The DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Handling limited datasets with neural networks in medical applications: A small-data approach
Open accessAbstract
MOTIVATION: Single-centre studies in medical domain are often characterised by limited samples due to the complexity and high costs of patient data collection. Machine learning methods for regression modelling of small datasets (less than 10 observations per predictor variable) remain scarce. Our work bridges this gap by developing a novel framework for application of artificial neural networks (NNs) for regression tasks involving small medical datasets. METHODS: In order to address the sporadic fluctuations and validation issues that appear in regression NNs trained on small datasets, the method of multiple runs and surrogate data analysis were proposed in this work. The approach was compared to the state-of-the-art ensemble NNs; the effect of dataset size on NN performance was also investigated. RESULTS: The proposed framework was applied for the prediction of compressive strength (CS) of femoral trabecular bone in patients suffering from severe osteoarthritis. The NN model was able to estimate the CS of osteoarthritic trabecular bone from its structural and biological properties with a standard error of 0.85MPa. When evaluated on independent test samples, the NN achieved accuracy of 98.3%, outperforming an ensemble NN model by 11%. We reproduce this result on CS data of another porous solid (concrete) and demonstrate that the proposed framework allows for an NN modelled with as few as 56 samples to generalise on 300 independent test samples with 86.5% accuracy, which is comparable to the performance of an NN developed with 18 times larger dataset (1030 samples). CONCLUSION: The significance of this work is two-fold: the practical application allows for non-destructive prediction of bone fracture risk, while the novel methodology extends beyond the task considered in this study and provides a general framework for application of regression NNs to medical problems characterised by limited dataset sizes.
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
An Algorithm for Least-Squares Estimation of Nonlinear Parameters
Marquardt, D. W. (1963) · Journal of the Society for Industrial and Applied Mathematics · doi:10.1137/0111030 · Cited by 30,728
Neural Networks: A Comprehensive Foundation
Haykin, S. (1998) · Cited by 30,070
Multilayer feedforward networks are universal approximators
Hornik, K., Stinchcombe, M., & White, H. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90020-8 · Cited by 21,728
A method for the solution of certain non-linear problems in least squares
Levenberg, K. (1944) · Quarterly of Applied Mathematics · doi:10.1090/qam/10666 · Cited by 12,359
Multilayer feedforward networks are universal approximators
HornikK., StinchcombeM., & WhiteH. (1989) · Neural Networks · doi:10.5555/70405.70408 · Cited by 9,081
The Levenberg-Marquardt algorithm: Implementation and theory
Moré, J. J. (1978) · Lecture Notes in Mathematics · doi:10.1007/bfb0067700 · Cited by 5,773
Testing for nonlinearity in time series: the method of surrogate data
Theiler, J., Eubank, S., Longtin, A., Galdrikian, B., & Doyne Farmer, J. (1992) · Physica D: Nonlinear Phenomena · doi:10.1016/0167-2789(92)90102-s · Cited by 3,732
Popular Ensemble Methods: An Empirical Study
Opitz, D., & Maclin, R. (1999) · Journal of Artificial Intelligence Research · doi:10.1613/jair.614 · Cited by 2,953 · cited 1×
“Optiz & Maclin showed that this ensemble approach was “surprisingly effective, often producing results as good as Bag-ging” [43].”
Dietterich, T. G. (2000) · Machine Learning · doi:10.1023/a:1007607513941 · Cited by 2,941
Neural computing: theory and practice
(1989) · Choice Reviews Online · doi:10.5860/choice.27-1569 · Cited by 1,663
Improved Surrogate Data for Nonlinearity Tests
Schreiber, T., & Schmitz, A. (1996) · Physical Review Letters · doi:10.1103/physrevlett.77.635 · Cited by 1,506
Estimation of prediction error by using K-fold cross-validation
Fushiki, T. (2011) · Statistics and Computing · doi:10.1007/s11222-009-9153-8 · Cited by 1,470
Modeling of strength of high-performance concrete using artificial neural networks
Yeh, I.-C. (1998) · Cement and Concrete Research · doi:10.1016/s0008-8846(98)00165-3 · Cited by 1,447
Nguyen, D., & Widrow, B. (1990) · 1990 IJCNN International Joint Conference on Neural Networks · doi:10.1109/ijcnn.1990.137819 · Cited by 1,375
Artificial neural networks in medical diagnosis
Amato, F., López, A., Peña-Méndez, E. M., Vaňhara, P., Hampl, A., & Havel, J. (2013) · Journal of Applied Biomedicine · doi:10.2478/v10136-012-0031-x · Cited by 898
Nonparametric Statistical Methods, 2nd, Ed.
Borror, C. M. (2001) · Journal of Quality Technology · doi:10.1080/00224065.2001.11980073 · Cited by 874
Bone Compressive Strength: The Influence of Density and Strain Rate
Carter, D. R., & Hayes, W. C. (1976) · Science · doi:10.1126/science.996549 · Cited by 709
Prediction of femoral fracture load using automated finite element modeling
Keyak, J. H., Rossi, S. A., Jones, K. A., & Skinner, H. B. (1997) · Journal of Biomechanics · doi:10.1016/s0021-9290(97)00123-1 · Cited by 682
Mathematical relationships between bone density and mechanical properties: A literature review
Helgason, B., Perilli, E., Schileo, E., Taddei, F., Brynjólfsson, S., & Viceconti, M. (2008) · Clinical Biomechanics · doi:10.1016/j.clinbiomech.2007.08.024 · Cited by 589
Statistical Methods for the Analysis of Biomedical Data
Ziegel, E., & Woolson, R. F. (1989) · Technometrics · doi:10.2307/1268847 · Cited by 583
Cellular Materials in Nature and Medicine
Gibson, L. J., Ashby, M. F., & Harley, B. A. C. (2010) · Cited by 490
Osteoarthritis: Diagnosis and Treatment
(1961) · BMJ · doi:10.1136/bmj.1.5222.355-a · Cited by 452
Optimal division of data for neural network models in water resources applications
Bowden, G. J., Maier, H. R., & Dandy, G. C. (2002) · Water Resources Research · doi:10.1029/2001wr000266 · Cited by 322
Li, D.-C., Wu, C.-S., Tsai, T.-I., & Lina, Y.-S. (2007) · Computers & Operations Research · doi:10.1016/j.cor.2005.05.019 · Cited by 223
Comparing Sigmoid Transfer Functions for Neural Network Multistep Ahead Streamflow Forecasting
Yonaba, H., Anctil, F., & Fortin, V. (2010) · Journal of Hydrologic Engineering · doi:10.1061/(asce)he.1943-5584.0000188 · Cited by 208
Stability problems with artificial neural networks and the ensemble solution
Cunningham, P., Carney, J., & Jacob, S. (2000) · Artificial Intelligence in Medicine · doi:10.1016/s0933-3657(00)00065-8 · Cited by 198
Neural Networks and Artificial Intelligence for Biomedical Engineering
Hudson, D. L., & Cohen, M. E. (1999) · Institute of Electrical and Electronics Engineers eBooks · doi:10.1109/9780470545355 · Cited by 185
Learning from Little: Comparison of Classifiers Given Little Training
Forman, G., & Cohen, I. (2004) · Lecture notes in computer science · doi:10.1007/978-3-540-30116-5_17 · Cited by 163
Bone mineral density in osteoarthritis
Stewart, A., & Black, A. J. (2000) · Current Opinion in Rheumatology · doi:10.1097/00002281-200009000-00021 · Cited by 111
Machine Learning: An Indispensable Tool in Bioinformatics
Inza, I., Calvo, B., Armañanzas, R., Bengoetxea, E., Larrañaga, P., & Lozano, J. A. (2009) · Methods in molecular biology · doi:10.1007/978-1-60327-194-3_2 · Cited by 103
A bootstrap evaluation of the effect of data splitting on financial time series
LeBaron, B. D., & Weigend, A. S. (1998) · IEEE Transactions on Neural Networks · doi:10.1109/72.655043 · Cited by 103
Springer Handbook of Bio-/Neuroinformatics
Liang, L., Krishnamurthi, R., Kasabov, N. K., & Feigin, V. (2013) · Springer handbooks · doi:10.1007/978-3-642-30574-0 · Cited by 98
Eller-Vainicher, C., Zhukouskaya, V. V., Tolkachev, Y. V., Koritko, S. S., Cairoli, E., Grossi, E., Beck-Peccoz, P., Chiodini, I., & Shepelkevich, A. P. (2011) · Diabetes Care · doi:10.2337/dc11-0764 · Cited by 88
Power of surrogate data testing with respect to nonstationarity
Timmer, J. (1998) · Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics · doi:10.1103/physreve.58.5153 · Cited by 81
Perilli, E., Baleani, M., Öhman‐Mägi, C., Baruffaldi, F., & Viceconti, M. (2007) · Bone · doi:10.1016/j.bone.2007.07.014 · Cited by 79
Computational Modeling in Tissue Engineering
Geris, L. (2012) · Studies in mechanobiology, tissue engineering and biomaterials · doi:10.1007/978-3-642-32563-2 · Cited by 72
Bessho, M., Ohnishi, I., Okazaki, H., Sato, W., Kominami, H., Matsunaga, S., & Nakamura, K. (2004) · Journal of Orthopaedic Science · doi:10.1007/s00776-004-0824-1 · Cited by 62
Bone mineral density and association of osteoarthritis with fracture risk
Chan, M. Y., Eisman, J. A., & Nguyen, T. V. (2014) · Osteoarthritis and Cartilage · doi:10.1016/j.joca.2014.07.004 · Cited by 47
Neural networks for analysis of trabecular bone in osteoarthritis
Khovanova, N. A., Shaikhina, T., & Mallick, K. K. (2014) · Bioinspired Biomimetic and Nanobiomaterials · doi:10.1680/bbn.14.00006 · Cited by 26
Self-citationArtificial Neural Networks and Predictive Medicine: a Revolutionary Paradigm Shift
Grossi, E. (2011) · InTech eBooks · doi:10.5772/15810 · Cited by 25
Machine Learning Methodology in Bioinformatics
Campbell, C. (2013) · Springer eBooks · doi:10.1007/978-3-642-30574-0_12 · Cited by 16
Shaikhina, T., Khovanova, N. A., & Mallick, K. K. (2014) · IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI ...) · doi:10.1109/bhi.2014.6864441 · Cited by 16
Self-citationSurveying the methods of improving ANN generalization capability
Zhang, S., Liu, H., Gao, D., & Wang, W. (2004) · International Conference on Machine Learning and Cybernetics · doi:10.1109/icmlc.2003.1259681 · Cited by 16
Testing a neural coding hypothesis using surrogate data
Hirata, Y., Katori, Y., Shimokawa, H., Suzuki, H., Blenkinsop, T. A., Lang, E. J., & Aihara, K. (2008) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2008.05.004 · Cited by 15
Cited by
Artificial intelligence: Implications for the future of work
Howard, J. (2019) · American Journal of Industrial Medicine · doi:10.1002/ajim.23037 · Cited by 522
Evaluation of a decided sample size in machine learning applications
Rajput, D., Wang, W.-J., & Chen, C.-C. (2023) · BMC Bioinformatics · doi:10.1186/s12859-023-05156-9 · Cited by 411
“The winner’s curse reportedly inflates the effect size in small sample size studies because of random errors, selective analysis, selective outcomes reporting, and publication bias [7].”
BackgroundShaikhina, T., Lowe, D., Daga, S., Briggs, D., Higgins, R., & Khovanova, N. (2019) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2017.01.012 · Cited by 361
Self-citationOn the class overlap problem in imbalanced data classification
Vuttipittayamongkol, P., Elyan, E., & Petrovski, A. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2020.106631 · Cited by 290
Benchmarking Parametric and Machine Learning Models for Genomic Prediction of Complex Traits
Azodi, C. B., Bolger, E., McCarren, A., Roantree, M., de los Campos, G., & Shiu, S.-H. (2019) · G3 Genes|Genomes|Genetics · doi:10.1534/g3.119.400498 · Cited by 259
Metadata
- Authors
- Shaikhina, T., & Khovanova, N. A.
- Venue
- Artificial Intelligence in Medicine
- Publisher
- Elsevier BV
- Published
- 2017-01
- Volume
- 75
- Pages
- 51-63
- ISSN
- 0933-3657 (ISSN-L)
- OpenAlex
- W2568988948
- Cited by
- 296
- References
- 44
- FWCI
- 14.10
- Type
- journal article
- Language
- en
- Open access
- hybrid
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.