Electronic medical records in multiple sclerosis research

Abstract

With the massive digitalization of many processes involved in human activities, electronic medical records (EMR) are being increasingly deployed in medical centers. EMR have the potential to become a main major real‐life data source for future medical research and evaluation of practice. Multiple sclerosis is a paradigmatic example of a complex disease that can benefit from this new source of information. Today, researchers and clinicians alike have access to tools allowing an en masse identification of multiple sclerosis patients, and extraction of demographics and clinical variables with high accuracy. However no matter how “big” the (EMR) data might be, biases are inherent to EMR data generation. These have to be studied and eventually accounted for in analysis in order to fulfill the promise of personalized medicine for all, and carrying out large clinical and research studies in multiple sclerosis.

Development of electronic medical records for clinical and research purposes: the breast cancer module using an implementation framework in a middle income country- Malaysia

“…In such circumstances, efficient data management and computational workflows are needed to generate meaningful clinical data, rather than having textual data and building algorithms to mine retrospective data. With the increasing use of EMR data in research, EMR has high potential in becoming a major data source for future medical research and clinical service evaluation of a practice [ 6 – 8 ]. The rapid increase in quantity of clinical information in electronic format makes secondary use of clinical data a candidate for big data solutions [ 9 , 10 ].…”

Emerging importance of big data in neuroimmunological research

“…By the transition to EMR, the data of interest can be easily obtained by text mining techniques. Damotte and Gourraud reviewed EMR in this issue, and gave us an overview on how EMR is efficient for research in the field of neuroimmunological diseases, especially in MS research, and what the current limitations are …”

“…Damotte and Gourraud reviewed EMR in this issue, and gave us an overview on how EMR is efficient for research in the field of neuroimmunological diseases, especially in MS research, and what the current limitations are. 2 In the era of increasingly emphasizing big data, how should we maximize the voluminous data in research on neuroimmunological diseases and what should be the ideal strategy for carrying out research? At the end of a focused review in this issue, I briefly reviewed MS genetics, introducing the rationale for genetic contributions to MS susceptibility and severity, and emphasized the importance of active collaboration with researchers from different professions in carrying out research using large datasets.…”

Using Novel Data Types for Big Data Research in Epilepsy: Patient Records, Clinic Letters and Genetic Mutation

“…The i2b2 project used cTAKES and HITex (Health Information Text Extraction) to extract Crohn's disease, Ulcerative Colitis, multiple sclerosis (MS), and Rheumatoid arthritis [139]. A recent study on patients with known MS identified from electronic healthcare records used NLP techniques to accurately extract attributes specific to MS, namely: Expanded Disability Status Scale, Timed 25 Foot Walk, MS subtype and age of onset [140]. A study used clinic letters, available at www.mtsamples.com, to determine whether sentences containing disease and procedure information were attributable to a family member using the BioMedICUS NLP system and variety of phenotype data was extracted from 300 randomly chosen journal titles [141], [142] There have also been several epilepsy based NLP studies and applications developed.…”

“…Performance of specific phenotype extraction algorithms developed as part of the i2b2 project using cTAKES (Apache clinical Text Analysis and Knowledge Extraction System) and HITex (Health Information Text Extraction) showed that for an NLP approach high PPV (precision) and sensitivity (recall) was achieved for extracting the following phenotypes; Crohn's disease (98%,64%), Ulcerative Colitis (97%,68%) , MS (94%,68%), and Rheumatoid arthritis (89%,56%) [139]. As we aimed to extract epilepsy specific information other than a confirmed diagnosis, a recent study on patients with known MS identified from electronic healthcare records used NLP techniques to extract attributes specific to MS with high PPV and sensitivity, namely EDSS (Expanded Disability Status Scale) (97%,89%), T25FW (Timed 25 Foot Walk) (93%,87%), MS subtype (92%,74%) and age of onset (77%,64%) [140]. This study took into account items attributable only to the patient, as opposed to family members, which is an important distinction and interesting area of study in terms of identify potential risk factors for disease development.…”