A novel medical text classification model with Kalman filter for clinical decision making. (April 2023)

• Record Type: Journal Article
• Authors: Li, Jie; Huang, Qilin; Ren, Siyu; Jiang, Li; Deng, Bo; Qin, Yi
• Is Part Of: Biomedical signal processing and control. Volume 82(2023)
• Publication Date: 2023-04
• Subjects: Medical text classification -- Clinical decision support systems -- Sling window -- Kalman filter; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.104503
• Languages: English
• ISSNs: 1746-8094

Abstract

Abstract: Medical text classification has long been a challenging issue in the construction of clinical decision support systems because medical texts contain medical terminologies and various medical abbreviations. This paper proposes an ALBERT-based fusion Kalman-filter model, named AFKF, to address word-level and sentence-level noises in electronic medical records. Specifically, a sliding window scheme is explored to deal with the coupling relationship among large sequences. Furthermore, we design a fusion block on the basis of Kalman filter to integrate representations of multiple segment sequences. Experiments indicate that our approach significantly outperforms the baseline methods with real-world medical texts. Our fusion strategy also improves the performance of other feature classification models in the medical text classification task. Graphical abstract: Highlights: A new text classification model (i.e. AFKF) is proposed, which provides a valuable reference for subsequent clinical decision support systems. A sliding window scheme is proposed to pre-process the raw data. A fusion text feature strategy with a specific Kalman filter was designed to fuse the features of multiple segment sequences.