Micheal Olalekan Ajinaja

Micheal Olalekan Ajinaja

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
8 November 2022 in Iran Journal of Computer Science
Verified
Journal Article
Closed access
PDF file
MAMicheal Olalekan Ajinaja
Micheal Olalekan Ajinaja
AAAdebayo Olusola Adetunmbi
Adebayo Olusola Adetunmbi
CUChukwuemeka Christian Ugwu
Chukwuemeka Christian Ugwu
Olugbemiga Solomon POPOỌLAOlugbemiga Solomon POPOỌLA
Olugbemiga Solomon POPOỌLA

22 August 2022 in Research Square
Verified
Preprint
Open access
PDF file
MAMicheal Olalekan Ajinaja
Micheal Olalekan Ajinaja
OAOlusola Adebayo Adetunmbi
Olusola Adebayo Adetunmbi
CUChukwuemeka Christian Ugwu
Chukwuemeka Christian Ugwu
PSPopoola Olugbemiga Solomon
Popoola Olugbemiga Solomon
One of the key applications of Natural Language Processing (NLP) is to automatically extract topics from large volumes of text. Latent Dirichlet Allocation (LDA) technique is commonly used to extract topics based on word frequency from the pre-processed documents. A major issue of LDA is that the quality of topics extracted are poor if the document do not coherently discuss a single topic. However, Gibbs sampling uses word by word basis which changes the topic assignment of one word and can be used on documents having different topics. Hence, this paper proposed a hybrid based semantic similarity measure for topic modelling using LDA and Gibbs sampling to exploit the strength of automatic text extraction and improve coherence score. Unstructured dataset was obtained from a public repository to validate the performance of the proposed model. The evaluation carried out shows that the proposed LDA-Gibbs had a coherence score of 0. 52650 as against LDA coherence score 0.46504. The proposed multi-level model provides better quality of topics extracted.

24 March 2026 in Cureus Journal of Computer Science
Verified
Journal Article
Open access
PDF file
YOYetunde E. Ogunwale
Yetunde E. Ogunwale
JFJohnson T. Fakoya
Johnson T. Fakoya
OOOluyemisi A. Oyedemi
Oluyemisi A. Oyedemi
AAAkeem A. Abiona
Akeem A. Abiona
MAMicheal Olalekan Ajinaja
Micheal Olalekan Ajinaja
OOOluyemisi Oyedemi
Oluyemisi Oyedemi
Sepsis prediction in intensive care units (ICUs) remains a major clinical challenge because delayed recognition substantially increases mortality and treatment complexity. This study proposes a machine learning-driven framework for early sepsis prediction that integrates structured preprocessing of ICU time-series data, multi-horizon risk modeling, and explainable prediction analysis. Using the publicly available PhysioNet/Computing in Cardiology 2019 Sepsis Challenge dataset, comprising 40,336 ICU patient records from two hospital systems and approximately 1.42 million hourly clinical observations, this study evaluates early sepsis prediction under substantial class imbalance, with septic cases representing approximately 7.3% of the dataset. Three widely used machine learning algorithms - logistic regression, random forest, and gradient boosting - were implemented to establish baseline predictive performance. The framework evaluates prediction capability at three clinically relevant time horizons: at sepsis onset, 3 hours prior to onset, and 6 hours prior to onset, enabling systematic assessment of early warning capability. Model performance was assessed using discrimination and calibration metrics, including area under the receiver operating characteristic curve (AUROC), area under the precision-recall curve, sensitivity at fixed specificity, and Brier score. To support clinical transparency, explainable artificial intelligence techniques based on SHapley Additive exPlanations were incorporated to identify both global and patient-level predictors influencing model outputs. Results show that gradient boosting consistently achieved the strongest predictive performance across all prediction horizons, achieving an AUROC of 0.89 at sepsis onset while maintaining clinically meaningful discrimination at earlier prediction windows. Explainability analysis highlights physiologically relevant predictors consistent with established sepsis pathophysiology. These findings demonstrate that ensemble-based machine learning models can provide accurate, calibrated, and interpretable early sepsis prediction using routinely collected ICU data, supporting the development of reliable clinical decision-support tools for timely identification of high-risk patients.