Sample size estimation in diagnostic test studies of biomedical informatics

OBJECTIVES This review provided a conceptual framework of sample size calculations in the studies of diagnostic test accuracy in various conditions and test outcomes. METHODS The formulae of sample size calculations for estimation of adequate sensitivity/specificity, likelihood ratio and AUC as an overall index of accuracy and also for testing in single modality and comparing two diagnostic tasks have been presented for desired confidence interval. RESULTS The required sample sizes were calculated and tabulated with different levels of accuracies and marginal errors with 95% confidence level for estimating and for various effect sizes with 80% power for purpose of testing as well. The results show how sample size is varied with accuracy index and effect size of interest. CONCLUSION This would help the clinicians when designing diagnostic test studies that an adequate sample size is chosen based on statistical principles in order to guarantee the reliability of study.

[1]  Augusto Azuara-Blanco,et al.  Sample size in studies on diagnostic accuracy in ophthalmology: a literature survey , 2007, British Journal of Ophthalmology.

[2]  Lucas M Bachmann,et al.  Sample sizes of studies on diagnostic accuracy: literature survey , 2006, BMJ : British Medical Journal.

[3]  Gregory F Cooper,et al.  Research Paper: Creating a Text Classifier to Detect Radiology Reports Describing Mediastinal Findings Associated with Inhalational Anthrax and Other Disorders , 2003, J. Am. Medical Informatics Assoc..

[4]  J. Hanley.  Receiver operating characteristic (ROC) methodology: the state of the art. , 1989, Critical reviews in diagnostic imaging.

[5]  H E Rockette,et al.  Empiric assessment of parameters that affect the design of multireader receiver operating characteristic studies. , 1999, Academic radiology.

[6]  James A Hanley,et al.  Comparison of three methods for estimating the standard error of the area under the curve in ROC analysis of quantitative data. , 2002, Academic radiology.

[7]  N A Obuchowski,et al.  Sample size calculations in studies of test accuracy , 1998, Statistical methods in medical research.

[8]  Yindalon Aphinyanagphongs,et al.  Text Categorization Models for Retrieval of High Quality Articles in Internal Medicine , 2003, AMIA.

[9]  G. Samsa,et al.  Likelihood ratios with confidence: sample size estimation for diagnostic test studies. , 1991, Journal of clinical epidemiology.

[10]  N A Obuchowski,et al.  Computing Sample Size for Receiver Operating Characteristic Studies , 1994, Investigative radiology.

[11]  Jialiang Li,et al.  On sample size for sensitivity and specificity in prospective diagnostic accuracy studies , 2004, Statistics in medicine.

[12]  Rajeev Kumar,et al.  Receiver operating characteristic (ROC) curve for medical researchers , 2011, Indian pediatrics.

[13]  K. Zou,et al.  Receiver-Operating Characteristic Analysis for Evaluating Diagnostic Tests and Predictive Models , 2007, Circulation.

[14]  R. Newcombe,et al.  Confidence intervals for an effect size measure based on the Mann–Whitney statistic. Part 2: asymptotic methods and evaluation , 2006, Statistics in medicine.

[15]  William J. Long,et al.  Research Paper: Evaluation of a Cardiac Diagnostic Program in a Typical Clinical Setting , 2003, J. Am. Medical Informatics Assoc..

[16]  D. Bamber.  The area above the ordinal dominance graph and the area below the receiver operating characteristic graph , 1975 .

[17]  S. Carley,et al.  An introduction to power and sample size estimation , 2003, Emergency medicine journal : EMJ.

[18]  R. Connor.  Sample size for testing differences in proportions for the paired-sample design. , 1987, Biometrics.

[19]  C. Metz,et al.  A New Approach for Testing the Significance of Differences Between ROC Curves Measured from Correlated Data , 1984 .

[20]  S. Carley,et al.  Simple nomograms to calculate sample size in diagnostic studies , 2005, Emergency Medicine Journal.

[21]  Sabine Van Huffel,et al.  Preoperative prediction of malignancy of ovarian tumors using least squares support vector machines , 2003, Artif. Intell. Medicine.

[22]  K Linnet,et al.  Comparison of quantitative diagnostic tests: type I error, power, and sample size. , 1987, Statistics in medicine.

[23]  Geoffrey T Fosgate,et al.  Practical Sample Size Calculations for Surveillance and Diagnostic Investigations , 2009, Journal of veterinary diagnostic investigation : official publication of the American Association of Veterinary Laboratory Diagnosticians, Inc.

[24]  R. Brian Haynes,et al.  Sample size determination for bibliographic retrieval studies , 2008, BMC Medical Informatics Decis. Mak..

[25]  J. Hanley,et al.  A method of comparing the areas under receiver operating characteristic curves derived from the same cases. , 1983, Radiology.

[26]  J A Hanley,et al.  A Comparison of Parametric and Nonparametric Approaches to ROC Analysis of Quantitative Diagnostic Tests , 1997, Medical decision making : an international journal of the Society for Medical Decision Making.

[27]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[28]  C A Beam,et al.  Strategies for improving power in diagnostic radiology research. , 1992, AJR. American journal of roentgenology.

[29]  Qing Zeng-Treitler,et al.  Predicting sample size required for classification performance , 2012, BMC Medical Informatics and Decision Making.

[30]  R. Newcombe.  Two-sided confidence intervals for the single proportion: comparison of seven methods. , 1998, Statistics in medicine.

[31]  N. Buderer,et al.  Statistical methodology: I. Incorporating the prevalence of disease into the sample size calculation for sensitivity and specificity. , 1996, Academic emergency medicine : official journal of the Society for Academic Emergency Medicine.

[32]  N A Obuchowski,et al.  Sample size tables for receiver operating characteristic studies. , 2000, AJR. American journal of roentgenology.

[33]  J. Fleiss,et al.  Sample size determination in studies with matched pairs. , 1988, Journal of clinical epidemiology.

[34]  Nancy K Roderer,et al.  A current perspective on medical informatics and health sciences librarianship. , 2005, Journal of the Medical Library Association : JMLA.

[35]  Lucila Ohno-Machado,et al.  The use of receiver operating characteristic curves in biomedical informatics , 2005, J. Biomed. Informatics.

[36]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[37]  Haitao Chu,et al.  Sample size calculation using exact methods in diagnostic test studies. , 2007, Journal of clinical epidemiology.

[38]  C. Metz,et al.  Maximum likelihood estimation of receiver operating characteristic (ROC) curves from continuously-distributed data. , 1998, Statistics in medicine.

[39]  J A Hanley,et al.  Sampling variability of nonparametric estimates of the areas under receiver operating characteristic curves: an update. , 1997, Academic radiology.

[40]  M. Kramer,et al.  Clinical Epidemiology and Biostatistics , 1988, Springer Berlin Heidelberg.

[41]  A. Indrayan,et al.  A simple nomogram for sample size for estimating sensitivity and specificity of medical tests , 2010, Indian journal of ophthalmology.

[42]  J. Swets.  ROC analysis applied to the evaluation of medical imaging techniques. , 1979, Investigative radiology.

[43]  J M Lachin,et al.  Power and sample size evaluation for the McNemar test with application to matched case-control studies. , 1992, Statistics in medicine.

[44]  Abhaya Indrayan,et al.  A nomogram for single-stage cluster-sample surveys in a community for estimation of a prevalence rate. , 2002, International journal of epidemiology.

[45]  A. Flahault,et al.  Sample size calculation should be performed for design accuracy in diagnostic test studies. , 2005, Journal of clinical epidemiology.

[46]  A. Agresti,et al.  Approximate is Better than “Exact” for Interval Estimation of Binomial Proportions , 1998 .

[47]  Jason Fine,et al.  Sample size for positive and negative predictive value in diagnostic research using case-control designs. , 2008, Biostatistics.