Mara Scientific
2 min readJul 14, 2022


All healthcare facilities use and maintain Hospital management information Systems (Both Paper and Electronic) to collect and store medical information from patients. These systems are used in clinical care and healthcare administration to collect and manage a variety of medical information from individual patients over prolonged periods of time. These Patient-level variables can include demographics, diagnoses, problem lists, medications, vital signs, and laboratory data all captured for periods well over a decade in some cases.

Furthermore, as is most often the case with paper records Health institutions must consider issues such as misplaced files, papers, andfolders and destruction of this information.

As a result, it’s imperative that technology adopts to facilitate such large amounts of data generated but also provides the level of clarity needed by a health practitioner as and when it is needed. With advancements in technology there have been various approaches but the one we look at in this article is Computational Phenotyping.

Computational phenotyping is the process of converting massive amounts of Electronic Health Record (EHR) data into meaningful medical concepts that can be used to predict an individual’s risk of disease or response to drug therapy. It also extracts phenotypes from EHR data, accelerating the adoption and application of phenotype-driven initiatives to advance scientific discovery and improve healthcare delivery.

Raw data is obtained from a variety of sources, including patient personal information, medication, lab test reports, doctor’s prescriptions, sensor data, and so on. This raw data is fed into an algorithm, which generates medical insights, this data aids clinical operations or genomic studies. According to the National Academies of Medicine, an EHR has multiple core functionalities, including the capture of health information, orders and results management, clinical decision support, health information exchange, electronic communication, patient support, administrative processes, and population health reporting.

It must be noted however that, it is impossible to overlook the beneficial effects of data sources for computational phenotyping. The best course of action is for all parties involved to create EHRs that centralize data from different healthcare facilities while also including data pre-processing, a stage that will check on the quality and correctness of the data and lessen duplications and data fragmentation. This will make it easier for researchers to examine various population phenotypes in pursuit of ground-breaking treatments for various diseases.