Please use this identifier to cite or link to this item:
http://hdl.handle.net/1942/42640
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | FALTER, Maarten | - |
dc.contributor.author | Godderis, Dries | - |
dc.contributor.author | SCHERRENBERG, Martijn | - |
dc.contributor.author | KIZILKILIC, Sevda | - |
dc.contributor.author | XU, Linqi | - |
dc.contributor.author | Mertens, Marc | - |
dc.contributor.author | Jansen , Jan | - |
dc.contributor.author | Legroux, Pascal | - |
dc.contributor.author | Sinnaeve, Peter | - |
dc.contributor.author | KINDERMANS, Hanne | - |
dc.contributor.author | NEVEN, Frank | - |
dc.contributor.author | DENDALE, Paul | - |
dc.date.accessioned | 2024-03-18T09:26:38Z | - |
dc.date.available | 2024-03-18T09:26:38Z | - |
dc.date.issued | 2024 | - |
dc.date.submitted | 2024-03-18T08:57:08Z | - |
dc.identifier.citation | European Heart Journal - Digital Health, | - |
dc.identifier.uri | http://hdl.handle.net/1942/42640 | - |
dc.description.abstract | Aims ICD codes are used for classification of hospitalizations. The codes are used for administrative, financial, and research purposes. It is known, however, that errors occur. Natural language processing (NLP) offers promising solutions for optimizing the process. To investigate methods for automatic classification of disease in unstructured medical records using NLP and to compare these to conventional ICD coding.Methods and results Two datasets were used: the open-source Medical Information Mart for Intensive Care (MIMIC)-III dataset (n = 55.177) and a dataset from a hospital in Belgium (n = 12.706). Automated searches using NLP algorithms were performed for the diagnoses 'atrial fibrillation (AF)' and 'heart failure (HF)'. Four methods were used: rule-based search, logistic regression, term frequency-inverse document frequency (TF-IDF), Extreme Gradient Boosting (XGBoost), and Bio-Bidirectional Encoder Representations from Transformers (BioBERT). All algorithms were developed on the MIMIC-III dataset. The best performing algorithm was then deployed on the Belgian dataset. After preprocessing a total of 1438 reports was retained in the Belgian dataset. XGBoost on TF-IDF matrix resulted in an accuracy of 0.94 and 0.92 for AF and HF, respectively. There were 211 mismatches between algorithm and ICD codes. One hundred and three were due to a difference in data availability or differing definitions. In the remaining 108 mismatches, 70% were due to incorrect labelling by the algorithm and 30% were due to erroneous ICD coding (2% of total hospitalizations).Conclusion A newly developed NLP algorithm attained a high accuracy for classifying disease in medical records. XGBoost outperformed the deep learning technique BioBERT. NLP algorithms could be used to identify ICD-coding errors and optimize and support the ICD-coding process. Graphical Abstract | - |
dc.description.sponsorship | Funding P.D., H.K., and S.E.K. received funding through the Horizon 2020 CoroPrevention project, project number 848056. M.F. received funding through the Flanders Research Foundation FWO, file number 1SE1222N. | - |
dc.language.iso | en | - |
dc.publisher | OXFORD UNIV PRESS | - |
dc.rights | The Author(s) 2024. Published by Oxford University Press on behalf of the European Society of Cardiology. This is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercial License (https://creativecommons.org/licenses/by-nc/4.0/), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited. For commercial re-use, please contact journals.permissions@oup.com | - |
dc.subject.other | Atrial fibrillation | - |
dc.subject.other | Heart failure | - |
dc.subject.other | ICD codes | - |
dc.subject.other | International classification of disease | - |
dc.subject.other | Natural language processing | - |
dc.subject.other | Machine learning | - |
dc.subject.other | Deep learning | - |
dc.subject.other | XGBoost | - |
dc.subject.other | BioBERT | - |
dc.title | Using natural language processing for automated classification of disease and to identify misclassified ICD codes in cardiac disease | - |
dc.type | Journal Contribution | - |
local.format.pages | 6 | - |
local.bibliographicCitation.jcat | A1 | - |
dc.description.notes | Falter, M (corresponding author), Hasselt Univ, Fac Med & Life Sci, Agoralaan Gebouw D, B-3590 Hasselt, Belgium.; Falter, M (corresponding author), Jessa Hosp, Heart Ctr Hasselt, Stadsomvaart 11, B-3500 Hasselt, Belgium.; Falter, M (corresponding author), KULeuven, Fac Med, Dept Cardiol, Herestr 49, B-3000 Leuven, Belgium. | - |
dc.description.notes | maarten.falter@jessazh.be | - |
local.publisher.place | GREAT CLARENDON ST, OXFORD OX2 6DP, ENGLAND | - |
local.type.refereed | Refereed | - |
local.type.specified | Article | - |
local.bibliographicCitation.status | Early view | - |
local.type.programme | H2020 | - |
local.relation.h2020 | 848056 | - |
dc.identifier.doi | 10.1093/ehjdh/ztae008 | - |
dc.identifier.isi | 001176104500001 | - |
dc.contributor.orcid | Scherrenberg, Martijn/0000-0001-9483-3828 | - |
local.provider.type | wosris | - |
local.description.affiliation | [Falter, Maarten; Scherrenberg, Martijn; Kizilkilic, Sevda Ece; Xu, Linqi; Kindermans, Hanne; Dendale, Paul] Hasselt Univ, Fac Med & Life Sci, Agoralaan Gebouw D, B-3590 Hasselt, Belgium. | - |
local.description.affiliation | [Falter, Maarten; Scherrenberg, Martijn; Kizilkilic, Sevda Ece; Xu, Linqi; Dendale, Paul] Jessa Hosp, Heart Ctr Hasselt, Stadsomvaart 11, B-3500 Hasselt, Belgium. | - |
local.description.affiliation | [Falter, Maarten; Sinnaeve, Peter] KULeuven, Fac Med, Dept Cardiol, Herestr 49, B-3000 Leuven, Belgium. | - |
local.description.affiliation | [Godderis, Dries; Neven, Frank] Hasselt Univ, Data Sci Inst, Agoralaan Gebouw D, B-3590 Hasselt, Belgium. | - |
local.description.affiliation | [Scherrenberg, Martijn] Antwerp Univ, Fac Med & Hlth Sci, Univ Pl 1, B-2610 Antwerp, Belgium. | - |
local.description.affiliation | [Kizilkilic, Sevda Ece] Univ Ghent, Fac Med & Hlth Sci, Corneel Heymanslaan 10, B-9000 Ghent, Belgium. | - |
local.description.affiliation | [Mertens, Marc; Jansen, Jan; Legroux, Pascal] Jessa Hosp, Dept Informat & Commun Technol, Stadsomvaart 11, B-3500 Hasselt, Belgium. | - |
local.uhasselt.international | no | - |
item.contributor | FALTER, Maarten | - |
item.contributor | Godderis, Dries | - |
item.contributor | SCHERRENBERG, Martijn | - |
item.contributor | KIZILKILIC, Sevda | - |
item.contributor | XU, Linqi | - |
item.contributor | Mertens, Marc | - |
item.contributor | Jansen , Jan | - |
item.contributor | Legroux, Pascal | - |
item.contributor | Sinnaeve, Peter | - |
item.contributor | KINDERMANS, Hanne | - |
item.contributor | NEVEN, Frank | - |
item.contributor | DENDALE, Paul | - |
item.fulltext | With Fulltext | - |
item.accessRights | Open Access | - |
item.fullcitation | FALTER, Maarten; Godderis, Dries; SCHERRENBERG, Martijn; KIZILKILIC, Sevda; XU, Linqi; Mertens, Marc; Jansen , Jan; Legroux, Pascal; Sinnaeve, Peter; KINDERMANS, Hanne; NEVEN, Frank & DENDALE, Paul (2024) Using natural language processing for automated classification of disease and to identify misclassified ICD codes in cardiac disease. In: European Heart Journal - Digital Health,. | - |
crisitem.journal.eissn | 2634-3916 | - |
Appears in Collections: | Research publications |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
ztae008.pdf | Early view | 302.38 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.