Multimodal Prediction of COVID-19 ICU Admissions and Demand Using Clinical, Governmental, and Social Media Data with GBM and LSTM Models
Corresponding author: T. T. Sabin
Abstract
During pandemics such as COVID-19, it is very important to accurately and quickly predict how bad the disease will get so that resources and patient care can be used most effectively. This study suggests a dual-model machine learning framework that uses data from three sources—Electronic Health Records (EHRs), government-reported case statistics, and social media sentiment trends—to predict ICU admissions at both the patient and population levels. A Gradient Boosting Machine (GBM) classifier was trained on structured clinical features, such as age, comorbidities (such as diabetes and high blood pressure), pneumonia status, and the need for intubation to predict the likelihood of a patient being admitted to the ICU. This model was 93% accurate and had an AUC of 94.5%. SHAP-based feature importance showed that age, hypertension, and pneumonia were the best predictors. Using trends in hospitalization rates, changes in public policy, and social media sentiment over time, a Long Short-Term Memory (LSTM) model was created to predict how many people will need an ICU over time. This model was 95% accurate and had a ±10% error margin for predicting ICU admissions over the next 14 days. All data were aligned in time and combined using region-level tags. To improve model performance, data preprocessing, hyperparameter tuning (using grid search and Bayesian optimization), and comparisons with baseline models, such as ARIMA and linear regression, were performed. This method shows how multimodal, easy-to-understand AI models can be used in healthcare decision support systems for real-time patient triage and hospital capacity planning.
Keywords:
COVID-19 severity prediction, ICU admission forecasting, machine learning in healthcare, Gradient Boosting Machine (GBM), Long Short-Term Memory (LSTM), feature importance analysis, disease severity classification, time-series forecasting, healthcare resource optimization, pandemic preparednessDownloads
References
N. Narayan Das, N. Kumar, M. Kaur, V. Kumar, and D. Singh, "Automated Deep Transfer Learning-Based Approach for Detection of COVID-19 Infection in Chest X-rays," IRBM, vol. 43, no. 2, pp. 114–119, Apr. 2022.
N. Kumar, M. Gupta, D. Gupta, and S. Tiwari, "Novel deep transfer learning model for COVID-19 patient detection using X-ray chest images," Journal of Ambient Intelligence and Humanized Computing, vol. 14, no. 1, pp. 469–478, Jan. 2023.
J. Li, W. Huang, C. L. Sia, Z. Chen, T. Wu, and Q. Wang, "Enhancing COVID-19 Epidemic Forecasting Accuracy by Combining Real-time and Historical Data From Multiple Internet-Based Sources: Analysis of Social Media Data, Online News Articles, and Search Queries," JMIR Public Health and Surveillance, vol. 8, no. 6, Jun. 2022, Art. no. e35266.
L. Ansell and L. Dalla Valle, "A new data integration framework for Covid-19 social media information," Scientific Reports, vol. 13, no. 1, Apr. 2023, Art. no. 6170.
N. Altieri et al., "Curating a COVID-19 Data Repository and Forecasting County-Level Death Counts in the United States," Harvard Data Science Review, Feb. 2021.
Z. Zhao et al., "Prediction model and risk scores of ICU admission and mortality in COVID-19," PLOS ONE, vol. 15, no. 7, Jul. 2020, Art. no. e0236618.
S. Bhatia et al., "Severity and mortality prediction models to triage Indian COVID-19 patients," PLOS Digital Health, vol. 1, no. 3, Mar. 2022, Art. no. e0000020.
M. D. B. Braga et al., "Artificial neural networks for short-term forecasting of cases, deaths, and hospital beds occupancy in the COVID-19 pandemic at the Brazilian Amazon," PLOS ONE, vol. 16, no. 3, Mar. 2021, Art. no. e0248161.
A. Patrício, R. S. Costa, and R. Henriques, "Predictability of COVID-19 Hospitalizations, Intensive Care Unit Admissions, and Respiratory Assistance in Portugal: Longitudinal Cohort Study," Journal of Medical Internet Research, vol. 23, no. 4, Apr. 2021, Art. no. e26075.
H. Chao et al., "Integrative analysis for COVID-19 patient outcome prediction," Medical Image Analysis, vol. 67, Jan. 2021, Art. no. 101844.
J. Devaraj et al., "Forecasting of COVID-19 cases using deep learning models: Is it reliable and practically significant?," Results in Physics, vol. 21, Feb. 2021, Art. no. 103817.
A. A. Alrajhi et al., "Data-Driven Prediction for COVID-19 Severity in Hospitalized Patients," International Journal of Environmental Research and Public Health, vol. 19, no. 5, Mar. 2022, Art. no. 2958.
M. M. B. Azam et al., "A hybrid contextual framework to predict severity of infectious disease: COVID-19 case study," Egyptian Informatics Journal, vol. 27, Sep. 2024, Art. no. 100508.
D. Liu et al., "Real-Time Forecasting of the COVID-19 Outbreak in Chinese Provinces: Machine Learning Approach Using Novel Digital Data and Estimates From Mechanistic Models," Journal of Medical Internet Research, vol. 22, no. 8, Aug. 2020, Art. no. e20285.
S. Ma and S. Yang, "COVID-19 forecasts using Internet search information in the United States," Scientific Reports, vol. 12, no. 1, Jul. 2022, Art. no. 11539.
A. J. Aljaaf, T. M. Mohsin, D. Al-Jumeily, and M. Alloghani, "A fusion of data science and feed-forward neural network-based modelling of COVID-19 outbreak forecasting in IRAQ," Journal of Biomedical Informatics, vol. 118, Jun. 2021, Art. no. 103766.
M. D. Hssayeni et al., "The forecast of COVID-19 spread risk at the county level," Journal of Big Data, vol. 8, no. 1, Dec. 2021, Art. no. 99.
M. Ala’raj, M. Majdalawieh, and N. Nizamuddin, "Modeling and forecasting of COVID-19 using a hybrid dynamic model based on SEIRD with ARIMA corrections," Infectious Disease Modelling, vol. 6, pp. 98–111, 2021.
H. Alalawi, M. Alsuwat, and H. Alhakami, "A Survey of the Application of Artifical Intellegence on COVID-19 Diagnosis and Prediction," Engineering, Technology & Applied Science Research, vol. 11, no. 6, pp. 7824–7835, Dec. 2021.
N. Kumar, A. Hashmi, M. Gupta, and A. Kundu, "Automatic Diagnosis of Covid-19 Related Pneumonia from CXR and CT-Scan Images," Engineering, Technology & Applied Science Research, vol. 12, no. 1, pp. 7993–7997, Feb. 2022.
K. E. ArunKumar, D. V. Kalaga, Ch. M. Sai Kumar, G. Chilkoor, M. Kawaji, and T. M. Brenza, "Forecasting the dynamics of cumulative COVID-19 cases (confirmed, recovered and deaths) for top-16 countries using statistical machine learning models: Auto-Regressive Integrated Moving Average (ARIMA) and Seasonal Auto-Regressive Integrated Moving Average (SARIMA)," Applied Soft Computing, vol. 103, May 2021, Art. no. 107161.
Y. Zhang-James et al., "A seq2seq model to forecast the COVID-19 cases, deaths and reproductive R numbers in US counties." In Review, Apr. 26, 2021.
S. G. Khatami et al., "Curating, Collecting, and Cataloguing Global COVID-19 Datasets for the Aim of Predicting Personalized Risk," Data, vol. 9, no. 2, Jan. 2024, Art. no. 25.
Md. S. Satu et al., "Short-Term Prediction of COVID-19 Cases Using Machine Learning Models," Applied Sciences, vol. 11, no. 9, May 2021, Art. no. 4266.
P. G. Asteris et al., "Prognosis of COVID-19 severity using DERGA, a novel machine learning algorithm," European Journal of Internal Medicine, vol. 125, pp. 67–73, Jul. 2024.
K. Raza, "Artificial Intelligence Against COVID-19: A Meta-analysis of Current Research," in Big Data Analytics and Artificial Intelligence Against COVID-19: Innovation Vision and Approach, vol. 78, A. E. Hassanien, N. Dey, and S. Elghamrawy, Eds. Springer International Publishing, 2020, pp. 165–176.
F. N. Khan, A. A. Khanam, A. Ramlal, and S. Ahmad, "A Review on Predictive Systems and Data Models for COVID-19," in Computational Intelligence Methods in COVID-19: Surveillance, Prevention, Prediction and Diagnosis, vol. 923, K. Raza, Ed. Springer Singapore, 2021, pp. 123–164.
E. Dong, H. Du, and L. Gardner, "CSSEGISandData/COVID-19." Sep. 04, 2025, [Online]. Available: https://github.com/CSSEGISandData/COVID-19.
"COVID-19 Reported Patient Impact and Hospital Capacity by Facility | HealthData.gov," U.S. Department of Health and Human Services. https://healthdata.gov/Hospital/COVID-19-Reported-Patient-Impact-and-Hospital-Capa/anag-cw7u/about_data.
"Oxford COVID-19 Government Response Tracker," Blavatnik School of Government, Mar. 18, 2020. https://www.bsg.ox.ac.uk/research/covid-19-government-response-tracker.
"COVID-19 India data - Ministry of Health and Family Welfare | GOI." https://www.mohfw.gov.in/.
"COVID-19 Dataset." Kaggle, [Online]. Available: https://www.kaggle.com/datasets/meirnizri/covid19-dataset.
N. Kumar and D. Aggarwal, "LEARNING-based Focused WEB Crawler," IETE Journal of Research, vol. 69, no. 4, pp. 2037–2045, May 2023.
Downloads
How to Cite
License
Copyright (c) 2025 T. T. Sabin, B. S. Sunitha
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
