Smart City Gnosys
Smart city article details
| Title | X-Pand: Explainable Random Forest With Feature Selection For Covid-19 Like Pandemics In Smart Cities |
|---|---|
| ID_Doc | 62093 |
| Authors | Bhattacharya P.; Verma A.; Kumar A.; Mukherjee T.; Bhushan B.; Dutta P.K. |
| Year | 2024 |
| Published | IET Conference Proceedings, 2024, 37 |
| DOI | http://dx.doi.org/10.1049/icp.2025.0922 |
| Abstract | The criticality of COVID-19 has burdened our healthcare resources. Thus, there is a growing need to advance our healthcare frameworks. Recently, with the rise of Explainable Artificial Intelligence (XAI) models in healthcare that leverage interpretability and solve the black-box nature of AI, healthcare frameworks and designs in smart cities have improved many folds. To address the crisis in light of future COVID-19-like pandemics in smart cities, we propose a case-study, X-Pand, that utilizes an XAI framework over Random Forest (RF) algorithm for feature selection in COVID-19 detection. Unlike recent schemes that are mostly non-interpretable, X-Pand emphasizes transparency and interpretability, crucial for gaining actionable insights and trust in automated health diagnostics. We present a feature ranking mechanism, which integrates Shapley Additive Explanations (SHAP) for enhanced decision tree interpretability, optimizing feature selection and improving diagnostic accuracy. We evaluate X-Pand on a comprehensive COVID-19 clinical spectrum dataset, demonstrating superior performance in terms of accuracy, sensitivity, and specificity compared to traditional models like XGBoost, Support Vector Machine (SVM), and Multi-Layer Perceptron (MLP). Our findings reveal that X-Pand not only achieves higher prediction accuracy but also offers clearer justifications for its decisions, thus enabling more informed and confident clinical decisions. © The Institution of Engineering & Technology 2024. |
| Author Keywords | COVID-19; Explainable Artificial Intelligence; Future Pandemics; Machine Learning; Random Forest |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
7034  | 0.883 | Parasar D.; Kazi N.A.; Warule L.N.; Guru V. | Ai-Driven Prioritization And Detection Of Covid-19 Cases In Smart City: An Integration Of X-Ray Imaging And Resnet-18 Machine Learning Model | Healthcare-Driven Intelligent Computing Paradigms to Secure Futuristic Smart Cities (2024) |
| 26782 | 0.87 | Alrashdi I. | Fog-Based Deep Learning Framework For Real-Time Pandemic Screening In Smart Cities From Multi-Site Tomographies | BMC Medical Imaging, 24, 1 (2024) |
| 23709 | 0.864 | Andreas A.; Mavromoustakis C.X.; Mastorakis G.; Batalla J.M.; Sahalos J.N.; Pallis E.; Markakis E. | Enhancement Of Covid-19 Detection By Unravelling Its Structure And Selecting The Optimal Attributes | Proceedings - IEEE Global Communications Conference, GLOBECOM (2021) |
| 3531 | 0.854 | Ezugwu A.E.; Hashem I.A.T.; Oyelade O.N.; Almutari M.; Al-Garadi M.A.; Abdullahi I.N.; Otegbeye O.; Shukla A.K.; Chiroma H. | A Novel Smart City-Based Framework On Perspectives For Application Of Machine Learning In Combating Covid-19 | BioMed Research International, 2021 (2021) |
| 33115 | 0.85 | Herath H.M.K.K.M.B. | Internet-Assisted Data Intelligence For Pandemic Prediction: An Intelligent Framework | Studies in Computational Intelligence, 994 (2022) |