Leveraging Big Data Analytics to Uncover New Insights of Electronic Health Records

Background
Improving patient care is one of the healthcare system’s key objectives. Although several factors can be involved in this process, structured investigation of electronic health records (EHR) provides factual and continuous reporting of the clinical data.
Big data analytics have revolutionized the efficiency of healthcare research by providing informative insights, analyzing patient outcomes, and improving healthcare delivery via evidence-based feedback. Therefore, the EHR must be designed systematically and feasibly to facilitate information extraction and to leverage the use of the clinical data of large populations in research and innovations.
The latter can be invested to improve patient outcomes based on EHR’s main components, including patient demographics, medical history, medications, immunization history, laboratory results, radiology and imaging reports, clinical notes, vital signs, procedures, surgeries, visit history, and social determinants of health.
Recently, this topic has attracted great attention, and several articles encompass a wide range of special interests in big data analytics and EHR (Figure 1).

Designs and protocols
Different types of data aggregation can be used to conduct in-depth investigations of various components of EHR. This includes combining and analyzing the EHR data using different aggregation models, temporal, spatial, summarization, and hierarchical aggregations.
In addition, statistical and predictive modeling of the available EHR data can anticipate future health research trends and potential outcomes and therefore, facilitate the designing of a well-informed care and management plan.
Furthermore, big data analytics provides real-time monitoring and analysis of EHR data and timely updates of the patient’s data. This enhances the ability to create research findings that meet the current needs, particularly in critical situations such as disease outbreaks or emergencies.
The large sample sizes and the diversity of the EHR data support population-based studies that investigate disease prevalence, incidence rates, and patterns of health behaviors (Figure 2).

Selected free full text articles
- Ross MK, Wei W, Ohno-Machado L. Big data and the electronic health record. Yearb Med Inform. 2014 Aug 15;9(1):97-104. doi: 10.15265/IY-2014-0003. PMID: 25123728; PMCID: PMC4287068. https://pubmed.ncbi.nlm.nih.gov/25123728/
- Miotto R, Wang F, Wang S, Jiang X, Dudley JT. Deep learning for healthcare: review, opportunities and challenges. Brief Bioinform. 2018 Nov 27;19(6):1236-1246. doi: 10.1093/bib/bbx044. PMID: 28481991; PMCID: PMC6455466. https://pubmed.ncbi.nlm.nih.gov/28481991/
- Wu PY, Cheng CW, Kaddi CD, Venugopalan J, Hoffman R, Wang MD. -Omic and Electronic Health Record Big Data Analytics for Precision Medicine. IEEE Trans Biomed Eng. 2017 Feb;64(2):263-273. doi: 10.1109/TBME.2016.2573285. Epub 2016 Oct 10. PMID: 27740470; PMCID: PMC5859562. https://pubmed.ncbi.nlm.nih.gov/27740470/
- Chen W, Xie F, Mccarthy DP, Reynolds KL, Lee M, Coleman KJ, Getahun D, Koebnick C, Jacobsen SJ. Research data warehouse: using electronic health records to conduct population-based observational studies. JAMIA Open. 2023 Jun 21;6(2):ooad039. doi: 10.1093/jamiaopen/ooad039. PMID: 37359950; PMCID: PMC10284679. https://pubmed.ncbi.nlm.nih.gov/37359950/
- Ristevski B, Chen M. Big Data Analytics in Medicine and Healthcare. J Integr Bioinform. 2018 May 10;15(3):20170030. doi: 10.1515/jib-2017-0030. PMID: 29746254; PMCID: PMC6340124. https://pubmed.ncbi.nlm.nih.gov/29746254/
Leave a Reply