The Revival of the Notes Field: Leveraging the Unstructured Content in Electronic Health Records

Abstract

Clinical practice requires the production of a time-and resource-consuming great amount of notes. They contain relevant information, but their secondary use is almost impossible, due to their unstructured nature. Researchers are trying to address this problems, with traditional and promising novel techniques. Application in real hospital settings seems not to be possible yet, though, both because of relatively small and dirty dataset, and for the lack of language-specific pre-trained models. Aim: Our aim is to demonstrate the potential of the above techniques, but also raise awareness of the still open challenges that the scientific communities of IT and medical practitioners must jointly address to realize the full potential of unstructured content that is daily produced and digitized in hospital settings, both to improve its data quality and leverage the insights from data-driven predictive models. Methods: To this extent, we present a narrative literature review of the most recent and relevant contributions to leverage the application of Natural Language Processing techniques to the free-text content electronic patient records. In particular, we focused on four selected application domains, namely: data quality, information extraction, sentiment analysis and predictive models, and automated patient cohort selection. Then, we will present a few empirical studies that we undertook at a major teaching hospital specializing in musculoskeletal diseases. Results: We provide the reader with some simple and affordable pipelines, which demonstrate the feasibility of reaching literature performance levels with a single institution non-English dataset. In such a way, we bridged literature and real world needs, performing a step further toward the revival of notes fields.

An Electronic Health Record Text Mining Tool to Collect Real‐World Drug Treatment Outcomes: A Validation Study in Patients With Metastatic Renal Cell Carcinoma

“…These free‐text notes, in particular, contain very detailed and nuanced information about patients, their illnesses, and treatment trajectory, including efficacy and side effects of drug treatment. However, because these free‐text notes are unstructured, they are less suitable for automated information extraction 13,14 . Therefore, manual chart review is still the standard method for data collection from EHRs 12 .…”

Humanizing Big Data: Recognizing the Human Aspect of Big Data

“…However, data derived from the EHR are of multiple types (27). One estimate has 80% of data contained in EHRs as unstructured (26,28). These varied entries in the EHR have value in that they can be used to formulate phenotypic classifications of patients.…”

“…These varied entries in the EHR have value in that they can be used to formulate phenotypic classifications of patients. The technical challenges to this conversion process involve sophisticated algorithms using machine learning, natural language processing (NLP), and artificial intelligence (AI) (26). In the clinical genetic setting, examples of unstructured data that are difficult to convert to structured formats include EHRs, genomics, and other omic datasets.…”

“…In essence, challenges to data quality, reliability, accuracy and integration must always be addressed. The ultimate goal is to discover associations between genetic/genomic variations and clinical phenotypes that are accurate and clinically meaningful in that they can be used to manage patient care, essentially creating predictive models (26).…”

MedCATTrainer: A Biomedical Free Text Annotation Interface with Active Learning and Research Use Case Specific Customisation

“…However, significant progress has been made on agreement and usage of standardised terminologies such as the Systematized Nomenclature of Medical Clinical Terms (SNOMED-CT) (Stearns et al, 2001) and the Unified Medical Language System (UMLS) (Bodenreider, 2004). Annotating EHR text with these concept databases is often seen as a first step in delivering data driven applications such as precision medicine, clinical decision support or real time disease surveillance (Assale et al, 2019).…”