A case study of using artificial neural networks for classifying cause of death from verbal autopsy
The DOI matches its Crossref record.
Abstract
Background Artificial neural networks (ANN) are gaining prominence as a method of classification in a wide range of disciplines. In this study ANN is applied to data from a verbal autopsy study as a means of classifying cause of death. Methods A simulated ANN was trained on a subset of verbal autopsy data, and the performance was tested on the remaining data. The performance of the ANN models were compared to two other classification methods (physician review and logistic regression) which have been tested on the same verbal autopsy data. Results Artificial neural network models were as accurate as or better than the other techniques in estimating the cause-specific mortality fraction (CSMF). They estimated the CSMF within 10% of true value in 8 out of 16 causes of death. Their sensitivity and specificity compared favourably with that of data-derived algorithms based on logistic regression models. Conclusions Cross-validation is crucial in preventing the over-fitting of the ANN models to the training data. Artificial neural network models are a potentially useful technique for classifying causes of death from verbal autopsies. Large training data sets are needed to improve the performance of data-derived algorithms, in particular ANN models. KEY MESSAGES Artifical neural networks have potential for classifying causes of death from verbal autopsies. Large datasets are needed to train neural networks and for validating their performance. Generalizability of neural network models to various settings needs further evaluation.
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
Cited by
Clinical, educational, and epidemiological value of autopsy
Burton, J. L., & Underwood, J. (2007) · The Lancet · doi:10.1016/s0140-6736(07)60376-6 · Cited by 440
Verbal Autopsy: Methods in Transition
Fottrell, E., & Byass, P. (2010) · Epidemiologic Reviews · doi:10.1093/epirev/mxq003 · Cited by 195
“Extensive use of open-ended questions and the subjective nature of physician review has face validity because of its similarity to taking medical histories (69), but it means that specific techniques used for diagnosis can differ considerably between individuals over time and between settings (27, 67), and final diagn…”
BackgroundMethodInfluentialMurray, C. J., Lopez, A. D., Black, R., Ahuja, R., Ali, S. M., Baqui, A., Dandona, L., Dantzer, E., Das, V., Dhingra, U., et al. (2011) · Population Health Metrics · doi:10.1186/1478-7954-9-27 · Cited by 194
“A variety of methods have been proposed for VA cause assignment [1,2], ranging from physician-certified verbal autopsy (PCVA) [3,4] to data-derived algorithms [5-7], various applications of Bayes’ theorem [8-13], and direct statistical estimation of cause fractions [14].”
MethodMurray, C. J., Lozano, R., Flaxman, A. D., Vahdatpour, A., & Lopez, A. D. (2011) · Population Health Metrics · doi:10.1186/1478-7954-9-28 · Cited by 96
The Global Network Neonatal Cause of Death algorithm for low‐resource settings
Garces, A. L., McClure, E. M., Pérez, W., Hambidge, K. M., Krebs, N. F., Figueroa, L., Bose, C. L., Carlo, W. A., Tenge, C., Esamai, F., et al. (2017) · Acta Paediatrica · doi:10.1111/apa.13805 · Cited by 30
Metadata
- Authors
- Boulle, A., Chandramohan, D., & Weller, P.
- Venue
- International Journal of Epidemiology
- Publisher
- Oxford University Press (OUP)
- Published
- 2001-06
- Volume
- 30
- Issue
- 3
- Pages
- 515-520
- ISSN
- 0300-5771 (ISSN-L)
- 1464-3685
- OpenAlex
- W2162504357
- Cited by
- 49
- References
- 0
- FWCI
- 3.32
- Type
- journal article
- Language
- en
- Open access
- closed
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.