Various studies use numerous probabilistic methods to establish a cause-effect relationship between a drug and a disease. However, only a limited number of machine learning studies on establishing cause-effect relationships can be found on the internet. In this study, we explore machine learning approaches for interpreting large quantities of multivariate patient-based laboratory data for establishing cause-effect relationships for critically ill patients. We adopt principal component analysis as a primary method to capture daily patient changes after a medical intervention so that the causal relationship between the medical treatments and the outcomes can be established. Model validity and stability are evaluated using bootstrap testing. The model exhibits an acceptable significance level with a two-tailed test. Moreover, results show that the approach provides promising results in interpreting large quantities of patient data and establishing cause-effect relationships for making informed decisions for critically ill patients. If fused with other machine learning and probabilistic models, the proposed approach can provide the healthcare industry with an added tool for daily routine clinical practices. Furthermore, the approach will be able to support clinical decision-making and enable effective patient-tailored care for better health outcomes.