xAI

13 gain · 15 problem · 0 high-evidence

1. gainClimateModerate evidenceImpact 79

   Explainable AI-Supported Cyber-Physical Collaboration for Sustainable Manufacturing in Industry 5.0: Experimental findings show that the proposed CNN-Transformer architecture achieves 98.5% accuracy and outperforms existing CPHS systems while maintaining low latency.

   In this study, we present an innovative approach to the sustainable manufacturing of industrial parts using an explainable artificial intelligence (XAI)- based cyber-physical collaboration system for Industry 5.0. Current cyber-physical human systems (CPHSs) have been found to integrate AI only to a limited extent and often lack explainability.

   Sep 3, 2026

   1 source

   • Journal of Visualized ExperimentsPeer-reviewed
2. gainHealthModerate evidenceImpact 75

   FedMediFormer-XAI combined federated learning, multimodal transformers, diffusion augmentation and GNN drug recommendation to achieve 94.2% accuracy for diabetes prediction and NDCG 0.91 for personalized drug recommendation while enabling privacy-preserving training without sharing raw patient data.

   Researchers described FedMediFormer-XAI, a framework that combines federated learning, multimodal transformers, diffusion-based data augmentation, graph neural networks for drug recommendation, and explainable AI to address fragmented diabetes data, privacy concerns, and lack of personalized guidance. It was tested on diverse inputs including clinical records, glucose monitoring, retinal fundus images, wearable sensors, and pharmacological information.

   Sep 10, 2026

   1 source

   • Journal of Visualized ExperimentsPeer-reviewed
3. problemHealthModerate evidenceImpact 74

   Four machine learning (ML) algorithms (Random Survival Forest, XGBoost, Elastic Net-regularized Cox, Support Vector Machine) were trained (80%) and tested (20%) to predict overall survival (OS).

   Background Enfortumab vedotin (EV) has transformed treatment for advanced urothelial carcinoma (aUC), but outcomes vary. Machine learning (ML) with explainable artificial intelligence (XAI) may improve survival prediction.

   Sep 4, 2026

   1 source

   • Expert Opinion on Biological TherapyPeer-reviewed
4. gainCrimeHigh evidenceImpact 71

   XAI-driven data mining applied to IoT ecosystems can detect anomalies and support automated security decisions through transparent and interpretable reasoning for smart city infrastructure.

   Published February 20, 2026, this peer-reviewed survey in Cognitive Computation reviews XAI-driven data mining for self-defending IoT systems. It describes how IoT expansion in smart cities, healthcare, and industrial automation creates need for real-time, scalable security, and how XAI methods aim to detect anomalies and support automated decisions with transparent reasoning.

   Jul 13, 2026

   4 sources

   • Cognitive ComputationPeer-reviewed
   • Journal of Cybersecurity and PrivacyPeer-reviewed
   • International Journal of Scientific Research in Science and TechnologyPeer-reviewed
   • Communications MaterialsPeer-reviewed
5. problemCrimeHigh evidenceImpact 71

   Traditional and opaque AI security mechanisms are inadequate for protecting interconnected urban IoT infrastructures, facing challenges of data privacy, scalability, computational constraints, and limited interpretability.

   Published February 20, 2026, this peer-reviewed survey in Cognitive Computation reviews XAI-driven data mining for self-defending IoT systems. It describes how IoT expansion in smart cities, healthcare, and industrial automation creates need for real-time, scalable security, and how XAI methods aim to detect anomalies and support automated decisions with transparent reasoning.

   Jul 13, 2026

   4 sources

   • Cognitive ComputationPeer-reviewed
   • Journal of Cybersecurity and PrivacyPeer-reviewed
   • International Journal of Scientific Research in Science and TechnologyPeer-reviewed
   • Communications MaterialsPeer-reviewed
6. gainHealthModerate evidenceImpact 68

   Cases without consensus were excluded from the AI accuracy analysis. AI accuracy was calculated as the proportion of correct classifications among consensus cases, and the two models were compared using McNemar's test with continuity correction.

   Purpose The purpose of this study was to evaluate the performance of two general-use artificial intelligence models, ChatGPT and Grok, in classifying impacted mandibular third molars using the Pell and Gregory system on panoramic radiographs, compared with a resident consensus reference standard. Materials and methods One hundred panoramic radiographic images of impacted mandibular third molars were independently classified by two blinded resident reviewers using the Pell and Gregory classification system.

   Sep 5, 2026

   1 source

   • CureusPeer-reviewed
7. problemHealthModerate evidenceImpact 68

   Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without explaining the basis of their outputs, raising concerns about clinical safety, accountability, and trust.

   Most artificial intelligence (AI) models used in radiology are black boxes-they produce predictions without explaining the basis of their outputs, raising concerns about clinical safety, accountability, and trust. To address this, a growing body of methods has been developed to help clinicians understand and evaluate AI predictions.

   Aug 22, 2026

   1 source

   • Diagnostic and Interventional RadiologyPeer-reviewed
8. gainHealthModerate evidenceImpact 68

   AI and machine learning models are being applied to predict chemical toxicity and flag hazardous compounds to inform regulatory decisions, with XAI methods like SHAP and LIME improving interpretability.

   On August 12, 2026, a review in the International Journal of Toxicology summarized AI and machine learning use in toxicological risk assessment to predict chemical toxicity and support regulatory decisions, noting that explainable AI methods like SHAP and LIME are being explored to make model decisions interpretable.

   Aug 14, 2026

   1 source

   • International Journal of ToxicologyPeer-reviewed
9. problemHealthModerate evidenceImpact 68

   Current AI toxicity models are limited by black-box opacity that lowers transparency and regulatory confidence, with most explainable AI applications still stuck at computational or preclinical stage.

   On August 12, 2026, a review in the International Journal of Toxicology summarized AI and machine learning use in toxicological risk assessment to predict chemical toxicity and support regulatory decisions, noting that explainable AI methods like SHAP and LIME are being explored to make model decisions interpretable.

   Aug 14, 2026

   1 source

   • International Journal of ToxicologyPeer-reviewed
10. problemHealthModerate evidenceImpact 68

    Routine reliance on generative AI chatbots can lead people to develop inaccurate beliefs and delusional self-narratives, with extreme cases described as AI-induced psychosis.

    A peer-reviewed philosophy paper published February 11, 2026 argues that false outputs from systems like ChatGPT, Claude, Gemini, DeepSeek and Grok should be understood not only as AI hallucinating at users, but as humans hallucinating with AI. Through distributed cognition theory, it describes how routine reliance on chatbots to think, remember and narrate can embed errors and reinforce users' own distorted beliefs.

    Jul 20, 2026

    1 source

    • Philosophy & TechnologyPeer-reviewed
11. gainLifestyleModerate evidenceImpact 67

    Explainable AI methods such as SHAP and Grad-CAM improve food quality control by identifying which spectral wavelengths or image regions drive predictions, increasing transparency for inspectors verifying contaminant detection and freshness assessments.

    Published April 24, 2026, this peer-reviewed review examines the use of explainable AI in Food Engineering. It describes how AI models using spectral imaging are used to detect contaminants and assess freshness to meet food quality standards, but their complexity creates opacity that hinders adoption by quality control inspectors.

    Jul 18, 2026

    1 source

    • Artificial Intelligence ReviewPeer-reviewed
12. problemLifestyleModerate evidenceImpact 67

    Opaque AI decision-making in food quality models hinders adoption by inspectors and limits reliability, with explainable AI still underutilized in Food Engineering.

    Published April 24, 2026, this peer-reviewed review examines the use of explainable AI in Food Engineering. It describes how AI models using spectral imaging are used to detect contaminants and assess freshness to meet food quality standards, but their complexity creates opacity that hinders adoption by quality control inspectors.

    Jul 18, 2026

    1 source

    • Artificial Intelligence ReviewPeer-reviewed