Explainable Multimodal Early-Warning Analytics for Preventing Falls and Avoidable Hospital Transfers in Long-Term Care: A FHIR-Native and Fairness-Aware Framework

References

[1] Akakpo, L., Gezah, F., Mupa, G. et al. (2026) ‘From bedside observation to systems improvement: A practical framework for strengthening resident safety and care coordination in post-acute care settings’, World Journal of Advanced Research and Reviews.

[2] Allam, A., Nagy, M., Thoma, G. and Krauthammer, M. (2019) ‘Neural networks versus logistic regression for 30 days all-cause readmission prediction’, Scientific Reports, 9, 9277.

[3] American Geriatrics Society Beers Criteria Update Expert Panel (2023) ‘American Geriatrics Society 2023 updated AGS Beers Criteria for potentially inappropriate medication use in older adults’, Journal of the American Geriatrics Society, 71(7), pp. 2052–2081.

[4] Ben-Assuli, O. and Padman, R. (2019) ‘Analysing repeated hospital readmissions using data mining techniques’, Health Systems, 8(2), pp. 93–113.

[5] Bouldin, E.D., Andresen, E.M., Dunton, N.E. et al. (2013) ‘Falls among adult patients hospitalized in the United States: prevalence and trends’, Journal of Patient Safety, 9(1), pp. 13–17.

[6] Centers for Medicare & Medicaid Services (2024) Nursing Home Quality Initiative and hospital transfer measures. Baltimore, MD: CMS.

[7] Chen, I.Y., Pierson, E., Rose, S., Joshi, S., Ferryman, K. and Ghassemi, M. (2021) ‘Ethical machine learning in healthcare’, Annual Review of Biomedical Data Science, 4, pp. 123–144.

[8] Choi, E., Bahadori, M.T., Schuetz, A., Stewart, W.F. and Sun, J. (2016) ‘Doctor AI: Predicting clinical events via recurrent neural networks’, Proceedings of Machine Learning for Healthcare, pp. 301–318.

[9] Feng, Q., Du, M., Zou, N. and Hu, X. (2023) ‘Fair machine learning in healthcare: A review’, arXiv:2206.14397.

[10] Goldstein, B.A., Navar, A.M., Pencina, M.J. and Ioannidis, J.P.A. (2017) ‘Opportunities and challenges in developing risk prediction models with electronic health records data’, Journal of the American Medical Informatics Association, 24(1), pp. 198–208.

[11] Harutyunyan, H., Khachatrian, H., Kale, D.C., Ver Steeg, G. and Galstyan, A. (2019) ‘Multitask learning and benchmarking with clinical time series data’, Scientific Data, 6, 96.

[12] HL7 International (2019) FHIR Release 4. Ann Arbor, MI: Health Level Seven International.

[13] Jiang, L.Y., Liu, X.C., Nejatian, N.P. et al. (2023) ‘Health system-scale language models are all-purpose prediction engines’, Nature, 619, pp. 357–362.

[14] Johnson, A.E.W., Pollard, T.J., Shen, L. et al. (2016) ‘MIMIC-III, a freely accessible critical care database’, Scientific Data, 3, 160035.

[15] Liu, L.T., Dean, S., Rolf, E., Simchowitz, M. and Hardt, M. (2018) ‘Delayed impact of fair machine learning’, Proceedings of the 35th International Conference on Machine Learning, pp. 3150–3158.

[16] Machekera, G., Mtemeli, P.S., Dongo, M.M. et al. (2026) ‘An explainable deep learning framework for energy-efficient water and sewer reticulation infrastructure: Predicting project risk, pumping demand and sustainable construction performance’.

[17] Mandel, J.C., Kreda, D.A., Mandl, K.D., Kohane, I.S. and Ramoni, R.B. (2016) ‘SMART on FHIR: a standards-based, interoperable apps platform for electronic health records’, Journal of the American Medical Informatics Association, 23(5), pp. 899–908.

[18] Morrison, C., Lee, J., Covinsky, K. et al. (2022) ‘Predicting potentially preventable hospital transfers from nursing homes’, Journal of the American Medical Directors Association, 23(5), pp. 789–796.

[19] Mupa, M.N. et al. (2025) ‘Predictive allocation of temperature-sensitive specialty medications: A KPI-driven framework for shortage resilience in underserved U.S. ZIP codes’.

[20] Mupa, M.N. et al. (2026a) ‘Operationalizing AI at scale: Repeatable frameworks for integration, adoption and performance measurement across enterprise and startup environments’, World Journal of Advanced Research and Reviews.

[21] Mupa, M.N. et al. (2026b) ‘Applied machine learning frameworks for workflow optimization, organizational efficiency and digital transformation’, World Journal of Advanced Research and Reviews.

[22] Na, L., Villalobos Carballo, K., Pauphilet, J. et al. (2023) ‘Patient outcome predictions improve operations at a large hospital network’, Manufacturing & Service Operations Management.

[23] Nakatani, H., Nakao, M., Uchiyama, H. et al. (2020) ‘Predicting inpatient falls using natural language processing of nursing records obtained from Japanese electronic medical records’, JMIR Medical Informatics, 8(4), e16970.

[24] National Institute of Standards and Technology (2023) Artificial Intelligence Risk Management Framework (AI RMF 1.0). Gaithersburg, MD: NIST.

[25] Obermeyer, Z., Powers, B., Vogeli, C. and Mullainathan, S. (2019) ‘Dissecting racial bias in an algorithm used to manage the health of populations’, Science, 366(6464), pp. 447–453.

[26] Ponti, M., Bet, P., Oliveira, C.L. and Castro, P.C. (2017) ‘Better than counting seconds: Identifying fallers among healthy elderly using fusion of accelerometer features and dual-task Timed Up and Go’, PLoS ONE, 12(4), e0175559.

[27] Rajkomar, A., Dean, J. and Kohane, I. (2019) ‘Machine learning in medicine’, New England Journal of Medicine, 380, pp. 1347–1358.

[28] Rajkomar, A., Hardt, M., Howell, M.D., Corrado, G. and Chin, M.H. (2018) ‘Ensuring fairness in machine learning to advance health equity’, Annals of Internal Medicine, 169(12), pp. 866–872.

[29] Rantz, M.J., Skubic, M., Miller, S.J. et al. (2015) ‘Sensor technology to support aging in place’, Journal of the American Medical Directors Association, 16(6), pp. 520–526.

[30] Shickel, B., Tighe, P.J., Bihorac, A. and Rashidi, P. (2018) ‘Deep EHR: A survey of recent advances in deep learning techniques for electronic health record analysis’, IEEE Journal of Biomedical and Health Informatics, 22(5), pp. 1589–1604.

[31] Siontis, G.C.M., Tzoulaki, I., Castaldi, P.J. and Ioannidis, J.P.A. (2015) ‘External validation of new risk prediction models is infrequent and reveals worse prognostic discrimination’, Journal of Clinical Epidemiology, 68(1), pp. 25–34.

[32] Steyerberg, E.W. (2019) Clinical Prediction Models. 2nd edn. Cham: Springer.

[33] Tinetti, M.E., Speechley, M. and Ginter, S.F. (1988) ‘Risk factors for falls among elderly persons living in the community’, New England Journal of Medicine, 319, pp. 1701–1707.

[34] Wiens, J., Saria, S., Sendak, M. et al. (2019) ‘Do no harm: a roadmap for responsible machine learning for health care’, Nature Medicine, 25, pp. 1337–1340.

[35] Zhang, Z., Ho, K.M. and Hong, Y. (2019) ‘Machine learning for the prediction of volume responsiveness in patients with oliguric acute kidney injury in critical care’, Critical Care, 23, 112.

@article{1720285,
      author = {Kwame Ofori Boakye, Grace Mupa, Rumbidzai Lyn Kasinamunda, Rudorwashe Tsitsi Karuma, Munashe Naphtali Mupa},
      title = {Explainable Multimodal Early-Warning Analytics for Preventing Falls and Avoidable Hospital Transfers in Long-Term Care: A FHIR-Native and Fairness-Aware Framework},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {10},
      number = {1},
      pages = {3940-3957},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1720285.pdf},
      abstract = {Falls, emergency department transfers, unplanned hospital admissions and 30-day readmissions are recurrent threats to safety, continuity and quality in long-term care. Existing risk tools commonly depend on single-source assessments, static scores or hospital-centric data models that do not exploit the temporal and multimodal information generated in nursing homes. This study develops and evaluates an explainable, FHIR-native and fairness-aware early-warning framework that integrates demographics, diagnoses, vital signs, medication burden, activities of daily living, prior utilization, mobility indicators and natural-language-derived change-of-condition signals. Because no single openly accessible Kaggle dataset contains all long-term-care modalities and all four outcomes, the empirical demonstration uses a reproducible 12,000-resident synthetic cohort calibrated to distributions and relationships reported in the Kaggle Diabetes 130-US Hospitals readmission dataset, an elderly fall-prediction dataset and peer-reviewed long-term-care literature. Facility-level holdout validation compared logistic regression, random forest and gradient boosting models. Performance was assessed with AUROC, area under the precision-recall curve, Brier score, sensitivity, specificity and calibration. Fairness was evaluated across sex, race and dual-eligibility groups at a capacity-constrained top-quintile alert threshold. The best-performing models achieved useful discrimination across outcomes, while calibration and subgroup analysis exposed operational trade-offs that would be hidden by accuracy alone. The framework maps inputs and outputs to FHIR resources and specifies an alert explanation packet comprising predicted risk, dominant drivers, uncertainty, trend context and recommended human review. The results support a governance model in which predictive analytics supplements, rather than replaces, nursing assessment and is continuously monitored for drift, workload effects and inequitable error profiles. The proposed architecture offers a practical foundation for prospective validation in skilled nursing facilities and for interoperable deployment across electronic health-record vendors.},
      keywords = {Long-Term Care, Nursing Homes, Falls, Hospital Transfer, Readmission, Multimodal Machine Learning, Explainable AI, Fairness, FHIR, Predictive Analytics.},
      month = {July},
      doi = {https://doi.org/10.64388/IREV10I1-1720285}
  }