Abdullahi Salahudeen Abdulraheem

Mr. Abdullahi Salahudeen Abdulraheem

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 June 2025 in Pharmaceutical Science Advances
Verified
Journal Article
Open access
KOKARAMOT OYEDIRAN
KARAMOT OYEDIRAN
PBPeace-Ofonabasi O. Bassey
Peace-Ofonabasi O. Bassey
DODeborah A. Ogundemuren
Deborah A. Ogundemuren
AAAbdullahi Salahudeen Abdulraheem
Abdullahi Salahudeen Abdulraheem
CAChukwuemeka P. Azubuike
Chukwuemeka P. Azubuike
MARGARET OKONAWAN ILOMUANYAMARGARET OKONAWAN ILOMUANYA
MARGARET OKONAWAN ILOMUANYA
Despite significant advancements in highly active antiretroviral therapy (HAART), Human Immunodeficiency Virus (HIV) remains a global health challenge due to its high mutation rate, drug resistance, and the complexity of treatment optimization. Artificial intelligence (AI) has emerged as a transformative tool in HIV research, offering innovative solutions for predicting viral mutations, optimizing drug discovery and formulation design. However, challenges such as limited access to diverse datasets, ethical concerns, and model interpretability hinder the full potential of AI in HIV research. This review highlights gaps in AI-driven HIV research and explores advancements to address these challenges. AI-driven platforms, such as DeepHIV and geno2pheno, have demonstrated success in forecasting resistance mutations and guiding therapeutic decisions. AI is also revolutionizing drug formulation development by enhancing solubility, bioavailability, and stability, while improving patient adherence through advanced delivery systems. Current applications of AI in HIV mutation prediction, drug discovery, and formulation optimization have highlighted the potential of AI towards HIV management and eradication while addressing gaps in data availability and model transparency. By integrating structural, pharmacological, and clinical data, AI provides a comprehensive framework for rational drug design and personalized treatment strategies. By leveraging AI-driven insights, HIV treatment and prevention can become more personalized, efficient, and sustainable. Future research should focus on overcoming data limitations, enhancing model interpretability, and exploring innovative AI approaches to contribute to the global fight against the HIV epidemic.

26 September 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
Emmanuel OnahEmmanuel Onah
Emmanuel Onah
UEUche Jude Eze
Uche Jude Eze
AAAbdullahi Salahudeen Abdulraheem
Abdullahi Salahudeen Abdulraheem
UEUgochukwu Ezigbo
Ugochukwu Ezigbo
KAKosisochi Chinwendu Amorha
Kosisochi Chinwendu Amorha
Background/Objectives: Thyroid cancer, particularly well-differentiated thyroid cancer, is one of the most prevalent endocrine malignancies, with a rising incidence. Although it generally has a favorable prognosis, recurrence is common. Accurate prediction of recurrence is crucial for optimizing treatment plans and improving patient outcomes. This study aimed to advance the state-of-the-art in thyroid cancer recurrence prediction by refining feature engineering techniques and exploring a diverse ensemble of machine learning algorithms and an artificial neural network, using the differentiated thyroid cancer dataset from the UCI Machine Learning Repository; Methods: Various unsupervised data engineering methods, such as dimensionality reduction and clustering, were employed to enhance feature quality and mitigate noise, using stratified 10-fold cross-validation. The best-performing dimensionality reduction techniques were used to build classification model pipelines employing each of several machine learning models and an artificial neural network. The performance of these classification pipelines were assessed using metrics sensitive to class imbalance; Results: Principal Component Analysis and Truncated Singular Value Decomposition achieved superior clustering performance and moderate variances in their first principal components. Logistic Regression, Random Forest, Support Vector Machine, K-Nearest Neighbors, and Feedforward Neural Network models all achieved high performance, with Logistic Regression pipelines demonstrating balanced accuracy, F1 score, AUC, sensitivity, specificity, and precision—all greater than 0.93 on the test set and slightly lower in 10-fold cross-validation. Gradient Boosting classification pipelines performed the lowest, though still with respectable metrics; Conclusions: This study shows that employing feature engineering techniques like Principal Component Analysis or Truncated Singular Value Decomposition in Logistic Regression, Random Forest, Feedforward Neural Networks, Support Vector Machine, and K-Nearest Neighbors classification pipelines can improve thyroid cancer recurrence prediction accuracy and reliability, supporting more personalized treatment strategies in post-treatment patients.

2 October 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
DIDamilola Ibirogba
Damilola Ibirogba
OOOluwagbemisola Oyin Olukogbe
Oluwagbemisola Oyin Olukogbe
EAEbsitu ABATE Abate
Ebsitu ABATE Abate
MAMoses Asori
Moses Asori
Stephen T. EngmannStephen T. Engmann
Stephen T. Engmann
NONduka Okwose
Nduka Okwose
Background: Food Bioactive Substances (FBS), extra-nutritional constituents found in foods are promising strategies in the treatment of Non-Alcoholic Fatty Liver Disease (NAFLD). Existing clinical studies showed contradictory results regarding their therapeutic effect. This review aimed to evaluate the effectiveness of food-bioactive substances in patients with NAFLD and non-alcoholic steatohepatitis (NASH). Methods: Six controlled databases (PubMed, Embase, Scopus, ProQuest, CINAHL and Cochrane) were searched, yielding 10969 articles. The Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) guidelines were followed, while screening, quality assessment and data extraction of search results were conducted using Covidence. Results: Thirty-two studies were included in the systematic review, while 8 RCTs with 540 patients with NAFLD were included in the meta-analysis. The meta-analysis underscores the effects of the three most studied FBS (silymarin, curcumin and resveratrol) on key cardiovascular and metabolic markers, including BMI, waist circumference, AST, ALT, LDL, HDL, cholesterol and triglycerides of these patients. Overall, FBS showed a statistically significant reduction in BMI (SMD = -0.28; 95% CI: -0.45 to -0.10, p < 0.01), a slight reduction in LDL (SMD = -0.22; p = 0.02), HOMA-IR (SMD = -0.26, 95% CI = -0.51 to -0.02; p = 0.036), total cholesterol level SMD = -0.15 (95% CI: -0.40 to -0.10; I2 = 13%; p = 0.33), especially with silymarin showing the greatest statistically significant reduction in HOMA-IR (SMD = -0.16); p = 0.01), Total Cholesterol (SMD = -0.45, p <0.01), AST (SMD = -0.23, p <0.01) Conclusion: Silymarin appeared to be the most promising intervention, particularly for lowering BMI, LDL, cholesterol and triglycerides, but the high variability between studies limits the generalizability of these results