Meta analysis of the use of Bayesian networks in breast cancer diagnosis Metanálise do uso de redes bayesianas no diagnóstico de câncer de mama Metaanálisis del uso de los modelos bayesianos en el diagnóstico de cáncer de mama

The aim of this study was to determine the accuracy of Bayesian networks in supporting breast cancer diagnoses. Systematic review and metaanalysis were carried out, including articles and papers published between January 1990 and March 2013. We included prospective and retrospective cross-sectional studies of the accuracy of diagnoses of breast lesions (target conditions) made using Bayesian networks (index test). Four primary studies that included 1,223 breast lesions were analyzed, 89.52% (444/496) of the breast cancer cases and 6.33% (46/727) of the benign lesions were positive based on the Bayesian network analysis. The area under the curve (AUC) for the summary receiver operating characteristic curve (SROC) was 0.97, with a Q* value of 0.92. Using Bayesian networks to diagnose malignant lesions increased the pretest probability of a true positive from 40.03% to 90.05% and decreased the probability of a false negative to 6.44%. Therefore, our results demonstrated that Bayesian networks provide an accurate and non-invasive method to support breast cancer diagnosis. Medical Informatics; Bayes Theorem; Breast Neoplasms Resumo O objetivo deste estudo foi avaliar a acurácia das redes bayesianas no apoio ao diagnóstico de câncer de mama. Foram realizadas revisão sistemática e metanálise, que incluíram artigos e relatórios publicados entre Janeiro de 1990 e Março de 2013. Foram incluídos estudos transversais prospectivos e retrospectivos que avaliaram a acurácia do diagnóstico de lesões de mama (condição alvo) usando as redes bayesianas (teste em avaliação). Quatro estudos primários que incluíram 1.223 lesões de mama foram analisados, 89,52% (444/496) dos casos de câncer de mama e 6,33% (46/727) das lesões benignas foram positivas tendo-se como base a análise das redes bayesianas. A área dentro da curva SROC (característica de operação do receptor sumária) foi 0,97, com um valor Q* de 0,92. O uso de redes bayesianas no diagnóstico de lesões malignas aumentou a probabilidade pré-teste para um verdadeiro positivo de 40,03% para 90,05% e diminuiu a probabilidade de um falso negativo para 6,44%. Portanto, nossos resultados demonstraram que as redes bayesianas oferecem um método acurado e não invasivo no apoio ao diagnóstico de câncer de mama. Informática Médica; Teorema de Bayes; Neoplasias da Mama Cad. Saúde Pública, Rio de Janeiro, 31(1):26-38, jan, 2015 http://dx.doi.org/10.1590/0102-311X00205213 REVISÃO REVIEW 26 USE OF BAYESIAN NETWORKS IN BREAST CANCER DIAGNOSIS 27 Cad. Saúde Pública, Rio de Janeiro, 31(1):26-38, jan, 2015 Introduction Breast cancer is the most common type of cancer in women, and it is also a common cause of cancer-related mortality, both in developing and developed countries. Approximately 1.4 million new cases occurred in 2008 worldwide, representing 23% of all cancers 1,2. Fortunately, the early detection of breast cancer can improve the chance of successful treatment and recovery 3. In recent decades, artificial intelligence has become widely accepted in medical applications 4. One such application is Bayesian networks, which are becoming widely used to represent knowledge domains in the presence of uncertainty from randomness. Bayesian networks can be used as an analysis and decision aid in the interpretation of the results of a diagnostic test (e.g. mammography), signs and symptoms when uncertainty is known to be a dominant factor 5. A Bayesian network is a graphical model that represents probabilistic relationships among variables of interest 6. Such networks consist of a qualitative component (i.e., the structural model), which provides a visual representation of the interactions among variables, and a quantitative component (i.e., a set of local probability distributions), which permits probabilistic inference. Together, these components determine the unique joint probability distribution over the variables in a specific problem 7. In clinical medical practice, professionals can calculate probabilities using Bayes’ theorem without a computer for a specific diagnosis with limited parameters (i.e., a few conditional probabilities). If the factors that modify the probability of disease have interactions, however, the complexity of such calculations can increase exponentially, making it difficult to solve without computational support. In this case, Bayesian networks may be useful 8. In the Bayesian networks, the nodes represent uncertain variables, and typically, there is a primary or “root” node that represents the variable of interest, other nodes impact the probability of that primary node 6,7. For example, in medical diagnosis, estimating the probability of an event, such as the malignancy of a breast mass (“root” node), given a set of evidence (i.e., demographics, image characteristics, etc.) is a problem that can be solved with Bayesian networks 8. Patient risk factors, signs, symptoms, and the results of diagnostic test are inputs of the system 8. Each node necessarily contains mutually exclusive and collectively exhaustive instances 6,7. Mutually exclusive instances refer to events that cannot occur at the same time. For example, if a coin toss is the variable of interest, heads and tails are the mutually exclusive instances of that variable because they cannot occur simultaneously 8. When both the structure and probabilities are established, the Bayesian network can be used to determine the probability of one node based upon the available information about other conditionally dependent nodes using an inference algorithm. Inference is the reasoning process used to draw conclusions from available evidence based on the principles of probabilistic reasoning and Bayes’ theorem 6,7,8. This theory may be used to differentiate between benign and malignant breast diseases, using radiologists’ descriptions of breast imaging findings, helping to define which patients should be referred for biopsy and which should not be referred for this procedure 9. These systems can also perform more complex reasoning tasks, such as mammography-histology correlation, and detect sampling error better than radiologists 10. This technique can also be used to help the general practitioner to determine which breast lesions identified on physical examination should be directed to mammography or for mastologist. It can assist the pathologist to do the pathological diagnosis too. The purpose of this systematic review was to assess the accuracy of Bayesian networks in patients with breast lesions.