 Big data in healthcare encompasses various features distinct from those of other disciplines in traditional clinical epidemiology, with applications in predictive modeling, clinical decision support, disease surveillance, public health, and research. Analytic methods developed in data mining, such as classification, clustering, and regression, are frequently used for medical big data analyses, but technical issues like missing values, curse of dimensionality, and bias control limit their practical benefits. Propensity score analysis and instrumental variable analysis have been introduced to overcome these limitations, but challenges such as the absence of evidence of practical benefits, methodological issues including legal and ethical concerns, and clinical integration and utility issues must be addressed to realize the promise of medical big data in improving patient outcomes and reducing healthcare waste. This article was authored by Chung Ho Lee and Hyun Jin Yoon. We are article.tv, links in the description below.