FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313557631> ?p ?o ?g. }

• W4313557631 abstract "<sec> <title>BACKGROUND</title> Lower back pain is a common weakening condition that affects a large population. It is a leading cause of disability and lost productivity, and the associated medical costs and lost wages place a significant burden on individuals and society. Recent advances in artificial intelligence (AI) and natural language processing (NLP) have opened new opportunities for the identification and management of risk factors for lower back pain. In this paper, we propose and train a deep learning model on a dataset of clinical notes that have been annotated with relevant risk factors, and we evaluate the model's performance in identifying risk factors in new clinical notes. </sec> <sec> <title>OBJECTIVE</title> The primary objective is to develop a novel deep learning approach to detect risk factors for underlying disease in patients presenting with lower back pain in clinical encounter notes. The secondary objective is to propose solutions to potential challenges of using deep learning and NLP techniques for identifying risk factors in EMR free text and make practical recommendations for future research in this area. </sec> <sec> <title>METHODS</title> We manually annotated clinical notes for the presence of six risk factors for severe underlying disease in patients presenting with lower back pain. Data was highly imbalanced, with only 12% of the annotated notes having at least one label. To address imbalanced data, a combination of semantic matching and regular expressions was used to further capture more notes to annotate. Further analysis was conducted to study the impact of down-sampling, binary formulation of multi-label classification and unsupervised pre-training on classification performance. Lastly, the proposed BERT-based model was compared using original BERT baselines for detecting lower back pain risk factors. </sec> <sec> <title>RESULTS</title> Of 2350 clinical notes labeled, 347 had at least one label, while 2402 had no labels. Down-sampling the training set to equalize the ratio of clinical notes with and without risk factors improved the average AUC by 21% for the BERT baseline. The proposed BERT-based model performed 3% better than the BERT baseline in multi-task learning. Unsupervised pre-training using causal language modeling on clinical notes can further improve performance by 1%. </sec> <sec> <title>CONCLUSIONS</title> Primary care clinical notes are likely to require manipulation to perform meaningful free-text analysis. The application of BERT Transformer models for multi-label classification on down-sampled annotated clinical notes is useful in detecting risk factors suggesting an indication for imaging for patients with lower back pain. </sec>" @default.
• W4313557631 created "2023-01-06" @default.
• W4313557631 creator A5005493395 @default.
• W4313557631 creator A5013989913 @default.
• W4313557631 creator A5015595611 @default.
• W4313557631 creator A5034708845 @default.
• W4313557631 date "2022-12-15" @default.
• W4313557631 modified "2023-10-16" @default.
• W4313557631 title "A Deep Learning Approach To Identifying Risk Factors Associated With Lower Back Pain In Electronic Medical Record Free Text (Preprint)" @default.
• W4313557631 cites W1832693441 @default.
• W4313557631 cites W1941659294 @default.
• W4313557631 cites W2338318698 @default.
• W4313557631 cites W2396881363 @default.
• W4313557631 cites W2486758140 @default.
• W4313557631 cites W2888140517 @default.
• W4313557631 cites W2900065283 @default.
• W4313557631 cites W2905810301 @default.
• W4313557631 cites W2920828889 @default.
• W4313557631 cites W2965972502 @default.
• W4313557631 cites W2970641574 @default.
• W4313557631 cites W2971258845 @default.
• W4313557631 cites W2995452567 @default.
• W4313557631 cites W3034238904 @default.
• W4313557631 cites W3129480798 @default.
• W4313557631 cites W3156636935 @default.
• W4313557631 cites W4206522381 @default.
• W4313557631 cites W4237084960 @default.
• W4313557631 cites W4246183800 @default.
• W4313557631 cites W4252608096 @default.
• W4313557631 doi "https://doi.org/10.2196/preprints.45105" @default.
• W4313557631 hasPublicationYear "2022" @default.
• W4313557631 type Work @default.
• W4313557631 citedByCount "0" @default.
• W4313557631 crossrefType "posted-content" @default.
• W4313557631 hasAuthorship W4313557631A5005493395 @default.
• W4313557631 hasAuthorship W4313557631A5013989913 @default.
• W4313557631 hasAuthorship W4313557631A5015595611 @default.
• W4313557631 hasAuthorship W4313557631A5034708845 @default.
• W4313557631 hasConcept C108583219 @default.
• W4313557631 hasConcept C119857082 @default.
• W4313557631 hasConcept C127413603 @default.
• W4313557631 hasConcept C136764020 @default.
• W4313557631 hasConcept C142724271 @default.
• W4313557631 hasConcept C154945302 @default.
• W4313557631 hasConcept C165064840 @default.
• W4313557631 hasConcept C201995342 @default.
• W4313557631 hasConcept C204321447 @default.
• W4313557631 hasConcept C23123220 @default.
• W4313557631 hasConcept C2779135771 @default.
• W4313557631 hasConcept C2780451532 @default.
• W4313557631 hasConcept C2908647359 @default.
• W4313557631 hasConcept C41008148 @default.
• W4313557631 hasConcept C43169469 @default.
• W4313557631 hasConcept C71924100 @default.
• W4313557631 hasConcept C99454951 @default.
• W4313557631 hasConceptScore W4313557631C108583219 @default.
• W4313557631 hasConceptScore W4313557631C119857082 @default.
• W4313557631 hasConceptScore W4313557631C127413603 @default.
• W4313557631 hasConceptScore W4313557631C136764020 @default.
• W4313557631 hasConceptScore W4313557631C142724271 @default.
• W4313557631 hasConceptScore W4313557631C154945302 @default.
• W4313557631 hasConceptScore W4313557631C165064840 @default.
• W4313557631 hasConceptScore W4313557631C201995342 @default.
• W4313557631 hasConceptScore W4313557631C204321447 @default.
• W4313557631 hasConceptScore W4313557631C23123220 @default.
• W4313557631 hasConceptScore W4313557631C2779135771 @default.
• W4313557631 hasConceptScore W4313557631C2780451532 @default.
• W4313557631 hasConceptScore W4313557631C2908647359 @default.
• W4313557631 hasConceptScore W4313557631C41008148 @default.
• W4313557631 hasConceptScore W4313557631C43169469 @default.
• W4313557631 hasConceptScore W4313557631C71924100 @default.
• W4313557631 hasConceptScore W4313557631C99454951 @default.
• W4313557631 hasLocation W43135576311 @default.
• W4313557631 hasOpenAccess W4313557631 @default.
• W4313557631 hasPrimaryLocation W43135576311 @default.
• W4313557631 hasRelatedWork W2787045460 @default.
• W4313557631 hasRelatedWork W2993873509 @default.
• W4313557631 hasRelatedWork W3014300295 @default.
• W4313557631 hasRelatedWork W3107474891 @default.
• W4313557631 hasRelatedWork W3128216712 @default.
• W4313557631 hasRelatedWork W4223943233 @default.
• W4313557631 hasRelatedWork W4225161397 @default.
• W4313557631 hasRelatedWork W4309045103 @default.
• W4313557631 hasRelatedWork W4312200629 @default.
• W4313557631 hasRelatedWork W61303690 @default.
• W4313557631 isParatext "false" @default.
• W4313557631 isRetracted "false" @default.
• W4313557631 workType "article" @default.