Predicting Hospital Re-admissions from Clinical Narratives
AUTHORS
Pankti Joshi,Department of Computer Science, Lakehead University, Thunder Bay, Ontario, Canada
Sabah Mohammed,Department of Computer Science, Lakehead University, Thunder Bay, Ontario, Canada
ABSTRACT
In this era, hospital re-admissions have been a significant concern as the numbers of re-admissions are increasing at an alarming rate worldwide. The central idea of this paper is to predict unplanned patient re-admissions within 30 days of their discharge. When a patient is admitted to a health care center, there are high chances of re-admissions based on many healthcare parameters. This paper proposes a Machine Learning-based K-Nearest Neighbor model to predict 30-day unplanned hospital re-admission using clinical notes. The extracted dataset will undergo various text pre-processing stages to improve the overall accuracy of the model. To validate our proposed model, we have implemented many other Machine Learning models to compare different parameters obtained from each of the models. The hyperparameter tuning techniques and feature extraction techniques have been implemented to study the prediction results. According to our observations, the K-Nearest Neighbor model got the best accuracy of 85 percent, while logistic regression did not provide high accuracy. In this way, the clinicians can intervene in patients’ conditions beforehand and predict possible re-admission chances and take various precautionary treatment steps to avoid unplanned re-admissions.
KEYWORDS
Hospital re-admission, Machine learning, Prediction system, Text cleaning
REFERENCES
[1] Canadian Institute for Health Information, “All patients readmitted to hospital,” Oct., (2020)
[2] Goldberger, A., Amaral, L., Glass, L., Hausdorff, J., Ivanov, P. C., Mark, R., Stanley, and H. E., “PhysioBank, physiotoolkit, and physionet: Components of a new research resource for complex physiologic signals,” Circulation [Online], vol.101, no.23, pp.215-220, (2000)
[3] Machine Learning Crash Course, Available: https://developers.google.com/machine-learning/crash-course, Oct., (2020)
[4] Z. Yu and W. B. Rouse, “A deeper look at the causes of hospital readmissions,” IEEE International Conference on Industrial Engineering and Engineering Management (IEEM), Singapore, pp.919-923, (2017) DOI: 10.1109/IEEM.2017.8290026(CrossRef)(Google Scholar)
[5] E´ chevin, Damien, Qing Li, and Marc-Andre´ Morin, “Hospital readmission is highly predictable from deep learning,” Chairede Recherche Industrials Alliances Licensees Economicus Changesets De´mographiques, (2017)
[6] Min X., Yu B., and Wang F., “Predictive modeling of the hospital readmission risk from patients’ claims data using machine learning: A case study on COPD,” Sci Rep, vol.9, no.1, 20 Feb., (2019) DOI: 10.1038/s41598-019- 39071-y, PMID: 30787351, PMCID: PMC6382784(CrossRef)(Google Scholar)
[7] M. M. Baig et al., “Machine learning-based risk of hospital readmissions: Predicting acute readmissions within 30 days of discharge,” 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Berlin, Germany, pp.2178-2181, (2019) DOI: 10.1109/EMBC.2019.8856646(CrossRef)(Google Scholar)
[8] Rajkomar, Alvin, Eyal Oren, Kai Chen, Andrew M. Dai, Nissan Hajaj, Michaela Hardt, and Peter J. Liu et al, “Scalable and accurate deep learning with electronic health records.” NPJ Digital Medicine, vol.1, no.1, pp.18, (2018)
[9] Zhang and Zhongheng, “Introduction to machine learning: K-nearest neighbors,” Annals of Translational Medicine, vol.4, no.11, (2016)
[10] O. Aborisade and M. Anwar, “Classification for authorship of tweets by comparing logistic regression and naive Bayes classifiers," 2018 IEEE International Conference on Information Reuse and Integration (IRI), Salt Lake City, UT, pp.269-276, (2018)
[11] Tin Kam Ho, “Random decision forests,” Proceedings of the International Conference on Document Analysis and Recognition, ICDAR, pp.278-282, (1995)
[12] Wang, Ruihu, “AdaBoost for feature selection, classification and its relation with SVM: A review,” Physics Procedia, vol.25, pp.800-807, (2012)
[13] Kingsford, Carl, and Steven L. Salzberg, “What are decision trees?,” Nature Biotechnology, vol.26, no.9, pp.1011-1013, (2018)
[14] Song, Yan-Yan, and L. U. Ying, “Decision tree methods: Applications for classification and prediction,” Shanghai Archives of Psychiatry, vol.27, no.2, pp.130, (2015)
[15] Natekin, Alexey, and Alois Knoll, “Gradient boosting machines: A tutorial,” Frontiers in Neurorobotics, vol.7, no.21, (2013) DOI: 10.3389/fnbot.2013.00021(CrossRef)(Google Scholar)
[16] Chen, Tianqi, and Carlos Guestrin, “Xgboost: A scalable tree boosting system.” In Proceedings of the 22nd Acmsigkdd International Conference on Knowledge Discovery and Data Mining, pp.785-794, (2016)