Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Feb 28;20(5):4340.
doi: 10.3390/ijerph20054340.

Integrating Structured and Unstructured EHR Data for Predicting Mortality by Machine Learning and Latent Dirichlet Allocation Method

Chih-Chou Chiu  1 , Chung-Min Wu  1 , Te-Nien Chien  2 , Ling-Jing Kao  1 , Chengcheng Li  2 , Chuan-Mei Chu  2
Affiliations

Integrating Structured and Unstructured EHR Data for Predicting Mortality by Machine Learning and Latent Dirichlet Allocation Method

Chih-Chou Chiu et al. Int J Environ Res Public Health. .

Abstract

An ICU is a critical care unit that provides advanced medical support and continuous monitoring for patients with severe illnesses or injuries. Predicting the mortality rate of ICU patients can not only improve patient outcomes, but also optimize resource allocation. Many studies have attempted to create scoring systems and models that predict the mortality of ICU patients using large amounts of structured clinical data. However, unstructured clinical data recorded during patient admission, such as notes made by physicians, is often overlooked. This study used the MIMIC-III database to predict mortality in ICU patients. In the first part of the study, only eight structured variables were used, including the six basic vital signs, the GCS, and the patient's age at admission. In the second part, unstructured predictor variables were extracted from the initial diagnosis made by physicians when the patients were admitted to the hospital and analyzed using Latent Dirichlet Allocation techniques. The structured and unstructured data were combined using machine learning methods to create a mortality risk prediction model for ICU patients. The results showed that combining structured and unstructured data improved the accuracy of the prediction of clinical outcomes in ICU patients over time. The model achieved an AUROC of 0.88, indicating accurate prediction of patient vital status. Additionally, the model was able to predict patient clinical outcomes over time, successfully identifying important variables. This study demonstrated that a small number of easily collectible structured variables, combined with unstructured data and analyzed using LDA topic modeling, can significantly improve the predictive performance of a mortality risk prediction model for ICU patients. These results suggest that initial clinical observations and diagnoses of ICU patients contain valuable information that can aid ICU medical and nursing staff in making important clinical decisions.

Keywords: electronic health records; intensive care units; machine learning; predictive modeling; structured vs. unstructured data.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Research scheme.
Figure 2
Figure 2
The process of data extraction.
Figure 3
Figure 3
Topic modelling in Python.
Figure 4
Figure 4
ROC curves for the different classifiers. (a) 3-day mortality. (b) 30-day mortality. (c) 365-day mortality.
See this image and copyright information in PMC

References

    1. Marshall J.C., Bosco L., Adhikari N.K., Connolly B., Diaz J.V., Dorman T., Fowler R.A., Meyfroidt G., Nakagawa S., Pelosi P., et al. What is an intensive care unit? A report of the task force of the World Federation of Societies of Intensive and Critical Care Medicine. J. Crit. Care. 2017;37:270–276. doi: 10.1016/j.jcrc.2016.07.015. - DOI - PubMed
    1. Mahbub M., Srinivasan S., Danciu I., Peluso A., Begoli E., Tamang S., Peterson G.D. Unstructured clinical notes within the 24 hours since admission predict short, mid & long-term mortality in adult ICU patients. PLoS ONE. 2022;17:e0262182. - PMC - PubMed
    1. Chen W., Long G., Yao L., Sheng Q.Z. AMRNN: Attended multi-task recurrent neural networks for dynamic illness severity prediction. World Wide Web. 2019;23:2753–2770. doi: 10.1007/s11280-019-00720-x. - DOI
    1. Romana S., Bernhard F. Iatrogenic events contributing to paediatric intensive care unit admission. Swiss Med. Wkly. 2021;151:7. - PubMed
    1. Caicedo-Torres W., Gutierrez K. ISeeU2: Visually interpretable mortality prediction inside the ICU using deep learning and free-text medical notes. Expert Syst. Appl. 2022;202:117190. doi: 10.1016/j.eswa.2022.117190. - DOI