Assigning clinical codes with data-driven concept representation on Dutch clinical free text

Scheurwegs, Elyne; Luyckx, Kim; Luyten, Léon; Goethals, Bart; Daelemans, Walter

doi:10.1016/j.jbi.2017.04.007

Cited by 9 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the first representation, we applied an IDF-weighted fuzzy matching dictionary-based approach using several ontologies (e.g., UMLS, 3BT, medication brand names, ...) as underlying ontologies. The second representation consists of an unsupervised approach based on linguistic pattern matching and mutual information (LMI) [25].…”

Section: Data Representationmentioning

confidence: 99%

Selecting relevant features from the electronic health record for clinical code prediction

Scheurwegs

Čule

Luyckx

et al. 2017

Journal of Biomedical Informatics

Self Cite

View full text Add to dashboard Cite

A multitude of information sources is present in the electronic health record (EHR), each of which can contain clues to automatically assign diagnosis and procedure codes. These sources however show information overlap and quality differences, which complicates the retrieval of these clues. Through feature selection, a denser representation with a consistent quality and less information overlap can be obtained. We introduce and compare coverage-based feature selection methods, based on confidence and information gain. These approaches were evaluated over a range of medical specialties, with seven different medical specialties for ICD-9-CM code prediction (six at the Antwerp University Hospital and one in the MIMIC-III dataset) and two different medical specialties for ICD-10-CM code prediction. Using confidence coverage to integrate all sources in an EHR shows a consistent improvement in F-measure (49.83% for diagnosis codes on average), both compared with the baseline (44.25% for diagnosis codes on average) and with using the best standalone source (44.41% for diagnosis codes on average). Confidence coverage creates a concise patient stay representation independent of a rigid framework such as UMLS, and contains easily interpretable features. Confidence coverage has several advantages to a baseline setup. In our baseline setup, feature selection was limited to a filter removing features with less than five total occurrences in the trainingset. Prediction results improved consistently when using multiple heterogeneous sources to predict clinical codes, while reducing the number of features and the processing time.

show abstract

Section: Data Representationmentioning

confidence: 99%

Selecting relevant features from the electronic health record for clinical code prediction

Scheurwegs

Čule

Luyckx

et al. 2017

Journal of Biomedical Informatics

Self Cite

View full text Add to dashboard Cite

show abstract

“…Publications, n (%) Data language [15-17,19-25,27-38,41-48,50,51,53-68,71,72,74,75,78-80,83-88,90-92,96,97,99-112,114,116,119-124,126-135, 137,140,142-149,151-154,156-159,161,162,165-176,179,181,184-187,189-192,194-196,198,200-208] 153 (78.9) English [39,49,52,73,76,77,81,89,93,94,113,115,118,125,136,138,139,155,163,164,177,178,182,183,188,193,197] 27 (13.9) French [18,26,69,95,117,150,160,180,199] 9 (4.6) German [40,65,82] 3 (1.5) Korean…”

Section: Referencesmentioning

confidence: 99%

“…(40); ML: 11(44); DL c : 4 (16) S a : 14 (74); ML b : 5(26) Medical concepts (n=37) S: 22 (56); ML: 12 (31); DL: 5 (13) S: 4 (67); ML: 2 (33) Specific characteristics (n=40)[49,52, S: 8 (57); ML: 1 (7); DL: 5 (36) S: 10 (77); ML: 3(23) Drugs and adverse events (n=26)[49,52,[116][117][118][119][120][121] S: 2 (25); ML: 2 (25); DL: 4 (50) S: 1 (50); ML: 1 (50) Findings and symptoms (n=8)…”

mentioning

confidence: 99%

Applying Natural Language Processing to Textual Data From Clinical Data Warehouses: Systematic Review

Bazoge,

Morin,

Daille

et al. 2023

JMIR Med Inform

View full text Add to dashboard Cite

Background In recent years, health data collected during the clinical care process have been often repurposed for secondary use through clinical data warehouses (CDWs), which interconnect disparate data from different sources. A large amount of information of high clinical value is stored in unstructured text format. Natural language processing (NLP), which implements algorithms that can operate on massive unstructured textual data, has the potential to structure the data and make clinical information more accessible. Objective The aim of this review was to provide an overview of studies applying NLP to textual data from CDWs. It focuses on identifying the (1) NLP tasks applied to data from CDWs and (2) NLP methods used to tackle these tasks. Methods This review was performed according to the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. We searched for relevant articles in 3 bibliographic databases: PubMed, Google Scholar, and ACL Anthology. We reviewed the titles and abstracts and included articles according to the following inclusion criteria: (1) focus on NLP applied to textual data from CDWs, (2) articles published between 1995 and 2021, and (3) written in English. Results We identified 1353 articles, of which 194 (14.34%) met the inclusion criteria. Among all identified NLP tasks in the included papers, information extraction from clinical text (112/194, 57.7%) and the identification of patients (51/194, 26.3%) were the most frequent tasks. To address the various tasks, symbolic methods were the most common NLP methods (124/232, 53.4%), showing that some tasks can be partially achieved with classical NLP techniques, such as regular expressions or pattern matching that exploit specialized lexica, such as drug lists and terminologies. Machine learning (70/232, 30.2%) and deep learning (38/232, 16.4%) have been increasingly used in recent years, including the most recent approaches based on transformers. NLP methods were mostly applied to English language data (153/194, 78.9%). Conclusions CDWs are central to the secondary use of clinical texts for research purposes. Although the use of NLP on data from CDWs is growing, there remain challenges in this field, especially with regard to languages other than English. Clinical NLP is an effective strategy for accessing, extracting, and transforming data from CDWs. Information retrieved with NLP can assist in clinical research and have an impact on clinical practice.

show abstract

“…Berdasarkan hasil pengamatan yang telah dilakukan, ketidakakuratan kode diagnosis yang disebabkan karena salah dalam pemilihan kode salah satunya dipengaruhi oleh ketidakjelasan informasi medis berupa diagnosis oleh dokter yang tercantum dalam dokumen rekam medis. Hal ini sesuai dengan penelitian terdahulu yang menyebutkan bahwa terjadinya kesalahan pemilihan kode disebabkan karena penulisan diagnosis yang sulit terbaca, tidak sesuai terminologi medis di ICD-10, atau penggunaan singkatan yang tidak sesuai daftar singkatan yang berlaku [14] [15]. Dalam proses pengkodean komunikasi antara pemberi diagnosis yaitu dokter dengan coder adalah hal yang penting [11].…”

Section: Ketidakjelasan Informasi Medisunclassified

Analisis Hubungan Ketepatan Penulisan Diagnosis dengan Keakuratan Kode Diagnosis pada Kasus Obstetri dan Ginekologi di Rumah Sakit Tk. IV DKT Kediri

Puspaningtyas

Sangkot

Akbar

et al. 2022

rmik

View full text Add to dashboard Cite

Activity of determining the disease code and writing the diagnosis must be in accordance with the correct medical terminology and the classification rules that apply in Indonesia, namely ICD-10 in order to get the right and accurate code. This study aims to analyze the relationship between the accuracy of writing a diagnosis and the accuracy of the diagnosis code in obstetrics and gynecology cases at Rumah Sakit Tk. IV DKT Kediri. The method used in this research is analytic research with cross sectional approach. Based on Slovin's formula, the sample used was 100 medical record documents of inpatients. The sampling technique used is simple random sampling. The data collection technique used observation with a checklist instrument. Data on the accuracy of writing the diagnosis and the accuracy of the diagnosis code were analyzed univariately, while the relationship between the accuracy of writing the diagnosis and the accuracy of the diagnosis code was analyzed using SPSS with Chi-Square test. The results showed that the accuracy of writing the diagnosis was 56%, the accuracy of the diagnosis code was 43%, and there was a relationship between the accuracy of writing the diagnosis and the accuracy of the diagnostic code for obstetrics and gynecology cases at Rumah Sakit Tk. IV DKT Kediri (p < 0.025).

show abstract

Assigning clinical codes with data-driven concept representation on Dutch clinical free text

Cited by 9 publications

References 19 publications

Selecting relevant features from the electronic health record for clinical code prediction

Selecting relevant features from the electronic health record for clinical code prediction

Applying Natural Language Processing to Textual Data From Clinical Data Warehouses: Systematic Review

Analisis Hubungan Ketepatan Penulisan Diagnosis dengan Keakuratan Kode Diagnosis pada Kasus Obstetri dan Ginekologi di Rumah Sakit Tk. IV DKT Kediri

Contact Info

Product

Resources

About