Data privacy and security remain critical concerns due to the sensitive nature of healthcare information

The gap

Evidence profile

Sourced from the inline gaps and future-work section and limitations section of the source papers, classified as general, spanning 4 journals. Those papers have been cited 1 times in total.

Supporting evidence — 4 representative gaps

• Long-Life IoT Sensing and AI-Supported Analytics for Smart District Heating: Lessons from the LoLiPoP-IoT Project (2026) · Journal of Artificial Intelligence and Data Analytics · doi

  Future work should examine federated or privacy- preserving AI methods that allow learning across buildings or districts without unnecessary centralisation of sensitive indoor environmental data. • Digital twins should be investigated as a validation environment for AI-supported control and optimisation. Machine Learning for District Heating and Cooling: A Review of Open Problems and Deployment Barriers.

  generalinline gaps
  Keywords: learning future examine federated privacy preserving allow across buildings districts without unnecessary centralisation sensitive indoor
• Wearable Edge-IoT and AI-Driven Cardiopulmonary Health Monitoring: A Review of Geofenced Air-Quality Intervention Frameworks (2026) · International Journal of Recent Advances in Multidisciplinary Topics · doi

  Future research is expected to focus on several emerging directions, including federated learning, explainable AI, and precision environmental medicine. Federated Learning offers a privacy-preserving framework for collaboratively training machine learning models across multiple hospitals, wearable devices, and healthcare institutions without sharing sensitive patient data. Explainable Artificial Intelligence (XAI) techniques will improve model transparency by identifying the key physiological and environmental factors influencing individual health predictions.

  generalfuture-work sectionevidence 5/5
  Keywords: future research expected focus several emerging directions including
• Advanced Healthcare Analytics Using AI, ML, and IoT: A CNNBased Algorithmic Approach (2026) · International Journal of Drug Delivery Technology · cited 1× · doi

  Data privacy and security remain critical concerns due to the sensitive nature of healthcare information. High computational requirements of deep learning models limit deployment on resource-constrained edge devices. Interoperability issues among heterogeneous devices and lack of standardized protocols hinder large-scale implementation.

  generallimitations sectionevidence 5/5
  Keywords: data privacy security remain critical concerns due sensitive
• An intelligent RFID-based healthcare informatics system using trust-based access control for data access and situational awareness (2026) · The Journal of Supercomputing · doi

  large-scale validation in real hospital environments involving heterogeneous RFID devices and dynamic network conditions - incorporation of federated learning and explainable AI to support privacy-preserving trust prediction and transparent access decisions - examination of post-quantum security, cross-chain interoperability, and adaptive ASCON parameter selection for improved resilience - integration with wearable sensors and edge computing to enhance real-time situational awareness and emergency

  generalfuture-work sectionevidence 5/5
  Keywords: large-scale validation real hospital environments involving heterogeneous rfid

Questions about this gap