Statistical evaluation of diagnostic performance in general and Receiver Operating Characteristic (ROC) analysis in particular are important for assessing the performance of medical tests and statistical classifiers, as well as for evaluating predictive models or algorithms. This book presents innovative approaches in ROC analysis, which are releva
This book describes statistical techniques for the design and evaluation of research studies on medical diagnostic tests, screening tests, biomarkers and new technologies for classification and prediction in medicine.
Praise for the First Edition " . . . the book is a valuable addition to the literature in the field, serving as a much-needed guide for both clinicians and advanced students."—Zentralblatt MATH A new edition of the cutting-edge guide to diagnostic tests in medical research In recent years, a considerable amount of research has focused on evolving methods for designing and analyzing diagnostic accuracy studies. Statistical Methods in Diagnostic Medicine, Second Edition continues to provide a comprehensive approach to the topic, guiding readers through the necessary practices for understanding these studies and generalizing the results to patient populations. Following a basic introduction to measuring test accuracy and study design, the authors successfully define various measures of diagnostic accuracy, describe strategies for designing diagnostic accuracy studies, and present key statistical methods for estimating and comparing test accuracy. Topics new to the Second Edition include: Methods for tests designed to detect and locate lesions Recommendations for covariate-adjustment Methods for estimating and comparing predictive values and sample size calculations Correcting techniques for verification and imperfect standard biases Sample size calculation for multiple reader studies when pilot data are available Updated meta-analysis methods, now incorporating random effects Three case studies thoroughly showcase some of the questions and statistical issues that arise in diagnostic medicine, with all associated data provided in detailed appendices. A related web site features Fortran, SAS®, and R software packages so that readers can conduct their own analyses. Statistical Methods in Diagnostic Medicine, Second Edition is an excellent supplement for biostatistics courses at the graduate level. It also serves as a valuable reference for clinicians and researchers working in the fields of medicine, epidemiology, and biostatistics.
Technology assessment can lead to the rapid application of essential diagnostic technologies and prevent the wide diffusion of marginally useful methods. In both of these ways, it can increase quality of care and decrease the cost of health care. This comprehensive monograph carefully explores methods of and barriers to diagnostic technology assessment and describes both the rationale and the guidelines for meaningful evaluation. While proposing a multi-institutional approach, it emphasizes some of the problems involved and defines a mechanism for improving the evaluation and use of medical technology and essential resources needed to enhance patient care.
Getting the right diagnosis is a key aspect of health care - it provides an explanation of a patient's health problem and informs subsequent health care decisions. The diagnostic process is a complex, collaborative activity that involves clinical reasoning and information gathering to determine a patient's health problem. According to Improving Diagnosis in Health Care, diagnostic errors-inaccurate or delayed diagnoses-persist throughout all settings of care and continue to harm an unacceptable number of patients. It is likely that most people will experience at least one diagnostic error in their lifetime, sometimes with devastating consequences. Diagnostic errors may cause harm to patients by preventing or delaying appropriate treatment, providing unnecessary or harmful treatment, or resulting in psychological or financial repercussions. The committee concluded that improving the diagnostic process is not only possible, but also represents a moral, professional, and public health imperative. Improving Diagnosis in Health Care, a continuation of the landmark Institute of Medicine reports To Err Is Human (2000) and Crossing the Quality Chasm (2001), finds that diagnosis-and, in particular, the occurrence of diagnostic errorsâ€"has been largely unappreciated in efforts to improve the quality and safety of health care. Without a dedicated focus on improving diagnosis, diagnostic errors will likely worsen as the delivery of health care and the diagnostic process continue to increase in complexity. Just as the diagnostic process is a collaborative activity, improving diagnosis will require collaboration and a widespread commitment to change among health care professionals, health care organizations, patients and their families, researchers, and policy makers. The recommendations of Improving Diagnosis in Health Care contribute to the growing momentum for change in this crucial area of health care quality and safety.
The aim of this book is to present statistical problems and methods in a friendly way to radiologists, emphasizing statistical issues and methods most frequently used in radiological studies (e.g., nonparametric tests, analysis of intra- and interobserver reproducibility, comparison of sensitivity and specificity among different imaging modality, difference between clinical and screening application of diagnostic tests, ect.). The tests will be presented starting from a radiological "problem" and all examples of statistical methods applications will be "radiological".
Since ROC curves have become ubiquitous in many application areas, the various advances have been scattered across disparate articles and texts. ROC Curves for Continuous Data is the first book solely devoted to the subject, bringing together all the relevant material to provide a clear understanding of how to analyze ROC curves.The fundamenta
This book is the first exclusively devoted to the systematic synthesis of diagnostic test accuracy studies. It builds upon the major recent developments in reporting standards, search methods, and, in particular, statistical tools specifically devoted to diagnostic studies. In addition, it borrows extensively from the latest advances in systematic reviews and meta-analyses of intervention studies. After a section dedicated to methods for designing reviews, synthesizing evidence and appraising inconsistency in research, the application of these approaches is demonstrated in the context of case studies from various clinical disciplines. Diagnosis is central in medical decision-making, and in many other fields of human endeavor, such as education and psychology. The plurality of sources of evidence on diagnostic test accuracy poses a huge challenge for practitioners and researchers, as do the multiple dimensions of evidence validity, which include sensitivity, specificity, predictive values, and likelihood ratios. This book offers an invaluable resource for anyone aiming to improve decision-making processes in diagnosis, classification or risk prognostication, from epidemiologists to biostatisticians, radiologists, laboratory physicians and graduate students, as any physician interested in refining his methodological skills in clinical diagnosis.
In biomedical studies, it is usually the case that several diagnostic tests can be performedon an individual or multiple disease markers are available simultaneously, and that many of them may be associated with the clinical outcome. In practice, a single test or marker often has limited diagnostic performance. Therefore, it is important to combine multiple sources of information available to achieve higher classification performance. This dissertation focuses on statistical methods for combining multiple diagnostic tests and the corresponding performance evaluation metrics. In the first project, we provide a survey of the current state of the art in methods for combining multiple tests. We categorize existing methods into three general groups and conduct extensive simulation studies to compare the performance of different combination methods. The reviewed methods serve as benchmark for developing new combination approaches in the following projects. In the second project, we consider the problem of combining multiple tests whose values are missing at random (MAR). In addition, we aim to exploit the known monotonicity relationship between the input variables and the disease outcome for gains in diagnostic accuracy. We develop a novel likelihood-based approach to monotone classification that accounts for missing inputs in a natural and principled way. The risk score function is obtained through the nonparametric maximum likelihood estimation (NPMLE). A novel expectation-maximization (EM)-type algorithm is devised to compute the NPMLE by treating the monotonicity-constrained risk score function as a cumulative distribution for a latent random vector. Through simulation studies and a real data example, we demonstrate that the proposed method outperforms state-of-the-art methods for combining multiple inputs under monotonic assumption, especially when the inputs contain missing data. We illustrate our approach with a dataset from a recent nonalcoholic fatty liver disease (NALFD) study. In the third project, our approach established in the second part is extended to the scenario where one covariate is randomly censored. The proposed approach consists of two steps. In step one, we use a Cox proportional hazards model for the distribution of the censored covariate given other covariates in the model, this conditional distribution is used for calculating the observed likelihood of data. In step two, a similar expectation maximization (EM)-type algorithm is devised, based on observed data likelihood from step one, to compute the NPMLE of the monotonicity-constrained risk score function. Through simulation studies, we demonstrate that the proposed method outperforms the simple but inefficient complete-case analysis as well as the substitution methods. We apply our method to the data set from a primary biliary cirrhosis (PBC) study conducted at Mayo Clinic. The proposed methods in part two and three can be extended to multi-class cases, where the labels have an inherent order but no meaningful numeric distance between them. A natural question arises as to how to evaluate the classification performance under such setting. Therefore, in the fourth project, we consider the problem of performance evaluation metrics for ordinal classification. We propose three novel performance evaluation metrics that better capture the ordinality of the outcomes. The first metric is adapted from the area under the receiver operating characteristic (ROC) curve (AUC), while the latter two are simple and interpretable generalizations of the Harrell's concordance index (C-INDEX). Moreover, we show the optimality of the AUC based metrics through Neyman-Pearson lemma. We conduct extensive simulation studies to confirm the usefulness of the proposed performance metrics for ordinal classification.
