The Effectiveness of Phrase Skip-Gram in Primary Care NLP for the Prediction of Lung Cancer
| Autor: | Luik, Torec T., Rios, Miguel, Abu-Hanna, Ameen, van Weert, Henk C. P. M., Schut, Martijn C., Tucker, Allan, Henriques Abreu, Pedro, Cardoso, Jaime, Pereira Rodrigues, Pedro, Riaño, David |
|---|---|
| Přispěvatelé: | Medical Informatics, APH - Aging & Later Life, APH - Methodology, General practice, ACS - Heart failure & arrhythmias, APH - Personalized Medicine, APH - Quality of Care |
| Rok vydání: | 2021 |
| Předmět: |
Phrase
Computer science business.industry Calibration (statistics) Deep learning Phrase skip-gram Cancer Primary care Prediction models medicine.disease computer.software_genre N-Grams Word embeddings medicine Artificial intelligence business Lung cancer computer Predictive modelling Natural language processing Gram |
| Zdroj: | Artificial Intelligence in Medicine ISBN: 9783030772109 AIME Artificial Intelligence in Medicine-19th International Conference on Artificial Intelligence in Medicine, AIME 2021, Proceedings, 12721 LNAI, 433-437 |
| DOI: | 10.1007/978-3-030-77211-6_51 |
| Popis: | Neural models that use context-dependency in the learned text are computationally expensive. We compare the effectiveness (predictive performance) and efficiency (computational effort) of a context-independent Phrase Skip-Gram (PSG) model and a contextualized Hierarchical Attention Network (HAN) model for early prediction of lung cancer using free-text patient files from Dutch primary care physicians. The performance of PSG (AUROC 0.74 (0.69–0.79)) was comparable to HAN (AUROC 0.73 (0.68–0.78)); it achieved better calibration; had much less parameters (301 versus > 300k) and much faster (36 versus 460 s). This demonstrates an important case in which the complex contextualized neural models were not required. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|