Predicting sample size required for classification performance

• Published in: BMC medical informatics and decision making Vol. 12; no. 1; p. 8
• Main Authors: Figueroa, Rosa L, Zeng-Treitler, Qing, Kandula, Sasikiran, Ngo, Long H
• Format: Journal Article
• Language: English
• Published: London BioMed Central 15.02.2012; BioMed Central Ltd; Springer Nature B.V; BMC
• Subjects: Algorithms; Classification; Confidence intervals; Data Interpretation, Statistical; Data processing; Decision making; Diagnosis, Computer-Assisted; Experiments; Health Informatics; Humans; Informatics; Information Systems and Communication Service; Learning; Learning algorithms; Learning Curve; Machine learning; Management; Management of Computing and Information Systems; Medical records; Medical research; Medicine; Medicine & Public Health; Methods; Models, Statistical; Nonlinear Dynamics; Pattern Recognition, Automated; Predictive Value of Tests; Probability Learning; Problem-Based Learning - methods; Reproducibility of Results; Research Article; Sample Size; Sampling; Stochastic Processes; Studies; United States; Learning Curve; Mean Absolute Error; Annotate Data; Root Mean Square Error; Active Learning
• ISSN: 1472-6947; 1472-6947
• DOI: 10.1186/1472-6947-12-8

Background Supervised learning methods need annotated data in order to generate efficient models. Annotated data, however, is a relatively scarce resource and can be expensive to obtain. For both passive and active learning methods, there is a need to estimate the size of the annotated sample required to reach a performance target. Methods We designed and implemented a method that fits an inverse power law model to points of a given learning curve created using a small annotated training set. Fitting is carried out using nonlinear weighted least squares optimization. The fitted model is then used to predict the classifier's performance and confidence interval for larger sample sizes. For evaluation, the nonlinear weighted curve fitting method was applied to a set of learning curves generated using clinical text and waveform classification tasks with active and passive sampling methods, and predictions were validated using standard goodness of fit measures. As control we used an un-weighted fitting method. Results A total of 568 models were fitted and the model predictions were compared with the observed performances. Depending on the data set and sampling method, it took between 80 to 560 annotated samples to achieve mean average and root mean squared error below 0.01. Results also show that our weighted fitting method outperformed the baseline un-weighted method (p < 0.05). Conclusions This paper describes a simple and effective sample size prediction algorithm that conducts weighted fitting of learning curves. The algorithm outperformed an un-weighted algorithm described in previous literature. It can help researchers determine annotation sample size for supervised machine learning.