FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4311252887> ?p ?o ?g. }

• W4311252887 abstract "<sec> <title>BACKGROUND</title> New drug treatments are regularly approved, and it is challenging to remain up-to-date in this rapidly changing environment. Fast and accurate visualization is important to allow a global understanding of the drug market. Automation of this information extraction provides a helpful starting point for the subject matter expert, helps to mitigate human errors, and saves time. </sec> <sec> <title>OBJECTIVE</title> We aimed to semiautomate disease population extraction from the free text of oncology drug approval descriptions from the BioMedTracker database for 6 selected drug targets. More specifically, we intended to extract (1) line of therapy, (2) stage of cancer of the patient population described in the approval, and (3) the clinical trials that provide evidence for the approval. We aimed to use these results in downstream applications, aiding the searchability of relevant content against related drug project sources. </sec> <sec> <title>METHODS</title> We fine-tuned a state-of-the-art deep learning model, Bidirectional Encoder Representations from Transformers, for each of the 3 desired outputs. We independently applied rule-based text mining approaches. We compared the performances of deep learning and rule-based approaches and selected the best method, which was then applied to new entries. The results were manually curated by a subject matter expert and then used to train new models. </sec> <sec> <title>RESULTS</title> The training data set is currently small (433 entries) and will enlarge over time when new approval descriptions become available or if a choice is made to take another drug target into account. The deep learning models achieved 61% and 56% 5-fold cross-validated accuracies for line of therapy and stage of cancer, respectively, which were treated as classification tasks. Trial identification is treated as a named entity recognition task, and the 5-fold cross-validated <i>F</i>₁-score is currently 87%. Although the scores of the classification tasks could seem low, the models comprise 5 classes each, and such scores are a marked improvement when compared to random classification. Moreover, we expect improved performance as the input data set grows, since deep learning models need to be trained on a large enough amount of data to be able to learn the task they are taught. The rule-based approach achieved 60% and 74% 5-fold cross-validated accuracies for line of therapy and stage of cancer, respectively. No attempt was made to define a rule-based approach for trial identification. </sec> <sec> <title>CONCLUSIONS</title> We developed a natural language processing algorithm that is currently assisting subject matter experts in disease population extraction, which supports health authority approvals. This algorithm achieves semiautomation, enabling subject matter experts to leverage the results for deeper analysis and to accelerate information retrieval in a crowded clinical environment such as oncology. </sec>" @default.
• W4311252887 created "2022-12-25" @default.
• W4311252887 creator A5011815307 @default.
• W4311252887 creator A5034247747 @default.
• W4311252887 creator A5038581186 @default.
• W4311252887 creator A5043649593 @default.
• W4311252887 creator A5045381853 @default.
• W4311252887 creator A5048994916 @default.
• W4311252887 creator A5060630803 @default.
• W4311252887 creator A5066896551 @default.
• W4311252887 creator A5074397529 @default.
• W4311252887 creator A5084097034 @default.
• W4311252887 date "2022-12-07" @default.
• W4311252887 modified "2023-09-27" @default.
• W4311252887 title "Categorizing drug approval populations and matching their clinical trials using natural language processing: a practical case study fine-tuning BERT (Preprint)" @default.
• W4311252887 cites W1808652302 @default.
• W4311252887 cites W1939796399 @default.
• W4311252887 cites W2117130368 @default.
• W4311252887 cites W2144578941 @default.
• W4311252887 cites W2145522203 @default.
• W4311252887 cites W2146089916 @default.
• W4311252887 cites W2151986118 @default.
• W4311252887 cites W2169099542 @default.
• W4311252887 cites W2282821441 @default.
• W4311252887 cites W2743028754 @default.
• W4311252887 cites W2760505947 @default.
• W4311252887 cites W2769851464 @default.
• W4311252887 cites W2911489562 @default.
• W4311252887 cites W2963339489 @default.
• W4311252887 cites W2979826702 @default.
• W4311252887 cites W2983214784 @default.
• W4311252887 cites W3034238904 @default.
• W4311252887 cites W3197876970 @default.
• W4311252887 cites W4220989182 @default.
• W4311252887 cites W4239943352 @default.
• W4311252887 cites W4252608096 @default.
• W4311252887 cites W4255421341 @default.
• W4311252887 doi "https://doi.org/10.2196/preprints.44876" @default.
• W4311252887 hasPublicationYear "2022" @default.
• W4311252887 type Work @default.
• W4311252887 citedByCount "0" @default.
• W4311252887 crossrefType "posted-content" @default.
• W4311252887 hasAuthorship W4311252887A5011815307 @default.
• W4311252887 hasAuthorship W4311252887A5034247747 @default.
• W4311252887 hasAuthorship W4311252887A5038581186 @default.
• W4311252887 hasAuthorship W4311252887A5043649593 @default.
• W4311252887 hasAuthorship W4311252887A5045381853 @default.
• W4311252887 hasAuthorship W4311252887A5048994916 @default.
• W4311252887 hasAuthorship W4311252887A5060630803 @default.
• W4311252887 hasAuthorship W4311252887A5066896551 @default.
• W4311252887 hasAuthorship W4311252887A5074397529 @default.
• W4311252887 hasAuthorship W4311252887A5084097034 @default.
• W4311252887 hasConcept C119857082 @default.
• W4311252887 hasConcept C136764020 @default.
• W4311252887 hasConcept C142724271 @default.
• W4311252887 hasConcept C154945302 @default.
• W4311252887 hasConcept C165064840 @default.
• W4311252887 hasConcept C204321447 @default.
• W4311252887 hasConcept C23123220 @default.
• W4311252887 hasConcept C2522767166 @default.
• W4311252887 hasConcept C2908647359 @default.
• W4311252887 hasConcept C41008148 @default.
• W4311252887 hasConcept C43169469 @default.
• W4311252887 hasConcept C71924100 @default.
• W4311252887 hasConcept C99454951 @default.
• W4311252887 hasConceptScore W4311252887C119857082 @default.
• W4311252887 hasConceptScore W4311252887C136764020 @default.
• W4311252887 hasConceptScore W4311252887C142724271 @default.
• W4311252887 hasConceptScore W4311252887C154945302 @default.
• W4311252887 hasConceptScore W4311252887C165064840 @default.
• W4311252887 hasConceptScore W4311252887C204321447 @default.
• W4311252887 hasConceptScore W4311252887C23123220 @default.
• W4311252887 hasConceptScore W4311252887C2522767166 @default.
• W4311252887 hasConceptScore W4311252887C2908647359 @default.
• W4311252887 hasConceptScore W4311252887C41008148 @default.
• W4311252887 hasConceptScore W4311252887C43169469 @default.
• W4311252887 hasConceptScore W4311252887C71924100 @default.
• W4311252887 hasConceptScore W4311252887C99454951 @default.
• W4311252887 hasLocation W43112528871 @default.
• W4311252887 hasOpenAccess W4311252887 @default.
• W4311252887 hasPrimaryLocation W43112528871 @default.
• W4311252887 hasRelatedWork W2119214692 @default.
• W4311252887 hasRelatedWork W2357241418 @default.
• W4311252887 hasRelatedWork W2366644548 @default.
• W4311252887 hasRelatedWork W2376314740 @default.
• W4311252887 hasRelatedWork W2384888906 @default.
• W4311252887 hasRelatedWork W2961085424 @default.
• W4311252887 hasRelatedWork W4286629047 @default.
• W4311252887 hasRelatedWork W4306321456 @default.
• W4311252887 hasRelatedWork W4306674287 @default.
• W4311252887 hasRelatedWork W4224009465 @default.
• W4311252887 isParatext "false" @default.
• W4311252887 isRetracted "false" @default.
• W4311252887 workType "article" @default.