Prediction of complications in diabetes mellitus using machine learning models with transplanted topic model features

Springer Science and Business Media LLC - 2024
Benedict Choonghyun Han1, Jimin Kim2, Jinwook Choi3,4
1Interdisciplinary Program in Bioengineering, Seoul National University, Seoul, Republic of Korea
2English Language and Literature, Seoul National University, Seoul, Republic of Korea
3Institute of Medical and Biological Engineering, Medical Research Center, Seoul National University, Seoul, Republic of Korea
4Department of Biomedical Engineering, College of Medicine, Seoul National University, Seoul, Republic of Korea

Tóm tắt

AbstractPurpose: This study aims to predict the progression of Diabetes Mellitus (DM) from the clinical notes through machine learning based on latent Dirichlet allocation (LDA) topic modeling. Particularly, 174,427 clinical notes of DM patients were collected from the electronic medical record (EMR) system of the Seoul National University Hospital outpatient clinic. Method: We developed a model to predict the development of DM complications. Topics developed by the topic model were exploited as the key feature of our machine-learning model. The proposed model generalized a correlation between topic structures and complications. Results: The model provided acceptable predictive performance for all four types of complications (diabetic retinopathy, diabetic nephropathy, nonalcoholic fatty liver disease, and cerebrovascular accident). Upon employing extreme gradient boosting (XGBoost), we obtained the F1 scores of the predictions for each complication type as 0.844, 0.921, 0.831, and 0.762. Conclusion: This study shows that a machine learning project based on topic modeling can effectively predict the progress of a disease. Furthermore, a unique way of topic model transplanting, which matches the dimension of the topic structures of the two data sets, is presented.

Từ khóa


Tài liệu tham khảo

2018 WHO, Diabetes. 2018. https://www.who.int/news-room/fact-sheets/detail/diabetes. Accessed November 26 2022.

Thomas PB, Robertson DH, Chawla NV. Predicting onset of complications from diabetes: a graph based approach. Appl Netw Sci. 2018;3(1):48. https://doi.org/10.1007/s41109-018-0106-z.

Ljubic B, Hai AA, Stanojevic M, Diaz W, Polimac D, Pavlovski M, Obradovic Z. Predicting complications of diabetes mellitus using advanced machine learning algorithms. J Am Med Inform Assoc. 2020;27(9):1343–51. https://doi.org/10.1093/jamia/ocaa120.

Blei DM, Ng AY, Jordan MI. Latent dirichlet allocation. J Mach Learn Res. 2003;3:993–1022.

Blei DM. Probabilistic topic models. Commun ACM. 2012;55(4):77–84. https://doi.org/10.1145/2133806.2133826.

Papadimitriou CH, Raghavan P, Tamaki H, Vempala S. Latent semantic indexing: a probabilistic analysis. J Comput Syst Sci. 2000;61(2):217–35. https://doi.org/10.1006/jcss.2000.1711.

Hofman T. Probabilistic latent semantic indexing. ACM. 1999;50–7. https://doi.org/10.1145/312624.312649.

Griffiths TL, Steyvers M. Finding scientific topics. Proc Natl Acad Sci. 2004;101(Suppl 1):5228–35. https://doi.org/10.1073/pnas.0307752101.

Perotte A, Ranganath R, Hirsch JS, Blei D, Elhadad N. Risk prediction for chronic kidney disease progression using heterogeneous electronic health record data and time series analysis. J Am Med Inform Assoc. 2015;22(4):872–80. https://doi.org/10.1093/jamia/ocv024.

Sarioglu E, Yadav K, Choi HA. Topic Modeling Based Classification of Clinical Reports, in: 51st Annual Meeting of the Association for Computational Linguistics Proceedings of the Student Research Workshop, pages, Sofia, Bulgaria, Association for Computational Linguistics, 2013:67–73.

Restificar A, Ananiadou S. Inferring appropriate eligibility criteria in clinical trial protocols without labeled data. in: Proceedings of the ACM sixth international workshop on Data and text mining in biomedical informatics, 2012:21–28.

Halpern Y, Horng S, Nathanson LA, Shapiro NI, Sontag D. A comparison of dimensionality reduction techniques for unstructured clinical text, in: ICML 2012 Workshop on Clinical Data Analysis, 2012.

Korea:VANK TVANo 21c Sejong Project. http://sejong.prkorea.com/kor/main.jsp. 2022. Accessed December 26 2022.

Blei D. in: LDA-c. 2016. https://github.com/blei-lab/lda-c. Accessed December 10 2022.

Liaw A, Wiener M. Classification and regression by randomForest, R News 2002. 2002. https://cogns.northwestern.edu/cbmg/LiawAndWiener2002.pdf. Accessed December 26 2022.

Greenwell B, Boehmke B, Cunningham J, Developers GGBM. Generalized Boosted Regression Models. 2018. https://cran.r-project.org/web/packages/gbm/index.html. Accessed December 26 2022.

Chen T, He T, Benesty M, Khotilovich V, Tang Y, Cho H et al. Xgboost:extreme gradient boosting, R package version (4 – 2), 2015. https://cran.r-project.org/web/packages/xgboost/index.html. Accessed December 26 2022.

Kuhn M. Building predictive models in R using the caret package. J Stat Softw. 2008;28:1–26.

Thông tin
Thông tin xuất bản

Springer Science and Business Media LLC

Thông tin tác giả