Search

Copyright of Huisarts En Wetenschap is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Huisarts En Wetenschap is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Huisarts En Wetenschap is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Huisarts En Wetenschap is the property of Springer Nature and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

There is an urgent need to standardize the semantics of biomedical data values, such as phenotypes, to enable comparative and integrative analyses. However, it is unlikely that all studies will use the same data collection protocols. As a result, retrospective standardization is often required, which involves matching of original (unstructured or locally coded) data to widely used coding or ontology systems such as SNOMED CT (clinical terms), ICD-10 (International Classification of Disease) and HPO (Human Phenotype Ontology). This data curation process is usually a time-consuming process performed by a human expert. To help mechanize this process, we have developed SORTA, a computer-aided system for rapidly encoding free text or locally coded values to a formal coding system or ontology. SORTA matches original data values (uploaded in semicolon delimited format) to a target coding system (uploaded in Excel spreadsheet, OWL ontology web language or OBO open biomedical ontologies format). It then semi- automatically shortlists candidate codes for each data value using Lucene and n-gram based matching algorithms, and can also learn from matches chosen by human experts. We evaluated SORTA’s applicability in two use cases. For the LifeLines biobank, we used SORTA to recode 90 000 free text values (including 5211 unique values) about physical exercise to MET (Metabolic Equivalent of Task) codes. For the CINEAS clinical symptom coding system, we used SORTA to map to HPO, enriching HPO when necessary (315 terms matched so far). Out of the shortlists at rank 1, we found a precision/recall of 0.97/0.98 in LifeLines and of 0.58/0.45 in CINEAS. More importantly, users found the tool both a major time saver and a quality improvement because SORTA reduced the chances of human mistakes. Thus, SORTA can dramatically ease data (re)coding tasks and we believe it will prove useful for many more projects. [ABSTRACT FROM AUTHOR]

Background: Electronic medical records have opened opportunities to analyze clinical practice at large scale. Structured registries and coding procedures such as the International Classification of Primary Care further improved these procedures. However, a large part of the information about the state of patient and the doctors' observations is still entered in free text fields. The main function of those fields is to report the doctor's line of thought, to remind oneself and his or her colleagues on follow-up actions, and to be accountable for clinical decisions. These fields contain rich information that can be complementary to that in coded fields, and until now, they have been hardly used for analysis., Objective: This study aims to develop a prediction model to convert the free text information on COVID-19-related symptoms from out of hours care electronic medical records into usable symptom-based data that can be analyzed at large scale., Methods: The design was a feasibility study in which we examined the content of the raw data, steps and methods for modelling, as well as the precision and accuracy of the models. A data prediction model for 27 preidentified COVID-19-relevant symptoms was developed for a data set derived from the database of primary-care out-of-hours consultations in Flanders. A multiclass, multilabel categorization classifier was developed. We tested two approaches, which were (1) a classical machine learning-based text categorization approach, Binary Relevance, and (2) a deep neural network learning approach with BERTje, including a domain-adapted version. Ethical approval was acquired through the Institutional Review Board of the Institute of Tropical Medicine and the ethics committee of the University Hospital of Antwerpen (ref 20/50/693)., Results: The sample set comprised 3957 fields. After cleaning, 2313 could be used for the experiments. Of the 2313 fields, 85% (n=1966) were used to train the model, and 15% (n=347) for testing. The normal BERTje model performed the best on the data. It reached a weighted F1 score of 0.70 and an exact match ratio or accuracy score of 0.38, indicating the instances for which the model has identified all correct codes. The other models achieved respectable results as well, ranging from 0.59 to 0.70 weighted F1. The Binary Relevance method performed the best on the data without a frequency threshold. As for the individual codes, the domain-adapted version of BERTje performs better on several of the less common objective codes, while BERTje reaches higher F1 scores for the least common labels especially, and for most other codes in general., Conclusions: The artificial intelligence model BERTje can reliably predict COVID-19-related information from medical records using text mining from the free text fields generated in primary care settings. This feasibility study invites researchers to examine further possibilities to use primary care routine data., (©Josefien Van Olmen, Jens Van Nooten, Hilde Philips, Annet Sollie, Walter Daelemans. Originally published in JMIR Medical Informatics (https://medinform.jmir.org), 27.04.2022.)