Integrating data analytics into health informatics: Advancing equity, pharmaceutical outcomes, and public health decision-making
Introduction: The integration of data analytics into health informatics has become vital for transforming raw clinical information into actionable insights that improve patient care and pharmaceutical outcomes.
Objectives: This study uses the Medical Information Mart for Intensive Care IV (MIMIC-IV) electronic health record dataset to examine differences in pharmaceutical prescription patterns and their relationship to clinical outcomes. We investigate how demographic characteristics, including age, gender, and race, affect prescribing patterns for three major drug classes: opioids, antibiotics, and antipsychotics.
Methods: We analyzed the MIMIC-IV intensive care unit dataset, incorporating preprocessing of demographic and prescription data to support fairness and outcome analysis. A decision tree model was trained to predict in-hospital mortality and evaluated using standard performance metrics.
Results: We examined the relationship between drug type and patient outcomes, finding that antibiotic prescriptions were associated with shorter hospital stays, whereas antipsychotic prescriptions were linked to longer hospitalizations. Our findings reveal statistically significant differences in prescribing patterns, where men were more likely to receive opioids, whereas women were more likely to receive antibiotics. In addition, considerable racial disparities suggest possible systemic inequities. Nevertheless, there was no statistically significant correlation between drug type and in-hospital mortality, indicating that underlying clinical conditions may play a more substantial role. The model achieved an area under the receiver operating characteristic curve of 0.9337 and an F1-score of 0.8235, outperforming several complex algorithms whereas remaining easily interpretable—an important advantage in clinical practice.
Conclusion: These results demonstrate the potential of transparent machine learning models to support enhanced medical decision-making and highlight the need for prescription strategies that prioritize fairness and equity.
- Muthukaruppasamy S, Thomas AS, Gopal JN, Anand AJ, Parimalasundar E. Diagnostics, treatment and patient care in the age of digital twins: A game-changer in healthcare. In: Handbook of Industrial and Business Applications with Digital Twins. United States: CRC Press; 2025. p. 282-305.
- Bhuiyan MNA, Mondal RS. AI-driven predictive analytics in healthcare: Evaluating impact on cost and efficiency. J Comput Anal Appl. 2023;31(4):1355-1371. doi: 10.48047/jocaaa.2023.31.04.26
- Abbas SR, Abbas Z, Zahir A, Lee SW. Federated learning in smart healthcare: A comprehensive review on privacy, security, and predictive analytics with IoT integration. Healthcare (Basel). 2024;12(24):2587. doi: 10.3390/healthcare12242587
- Marcos-Vidal JM, González R, Merino M, Higuera E, García C. Sedation for patients with sepsis: Towards a personalised approach. J Pers Med. 2023;13(12):1641. doi: 10.3390/jpm13121641
- Green S, Prainsack B, Sabatello M. Precision medicine and the problem of structural injustice. Med Health Care Philos. 2023;26(3):433-450. doi: 10.1007/s11019-023-10173-9
- Johnson A, Bulgarelli L, Pollard T, Horng S, Celi LA, Mark R. MIMIC-IV. PhysioNet. 2020. p. 49-55. doi: 10.13026/s6n6-xd98
- Hanna MG, Pantanowitz L, Jackson B, et al. Ethical and bias considerations in artificial intelligence/machine learning. Mod Pathol. 2025;38(3):100686. doi: 10.1016/j.modpat.2024.100686
- Bhuiyan MNA, Kamruzzaman M, Saha S, Siddiki MS, Mondal RS. Role of data analysis and integration of artificial intelligence. J Bus Manag Stud. 2025;7(4):379-388. doi: 10.32996/jbms.2025.7.4.20.26
- Zaidi SAJ, Ghafoor A, Kim J, Abbas Z, Lee SW. HeartEnsembleNet: An innovative hybrid ensemble learning approach for cardiovascular risk prediction. Healthcare (Basel). 2025;13(5):507. doi: 10.3390/healthcare13050507
- Kamruzzaman M, Mondal RS, Islam MK, Rahaman MA, Saha S. AI-driven predictive modelling of US economic growth using big data and explainable machine learning. Int J Comput Exp Sci Eng. 2024;10(4):1927-1938. doi: 10.22399/ijcesen.3612
- Mondal RS, Kamruzzaman M, Saha S, Bhuiyan MNA. Quantum machine learning approaches for high-dimensional cancer genomics data analysis. Comput Integr Manuf Syst. 2025;31(1):13-32. doi: 10.24297/j.cims.2025.1.21
- Torres PJ. Race and gender disparities in pain treatment and opioid prescribing. Soc Sci Med. 2025;374:118011. doi: 10.1016/j.socscimed.2025.118011
- Wilson M, Booker S, Saravanan A, et al. Disparities, inequities, and injustices in populations with pain: Nursing recommendations supporting ASPMN’s 2024 position statement. Pain Manag Nurs. 2025;26(2):139-148. doi: 10.1016/j.pmn.2024.10.016
- Yang N, Fang MC, Rambachan A. Sex disparities in opioid prescription and administration on a hospital medicine service. J Gen Intern Med. 2024;39:2679-2688. doi: 10.1007/s11606-024-08814-7
- Khan NF, Bykov K, Glynn RJ, Vine SM, Gagne JJ. Comparative risk of opioid overdose in patients who initiated antibiotics for urinary tract infection while on long-term opioid therapy. Am J Epidemiol. 2025;194(3):674-679. doi: 10.1093/aje/kwae248
- Qian J, Yuan Y, Shang Z, et al. Association between emergency department to intensive care units time and in-hospital mortality: An analysis of the MIMIC-IV database. BMJ Open. 2025;15(4):e090011. doi: 10.1136/bmjopen-2024-090011
- Ekong M, Monga TS, Daher JC, et al. From the intensive care unit to recovery: Managing post-intensive care syndrome in critically ill patients. Cureus. 2024;16(5):e61443. doi: 10.7759/cureus.61443
- Li C, Mowery DL, Ma X, et al. Realizing the potential of social determinants data in EHR systems: A scoping review of approaches for screening, linkage, extraction, analysis, and interventions. J Clin Transl Sci. 2024;8(1):e147. doi: 10.1017/cts.2024.571
- Gabitashvili A, Kellmeyer P. Predicting Length of Stay in Neurological ICU Patients using Classical Machine Learning and Neural Network Models: A Benchmark Study on MIMIC-IV [arXiv Preprint]; 2025. doi: 10.48550/arXiv.2505.17929
- Silva JM, Durden TE, Hirsch A. Erasing inequality: Examining discrepancies between electronic health records and patient narratives to uncover perceived stigma and dismissal in clinical encounters. Soc Sci Med. 2023;323:115837. doi: 10.1016/j.socscimed.2023.115837
- Williamson SM, Prybutok V. Balancing privacy and progress: A review of privacy challenges, systemic oversight, and patient perceptions in AI-driven healthcare. Appl Sci. 2024;14(2):675. doi: 10.3390/app14020675
- Ramakrishnaiah Y, Macesic N, Webb GI, Peleg AY, Tyagi S. EHR-ML: A data-driven framework for designing machine learning applications with electronic health records. Int J Med Inform. 2025;196:105816. doi: 10.1016/j.ijmedinf.2025.105816
- Percival V, Thoms OT, Oppenheim B, et al. The lancet commission on peaceful societies through health equity and gender equality. Lancet. 2023;402(10413):1661-1722. doi: 10.1016/S0140-6736(23)01348-X
- Kamruzzaman M, Saha S, Siddiki MS, Mondal RS, Bhuiyan MNA. Applications of artificial intelligence in small and medium scale business. J Bus Manag Stud. 2025;7(4):314-325. doi: 10.32996/jbms.2025.7.4.20.21
- Ghazalbash S, Zargoush M, Verter V, Perri D. Data-driven insights into interhospital care fragmentation: Implications for health policy and equity among older adults. PLoS One. 2025;20(2):e0316829. doi: 10.1371/journal.pone.0316829
- Chung RYN, Freedman B. Health inequalities in AI machine learning. In: Artificial Intelligence in Medicine. United States: Academic Press; 2024. p. 119-130.
- Johnson A, Bulgarelli L, Pollard T, et al. MIMIC-IV PhysioNet. RRID: SCR_007345. Ver. 3.1. [Preprint]; 2024.
- Johnson AEW, Bulgarelli L, Shen L, et al. MIMIC-IV, a freely accessible electronic health record dataset. Sci Data. 2023;10:1. doi: 10.1038/s41597-022-01899-x
- Saha S, Islam MK, Rahaman MA, Mondal RS, Kamruzzaman M. Machine learning driven analytics for national security operations: A wavelet-stochastic signal detection framework. J Comput Anal Appl. 2024;33(8):210. doi: 10.48047/jocaaa.2024.33.08.210
- Majchrowska S, Hildeman A, Mokhtari R, Diethe T, Teare P. Exploring interpretable echo analysis using self-supervised parcels. Comput Biol Med. 2025;192:110322. doi: 10.1016/j.compbiomed.2025.110322