NUST Institutions Library Catalogue Search for 'an:"123326"'

Predicting Alzheimer's Disease Progression Using Multimodal Longitudinal Analysis: A Machine Learning Approach /

By Nadeem, Maryam . . 67p. , Patients with Mild Cognitive Impairment (MCI) face an increased risk of developing Alzheimer's disease (AD), highlighting the importance of early diagnosis for effective interventions and management of the disease. In our study, we investigated the progression of AD in patients initially diagnosed with MCI using multimodal longitudinal data. A classification based framework was proposed for MCI prediction with baseline data of 569 stable MCI (sMCI) and 268 progressive MCI (pMCI) patients. Employing three supervised machine learning (ML) algorithms—support vector machine (SVM), logistic regression (LR), Random Forest (RF) and incorporating features such as cognitive function assessments, MRI, PET scans, CSF biomarkers, and genetic APOE status, the classification accuracies of 83.4%, 80.2%, and 80% were achieved respectively. Significant differences were observed in the performance of the models, with the SVM notably outperforming both LR and RF (p < 0.05). Impaired memory function and lower clinical tests scores were found as primary indicators of MCI patients progressing towards AD. Although the fusion of all modalities yielded accurate results for predicting MCI progression to AD, our analysis revealed less significant differences in evaluation metrics when only cognitive test results were used as features. This suggests that cognitive assessments alone are nearly as effective in predicting MCI progression, which can lead to more cost-effective strategies in clinical settings. This study underscores the need for further research aimed at developing new tools to assist clinicians in prognostic decision making. 30cm.

Place Hold on Predicting Alzheimer's Disease Progression Using Multimodal Longitudinal Analysis: A Machine Learning Approach /

AI-Based Forecasting of Mild Cognitive Impairment to Alzheimer's Disease Using Multi-Modal Approach /

By Saeed, Amna . . 90p. , With no medication currently available and a clinical trial failure rate of 99.6% for Alzheimer’s disease (AD) , early diagnosis is crucial to prevent its progression. MCI has been identified as a transitional stage between healthy aging and AD, making it promising for early detection. In this study, we propose a machine learning (ML) based survival analysis approach to predict the time to AD conversion in early MCI and late MCI stages separately, as we found that the progression rate varies in both stages. Unlike typical ML classifiers, ML-based survival analysis models can provide information about the timing and likelihood of disease progression. We employed multiple ML survival models, including Random Survival Forest (RSF), Extra Survival Trees (XST), Gradient Boosting Survival Analysis (GB), Survival Tree (ST), Cox-net, and Cox Proportional Hazard (CoxPH), on 291 eMCI and 546 lMCI subjects. The study also compared different data modalities, such as cognitive tests, neuroimaging tests, and cerebrospinal fluid (CSF) biomarkers, both individually and in combination to identify the most influential features for the models' performance. The results show that RSF outperformed traditional CoxPH and other ML models used in this study. For the eMCI dataset, RSF trained on multimodal data achieved a C-Index of 0.96 and an IBS of 0.02. For the lMCI dataset, the C-Index was 0.82 and the IBS was 0.16. Additionally, the multimodal analysis highlighted the importance of cognitive tests, as they exhibited a statistically significant improvement over other modalities and multimodal data, demonstrating their reliability in predicting AD progression. Finally, individual survival curves were generated using RSF on baseline data to predict the probability of early onset of AD in patients. This facilitates clinical decision-making by assisting clinicians in developing personalized treatment strategies and implementing preventive measures to slow down or potentially stop the progression of AD during its early stages. 30cm.

Place Hold on AI-Based Forecasting of Mild Cognitive Impairment to Alzheimer's Disease Using Multi-Modal Approach /

Diagnosis of Diabetes Mellitus through Predictive Modelling using Machine Learning /

By Shahid, Ayeza . . 69p. , Diabetes mellitus is a global health challenge, requiring early detection to prevent severe complications. This study utilizes machine learning for diabetes diagnosis, leveraging a dataset collected from the Pakistani population to ensure demographic relevance. Features included invasive parameters (e.g., fasting blood glucose, blood pressure) and non-invasive factors (e.g., age, gender, BMI, waist circumference). The data was split into training (70%) and testing (30%) sets and evaluated using nine classifiers, including Logistic Regression, Random Forest, XGBoost, and LightGBM. Ensemble models, particularly XGBoost achieved superior performance, with testing accuracy reaching 93%. This model demonstrated robustness in capturing complex feature interactions without requiring extensive feature selection. Integration into a mobile app and GUI further demonstrated the practical utility of these models, allowing users to input health parameters and receive instant predictions. This research highlights the importance of combining machine learning with regionspecific data for accurate and accessible diabetes prediction. It demonstrates the potential of predictive modeling to complement traditional diagnostics and improve early detection. Future work may focus on publicizing the mobile application and additional data to enhance model performance. 30cm.

Place Hold on Diagnosis of Diabetes Mellitus through Predictive Modelling using Machine Learning /

Metabolic Syndrome Management: Strategies for Early Detections and Preventive Interventions /

By Rehman, Sanam . . 67p. , The prediction and management of metabolic syndrome (MetS) is crucial due to its chronic nature and global health challenge. This study aims for early and accurate MetS diagnosis for timely prevention by managing associated risk factors. It utilizes machine learning (ML) and deep learning (DL) techniques while considering demographic and ethnic variability. Notably, there is a lack of MetS prediction research in the Pakistani population, which has unique genetic and lifestyle diversity. This study addresses this gap using a dataset of 502 individuals from five Pakistani cities (MetS prevalence = 43.4%), with 24 features from anthropometric, clinical, lifestyle, and family history data. It is the first study evaluating fifteen classifiers (12 ML and 3 DL models) through five-fold cross-validation. AdaBoost outperformed with 93.4% accuracy, an Area under Curve (AUC) of 0.97, and pvalue < 0.05. Feature importance analysis (Permutation and SHAP) identified fasting blood glucose, systolic blood pressure, triglycerides, and obesity as key biomarkers for MetS. Odds ratio analysis across gender and age groups (95% CI) showed that Body Mass Index (BMI), blood pressure, and glucose levels were strongly associated with MetS in aging males, while glucose and HDL were more influential in older females. This study provides population-specific insights into MetS risk, enhancing early prediction accuracy and enabling targeted interventions for high-risk individuals. 30cm.

Place Hold on Metabolic Syndrome Management: Strategies for Early Detections and Preventive Interventions /

Development of Flexible Strain Sensor Utilizing Recycled Electronic Components /

By Mughal, Muhammad Shahzaib . . 65p. , The development of flexible and cost-effective strain sensors is crucial for advancing prosthetic technology, particularly in artificial limb control. This research focuses on the development of a flexible strain sensor utilizing recycled electronic components to control the movement of a prosthetic hand while also measuring stress applied to the prosthetic fingers. This new design improves conventional flex sensors since it avoids noise, costs less and is more durable. While past studies depended on different sensor types, this study introduces sensing based on a parallel plate capacitor with just one layer. The sensor is made by using items from electronic waste, with conductive graphite from dry batteries and flexible campaign banners. Furthermore, a special type of silver paper is integrated with the parallel plate capacitor, improving sensor efficiency. The system uses five capacitive strain sensors, positioned on every finger, to sense finger bending. When the finger of the capacitor bends, the separation of the plates or their dielectric properties changes, increasing the capacitance. If the capacitance becomes greater than a certain number, the servo motor moves the associated robotic finger from 0 degrees to 180 degrees. Parallel to the finger movement detection, we create an extra system built on an Arduino that can sense the pressure applied to the prosthetic hand’s fingers, using separate supplies that are better for measuring force. 30cm.

Place Hold on Development of Flexible Strain Sensor Utilizing Recycled Electronic Components /