دورية أكاديمية
Can Race-sensitive Biomedical Embeddings Improve Healthcare Predictive Models?
| العنوان: | Can Race-sensitive Biomedical Embeddings Improve Healthcare Predictive Models? |
|---|---|
| المؤلفون: | Liu H; Department of Biomedical Informatics., Moustafa-Fahmy N; Department of Statistics, Columbia University, New York, NY, USA., Ta C; Department of Biomedical Informatics., Weng C; Department of Biomedical Informatics. |
| المصدر: | AMIA Joint Summits on Translational Science proceedings. AMIA Joint Summits on Translational Science [AMIA Jt Summits Transl Sci Proc] 2023 Jun 16; Vol. 2023, pp. 388-397. Date of Electronic Publication: 2023 Jun 16 (Print Publication: 2023). |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: AMIA Country of Publication: United States NLM ID: 101539486 Publication Model: eCollection Cited Medium: Internet ISSN: 2153-4063 (Electronic) NLM ISO Abbreviation: AMIA Jt Summits Transl Sci Proc Subsets: PubMed not MEDLINE |
| أسماء مطبوعة: | Original Publication: Bethesda, MD : AMIA, [2011]- |
| مستخلص: | This reproducibility study presents an algorithm to weigh in race distribution data of clinical research study samples when training biomedical embeddings. We extracted 12,864 PubMed abstracts published between January 1 st , 2000 and January 1 st , 2022 and weighed them based on the race distribution data extracted from their corresponding clinical trials registered on ClinicalTrials.gov. We trained Word2vec and BERT embeddings and evaluated their performance on predicting length of hospital stay (LHS) and intensive care unit (ICU) readmission using MIMIC-IV electronic health record data. We observed that models trained using race-sensitive embeddings do not consistently outperform the neutral embeddings ones when used for LHS prediction (with similar Mean Absolute Error 1.975 vs. 2.008) or ICU readmission prediction (with similar accuracy 74.61% vs. 75.17% and the same AUC 0.775), respectively. We conclude that demographic sensitive embeddings do not necessarily significantly improve the accuracy of health predictive models as previously reported in the literature. (©2023 AMIA - All rights reserved.) |
| References: | IJCAI (U S). 2019 Jul;2019:4897-4903. (PMID: 32116463) BMC Med Inform Decis Mak. 2019 Apr 9;19(Suppl 2):58. (PMID: 30961579) PLoS Comput Biol. 2020 Apr 23;16(4):e1007617. (PMID: 32324731) J Bone Joint Surg Am. 2014 Apr 2;96(7):e56. (PMID: 24695933) AMIA Jt Summits Transl Sci Proc. 2016 Jul 20;2016:41-50. (PMID: 27570647) BMC Med Inform Decis Mak. 2020 Dec 30;20(Suppl 11):295. (PMID: 33380338) Am Heart J. 2003 Aug;146(2):250-7. (PMID: 12891192) Pac Symp Biocomput. 2020;25:295-306. (PMID: 31797605) JAMA Netw Open. 2019 Jul 3;2(7):e196700. (PMID: 31268541) J Am Med Inform Assoc. 2018 Jan 1;25(1):72-80. (PMID: 28505280) Lancet Neurol. 2004 Oct;3(10):627-30. (PMID: 15380160) J Biomed Inform. 2020 Aug;108:103489. (PMID: 32592755) N Engl J Med. 2020 Aug 27;383(9):e59. (PMID: 32780573) J Am Med Inform Assoc. 2022 Jan 29;29(3):415-423. (PMID: 34918101) Bioinformatics. 2017 Jul 15;33(14):i37-i48. (PMID: 28881963) J Am Med Inform Assoc. 2020 Jan 1;27(1):47-55. (PMID: 31334805) |
| تواريخ الأحداث: | Date Created: 20230623 Latest Revision: 20230701 |
| رمز التحديث: | 20240628 |
| مُعرف محوري في PubMed: | PMC10283113 |
| PMID: | 37350869 |
| قاعدة البيانات: | MEDLINE |
| تدمد: | 2153-4063 |
|---|