Background: National electronic health record (EHR)

The gap

Evidence profile

Stated in the limitations and abstract and future work and inline gaps and cells research gap sections of the source papers, classified as general, spanning 6 journals. Those papers have been cited 2 times in total.

Supporting evidence — 7 representative gaps

• Artificial Intelligence in Opthamology:A study on different AIML approaches for Glaucoma prediction (2026) · Zenodo (CERN European Organization for Nuclear Research) · doi

  challenges. There are concerns regarding bias, reproducibility, and equity because most of the studies rely on datasets which are small or not diverse enough. The unequal distribution of disease prevalence and the underrepresentation of specific ethnic groups intensify these issues. To address these challenges, it is essential to develop larger and more varied datasets, preferably utilizing collaborative methods like Federated Learning to uphold patient privacy. Furthermore, specific techniques like fair identity normalization are being developed to ensure equitable screening performance across all populations. excel Ultimately, each method has its own advantages and disadvantages. at Imaging-focused models assessing structure but often miss functional elements. EHR-driven systems facilitate large-scale prescreening but lack ophthalmic specificity. Sensor-based approaches offer real-time physiological insights but face limitations due to device availability and cost. This underscores the necessity for multimodal integration, where structural, functional, and systemic data are merged to better represent actual clinical practice. Such approaches hold the greatest promise for enhancing diagnostic precision, predicting disease progression, and fostering the clinical acceptance of AI-driven glaucoma systems.

  generalstated in limitationsevidence 5/5
  Keywords: challenges datasets disease specific like functional driven systems approaches clinical there concerns regarding bias reproducibility
• Opportunities and Challenges in Using National EHR Networks for AI in Learning Health Systems (2026) · Learning Health Systems · cited 2× · doi

  Background: National electronic health record (EHR) networks can support learning health systems (LHSs) by enabling large-scale data aggregation, monitoring, and benchmarking, but their capacity to produce trustworthy and locally deployable machine learning and artificial intelligence (ML/AI) models remains uncertain.

  generalstated in abstractevidence 5/5
  Keywords: health learning background national electronic record networks support systems lhss enabling large scale aggregation monitoring
• FEDERATED AND EXPLAINABLE ARTIFICIAL INTELLIGENCE FOR PRIVACY-PRESERVING CLINICAL DECISION SUPPORT SYSTEMS (2026) · Zenodo (CERN European Organization for Nuclear Research) · doi

  Although the proposed framework shows promising results in combining Federated Learning (FL) with Explainable AI (XAI), there are still several areas where the system can be further improved. Future research can focus on enhancing performance, adaptability, and real-world applicability of the model. X.I. Personalized Federated Learning (pFL): One of the main challenges in federated learning is data heterogeneity, meaning that data collected from different hospitals may vary significantly in terms of quality, distribution, and patient demographics.In the current system, a single global model is shared across all clients. However, this approach may not always perform equally well for every institution. To address this issue, future work can explore Personalized Federated Learning (pFL).In this approach, instead of using one common model, each client can have a slightly customized version of the global model that better fits its local data. This can improve accuracy and make the system more adaptable to different healthcare environments. 554 International Journal of Advance and Innovative Research Volume 13, Issue 2: April - June 2026 ISSN 2394 - 7780 X.II. Integration of Multi-Modal Data: At present, the system mainly focuses on specific types of data such as medical images or structured health records. However, real-world healthcare data is much more complex and comes in different forms.

  generalstated in future workevidence 5/5
  Keywords: federated learning system model future different real world personalized global approach issue healthcare integration multi
• A novel trigonometric subpopulation and sine cosine range optimization framework to classify Helicobacter pylori infection in a south Indian cross-sectional study (2026) · Discover Artificial Intelligence · doi

  This research proposed a robust framework for H. pylori detection in endoscopic images using an optimized CNN model extended with metaheuristic optimization techniques. This study illustrated that implementing dynamic hyperparameter optimization can notably reduce time and computational costs, serving as a powerful approach to assist clinicians as a decision-support system. It also provides deployment metrics and explain- ability using Grad-CAM. The proposed TSOA and SCROA algorithms outperformed conventional metaheuris- tic approaches and other state-of-the-art methods. Statistical analysis confirmed the sig- nificance of these improvements across multiple performance metrics. Future studies will focus on evaluating the proposed algorithms on larger and more diverse datasets, extending the optimization and evaluating generalization performance. In addition, investigating privacy-preserving learning paradigms and federated learning Lewis et al. Discover Artificial Intelligence (2026) 6:600 Page 36 of 37 can enable secure model aggregation and facilitate collaborative training across multiple healthcare institutions without sharing sensitive patient data.

  generalstated in future workevidence 5/5
  Keywords: proposed optimization using model metrics algorithms across multiple performance evaluating learning robust framework pylori detection
• Machine learning-based fetal health prediction and development of smart web application (2026) · Frontiers in Artificial Intelligence · doi

  Thus, this future work should focus on privacy preserving AI through Federated learning, model updates, bias aware AI and explainable AI. One major limitation of this study is the usage of a single benchmark dataset namely Cardiotocography (CTG) data set obtained from UCI machine learning repository (Dua and Graff, 2019). Although we tested several classical machine learning, ensemble learning, and neural network based models, the advanced neural network based models like CNNs, RNNs, LSTMs and hybrid models have not been tested extensively due to the lack of more data set in the case of structured and fewer features of the dataset.

  generalstated in inline gapsevidence 5/5
  Keywords: learning models dataset machine tested neural network based thus future focus privacy preserving federated model
• Kidney Stone Detection Using Medical Imagingand Computational Intelligence - A Review (2026) · International Journal of Image, Graphics and Signal Processing · doi

  A number of researches have emerged with the aim of fixing these issues and facilitating clinically reliable AI- based kidney stone detector systems [75]. To address the above challenges and unlock the full potential of AI in nephrology, several exciting future directions have arisen. The above approaches, focused on technological innovation, privacy-preserving learning, explainability, and real-time in-clinical applications. 13.1. Privacy-Preserving Federated Learning Federated learning (FL) is a decentralized machine learning scheme for learning models across different institutions, without the need to exchange patient data. Rather than maintaining centralized database, at each hospital or clinic the model is trained using local data and only model updates (e.g., gradients and weights) are centralized aggregated [56]. This procedure provides a better and more comprehensive training set for model development, but at the same time, maintains patient anonymity. For kidney stone detection, FL can also be applied to effectively train models on multi-institution data from different imaging devices, scanner settings, and populations to achieve better generalizability and robustness [58].By the way, FL enables collaborative research under compliance with data protection laws like GDPR or HIPAA [64]. As well, by adopting secure encryption techniques, like differential privacy or homomorphic encryption, it can guarantee more data security in the training and the transmission [61]. Volume 18 (2026), Issue 4 – Page 158 Kidney Stone Detection Using Medical Imaging and Computational Intelligence - A Review 13.2. Clinical AI Tools in Real Time Real-time diagnostic aids will characterize the future of AI in nephrology by allowing AI to become a frictionless part of the clinic. These lightweight models also can be pruned, quantized, and edge-computed models that can be deployed directly on PPE or hospital servers to analyses as scan images are collected [60]. For example, an AI algorithm integrated in a CT scanner could automatically alert on suspected kidney stones as an image is taken, leading to more timely diagnosis and helping a radiologist while coping with busy periods of demand [64]. Likewise, the AI- based US apparatus might assist the technicians to concentrate on the suspected stone regions, even with lower resolution [69]. Moreover, cloud-based applications will facilitate tele-radiology, so that general practitioners in remote, poorly- and underserved areas can get access to AI-based diagnostics without having to shift to specialized machines [61]. 13.3. 3D Stones Detection and Measurement Recent developments in 3D medical imaging, technology and volumetric deep learning models have created new opportunities for accurate kidney stone detection and stone sizing. This 2D analysis is limited by slice thickness, resolution and anatomical complexity. Compared to 2D-CNN, in our 3D-CNN-based and U-Net-based methods, entire CT volumes can be taken as input and thus the kidney stones can be located and segmented in 3D [66,67]. Thereby, stone volume, density and surface can be accurately assessed, which are crucial for treatment planning and outcome prediction. For instance, volume measurement can aid a urologist in making a decision on whether a stone is treatable with extracorporeal shock wave lithotripsy (ESWL) as opposed to the need for surgery [68,61,70]. Furthermore, 3D assessment allows follow-up of stones that are growing or reducing during any conservative treatment. These models could be combined with patient-specific anatomical data, and clinical data (using, for example, an electronic health record (EHR)) to begin to develop predictive models for the management of nephrolithiasis [62,63].

  generalstated in future workevidence 5/5
  Keywords: stone models based kidney learning time detection stones privacy real clinical patient model using imaging
• Hierarchical federated edge learning with criticality-aware aggregation for privacy-preserving fetal health classification (2026) · Discover Computing · doi

  The lack of effective federated learning frameworks for fetal health classification is a significant research gap. - The need for frameworks that can preserve data privacy while achieving high accuracy is a research gap. - The challenge of addressing distributional heterogeneity in federated learning is a research gap.

  generalstated in cells research gapevidence 5/5
  Keywords: lack effective federated learning frameworks fetal health classification

Questions about this gap