ICU Days-to-Discharge Analysis with Machine Learning Technology
- 396 Downloads
ICU management depends on the level of occupation and the length of stay of the patients. Daily prediction of the days to discharge (DTD) of ICU patients is essential to that management. Previous studies showed a low predictive capability of internists and ML-generated models. Therefore, more elaborated combinations of ML technologies are required. Here, we present four approaches to the analysis of the DTDs of ICU patients from different perspectives: heterogeneity quantification, biomarker identification, phenotype recognition, and prediction. Several ML-based methods are proposed for each approach, which were tested with the data of 3,973 patients of a Spanish ICU. Results confirm the complexity of analyzing DTDs with intelligent data analysis methods.
KeywordsICU Patient phenotyping Days-to-discharge prediction Feature selection
Spanish Ministry of Science and Innovation (PID2019-105789RB-I00).
- 3.Cuadrado, D., Riaño, D. Josep Gomez, J., Rodriguez, A., Bodi, M.: Methods and measures to quantify ICU patient heterogeneity. Submitted (2021)Google Scholar
- 7.Jović, A., K. Brkić, K., Bogunović, N.: A review of feature selection methods with applications. In: 38th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO), Opatija, 2015, pp. 1200–1205. https://doi.org/10.1109/MIPRO.2015.7160458
- 17.Selleck, MJ, Senthil, M, Wall, NR.: Making meaningful clinical use of biomarkers. Biomark Insights 12 (2017). https://doi.org/10.1177/1177271917715236