Authors : Aluko Oluwadare Abiodun; Olawuni Adeolu; Babalola Donald Abayomi; Oyebiyi Adewale Julius

Volume/Issue : Volume 10 - 2025, Issue 9 - September

Google Scholar : https://tinyurl.com/jz65evz6

Scribd : https://tinyurl.com/fx7eyez4

DOI : https://doi.org/10.38124/ijisrt/25sep1438

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : This research focuses on establishing reliable machine learning models for clinical decision support by highlighting the crucial roles of data preprocessing and quality. Using the MIMIC-IV database, we developed and validated algorithms based on vital physiological indicators, including blood pressure, temperature, heart rate, respiratory rate, and blood oxygen saturation (SpO2).. The study reveals that the quality of the data provided to machine learning models significantly impacts their performance and reliability in clinical environments. To preserve data accuracy and quality, we have enforced rigorous data preprocessing and quality control guidelines, involving univariate and multivariate analyses. The refined data was utilized to educate an artificial neural network (ANN), which formulated an Early Warning Score (EWS) system. Remarkable performance was displayed by the model, with perfect classification scores (precision, recall, F1 score, and accuracy all equaling 1.0) for individual vital sign predictions. Additionally, the model's MSE and MAE were close to zero, indicating negligible error in the regression metrics. The AUC curve's area was consistently high across all parameters (ranging from 0.992 to 1.000), while the validation accuracy ranged from 94.6% to 100%. Such results are achievable when using high-quality data. Conversely, they also illustrate the negative effects of compromised data quality on performance. In conclusion, the successful development and trustworthy deployment of machine learning systems in healthcare settings rely on robust data preprocessing and quality control, as this research illustrates.

Keywords : Early Warning Systems (EWS), Machine Learning (ML), Area Under the ROC Curve (AUC), Artificial Neural Network (ANN).

References :

1. Suh, J., Lee, G., Kim, J. W., Shin, J., Kim, Y.-J., Lee, S.-W., & Kim, S. (2024). Privacy-preserving prediction of postoperative mortality in multi-institutional data: Development and usability study. JMIR Medical Informatics, 12, e56893.
2. Park, M., Bui, L. K., Jeong, M., Choi, E. J., Lee, N., Kwak, M., Kim, J., Jung, J., Giap, T.-T.-T., Guk, H., & Na, J. (2021). ICT-based person-centered community care platform (IPC3P) to enhance shared decision-making for integrated health and social care services. International Journal of Medical Informatics, 156, 104590.
3. Lai, H.-J., Tan, T.-H., Lin, C.-S., Chen, Y.-F., & Lin, H.-H. (2020). Designing a clinical decision support system to predict readmissions for patients admitted with all-cause conditions. Journal of Ambient Intelligence and Humanized Computing, 11(3), 1251–1264.
4. World Health Organization (2021): guide for action. Geneva: Rehabilitation in health system; Licence: CC BY-NC-SA 3.0 IGO.
5. Abdelgawad, Y. H., Abd El Razik, M. S., Saleh, D. A., Abuelela, M. H., & Salem, M. R. (2024). Promoting health information system in guiding decisions for improving performance: An intervention study at the Research Institute of Ophthalmology, Giza, Egypt. Frontiers in Digital Health, 6, Article 1288776.
6. Alruwaili, M. M., & Abuadas, F. H. (2024). Exploring nurses’ awareness and attitudes toward artificial intelligence: Implications for nursing practice. Digital Health. Advance online publication. 23(1):185. doi: 10.1186/s12411-023-02259-0
7. Yu, Z., Ashrafi, N., Li, H., Alaei, K., & Pishgar, M. (2024). Prediction of 30-day mortality for ICU patients with Sepsis-3. medRxiv. 31(11), pp. 2679-2688.
8. Ruissen, M. M., Torres-Peña, J. D., Uitbeijerse, B. S., Arenas de Larriva, A. P., Huisman, S. D., Namli, T., Salzsieder, E., Vogt, L., Ploessnig, M., van der Putte, B., Merle, A., Serra, G., Rodríguez, G., de Graaf, A. A., de Koning, E. J. P., Delgado-Lista, J., Sont, J. K., & POWER2DM Consortium. (2023). Clinical impact of an integrated e-health system for diabetes self-management support and shared decision making (POWER2DM): A randomised controlled trial. Diabetologia, 66, 2213–2225.
9. Ye-wen Chen, Yu-jie Li, Peng Deng, Zhi-yong Yang, Kun-hua Zhong, Li-ge Zhang, Yang Chen, Hong-yu Zhi, Xiao-yan Hu, Jian-teng Gu, Jiao-lin Ning, Kai-zhi Lu, Ju Zhang, Zheng-yuan Xia, Xiao-lin Qin, Bin Yi(2022) Learning to Predict In-Hospital Mortality Risk in the Intensive Care Unit with Attention-Based Temporal Convolution Network  BMC Anesthesiol. 22: 119.  doi: 10.1186/s12871-022-01625-5
10. Amsterdam UMC. (2023). A data pipeline for cloud-based ICU patient data processing and prediction. University of Amsterdam Research Priority Agenda Program AI for Health Decision-Making. doi: 10.2359/fcvm.2023.1359699
11. Rodríguez, M. O., Martinez, R. M., Martínez, A. P., et al. (2024). Closing the value-based circle in shared decision-making: A digital framework for informing the shared decision-making process through patient reported outcome and experience measures. Frontiers in Public Health. Advance online publication.
12. Karalliedde, J., French, O., Burnhill, G., et al. (2023). A pragmatic digital health informatics-based approach for aiding clinical prioritisation and reducing backlog of care: A study in cohort of 4022 people with diabetes. Diabetes Research and Clinical Practice, 203, 110834.
13. Field, M., Thwaites, D. I., Carolan, M., Delaney, G. P., Lehmann, J., Sykes, J., Vinod, S., & Holloway, L. (2022). Infrastructure platform for privacy-preserving distributed machine learning development of computer-assisted theragnostics in cancer. Journal of Biomedical Informatics, 134, 104181.
14. Deist, T. M., Dankers, F. J. W. M., Ojha, P., Price, G., Lambin, P., Dekker, A.,  (2020). Distributed learning on 20,000+ lung cancer patients – The Personal Health Train. Radiotherapy and Oncology, 144, 189–200.
15. Feng, T., Noren, D. P., Kulkarni, C., Mariani, S., Zhao, C., Ghosh, E., Swearingen, D., Frassica, J., McFarlane, D., & Conroy, B. (2023). Machine learning-based clinical decision support for infection risk prediction. Frontiers in Medicine,  doi:101213411.
16. Kramer, O., Even, A., Matot, I., Steinberg, Y., & Bitan, Y. (2021). The impact of data quality defects on clinical decision-making in the intensive care unit. Computer Methods and Programs in Biomedicine, 209, doi: 10.2136/67253
17. Gan, S., Kim, C., Chang, J., Lee, D. Y., & Park, R. W. (2024). Enhancing readmission prediction models by integrating insights from home healthcare notes: Retrospective cohort study. International Journal of Nursing Studies, 158, 104850.
18. Kooiman, B. E. A. M., Robberegt, S. J., Albers, C. J., Bockting, C. L. H., Stikkelbroek, Y. A. J., & Nauta, M. H. (2024). Congruency of multimodal data-driven personalization with shared decision-making for StayFine: Individualized app-based relapse prevention for anxiety and depression in young people. Journal Name. Advance online publication. doi: 10.1246/s40001-055-02422-5
19. Sassi, Z., Eickmann, S., Roller, R., Osmanodja, B., Burchardt, A., Samhammer, D., Dabrock, P., Möller, S., Budde, K., & Herrmann, A. (2024). Prospectively investigating the impact of AI on shared decision-making in post kidney transplant care (PRIMA-AI): Protocol for a longitudinal qualitative study among patients, their support persons and treating physicians at a tertiary care centre. BMJ Open, 14(10), e073422.
20. Wurhofer, D., Neunteufel, J., Strumegger, E.-M., Höppchen, I., Mayr, B., Egger, A., Sareban, M., Reich, B., Neudorfer, M., Niebauer, J., Smeddinck, J. D., & Kulnik, S. T. (2024). Investigating shared decision-making during the use of a digital health tool for physical activity planning in cardiac rehabilitation. Frontiers in Digital Health, 5, Article 1324488.
21. Almagharbeh, W. T. (2024). The impact of AI-based decision support systems on nursing workflows in critical care units. International Nursing Review. Advance online publication, doi: 10.2196/66293
22. Vázquez-Calatayud, M., García-García, R., Regaira-Martínez, E., & Gómez-Urquiza, J. (2024). Real-world and game-based learning to enhance decision-making. Nurse Education Today, 140, 106276.
23. Dhingra, L., Schiller, R., Teets, R., Shuman, S., DiFiglia, S., & Portenoy, R. (2021). Pain management in primary care: A randomized controlled trial of a computerized decision support tool. The American Journal of Medicine, 134(12), 1546–1554.
24. Steele Gray, C., Nie, J., Loganathan, M., & Tahsin, F. (2022). Supporting goal-oriented care using mobile technology: Findings from the mixed-methods trial of the ePRO tool. Annals of Family Medicine, 20(Supplement 1), 2763.
25. Al-Khatib, H., Zahran, H., & Mahmud, F. (2024). Telemedicine adoption during COVID-19 in rural areas: Barriers and facilitators. Telemedicine and e-Health, 30(1), 15-25.
26. Marcin, T., Hautz, S. C., Singh, H., Zwaan, L., Schwappach, D., Krummrey, G., Schauber, S. K., Nendaz, M., Exadaktylos, A. K., Müller, M., Lambrigger, C., Sauter, T. C., Lindner, G., Bosbach, S., Griesshammer, I., & Hautz, W. E. (2024). Effects of a computerised diagnostic decision support tool on diagnostic quality in emergency departments: Study protocol of the DDx-BRO multicentre cluster randomised cross-over trial. BMJ Open. 32(1), pp.2152-2164.
27. Shoesmith, W. D., Abdullah, A. C., Tan, B. Y., Kamu, A., Ho, C. M., Giridharan, B., Forman, D., & Fyfe, S. (2022). Development of a scale to measure shared problem-solving and decision-making in mental healthcare. Patient Education and Counseling, 105(7), 2480–2488.
28. Deo, R. C., Smith, R., & Patel, R. (2024). Software-driven chronic disease management: Algorithm design and implementation in a community-based blood pressure control pilot. SAGE Open Medicine, 12, 20503121241284025
29. Kim, H., & Park, S. (2023). Virtual reality for pain management in pediatric patients: A systematic review. Pediatric Pain Management, 18(2), 45-56
30. Koch, G., Wilbaux, M., Kasser, S., Schumacher, K., Steffens, B., Wellmann, S., & Pfister, M. (2022). Leveraging predictive pharmacometrics-based algorithms to enhance perinatal care Application to neonatal jaundice. Frontiers in Pharmacology, 14(5), pp. 1053-1065.
31. Singh, R., Patel, A., & Kumar, S. (2023). Machine learning for early detection of diabetic retinopathy using retinal images. Journal of Medical Imaging, 10(3), 230-239.