Multi-modal machine learning and gut microbiome pathway analysis for Alzheimer's risk prediction Tallat Jabeen, Faezeh Karimi, Ali R. Zomorrodi, Kaveh Khalilpour Alzheimer S and Dementia Diagnosis Assessment and Disease Monitoring, 2026 Introduction Early Alzheimer's disease (AD) risk assessment requires accessible alternatives to invasive biomarkers. We developed a multi‐modal machine learning framework using questionnaire metadata from participants with concurrent microbiome sequencing data. Methods We analyzed 9832 participants with 120 metadata features across five categories (demographic, dietary, lifestyle, nutritional, medical). Features were selected via Pearson correlation and chi‐squared tests. Four algorithms were trained using 10‐fold cross‐validation with synthetic minority oversampling technique (SMOTE), validated on 1967 samples. The 16S rRNA sequencing data from the same cohort with 2000 samples enabled microbiome composition analysis. Results Medical history (area under the curve [AUC] = 0.871) and dietary patterns (AUC = 0.874) achieved best performance, outperforming demographic (0.795), lifestyle (0.660), and nutritional (0.569) domains ( p < 0.001). Microbiome analysis revealed dysbiosis markers ( Prevotella/Bacteroides ratio: 1.921) linking dietary factors to potential neuroinflammatory pathways. Discussion These findings support non‐invasive, multi‐modal screening combining medical and dietary evaluation for AD risk stratification, with preliminary microbiome evidence suggesting gut–brain axis dysbiosis as a mechanistic pathway warranting validation in larger cohorts.
Who’s Plugging In? Exploring Socio-Economic and Demographic Patterns of Early EV Adopters in Australia Lachlan J. Masters, Tallat Jabeen, Mohammad Karimadini, Marty Fuentes, Faezeh Karimi, Kaveh Khalilpour Sustainability Switzerland, 2026 This study examines how socio-economic and demographic factors influence electric vehicle (EV) adoption in New South Wales (NSW), Australia. Using 2021 Australian Bureau of Statistics (ABS) census data and EV registration records, a cross-sectional analysis was conducted at the postcode level. Ordinary Least Squares (OLS) regression was applied to identify key determinants of EV uptake. The final model demonstrates strong explanatory power (R2 = 0.819%). Results indicate that economic status, captured through a combined income and mortgage indicator, is the strongest predictor, associated with an approximately 101.7% increase in EV registrations for each standard deviation increase. Vehicle ownership density also shows a strong positive effect (an 80.9% increase). In contrast, areas with higher reliance on active transport exhibit a statistically significant negative association with EV adoption. Additional factors, including age, education, and occupational composition (managers and professionals), show moderate positive effects. These findings highlight persistent socio-economic disparities in EV uptake and suggest that targeted policy interventions are required to support a more equitable transition to sustainable transport.
Deep Learning Framework for Breast Tumor Detection and Segmentation Using CT Imaging Zainab Pervaiz, Tallat Jabeen, Ruqaiyya Adil, Muhammad Waleed Khan, Aaysha Tariq, Muhammad Irfan Zafar, Ishrat Jabeen IEEE Access, 2026 Breast cancer remains the leading malignancy among women globally, yet AI-based detection systems focus predominantly on mammography while whole-body CT imaging is routinely performed for oncological staging thus, remains critically underexplored. Existing CT-based studies are limited by small datasets, geographical bias, and lack of spatial localization capabilities. This study introduces a radiologist-verified CT scan dataset of 9330 annotated slices from three Pakistani hospitals, approved by institutional ethics committees. Data was partitioned into training (70%), validation (15%), and test (15%) sets to develop a two-stage deep learning framework. The training data includes 6,106 whole-body CT slices (3,053 tumor, 3,053 normal). The perfectly balanced training dataset eliminates class-level imbalance, while detection-level imbalance is addressed through distributional focal loss mechanisms. We systematically evaluated seven transfer learning architectures (VGG16, VGG19, ResNet50V2, InceptionV3, DenseNet121, DenseNet201, EfficientNetB0–B5), revealing that VGG16 achieved optimal performance (82% accuracy, 0.80 AUC-ROC) compared to deeper architectures (ResNet50V2: 49%, EfficientNet: 50%), demonstrating that simpler models exhibit better inductive bias for constrained medical imaging datasets. Building upon this, we developed an integrated YOLOv11-Seg framework exploiting architectural innovations: C3K2 bottleneck modules for hierarchical feature extraction, Spatial Pyramid Pooling Fast (SPPF) for multi-scale context aggregation, and Pixel Spatial Attention (C2PSA) for enhanced boundary delineation. YOLOv11-Seg achieved 84.6% precision, 90% recall, 0.84 mAP@50, 0.839 Dice coefficient, and 0.724 mean IoU. Error analysis revealed false negatives (3.83%) primarily from low-contrast lesions and small tumors (<8 mm), while false positives (6.3%) resulted from fibrous tissue misclassification. Real-time video inference on >10,000 frames demonstrated 10 FPS processing, 93.1% sensitivity, 97.9% specificity, and 94.3% temporal consistency, enabling clinical workflow integration. Limitations of the current study include single-radiologist annotation, geographical homogeneity, retrospective design, and binary classification scope, warranting prospective multi-center validation, multi-class classification extension, and explainable AI development. This work establishes foundation for AI-assisted opportunistic breast cancer screening in whole-body CT imaging, particularly valuable for resource-constrained settings, with clear pathways toward comprehensive staging and diagnostic support systems.
Agent-Based Simulation of Gut-Neuron Interactions and Inflammatory Pathways in Neurodegenerative Diseases Tallat Jabeen, Faezeh Karimi, Ali R. Zomorrodi, Kaveh Khalilpour Proceedings 2025 IEEE International Conference on Medical Artificial Intelligence Medai 2025, 2025 The gut–brain axis represents a vital bidirectional communication network linking the gastrointestinal and central nervous systems. Growing evidence implicates disruptions in gut microbiota composition (dysbiosis) in the development of neurodegenerative conditions such as Alzheimer’s disease, Parkinson’s disease, autism spectrum disorder, and epilepsy. In this study, we introduce a computational agent-based model grounded in Lotka–Volterra dynamics to simulate interactions between key gut microbial populations and neuronal health. The model captures predator–prey-like dynamics, where microbiota act as microbial predators and neurons as vulnerable prey, while also incorporating the effects of metabolite accumulation and inflammatory signalling. Through sensitivity analysis, we identify biological parameters that most strongly influence system behaviour over time. Our findings provide mechanistic insights into how microbiome-driven inflammation may contribute to neurodegeneration and establish a systems-level framework for advancing gut–brain research in computational neuroscience and medical AI.
Smart Wireless Sensor Technology for Healthcare Monitoring System Using Cognitive Radio Networks Tallat Jabeen, Ishrat Jabeen, Humaira Ashraf, Ata Ullah, N. Z. Jhanjhi, Rania M. Ghoniem, Sayan Kumar Ray Sensors, 2023 Programmable Object Interfaces are increasingly intriguing researchers because of their broader applications, especially in the medical field. In a Wireless Body Area Network (WBAN), for example, patients’ health can be monitored using clinical nano sensors. Exchanging such sensitive data requires a high level of security and protection against attacks. To that end, the literature is rich with security schemes that include the advanced encryption standard, secure hashing algorithm, and digital signatures that aim to secure the data exchange. However, such schemes elevate the time complexity, rendering the data transmission slower. Cognitive radio technology with a medical body area network system involves communication links between WBAN gateways, server and nano sensors, which renders the entire system vulnerable to security attacks. In this paper, a novel DNA-based encryption technique is proposed to secure medical data sharing between sensing devices and central repositories. It has less computational time throughout authentication, encryption, and decryption. Our analysis of experimental attack scenarios shows that our technique is better than its counterparts.
An Intelligent Healthcare System Using IoT in Wireless Sensor Network Tallat Jabeen, Ishrat Jabeen, Humaira Ashraf, N. Z. Jhanjhi, Abdulsalam Yassine, M. Shamim Hossain Sensors, 2023 The Internet of Things (IoT) uses wireless networks without infrastructure to install a huge number of wireless sensors that track system, physical, and environmental factors. There are a variety of WSN uses, and some well-known application factors include energy consumption and lifespan duration for routing purposes. The sensors have detecting, processing, and communication capabilities. In this paper, an intelligent healthcare system is proposed which consists of nano sensors that collect real-time health status and transfer it to the doctor’s server. Time consumption and various attacks are major concerns, and some existing techniques contain stumbling blocks. Therefore, in this research, a genetic-based encryption method is advocated to protect data transmitted over a wireless channel using sensors to avoid an uncomfortable data transmission environment. An authentication procedure is also proposed for legitimate users to access the data channel. Results show that the proposed algorithm is lightweight and energy efficient, and time consumption is 90% lower with a higher security ratio.
A Monte Carlo based COVID-19 detection framework for smart healthcare Tallat Jabeen, Ishrat Jabeen, Humaira Ashraf, Nz Jhanjhi, Mamoona Humayun, Mehedi Masud, Sultan Aljahdali Computers Materials and Continua, 2022 COVID-19 is a novel coronavirus disease that has been declared as a global pandemic in 2019. It affects the whole world through person-to-person communication. This virus spreads by the droplets of coughs and sneezing, which are quickly falling over the surface. Therefore, anyone can get easily affected by breathing in the vicinity of the COVID-19 patient. Currently, vaccine for the disease is under clinical investigation in different pharmaceutical companies. Until now, multiple medical companies have delivered health monitoring kits. However, a wireless body area network (WBAN) is a healthcare system that consists of nano sensors used to detect the real-time health condition of the patient. The proposed approach delineates is to fill a gap between recent technology trends and healthcare structure. If COVID-19 affected patient is monitored through WBAN sensors and network, a physician or a doctor can guide the patient at the right time with the correct possible decision. This scenario helps the community to maintain social distancing and avoids an unpleasant environment for hospitalized patients Herein, a Monte Carlo algorithm guided protocol is developed to probe a secured cipher output. Security cipher helps to avoid wireless network issues like packet loss, network attacks, network interference, and routing problems. Monte Carlo based covid-19 detection technique gives 90% better results in terms of time complexity, performance, and efficiency. Results indicate that Monte Carlo based covid-19 detection technique with edge computing idea is robust in terms of time complexity, performance, and efficiency and thus, is advocated as a significant application for lessening hospital expenses.
Security and privacy concerned association rule mining technique for the accurate frequent pattern identification International Journal of Engineering and Technology Uae, 2018
Publications
1. A survey on healthcare data security in wireless body area networks.
2. A lightweight genetic based algorithm for data security in wireless body area networks.
3. A monte carlo based COVID-19 detection framework for smart healthcare.
4. An Intelligent Healthcare System Using IoT in Wireless Sensor Network.
5. Smart Wireless Sensor Technology for Healthcare Monitoring System using Cognitive Radio Networks.
