CoChat
Sign Up
Cited by 20Artificial Intelligence in HealthcareMachine Learning in HealthcareStatistical Methods and Bayesian Inference

The DOI matches its Crossref record.

The effect of imputing missing clinical attribute values on training lung cancer survival prediction model performance

Open access
Barakat, Mohamed S., Field, Matthew, Ghose, Aditya, Stirling, David, Holloway, Lois, Vinod, Shalini, Dekker, Andre, Thwaites, David·2017·Health Information Science and Systems
DOI 10.1007/s13755-017-0039-4PMC PMC5718991
Open this paper in CoChat — free accountOpen PDF

Abstract

According to the estimations of the World Health Organization and the International Agency for Research in Cancer, lung cancer is the most common cause of death from cancer worldwide. The last few years have witnessed a rise in the attention given to the use of clinical decision support systems in medicine generally and in cancer in particular. These can predict patients' likelihood of survival based on analysis of and learning from previously treated patients. The datasets that are mined for developing clinical decision support functionality are often incomplete, which adversely impacts the quality of the models developed and the decision support offered. Imputing missing data using a statistical analysis approach is a common method to addressing the missing data problem. This work investigates the effect of imputation methods for missing data in preparing a training dataset for a Non-Small Cell Lung Cancer survival prediction model using several machine learning algorithms. The investigation includes an assessment of the effect of imputation algorithm error on performance prediction and also a comparison between using a smaller complete real dataset or a larger dataset with imputed data. Our results show that even when the proportion of records with some missing data is very high (> 80%) imputation can lead to prediction models with an AUC (0.68-0.72) comparable to those trained with complete data records.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s13755-017-0039-4

Cites

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The most prominent data quality dimension in the DL papers is amount of data, which is empirically shown to benefit performance, albeit in a saturating manner.

    “The most prominent dimension is amount of data123–126,129,146–159,183–189 which is empirically shown to benefit performance, albeit in a saturating manner.”

    From The METRIC-framework for assessing data quality for trustworthy AI in medicine: A systematic review (2024) · cites this paper as [126]

    The Introduction says larger datasets improve model reliability, and “Imputations versus no imputation” reports that external-test AUC generally declined as training data decreased. That section also says the decline was relatively modest, but it does not establish a general saturating performance curve, particularly for deep-learning models. The claim that amount of data is the most prominent dimension across DL papers is the citing authors’ synthesis, not a finding established by this study. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • Another dominant topic in the DL papers is completeness, which the ML community almost exclusively refers to as missing data.

    “Another dominant topic is completeness to which the ML community almost exclusively refers to as missing data119,125–128,133–135,182.”

    From The METRIC-framework for assessing data quality for trustworthy AI in medicine: A systematic review (2024) · cites this paper as [126]

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

No references could be resolved yet.

Research works printed but not linked: 27

  1. Dekker A, et al. Rapid learning in practice: a lung cancer survival decision support system in routine patient care data. Radiother Oncol. 2014;113(1):47–53. · DOI
  2. Abernethy AP, et al. Rapid-learning system for cancer care. J Clin Oncol. 2010;28(27):4268–74. · DOI
  3. Sammut C, Webb GI. Encyclopedia of machine learning. Berlin: Springer; 2011.
  4. Beleites C, Neugebauer U, Bocklitz T, Krafft C, Popp J. Sample size planning for classification models. Anal Chim Acta. 2013;760:25–33. · DOI
  5. García-Laencina PJ, Abreu PH, Abreu MH, Afonoso N. Missing data imputation on the 5-year survival prediction of breast cancer patients with unknown discrete values. Comput Biol Med. 2015;59:125–33. · DOI
  6. Jayasurya K, et al. Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy. Med Phys. 2010;37(4):1401. · DOI
  7. García-Laencina PJ, Sancho-Gómez J-L, Figueiras-Vidal AR. Pattern classification with missing data: a review. Neural Comput Appl. 2009;19(2):263–82. · DOI
  8. Sterne JAC, et al. Multiple imputation for missing data in epidemiological and clinical research: potential and pitfalls. BMJ. 2009;338:b2393. · DOI · Paper page
  9. Jochems A, et al. Distributed learning: developing a predictive model based on data from multiple hospitals without data leaving the hospital—a real life proof of concept. Radiother Oncol. 2016;121(3):459–67. · DOI
  10. Kang J, Schwartz R, Flickinger J, Beriwal S. Machine learning approaches for predicting radiation therapy outcomes: a clinician’s perspective. Int J Radiat Oncol. 2015;93(5):1127–35. · DOI
  11. Olinsky A, Chen S, Harlow L. The comparative efficacy of imputation methods for missing data in structural equation modeling. Eur J Oper Res. 2003;151(1):53–79. · DOI
  12. Steyerberg EW, van Veen M. Imputation is beneficial for handling missing data in predictive models. J Clin Epidemiol. 2007;60(9):979. · DOI
  13. Opitz D, Maclin R (1999) Popular ensemble methods: an empirical study. http://jair.org/papers/paper614.html . Accessed 24 Oct 2016. · DOI · Paper page
  14. Rokach L. Ensemble-based classifiers. Artif Intell Rev. 2009;33(1–2):1–39.
  15. Polikar R. Ensemble based systems in decision making. IEEE Circuits Syst Mag. 2006;6(3):21–45. · DOI
  16. Seni G, Elder JF. Ensemble methods in data mining: improving accuracy through combining predictions. Synth Lect Data Min Knowl Discov. 2010;2(1):1–126. · DOI
  17. Little RJ. A test of missing completely at random for multivariate data with missing values. J Am Stat Assoc. 1988;83(404):1198–202. · DOI · Paper page
  18. Rubin DB. Inference and missing data. Biometrika. 1976;63(3):581–92. · DOI · Paper page
  19. Rubin DB. Multiple imputation for nonresponse in surveys, vol. 81. New York: Wiley; 2004.
  20. Aste M, Boninsegna M, Freno A, Trentin E. Techniques for dealing with incomplete data: a tutorial and survey. Pattern Anal Appl. 2014;18(1):1–29. · DOI
  21. Rahman G, Islam Z. A decision tree-based missing value imputation technique for data pre-processing. In: Proceedings of the ninth Australasian data mining conference—volume 121, Darlinghurst, Australia, 2011, p. 41–50.
  22. Berghmans T, Paesmans M, Sculier J-P. Prognostic factors in stage III non-small cell lung cancer: a review of conventional, metabolic and new biological variables. Ther Adv Med Oncol. 2011;3(3):127–38. · DOI
  23. Oberije C, et al. A Validated prediction model for overall survival from stage iii non-small cell lung cancer: toward survival prediction for individual patients. Int J Radiat Oncol. 2015;92(4):935–44. · DOI
  24. Hall Mark, Frank Eibe, Holmes Geoffrey, Pfahringer Bernhard, Reutemann Peter, Witten Ian H. The WEKA data mining software: an update. SIGKDD Explor. 2009;11(1):10–8. · DOI · Paper page
  25. Swets JA. Signal detection theory and ROC analysis in psychology and diagnostics: collected papers. New York: Psychology Press; 2014. · DOI
  26. Caruana R, Niculescu-Mizil A. An empirical comparison of supervised learning algorithms. In: Proceedings of the 23rd international conference on machine learning, New York, NY, USA, 2006, p. 161–168. · DOI · Paper page
  27. Schunk D. A Markov chain Monte Carlo algorithm for multiple imputation in large surveys. AStA Adv Stat Anal. 2008;92(1):101–14. · DOI

Cited by

Sorted by citations

Metadata

Authors
Barakat, M. S., Field, M., Ghose, A., Stirling, D., Holloway, L., Vinod, S., Dekker, A., & Thwaites, D.
Affiliations
  • UNSW Sydney (AU)
  • University of Wollongong (AU)
  • Maastricht University (NL)
  • The University of Sydney (AU)
Corresponding author
Barakat, Mohamed S.
ORCID
Venue
Health Information Science and Systems
Publisher
Springer Science and Business Media LLC
Published
2017-12
Volume
5
Issue
1
Pages
16-16
ISSN
2047-2501 (ISSN-L)
DOI
10.1007/s13755-017-0039-4
PMC
PMC5718991
OpenAlex
W2773512394
Cited by
20
References
0
Citations by year
2025: 6 · 2024: 3 · 2023: 1 · 2022: 2 · 2021: 2 · 2020: 3 · 2019: 1 · 2018: 2
FWCI
2.25
Type
journal article
Language
en
Open access
Licence
www.springer.com/tdm (unspecified)
Locations
  • Health Information Science and Systems (publishedVersion)
  • Europe PMC (PubMed Central) (publishedVersion)
  • PubMed Central (publishedVersion)
  • PubMed (publishedVersion)
  • Research Publications (Maastricht University) (publishedVersion, other-oa)
  • Research Online (University of Wollongong) (submittedVersion)
  • Figshare (submittedVersion)
  • UNSWorks (UNSW Sydney) (submittedVersion, cc-by-nc-nd)
  • Research Publications (Maastricht University) (submittedVersion, other-oa)
Funders
NSW Office Of Health and Medical Research (AUS) (RG14/11)
Topics
  • Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
  • Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning in Healthcare
  • Physical Sciences › Mathematics › Statistics and Probability › Statistical Methods and Bayesian Inference
Keywords
missing data imputation, non-small cell lung cancer, clinical decision support systems, imputation error, training data size, machine learning model performance

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