As other sectors advance through the aid of cognitive computing, whereas the health care sector is still evolving, offering more advantages for all consumers. The growing complexities of healthcare are compounded by an aging population that contributes to underprivileged decision-making contributing to adverse impacts on the standard of treatment and raises the cost of treatment. Advances in this field, however, is hampered by numerous challenges that create a gap between the knowledge base and user queries, query inconsistencies, and user domain information set. In recent years, the rapid development with the use of machine learning and artificial intelligence for medical applications has already been shown, from diagnostic heart failure to 1-D cardiovascular beatings and automated finding using multi-dimensional clinical data. Consequently, smart decision support structures are required, which can enable clinicians to make more informed treatment decisions. An innovative solution is to harness increasing healthcare digitization that produces enormous volumes of clinical data contained in e-HCR and merge it with advanced ML software to improve clinical decision-making, thus extending the medication evidence base at the same time. Through this work, we are investigating new methodologies as well as digging at specific real-life technologies already being implemented in the medical sector and concentrating mainly on studying about accurate depictions of patients from e-HCR. © 2020 Elsevier B.V.