For the full paper, click this Link: https://www.mdpi.com/4070604
Authors: Syed Shariar Alam Shuvo et al
Abstract
Patient recovery prediction and hospital length of stay estimation remain critical challenges in healthcare resource allocation and clinical decision-making. Inaccurate discharge planning drives substantial avoidable hospital costs, while existing machine learning models remain limited by narrow, single-domain data that fail to capture the multimodal complexity of modern smart ward environments. This study proposes IoT-ClinXAI, an explainable multimodal framework that fuses IoT environmental data, wearable physiological signals, and clinical records for accurate and transparent patient recovery prediction in smart hospital wards. A Multi-domain Hierarchical Consensus Feature-Selection method groups features into structured domains, applies Borda–Kemeny weighted consensus within each domain, and reduces cross-domain redundancy while preserving complementary information. A Snake Optimization–tuned Random Forest Regressor optimizes predictive performance through adaptive hyperparameter search, while a multi-scale SHAP framework provides global and patient-level explanations for transparent clinical inference. Experiments were conducted on a real-world IoT-enabled smart ward dataset comprising patient data and recovery duration. The proposed framework achieved strong predictive performance on the held-out test set, with 𝑅2 of 0.964, RMSE of 0.476 days, MAE of 0.342 days, and MAPE of 3.13%, yielding a 23.3% RMSE reduction over the unselected baseline and outperforming all feature-selection methods by 10.9–17.6% in RMSE. Statistical superiority was consistently confirmed across all pairwise comparisons using Wilcoxon signed-rank tests with Bonferroni correction (𝑝<0.001). SHAP analysis identified ward allocation, respiratory rate, and oxygen saturation as the dominant recovery predictors, while environmental IoT variables showed minimal predictive contribution. These results highlight IoT-ClinXAI as a reliable and useful framework for supporting bed management, discharge planning, and hospital resource optimization in resource-constrained healthcare settings.
Keywords:
Internet of Things; smart ward monitoring; hospital length of stay; explainable artificial intelligence; clinical decision support
Introduction
Efficient hospital resource management depends heavily on accurate prediction of patient recovery and length of stay (LOS), which directly affect bed allocation, staffing, discharge planning, and healthcare costs. IoT-enabled hospitals increasingly generate physiological, environmental, and clinical data through wearable sensors, smart monitoring systems, and connected infrastructure. These data can support earlier detection of patient deterioration, improved environmental conditions, and more efficient care delivery.
Machine learning has shown strong potential for LOS and recovery prediction, but most existing approaches rely mainly on clinical or physiological variables and rarely integrate environmental factors. Similarly, conventional feature-selection techniques often treat all variables uniformly, without considering differences among clinical, physiological, and environmental domains. This limits the ability of current systems to capture multimodal interactions relevant to patient recovery.
Explainable AI is also increasingly important in healthcare because predictive models must provide transparent and clinically meaningful results. Although SHAP is widely used for model interpretation, explainable multimodal IoT-based recovery prediction remains underexplored. Likewise, advanced optimization techniques such as Snake Optimization have received limited attention for tuning clinical regression models using multimodal smart-ward data.
To address these gaps, this study proposes IoT-ClinXAI, an explainable IoT-driven framework for smart-ward recovery prediction. The framework integrates Multi-domain Hierarchical Consensus Feature Selection (MHCFS) to identify relevant environmental, physiological, and clinical variables, Snake Optimization–Random Forest Regression (SO-RFR) for optimized recovery prediction, and SHAP-based explainability for global, population-level, and patient-level interpretation.
The proposed framework aims to improve predictive accuracy while supporting practical hospital decision-making, including bed allocation, discharge planning, patient-flow management, and resource optimization. The results further identify important recovery-related factors such as ward allocation, respiratory rate, and oxygen saturation, demonstrating the potential of explainable multimodal IoT analytics for smarter and more efficient healthcare management.
Conclusions and Future Work
This study presented IoT-ClinXAI, a multimodal framework that integrates domain-aware hierarchical feature selection, SO-based RFR, and SHAP-based XAI for patient recovery prediction in smart wards. The proposed framework consistently outperformed conventional feature-selection and optimization approaches, while the ablation study confirmed the contribution of each MHCFS tier to predictive performance and ranking stability. SHAP analysis identified clinically meaningful recovery drivers and provided transparent explanations that support trustworthy clinical decision-making. Furthermore, the low importance of environmental sensor features indicates that ward-level environmental measurements offer limited independent predictive value once clinical and physiological information is available, providing practical guidance for the design of smart hospital systems. These findings establish IoT-ClinXAI as a trustworthy and interpretable clinical decision-support framework for bed management, discharge planning, and hospital resource optimization, supported by robust and clinically meaningful predictions.
While the proposed IoT-ClinXAI framework demonstrates strong internal validity, several limitations remain. The small, single-center dataset limits generalizability, motivating future multi-center external validation across larger and more diverse populations. Integrating continuous wearable streams with temporal learning models could enable dynamic risk prediction and early detection of post-admission complications. Patient-level IoT sensing may also capture individualized environmental effects beyond ward-level measurements. Furthermore, causal inference methods, including propensity-score matching, directed acyclic graphs, and instrumental-variable analysis, should be explored to distinguish true physiological drivers of recovery from predictive associations and administrative proxies such as ward allocation. Future work should also investigate severity-aware modeling, fairness across demographic groups, distribution-shift monitoring, and compliance with emerging clinical AI regulations to support reliable, equitable, and trustworthy clinical decision support.
For the full paper, click this Link: https://www.mdpi.com/4070604
