In medicine, the first information technology wave to hit the art and science of healing was the
digitization of medical files, now known as electronic health records (EHRs). The data contained in
EHRs in combination with other sources have the potential to transform medical practice by
leveraging data, technologies, and healthcare delivery to improve the overall efficiency and quality
of care at a reasonable cost (11. Burgos S. Medical information technologies can increase quality and reduce costs.
Clinics. 2013;68(3):425, http://dx.doi.org/10.6061/clinics/2013(03)LE04.
http://dx.doi.org/10.6061/clinics/2013(0...
).
The widespread adoption of EHRs has generated large sets of data. The creative merging of datasets collected from patients and physicians could be a viable avenue to strengthen healthcare delivery. These massive datasets are currently understood as a byproduct of medical practice instead of utilizable assets that could play pivotal roles in patient care. Currently, for instance, most EHRs collect quantitative, qualitative, and transactional data, all of which could be collated, analyzed, and presented using sophisticated procedures and techniques that are now available to make use of text-based documents containing disparate and unstructured data.
The purposeful use of data is not a mystery to medical practice. Since their humble beginnings,
evidence-based undertakings have been grounded in the principle that questions answered through the
scientific method were superior to anecdotes, expert opinion, panels, and testimonials. In terms of
acknowledging the value of data and information in guiding a rational and logical decision-making
process, medicine has been at the forefront of adapting to modernity. However, physicians, nurses,
and healthcare facilities have been slow to embrace the newest methods to fully use the data
contained in EHRs. Let us examine four hidden benefits of EHRs (22. Murdoch TB, Detsky AS. The inevitable application of big data to health care.
JAMA. 2013;309(13):1351-52, http://dx.doi.org/10.1001/jama.2013.393.
http://dx.doi.org/10.1001/jama.2013.393...
).
EHRs may augment the attainment of new knowledge through the automated and systematic analysis of
unstructured data by applying advanced computational techniques that enable comprehensive data
collection. The acquisition of structured data to answer emerging clinical questions is onerous.
Narrow and automatic searches within EHRs using natural language processing (NLP) may be a less
expensive alternative. In fact, a 2011 study suggests that the automated identification of
postoperative complications within electronic medical records using NLP is far superior to patient
safety indicators linked to discharge coding (33. Murff HJ, FitzHenry F, Matheny ME, Gentry N, Kotter KL, Crimin K, et al.
Automated identification of postoperative complications within an electronic health record using
natural language processing. JAMA. 2011;306(8): 848-55,
http://dx.doi.org/10.1001/jama.2011.1204.
http://dx.doi.org/10.1001/jama.2011.1204...
). EHRs may
assist in the dissemination of new knowledge. As clinical practice evolves to incorporate the latest
evidence and facts guiding medical care, physicians encounter the daunting task of sorting through
large volumes of information to craft adequate and safe treatment options for patients with diverse
chronic illnesses. Tinkering with EHRs can generate on-screen dashboards that can guide medical care
decisions. Physicians could receive pop-up messages informing them about clinical presentation,
diagnostic work, and therapeutic choices made by clinicians facing similar case profiles. It appears
that data-driven healthcare decision-support tools aid the standardization of care and result in
cost savings.
EHRs may help to blend medical practice with personalized clinical initiatives by facilitating
opportunities to utilize analytical methods and techniques that can holistically integrate
biology-based interdisciplinary fields of study (e.g., metabolomics, phenomics) with EHR
datasets(44. Electronic Medical Records and Genomics (eMERGE) Network. National Human Genome
Research Institute. http://www.genome.gov/27540473. Accessed May 9 2013, .
http://www.genome.gov/27540473...
) to streamline genomics research and create a rich
culture of cooperation (55. Jensen PB, Jensen LJ, Brunak S. Mining electronic health records: towards better
research applications and clinical care. Nat Rev Genet. 2012;13(6): 395-405,
http://dx.doi.org/10.1038/nrg3208.
http://dx.doi.org/10.1038/nrg3208...
).
EHRs may empower patients to play more active roles in caring for their health by directly
delivering information to these individuals. Patients not only can know specific details about their
health parameters and illnesses but also can present medical records to other healthcare
professionals when needed. The benefits of this approach are twofold: information can be readily
accessed without filling out forms or having to interview patients with long questionnaires, and
traditional health-related data can be linked to other details associated with personal data, such
as diet, education, exercise, habits, hobbies, income, and military service (66. Brown JL. The unasked question. JAMA. 2012;308(18): 1869-70,
http://dx.doi.org/10.1001/jama.2012.14254.
http://dx.doi.org/10.1001/jama.2012.1425...
).
There will surely be problems along the way. Current EHR systems and health information exchange platforms are diverse and fragmented and have limited interoperability. Privacy issues will very likely emerge as a concern, especially for the protection of confidential information. Ultimately, interconnections between technology and medicine are inevitable, which explains why medical informatics plays a central role in healthcare.
REFERENCES
-
1Burgos S. Medical information technologies can increase quality and reduce costs. Clinics. 2013;68(3):425, http://dx.doi.org/10.6061/clinics/2013(03)LE04.
» http://dx.doi.org/10.6061/clinics/2013(03)LE04 -
2Murdoch TB, Detsky AS. The inevitable application of big data to health care. JAMA. 2013;309(13):1351-52, http://dx.doi.org/10.1001/jama.2013.393.
» http://dx.doi.org/10.1001/jama.2013.393 -
3Murff HJ, FitzHenry F, Matheny ME, Gentry N, Kotter KL, Crimin K, et al. Automated identification of postoperative complications within an electronic health record using natural language processing. JAMA. 2011;306(8): 848-55, http://dx.doi.org/10.1001/jama.2011.1204.
» http://dx.doi.org/10.1001/jama.2011.1204 -
4Electronic Medical Records and Genomics (eMERGE) Network. National Human Genome Research Institute. http://www.genome.gov/27540473 Accessed May 9 2013, .
» http://www.genome.gov/27540473 -
5Jensen PB, Jensen LJ, Brunak S. Mining electronic health records: towards better research applications and clinical care. Nat Rev Genet. 2012;13(6): 395-405, http://dx.doi.org/10.1038/nrg3208.
» http://dx.doi.org/10.1038/nrg3208 -
6Brown JL. The unasked question. JAMA. 2012;308(18): 1869-70, http://dx.doi.org/10.1001/jama.2012.14254.
» http://dx.doi.org/10.1001/jama.2012.14254
-
No potential conflict of interest was reported.
Publication Dates
-
Publication in this collection
2013