Explainable artificial intelligence for cross domain evaluation of predictive models in multi-disease diagnosis Zulfikar Ali Ansari, K. Kiran Kumar, Shahin Fatima, Shadab Siddiqui, Syed Wahaj Mohsin Discover Computing, 2026 Accurate and interpretable disease prediction is one of the major challenges faced in healthcare, especially for breast, heart, and lung cancers. This study proposes a highly structured, leakage-safe benchmarking framework for comparing conventional tabular Machine Learning (ML) models for multi-disease prediction, which is not a new ML model. Six conventional ML models, namely support vector machine (SVM), logistic regression (LR), random forest (RF), XGBoost, decision tree (DT), and k-nearest neighbors (KNN), were evaluated using nested cross-validation for proper model selection and performance on three benchmarking datasets. To improve the interpretability of the models, the authors incorporated Explainable AI (XAI) techniques, namely local interpretable model-agnostic explanations (LIME) for better instance-level interpretability and permutation feature importance (PFI) for better global interpretability. The results indicate high discriminative ability of the models, with random forest and XGBoost models achieving the best classification accuracy. SVM and logistic regression models also achieved the best results for ROC-AUC metric under outer-fold validation. The novelty of the paper is not the architecture of the ML models but the fact that the authors propose a highly structured, leakage-safe preprocessing pipeline, nested validation, statistically sound multi-model comparisons, and robust local–global interpretability aggregation, all of which are incorporated into a single benchmarking template.
Federated microservices architecture with blockchain for privacy-preserving and scalable healthcare analytics Murikipudi Harshith, Zulfikar Ali Ansari, Shahin Fatima, Shadab Siddiqui, Sreyan Swarna, D. R. Nidhish Reddy, Syed Wahaj Mohsin Scientific Reports, 2026 Nowadays, the digitalisation of healthcare has, in turn, generated outstanding volumes of heterogeneous data from EHRs, IoMT devices, and telemedicine platforms, requiring secure and scalable analytical frameworks. Existing monolithic systems now face issues related to scalability, interoperability, and compliance while also putting patient privacy at risk. Our study describes a new federated microservices architecture that integrates Kubernetes-orchestrated microservices, TensorFlow Federated learning, and Hyperledger Fabric blockchain to enable privacy-preserving, scalable, and auditable analytics in healthcare. In contrast to prior works focusing on isolated solutions, our framework presents an end-to-end deployable system with modular scalability, differential privacy, and immutable auditability. We have evaluated the framework on 100,000 synthetic Synthea records and a real-world dataset of 20,000 diabetes patients. The framework achieved 95.2% predictive accuracy, 42% lower latency, and 10 × faster recovery than the monolithic baselines while ensuring zero breach success in adversarial simulations. These results demonstrate that the proposed architecture not only improves clinical decision support accuracy but also provides operational resilience, regulatory compliance, and cost efficiency. This work lays the foundation for next-generation intelligent healthcare systems, with future extensions toward multimodal data and explainable AI to enhance trust and adoption in clinical practice.
Dual explainability framework for heart disease prediction using LIME and permutation feature importance Zulfikar Ali Ansari, Wasim Khan, Md Shamsul Haque Ansari, Shahin Fatima, Shadab Siddiqui Discover Applied Sciences, 2026 Heart disease continues to be one of the leading causes of mortality worldwide, which highlights the immediate need for accurate and interpretable predictive models to support early detection. This work mainly focused a reasonable assessment of various effective machine learning (ML) Algorithms: Logistic Regression (LR), Support Vector Machine (SVM), Decision Tree (DT), Random Forest (RF), XG-Boost, Naive Bayes (NB), and K-Nearest Neighbours (KNN) applied to the publicly available UCI heart disease dataset. To address the critical challenge of explainability in clinical decision support systems, Our proposed dual explainability framework combining Local Interpretable Model-Agnostic Explanations (LIME) and Permutation Feature Importance (PFI) was implemented and evaluated using the publicly available UCI Cleveland Heart Disease dataset (n = 303). The framework achieved robust predictive accuracy and consistent interpretability across multiple machine learning models. While the results demonstrate strong internal validation, they are based solely on this dataset, and future work will extend the framework to larger and multi-institutional datasets to ensure broader clinical generalizability. Finally, performance has been evaluated using accuracy, precision, recall, and F1-score. Among all classifiers, the results show that Random Forest and Decision Tree achieved the highest predictive accuracy of 99%. The combined use of LIME and PFI revealed that features such as ST depression (oldpeak), chest pain type, and maximum heart rate (thalach) consistently influenced predictions. This dual-layer interpretability framework enhances the transparency of ML predictions and supports trustworthy AI-driven decision-making in healthcare. Combines LIME and PFI for dual-level transparency in Healthcare Machine Learning. Presents a rigorous 5$$\times $$5-fold cross-validation, model calibration, and statistical significance testing for reliability. Confirms clinical consistency of top features (ST depression, chest pain, thalach) with cardiology evidence.
Explainable Machine Learning Framework for Chronic Kidney Disease Prediction Using Multi-Model Comparative Analysis and LIME Interpretability Zulfikar Ali Ansari, Nafees Akhter Farooqui, Noorishta Hashmi, Nitin Chopde, Pradumn Kumar Gupta, Gyan Chand Yadev 2026 2nd International Conference on Cognitive Computing in Engineering Communications Sciences and Biomedical Health Informatics Ic3ecsbhi 2026, 2026 Chronic Kidney Disease (CKD) is a painful and usually symptomless disorder, which requires early diagnosis to avoid renal failure. This study describes a predictive machine learning model of CKD, which combines several classification algorithms and model interpretability by Local Interpretable Model-Agnostic Explanations (LIME). A CKD dataset with 400 patient records and 26 clinical attributes, which is publicly available, was trained and tested using five supervised learning algorithms, including Logistic Regression (LR), Support Vector Machine (SVM), K-Nearest Neighbours (KNN), the Random Forest, and XGBoost. Preprocessing of the data involved normalisation, categorisation, and the filling of missing values to ensure consistency of the models. It was experimentally proven that ensemble models were higher in performance as XGBoost and the Random Forest had 98.8% and 98.5% accuracy <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(\mathrm{F} 1=0.99$</tex> and <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\text{AUC}=1.00)$</tex> respectively, which significantly surpassed all other classifiers. The interpretability offered by LIMF revealed the effects of the main biomarkers (serum creatinine, blood urea, haemoglobin, and specific gravity) on the prediction made by the model. The suggested framework produces accurate diagnostic results and, at the same time, improves clinical confidence with its interpretable predictions being transparent. This will be further expanded in future work, based on federated and cross-institutional datasets, to perform scalable CKD diagnosis without compromising privacy.
The role of explainable AI in enhancing breast cancer diagnosis using machine learning and deep learning models Zulfikar Ali Ansari, Manish Madhava Tripathi, Rafeeq Ahmed Discover Artificial Intelligence, 2025 Breast cancer is still a big health issue around the world, and it needs to be found quickly and perfectly to improve patient outcomes and lower death rates. Although artificial intelligence (AI) has showed amazing promise in breast cancer prediction mainly machine learning (ML) algorithms as well as deep learning (DL), practical use of these models is greatly hampered by their lack of interpretability and transparency. By giving complicated AI models interpretability, explainable artificial intelligence (XAI) becomes an essential tool to improve trust and transparency. XAI's efficacy in clinical environments is yet perfectly unidentified however, and its proper implementation into breast cancer diagnostics is hence ignored. Focussing on their interpretability, clinical application, and influence on decision-making, this paper systematically reviews machine learning, deep learning impact on breast cancer diagnosis and current XAI approaches used to breast cancer detection, prognosis, and treatment. This work presents a thorough assessment of XAI approaches classified by data kinds (imaging, genomic, and clinical), a comparative analysis of LIME (Local Interpretable Model-agnostic Explanations), SHAP (SHapley Additive exPlanations), and Grad-CAM, and highlights important issues and future directions of research. This work highlights the possibility of XAI to enhance clinical decision-making and patient confidence by closing the gap between great diagnosis accuracy and interpretability. The results support multidisciplinary cooperation among medical experts, scientists in artificial intelligence, and legislators to guarantee the responsible and ethical integration of artificial intelligence in society.
A multi-model deep learning framework for SEM-based defect detection in Perovskite thin films Zulfikar Ali Ansari, Sahil Soni, Shahin Fatima, Shadab Siddiqui, P. Venkata Hari Prasad Scientific Reports, 2025 The urgent need to transition toward sustainable energy sources has positioned perovskite solar cells (PSCs) as a leading candidate for next-generation photovoltaics. Among them, formamidinium lead iodide ([Formula: see text]) based devices have demonstrated power conversion efficiencies (PCEs) exceeding 25% with the potential for low-cost fabrication. However, structural defects such as pinholes, [Formula: see text] accumulation, and grain boundary irregularities significantly compromise their efficiency, stability, and long-term reliability. Conventional defect characterization using scanning electron microscopy (SEM) is labor-intensive, subjective, and unsuitable for large-scale quality control, underscoring the need for automated, high-precision detection strategies. In this study, we propose a multi-model deep learning framework for automated defect classification in mixed-dimensionality [Formula: see text] perovskite films. The framework targets five critical defect types: pure 3D perovskite, 3D perovskite with [Formula: see text] excess, 3D perovskite with pinholes, 3D-2D mixed perovskite, and 3D-2D mixed perovskite with pinholes. Three complementary architectures are benchmarked: ResNet50V2 and DenseNet169 for high-accuracy classification, and YOLOv9 for real-time detection with computational efficiency. Extensive data augmentation and transfer learning were employed to mitigate dataset scarcity, enabling robust feature extraction from a limited set of 2,380 SEM images. The results show that ResNet50V2 and DenseNet169 achieved a test accuracy of 96.7% and weighted F1-score of 0.966, while YOLOv9, though moderate in accuracy (45.0%), demonstrated exceptional computational efficiency with an 8-minute training time. The proposed framework not only enables precise identification of morphological defects but also supports scalable quality control in PSC manufacturing. Furthermore, the deployment of the trained models as an interactive Streamlit-based web application demonstrates its practical utility for real-time laboratory and industrial adoption. These findings highlight the potential of deep learning-driven defect analysis to accelerate the optimization and commercialization of perovskite solar cell technologies.
Next-Gen Mechatronics: The Role of Artificial Intelligence Nafees Akhter Farooqui, Zulfikar Ali Ansari, Rafeeq Ahmed, Ahmad Neyaz Khan, Shadab Siddiqui, Mohammad Ishrat, Mohd Haleem, Sarosh Patel Advancements in Artificial Intelligence and Machine Learning, 2025
Automated Gear Inspection Using Artificial Intelligence Zulfikar Ali Ansari, Nafees Akhter Farooqui, Md Shamsul Haque Ansari, Hemlata Pant, Anwar Ahmed Shaikh, Mohammad Arif Proceedings of the 2025 International Conference on Artificial Intelligence and Emerging Technology Global AI Summit 2025, 2025
Crime Detection Using Sentiment Analysis Ruba Khan, Shadab Siddiqui, Abhishek Rastogi, Zulfikar Ali Ansari Advances in Distributed Computing and Artificial Intelligence Journal, 2021
RECENT SCHOLAR PUBLICATIONS
Explainable artificial intelligence for cross domain evaluation of predictive models in multi-disease diagnosis ZA Ansari, KK Kumar, S Fatima, S Siddiqui, SW Mohsin Discover Computing 29 (1), 163 , 2026 2026 Citations: 1
Context-aware anomaly detection in attributed graphs via deep skip-gram and multi-level feature fusion W Khan, ZA Ansari, KK Kumar, J Sreedhar International Journal of Data Science and Analytics 21 (1), 2 , 2026 2026 Citations: 1
Explainable Machine Learning Framework for Chronic Kidney Disease Prediction Using Multi-Model Comparative Analysis and LIME Interpretability ZA Ansari, NA Farooqui, N Hashmi, N Chopde, PK Gupta, GC Yadev Cognitive Computing in Engineering, Communications, Sciences and Biomedical … , 2026 2026
Enhancing transparency in breast cancer diagnosis through LIME-driven machine learning models SSAAS Zulfikar Ali Ansari1, Md Shamsul Haque Ansari2, Alka Singh3, Naziya ... International Journal of Advanced Technology and Engineering Exploration 13 … , 2026 2026
Federated microservices architecture with blockchain for privacy-preserving and scalable healthcare analytics M Harshith, ZA Ansari, S Fatima, S Siddiqui, S Swarna, DRN Reddy, ... Scientific Reports , 2026 2026 Citations: 2
Explainable breast cancer diagnosis: integrating genetic algorithms with LIME-based machine learning ZA Ansari, MSH Ansari, A Khan, H Pant, S Fahad, PVH Prasad Evolutionary Intelligence 19 (1), 11 , 2026 2026 Citations: 2
Dual explainability framework for heart disease prediction using LIME and permutation feature importance ZA Ansari, W Khan, MSH Ansari, S Fatima, S Siddiqui Discover Applied Sciences , 2025 2025
A Hybrid Method Based on Deep Learning for Classifying and Predicting Rice Plant Diseases ZA Ansari, NA Farooqui, N Adeel, H Pant, N Hashmi, VK Chaudhary 2025 3rd International Conference on IoT, Communication and Automation … , 2025 2025
A multi-model deep learning framework for SEM-based defect detection in Perovskite thin films ZA Ansari, S Soni, S Fatima, S Siddiqui, PVH Prasad Scientific Reports 15 (1), 41909 , 2025 2025 Citations: 1
Automated Gear Inspection Using Artificial Intelligence ZA Ansari, NA Farooqui, MSH Ansari, H Pant, AA Shaikh, M Arif 2025 2nd Global AI Summit-International Conference on Artificial … , 2025 2025
Consensus Representation for Multiview Clustering Based on Concept Factorization SS Mutyala Sirisha, AC Priya Ranjani, Ghufran Ahmad Khan, Zulfikar Ali ... Artificial Intelligence and Smart Technologies for Sustainability Conference … , 2025 2025
Optimized and interpretable machine learning framework for early breast cancer detection ZA Ansari, MSH Ansari, A Khan, NZ Jhanjhi, G Rathnamma Health and Technology 15 (6), 1135-1147 , 2025 2025 Citations: 4
Integrated Ensemble Strategy for Breast Cancer Detection Using Dimensionality Reduction Technique ZA Ansari, M Arif, NB Rajaboina, AA Shaikh, Y Singh ADCAIJ: Advances in Distributed Computing and Artificial Intelligence … , 2025 2025
Next-Gen Mechatronics: The Role of Artificial Intelligence NA Farooqui, ZA Ansari, R Ahmed, AN Khan, S Siddiqui, M Ishrat, ... Advancements in Artificial Intelligence and Machine Learning, 1-24 , 2025 2025 Citations: 1
The role of explainable AI in enhancing breast cancer diagnosis using machine learning and deep learning models ZA Ansari, MM Tripathi, R Ahmed Discover Artificial Intelligence 5 (1), 75 , 2025 2025 Citations: 22
Empowering Breast Cancer Diagnostics: SHAP-Enhanced Explainable AI ZA Ansari, R Ahmed, MM Tripathi, NA Farooqui, MSH Ansari, S Siddiqui, ... International Conference on Green Artificial Intelligence and Industrial … , 2025 2025
Multiple manifold regularization based on non-negative matrix factorization for multi-view clustering M Sirisha, GA Khan, J Khan, H Pant, K Zainab, ZA Ansari, SH Ansari 2025 3rd International Conference on Disruptive Technologies (ICDT), 362-367 , 2025 2025 Citations: 3
Understanding the landscape: a review of explainable ai in healthcare decision-making ZA Ansari, MM Tripathi, R Ahmed 2024 Citations: 3
Quantifying breast cancer: radiomics, machine learning, and dimensionality reduction for enhanced image-based diagnosis Z Ali Ansari, M Madhava Tripathi, R Ahmed International Journal of Computing and Digital Systems 16 (1), 1535-1552 , 2024 2024 Citations: 4
Zubair Ashraf, Zulfikar Ali Ansari, Rafeeq Ahmed, and Mourade Azrour T Anwar, GA Khan Blockchain and Machine Learning for IoT Security, 56 , 2024 2024
MOST CITED SCHOLAR PUBLICATIONS
The role of explainable AI in enhancing breast cancer diagnosis using machine learning and deep learning models ZA Ansari, MM Tripathi, R Ahmed Discover Artificial Intelligence 5 (1), 75 , 2025 2025.0 Citations: 22
The Combination of Blockchain and the Internet of Things (IoT): Applications, Opportunities, and Challenges for Industry T Anwar, GA Khan, Z Ashraf, ZA Ansari, M Ahmed, Rafeeq , Azrour Blockchain and Machine Learning for IoT Security 1, 164 , 2024 2024.0 Citations: 20
Crime Detection Using Sentiment Analysis R Khan, S Siddiqui, A Rastogi, Z Ali Ansari Ediciones Universidad de Salamanca (España) , 2021 2021.0 Citations: 13
Endoscopic third ventriculostomy in noncommunicating hydrocephalus: report on a short series of 53 children A Sarmast, N Khursheed, A Ramzan, F Shaheen, A Wani, S Singh, Z Ali, ... Asian journal of neurosurgery 14 (01), 35-40 , 2019 2019.0 Citations: 11
Molecular characterization and chemical profiling of different populations of Convolvulus pluricaulis (Convolvulaceae); an important herb of Ayurvedic medicine. 3 SH Ganie, Z Ali, S Das, PS Srivastava, MP Sharma Biotechnology 5, 295-302 , 2015 2015.0 Citations: 10
Optimized and interpretable machine learning framework for early breast cancer detection ZA Ansari, MSH Ansari, A Khan, NZ Jhanjhi, G Rathnamma Health and Technology 15 (6), 1135-1147 , 2025 2025.0 Citations: 4
Quantifying breast cancer: radiomics, machine learning, and dimensionality reduction for enhanced image-based diagnosis Z Ali Ansari, M Madhava Tripathi, R Ahmed International Journal of Computing and Digital Systems 16 (1), 1535-1552 , 2024 2024.0 Citations: 4
Effect of pulp blending on standardization and acceptability of Seabuckthorn: Apricot nectar H Naik, Z Ali, S Zameer, AH Rather Food & Nutrition Journal 124 (8), 1-10 , 2017 2017.0 Citations: 4
Multiple manifold regularization based on non-negative matrix factorization for multi-view clustering M Sirisha, GA Khan, J Khan, H Pant, K Zainab, ZA Ansari, SH Ansari 2025 3rd International Conference on Disruptive Technologies (ICDT), 362-367 , 2025 2025.0 Citations: 3
Understanding the landscape: a review of explainable ai in healthcare decision-making ZA Ansari, MM Tripathi, R Ahmed 2024.0 Citations: 3
Currency Detection for Visually Impaired KGS ShwetaYadav, Mr. Zulfikar Ali Ansari Journal of Emerging Technologies and Innovative Research (JETIR) www.jetir … , 2020 2020.0 Citations: 3
Comparative performance study of four different serological tests for the diagnosis of dromedary brucellosis F Khan, R Khawar, MZ Ansari, U Wernery J. Camel Pract. Res 23, 213-217 , 2016 2016.0 Citations: 3
Federated microservices architecture with blockchain for privacy-preserving and scalable healthcare analytics M Harshith, ZA Ansari, S Fatima, S Siddiqui, S Swarna, DRN Reddy, ... Scientific Reports , 2026 2026.0 Citations: 2
Explainable breast cancer diagnosis: integrating genetic algorithms with LIME-based machine learning ZA Ansari, MSH Ansari, A Khan, H Pant, S Fahad, PVH Prasad Evolutionary Intelligence 19 (1), 11 , 2026 2026.0 Citations: 2
Technological advancements in waste management NA Farooqui, MSH Ansari, ZA Ansari, R Mehra Municipal Solid Waste Management and Recycling Technologies, 327-342 , 2024 2024.0 Citations: 2
Meningioma presenting as acute subdural hematoma AA Wani, A Sarmast, NK Malik, AU Ramzan, Z Ali Austin Neurosurg Open Access 3 (1), 1046 , 2016 2016.0 Citations: 2
Explainable artificial intelligence for cross domain evaluation of predictive models in multi-disease diagnosis ZA Ansari, KK Kumar, S Fatima, S Siddiqui, SW Mohsin Discover Computing 29 (1), 163 , 2026 2026.0 Citations: 1
Context-aware anomaly detection in attributed graphs via deep skip-gram and multi-level feature fusion W Khan, ZA Ansari, KK Kumar, J Sreedhar International Journal of Data Science and Analytics 21 (1), 2 , 2026 2026.0 Citations: 1
A multi-model deep learning framework for SEM-based defect detection in Perovskite thin films ZA Ansari, S Soni, S Fatima, S Siddiqui, PVH Prasad Scientific Reports 15 (1), 41909 , 2025 2025.0 Citations: 1
