using translated data. There remains a trade-off between completeness of systematic reviews (including all available studies) and risk of error (due to poor translation).
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Language bias in randomised controlled trials published in English and German
Egger, M., Zellweger-Zähner, T., Schneider, M., Junker, C., Lengeler, C., & Antes, G. (1997) · The Lancet · doi:10.1016/s0140-6736(97)02419-7 · Cited by 1,028
Finding What Works in Health Care: Standards for Systematic Reviews
Committee on Standards for Systematic Reviews of Comparative Effectiveness Research, Board on Health Care Services, & Institute of Medicine (2011) · doi:10.17226/13059 · Cited by 289
Data Extraction Errors in Meta-analyses That Use Standardized Mean Differences
Gøtzsche, P. C., Hróbjartsson, A., Marić, K., & Tendal, B. (2007) · JAMA · doi:10.1001/jama.298.4.430 · Cited by 238 · cited 1×
“Re-analyses of published meta-analyses and studies assessing extraction error rates have found discrepancies with the original papers in about one quarter to two thirds [7–10].”
MethodJones, A. P., Remmington, T., Williamson, P. R., Ashby, D., & Smyth, R. L. (2005) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2004.11.024 · Cited by 114 · cited 1×
“Re-analyses of published meta-analyses and studies assessing extraction error rates have found discrepancies with the original papers in about one quarter to two thirds [7–10].”
MethodHorton, J., Vandermeer, B., Hartling, L., Tjosvold, L., Klassen, T. P., & Buscemi, N. (2010) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2009.04.007 · Cited by 81
Cited by
Systematic review automation technologies
Tsafnat, G., Glasziou, P., Choong, M. K., Dunn, A., Galgani, F., & Coiera, E. (2014) · Systematic Reviews · doi:10.1186/2046-4053-3-74 · Cited by 472
“Language bias remains an unanswered problem with little existing systems available to address it [45].”
BackgroundClinical Natural Language Processing in languages other than English: opportunities and challenges
Névéol, A., Dalianis, H., Velupillai, S., Savova, G., & Zweigenbaum, P. (2018) · Journal of Biomedical Semantics · doi:10.1186/s13326-018-0179-8 · Cited by 311
Pineles, B. L., Hsu, S., Park, E., & Samet, J. M. (2016) · American Journal of Epidemiology · doi:10.1093/aje/kwv301 · Cited by 202
Tools to support the automation of systematic reviews: a scoping review.
Khalil, H., Ameen, D., & Zarnegar, A. (2022) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2021.12.005 · Cited by 190
Resource use during systematic review production varies widely: a scoping review
Nussbaumer-Streit, B., Ellen, M., Klerings, I., Sfetcu, R., Riva, N., Mahmić-Kaknjo, M., Poulentzas, G., Martinez, P., Baladia, E., Ziganshina, L. E., et al. (2021) · Journal of Clinical Epidemiology · doi:10.1016/j.jclinepi.2021.05.019 · Cited by 98
Metadata
- Authors
- Balk, E. M., Chung, M., Chen, M. L., Chang, L. K. W., & Trikalinos, T. A.
- Venue
- Systematic Reviews
- Published
- 2013-11-07
- Volume
- 2
- Issue
- 1
- Pages
- 97-97
- ISSN
- 2046-4053 (ISSN-L)
- OpenAlex
- W2124837084
- Cited by
- 70
- References
- 5
- FWCI
- 3.23
- Type
- journal article
- Language
- en
- Open access
- gold
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.