Machine Learning-Based Optimization of Healthcare Building Environments for Improving Indoor Thermal Comfort, Daylight Exposure, and Patient Well-Being
Keywords:
machine learning; indoor thermal comfort; daylight autonomy; healthcare buildings; multi-objective optimization; patient well-beingAbstract
Healthcare buildings must support thermal comfort, daylight exposure, and patient well-being simultaneously, yet design and operation often optimize these outcomes in separate models and at different time scales. Static setpoints and rule-based shading can satisfy average energy targets while producing local discomfort, glare, or insufficient daylight in patient rooms. This manuscript develops a machine-learning-based optimization framework that connects room-level environmental predictors to clinical-adjacent well-being indicators and uses constrained multi-objective optimization to select design and control variables. The framework couples a physics-informed feature representation with a Gaussian-process or ensemble surrogate, models uncertainty from weather, occupancy, and model discrepancy, and solves a weighted objective subject to operative temperature, daylight autonomy, useful daylight illuminance, and glare constraints. Patient well-being enters as a transparent proxy composed of view access, daylight sufficiency, thermal stability, and controllability, rather than as a validated clinical endpoint. A robust expected-value formulation and a Bayesian optimization acquisition rule reduce the risk of selecting designs that perform well only under nominal conditions. The main contribution is a reproducible methodological architecture that translates healthcare-specific comfort and well-being constraints into an optimization problem that can be evaluated with simulation, monitored post-occupancy, and updated through digital-twin calibration. The discussion identifies trade-offs among solar control, daylight, and thermal load; failure modes such as surrogate extrapolation, occupancy shift, and glare metric misspecification; and governance requirements for clinical environments. The framework provides a technically defensible basis for prospective evaluation before deployment and clarifies which claims require empirical validation.
References
1. Fanger, P. O. (1970). Thermal comfort: Analysis and applications in environmental engineering. Danish Technical Press.
2. ASHRAE. (2020). ANSI/ASHRAE Standard 55-2020: Thermal environmental conditions for human occupancy. ASHRAE.
3. Brager, G. S., & de Dear, R. J. (1998). Thermal adaptation in the built environment: A literature review. Energy and Buildings, 27(1), 83–96.
4. Reinhart, C. F., Mardaljevic, J., & Rogers, Z. (2006). Dynamic daylight performance metrics for sustainable building design. LEUKOS, 3(1), 7–31.
5. Nabil, A., & Mardaljevic, J. (2006). Useful daylight illuminances: A replacement for daylight factors. Energy and Buildings, 38(7), 905–913.
6. Carlucci, S., Causone, F., De Rosa, F., & Pagliano, L. (2015). A review of indices for assessing visual comfort with a view to their use in optimization processes to support building integrated design. Renewable and Sustainable Energy Reviews, 47, 1016–1033.
7. Ulrich, R. S. (1984). View through a window may influence recovery from surgery. Science, 224(4647), 420–421.
8. Dijkstra, K., Pieterse, M. E., & Pruyn, A. T. H. (2006). Physical environmental stimuli that turn healthcare facilities into healing environments through psychologically mediated effects: Systematic review. Journal of Advanced Nursing, 56(2), 166–181.
9. Frontczak, M., & Wargocki, P. (2011). Literature survey on how different factors influence human comfort in indoor environments. Building and Environment, 46(4), 922–937.
10. Tzempelikos, A., & Athienitis, A. K. (2007). The impact of shading design and control on building cooling and lighting demand. Solar Energy, 81(3), 369–382.
11. Amasyali, K., & El-Gohary, N. M. (2018). A review of data-driven building energy consumption prediction studies. Renewable and Sustainable Energy Reviews, 81, 1192–1205.
12. Tabasi, S. F., Luo, D., Rafizadeh, H. R., Le Nguyen, K., & Banihashemi, S. (2025). Generative optimization of building blocks for density, solar and structural performance. Journal of Building Engineering, 111, 113307.
13. Killian, M., & Kozek, M. (2016). Ten questions concerning model predictive control for energy efficient buildings. Building and Environment, 105, 403–412.
14. Wang, Z., & Hong, T. (2020). Reinforcement learning for building controls: The opportunities and challenges. Applied Energy, 269, 115036.
15. Bishop, C. M. (2006). Pattern recognition and machine learning. Springer.
16. Rasmussen, C. E., & Williams, C. K. I. (2006). Gaussian processes for machine learning. MIT Press.
17. Hong, T., Wang, Z., Luo, X., & Zhang, W. (2020). State-of-the-art on research and applications of machine learning in the building life cycle. Energy and Buildings, 212, 109831.
18. Allen, J. G., MacNaughton, P., Laurent, J. G. C., Flanigan, S. S., Eitland, E. S., & Spengler, J. D. (2015). Green buildings and health. Current Environmental Health Reports, 2(3), 250–258.
19. World Health Organization. (2018). WHO housing and health guidelines. World Health Organization.
20. de Dear, R., & Brager, G. S. (2002). Thermal comfort in naturally ventilated buildings: Revisions to ASHRAE Standard 55. Energy and Buildings, 34(6), 549–561.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Bioinformatics Insights and Analytics

This work is licensed under a Creative Commons Attribution 4.0 International License.