Predicting rapid progression phases in glaucoma using a soft voting ensemble classifier exploiting Kalman filtering.
| Autor: | Jones IA; Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, MI, 48109, USA., Van Oyen MP; Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, MI, 48109, USA. vanoyen@umich.edu., Lavieri MS; Department of Industrial and Operations Engineering, University of Michigan, Ann Arbor, MI, 48109, USA., Andrews CA; Kellogg Eye Institute, Ann Arbor, MI, 48105, USA., Stein JD; Kellogg Eye Institute, Ann Arbor, MI, 48105, USA. |
|---|---|
| Jazyk: | angličtina |
| Zdroj: | Health care management science [Health Care Manag Sci] 2021 Dec; Vol. 24 (4), pp. 686-701. Date of Electronic Publication: 2021 May 13. |
| DOI: | 10.1007/s10729-021-09564-2 |
| Abstrakt: | In managing patients with chronic diseases, such as open angle glaucoma (OAG), the case treated in this paper, medical tests capture the disease phase (e.g. regression, stability, progression, etc.) the patient is currently in. When medical tests have low residual variability (e.g. empirical difference between the patient's true and recorded value is small) they can effectively, without the use of sophisticated methods, identify the patient's current disease phase; however, when medical tests have moderate to high residual variability this may not be the case. This paper presents a framework for handling the latter case. The framework presented integrates the outputs of interacting multiple model Kalman filtering with supervised learning classification. The purpose of this integration is to estimate the true values of patients' disease metrics by allowing for rapid and non-rapid phases; and dynamically adapting to changes in these values over time. We apply our framework to classifying whether a patient with OAG will experience rapid progression over the next two or three years from the time of classification. The performance (AUC) of our model increased by approximately 7% (increased from 0.752 to 0.819) when the Kalman filtering results were incorporated as additional features in the supervised learning model. These results suggest the combination of filters and statistical learning methods in clinical health has significant benefits. Although this paper applies our methodology to OAG, the methodology developed is applicable to other chronic conditions. (© 2021. The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.) |
| Databáze: | MEDLINE |
| Externí odkaz: |
|