Patients, namely we, are complex, and many factors influence our health beyond a single diagnosis or treatment decision. Our digital patient care record, now the Electronic Medical Record (EMR), was initially developed to document patient diagnostic encounters, track treatments, standardize reimbursement and ensure regulatory compliance. Now EMRs are at the centre of healthcare innovation. They not only capture the longitudinal history of ours, the patient's, diagnostic and care journey but can also support clinical decision-making and prognostic analytics, which are important to palliative as well as preventive care in addition to outcomes-based research.
As EMRs continue to evolve, their role extends beyond administrative and reimbursement documentation. They can serve as a foundation for data-driven healthcare, influencing patient outcomes, research, and policy decisions. Let's explore some of the key aspects that shape the future of EMRs and their evolution into Electronic Health Records (EHRs) focused on the total health of the patient, including data integration, interoperability challenges, and their potential in generating real-world evidence (RWE).
Expanding the Scope of EMRs to EHRs for Greater Impact
Electronic Medical Records (EMRs) primarily consist of structured, digitally coded data, including reimbursement codes for diagnoses, medications, procedures, laboratory results, and demographics (1). While these elements are essential for administrative and clinical processes, they do not provide a complete picture of our health. Additional interpretative metrics from the physician's perspective are needed to understand the diagnosis and treatment decisions. These are often within the physician's notes as part of the patient’s chart, but not structurally encoded into the EMR itself. Newer AI technologies including NLP can now enable extraction of these critical details and inclusion within an expanded Electronic Health Record (2). The Electronic Health Record (EHR) extends the EMR format by focusing on the total health of the patient with input from all clinicians involved in a patient´s care (3).
Beyond actual medical treatment, a patient’s social and environmental context can also significantly influence health outcomes. Social determinants of health (SDoH), including socio-economic status, access to healthcare services, and medication adherence, can directly affect disease progression and treatment effectiveness (4).
Furthermore, insight into environmental factors, such as air quality, housing stability, and workplace conditions, could also play a beneficial role (5). For example, if a patient faces transportation challenges, offering remote consultations could improve engagement. If medication regimens are complex, alternative treatment options might be considered to increase adherence. Ultimately, the goal is to enhance the actionability of patient data and insights into patient journey and treatment pathways without increasing the administrative burden on healthcare providers.
Many modern EHRs support fields from patient chart detail as well as SDoH, transportation barriers, and other non-clinical factors and incorporate predictive analytics, such as Epic’s Sepsis Model and AI-driven clinical decision support. However, factors like data incompleteness, bias, interoperability and data access restrict and hinder the optimal use of this crucial information (2). The key question is not so much whether additional data should be included, but more how to make additional information accessible, user-friendly and how to make sure the data is standardized to be leveraged effectively.
Improving Retrospective Research and Real-World Evidence (RWE)
Besides gathering a more complete picture of the individual patients, a more inclusive, complete and standardized EMR to EHR serves another purpose: broader healthcare insights.
By integrating additional data sources into EHRs, real-world insights derived from aggregated and retrospective data can be unlocked. It can help identify disease patterns, assess treatment effectiveness, and uncover healthcare disparities (6). In addition, predictive and prognostic modelling can be enhanced. Machine learning algorithms can identify early signs of disease progression, predict treatment responses, and highlight high-risk populations for targeted interventions. This shift from reactive to preventive care could reduce hospital admissions and improve healthcare efficiency.
Investing in the Future of Healthcare Data
For EMRs and EHRs to unlock their full potential, they must continue evolving not only to support individual patient care but also to enable the secondary use of data for broader insights (2). While their primary role is to guide diagnosis and treatment, expanding EHRs with additional data points can provide a more comprehensive and holistic understanding of patient health, their journey and treatment outcomes. Enhanced datasets will drive more robust RWE research, allowing for better evaluation of healthcare interventions across diverse populations (7).
Ultimately, digital health data should be leveraged to optimise patient care and healthcare delivery, ensuring that each euro spent maximises patient outcomes, such as increased quality-adjusted life years (QALYs). This focus on healthcare economics and outcomes research (HEOR) is essential for making informed, cost-effective decisions that improve patient well-being while maintaining financial sustainability. Healthcare should be an investment into bettering care and access for all patients.
Bibliography
1. SBS. (2025). EMR vs HIS: Understanding the key differences & choosing the right system. SBS. https://sbs-me.com/emr-vs-his-vs-ehr-the-key-differences/
2. Sarwar, T., Seifollahi, S., Chan, J., Zhang, X., Aksakalli, V., Hudson, I., Verspoor, K., & Cavedon, L. (2022). The secondary use of electronic health records for data mining: Data characteristics and challenges. ACM Computing Surveys (CSUR), 55(2), 1–40. https://doi.org/10.1145/3490234
3. Garrett, P., & Seidman, J. (2011). EMR vs EHR – What is the difference? HealthIT.gov. https://www.healthit.gov/buzz-blog/electronic-health-and-medical-records/emr-vs-ehr-difference
4. Okunrintemi, V., et al. (2019). Association of Income Disparities with Patient-Reported Healthcare Experience. Journal of General Internal Medicine, 34(6), 884–892. https://doi.org/10.1007/s11606-019-04848-4
5. Sundas, A., et al. (2024). The Effects of Environmental Factors on General Human Health: A Scoping Review. Healthcare, 12(21), 2123. https://doi.org/10.3390/healthcare12212123
6. World Health Organization. (n.d.). Improving health-care delivery and innovation through secondary use of health data. World Health Organization Europe. https://www.who.int/europe/activities/improving-health-care-delivery-and-innovation-through-secondary-use-of-health-data#:~:text=Secondary%20use%20of%20health%20data%20is%20the%20processing%20of%20health,which%20the%20data%20were%20collected
7. ISPOR. (n.d.). Real-world evidence. The International Society for Pharmacoeconomics and Outcomes Research. https://www.ispor.org/strategic-initiatives/real-world-evidence
