Neural classification of Norwegian radiology reports: using NLP to detect findings in CT-scans of children

BACKGROUND: With a motivation of quality assurance, machine learning techniques were trained to classify Norwegian radiology reports of paediatric CT examinations according to their description of abnormal findings. METHODS: 13.506 reports from CT-scans of children, 1000 reports from CT scan of adul...

Descripción completa

Detalles Bibliográficos
Autores principales: Dahl, Fredrik A., Rama, Taraka, Hurlen, Petter, Brekke, Pål H., Husby, Haldor, Gundersen, Tore, Nytrø, Øystein, Øvrelid, Lilja
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BioMed Central 2021
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7934405/
https://www.ncbi.nlm.nih.gov/pubmed/33663479
http://dx.doi.org/10.1186/s12911-021-01451-8
Descripción
Sumario:BACKGROUND: With a motivation of quality assurance, machine learning techniques were trained to classify Norwegian radiology reports of paediatric CT examinations according to their description of abnormal findings. METHODS: 13.506 reports from CT-scans of children, 1000 reports from CT scan of adults and 1000 reports from X-ray examination of adults were classified as positive or negative by a radiologist, according to the presence of abnormal findings. Inter-rater reliability was evaluated by comparison with a clinician’s classifications of 500 reports. Test–retest reliability of the radiologist was performed on the same 500 reports. A convolutional neural network model (CNN), a bidirectional recurrent neural network model (bi-LSTM) and a support vector machine model (SVM) were trained on a random selection of the children’s data set. Models were evaluated on the remaining CT-children reports and the adult data sets. RESULTS: Test–retest reliability: Cohen’s Kappa = 0.86 and F1 = 0.919. Inter-rater reliability: Kappa = 0.80 and F1 = 0.885. Model performances on the Children-CT data were as follows. CNN: (AUC = 0.981, F1 = 0.930), bi-LSTM: (AUC = 0.978, F1 = 0.927), SVM: (AUC = 0.975, F1 = 0.912). On the adult data sets, the models had AUC around 0.95 and F1 around 0.91. CONCLUSIONS: The models performed close to perfectly on its defined domain, and also performed convincingly on reports pertaining to a different patient group and a different modality. The models were deemed suitable for classifying radiology reports for future quality assurance purposes, where the fraction of the examinations with abnormal findings for different sub-groups of patients is a parameter of interest.