Comparing two machine learning approaches in predicting lupus hospitalization using longitudinal data
Abstract Systemic lupus erythematosus (SLE) is a heterogeneous autoimmune disease characterized by flares ranging from mild to life-threatening. Severe flares and complications can require hospitalizations, which account for most of the direct costs of SLE care. This study investigates two machine l...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-09-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-20845-w |
| _version_ | 1811202814912757760 |
|---|---|
| author | Yijun Zhao Dylan Smith April Jorge |
| author_facet | Yijun Zhao Dylan Smith April Jorge |
| author_sort | Yijun Zhao |
| collection | DOAJ |
| description | Abstract Systemic lupus erythematosus (SLE) is a heterogeneous autoimmune disease characterized by flares ranging from mild to life-threatening. Severe flares and complications can require hospitalizations, which account for most of the direct costs of SLE care. This study investigates two machine learning approaches in predicting SLE hospitalizations using longitudinal data from 925 patients enrolled in a multicenter electronic health record (EHR)-based lupus cohort. Our first Differential approach accounts for the time dependencies in sequential data by introducing additional lagged variables between consecutive time steps. We next evaluate the performance of LSTM, a state-of-the-art deep learning model designed for time series. Our experimental results demonstrate that both methods can effectively predict lupus hospitalizations, but each has its strengths and limitations. Specifically, the Differential approach can be integrated into any non-temporal machine learning algorithms and is preferred for tasks with short observation periods. On the contrary, the LSTM model is desirable for studies utilizing long observation intervals attributing to its capability in capturing long-term dependencies embedded in the longitudinal data. Furthermore, the Differential approach has more options in handling class imbalance in the underlying data and delivers stable performance across different prognostic horizons. LSTM, on the other hand, demands more class-balanced training data and outperforms the Differential approach when there are sufficient positive samples facilitating model training. Capitalizing on our experimental results, we further study the optimal length of patient monitoring periods for different prediction horizons. |
| first_indexed | 2024-04-12T02:45:01Z |
| format | Article |
| id | doaj.art-11cabd1cb2bd4af9bed08f5518f2dc8f |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T02:45:01Z |
| publishDate | 2022-09-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-11cabd1cb2bd4af9bed08f5518f2dc8f2022-12-22T03:51:11ZengNature PortfolioScientific Reports2045-23222022-09-0112111010.1038/s41598-022-20845-wComparing two machine learning approaches in predicting lupus hospitalization using longitudinal dataYijun Zhao0Dylan Smith1April Jorge2Computer and Information Sciences Department, Fordham UniversityComputer and Information Sciences Department, Fordham UniversityDivision of Rheumatology, Allergy, and Immunology, Massachusetts General HospitalAbstract Systemic lupus erythematosus (SLE) is a heterogeneous autoimmune disease characterized by flares ranging from mild to life-threatening. Severe flares and complications can require hospitalizations, which account for most of the direct costs of SLE care. This study investigates two machine learning approaches in predicting SLE hospitalizations using longitudinal data from 925 patients enrolled in a multicenter electronic health record (EHR)-based lupus cohort. Our first Differential approach accounts for the time dependencies in sequential data by introducing additional lagged variables between consecutive time steps. We next evaluate the performance of LSTM, a state-of-the-art deep learning model designed for time series. Our experimental results demonstrate that both methods can effectively predict lupus hospitalizations, but each has its strengths and limitations. Specifically, the Differential approach can be integrated into any non-temporal machine learning algorithms and is preferred for tasks with short observation periods. On the contrary, the LSTM model is desirable for studies utilizing long observation intervals attributing to its capability in capturing long-term dependencies embedded in the longitudinal data. Furthermore, the Differential approach has more options in handling class imbalance in the underlying data and delivers stable performance across different prognostic horizons. LSTM, on the other hand, demands more class-balanced training data and outperforms the Differential approach when there are sufficient positive samples facilitating model training. Capitalizing on our experimental results, we further study the optimal length of patient monitoring periods for different prediction horizons.https://doi.org/10.1038/s41598-022-20845-w |
| spellingShingle | Yijun Zhao Dylan Smith April Jorge Comparing two machine learning approaches in predicting lupus hospitalization using longitudinal data Scientific Reports |
| title | Comparing two machine learning approaches in predicting lupus hospitalization using longitudinal data |
| title_full | Comparing two machine learning approaches in predicting lupus hospitalization using longitudinal data |
| title_fullStr | Comparing two machine learning approaches in predicting lupus hospitalization using longitudinal data |
| title_full_unstemmed | Comparing two machine learning approaches in predicting lupus hospitalization using longitudinal data |
| title_short | Comparing two machine learning approaches in predicting lupus hospitalization using longitudinal data |
| title_sort | comparing two machine learning approaches in predicting lupus hospitalization using longitudinal data |
| url | https://doi.org/10.1038/s41598-022-20845-w |
| work_keys_str_mv | AT yijunzhao comparingtwomachinelearningapproachesinpredictinglupushospitalizationusinglongitudinaldata AT dylansmith comparingtwomachinelearningapproachesinpredictinglupushospitalizationusinglongitudinaldata AT apriljorge comparingtwomachinelearningapproachesinpredictinglupushospitalizationusinglongitudinaldata |