Samuel Naandam

Dr. Samuel Naandam


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
2 January 2025 in Data
Verified
Journal Article
Open access
PDF file
ZYZhengxiao Yang
Zhengxiao Yang
HZHao Zhou
Hao Zhou
SSSudesh Srivastav
Sudesh Srivastav
JSJeffrey Shaffer
Jeffrey Shaffer
KAKuukua E. Abraham
Kuukua E. Abraham
Samuel KakrabaSamuel Kakraba
Samuel Kakraba
Patient-level grouped data are prevalent in public health and medical fields, and multiple instance learning (MIL) offers a framework to address the challenges associated with this type of data structure. This study compares four data aggregation methods designed to tackle the grouped structure in classification tasks: post-mean, post-max, post-min, and pre-mean aggregation. We developed a customized AI pipeline that incorporates twelve machine learning algorithms along with the four aggregation methods to detect Parkinson’s disease (PD) using multiple voice recordings from individuals available in the UCI Machine Learning Repository, which includes 756 voice recordings from 188 PD patients and 64 healthy individuals. Seven performance metrics—accuracy, precision, sensitivity, specificity, F1 score, AUC, and MCC—were utilized for model evaluation. Various techniques, such as Bag Over-Sampling (BOS), cross-validation, and grid search, were implemented to enhance classification performance. Among the four aggregation methods, post-mean aggregation combined with XGBoost achieved the highest accuracy (0.880), F1 score (0.922), and MCC (0.672). Furthermore, we identified potential trends in selecting aggregation methods that are suitable for imbalanced data, particularly based on their differences in sensitivity and specificity. These findings provide meaningful implications for the further exploration of grouped imbalanced data.

Verified
Journal Article
Open access
PDF file
Samuel NaandamSamuel Naandam
Samuel Naandam
PCPaul Chataa
Paul Chataa
GGGideon Gogovi
Gideon Gogovi
This study presents a mathematical model to describe the transmission dynamics of malaria in a highly endemic region, with a focus on vaccination and vaccine-induced immunity as primary control measures. By determining the basic reproduction number (R0), we evaluate the impact of these interventions on malaria-free and malaria-persistent equilibria. Our analysis shows that the malaria-free equilibrium is locally asymptotically stable when R0<1 and unstable otherwise. Numerical simulations demonstrate that increasing vaccination coverage and improving vaccine-induced immunity significantly reduce R0. A sensitivity analysis using partial rank correlation coefficients highlights the influence of key parameters, such as the mosquito-to-human transmission rate and mosquito birth and death rates, on malaria transmission. These findings underscore the potential of integrated strategies, combining vaccination with other interventions, to manage malaria effectively in highly endemic regions.

5 December 2024 in Preprints.org
Verified
Preprint
Open access
PDF file
ZYZhengxiao Yang
Zhengxiao Yang
HZHao Zhou
Hao Zhou
SSSudesh Srivastav
Sudesh Srivastav
JSJeffrey Shaffer
Jeffrey Shaffer
KAKuukua E Abraham
Kuukua E Abraham
Samuel KakrabaSamuel Kakraba
Samuel Kakraba
Patient-level grouped data is prevalent in public health and medical fields, and Multiple Instance Learning (MIL) offers a framework to address the challenges associated with this type of data structure. This study compares four data aggregation methods designed to tackle the grouped structure in classification tasks: post-mean, post-max, post-min, and pre-mean aggregation. We developed a customized AI pipeline that incorporates twelve machine learning algorithms along with the four aggregation methods to detect Parkinson's Disease (PD) using multiple voice recordings from individuals available in the UCI Machine Learning Repository, which includes 756 voice recordings from 188 PD patients and 64 healthy individuals. Seven performance metrics—Accuracy, Precision, Sensitivity, Specificity, F1 score, AUC, and MCC—were utilized for model evaluation. Various techniques, such as Bag Over-sampling (BOS), Cross-validation, and Grid Search, were implemented to enhance classification performance. Among the four aggregation methods, post-mean aggregation combined with XGBoost achieved the highest accuracy (0.921), F1 score (0.949), and MCC (0.783). Furthermore, we identified potential trends in selecting aggregation methods that are suitable for imbalanced data, particularly based on their differences in sensitivity and specificity. These findings provide meaningful implications for further exploration of grouped imbalanced data.

7 August 2024
Verified
Book Chapter
Closed access
PDF file
BOBismark Oduro
Bismark Oduro
DMDavid Mock
David Mock
AMAttou Miloua
Attou Miloua
Samuel NaandamSamuel Naandam
Samuel Naandam
PCPaul Chataa
Paul Chataa

7 July 2025 in medRxiv
Verified
Preprint
Open access
PDF file
MPMichael Asamani Pobbi
Michael Asamani Pobbi
Samuel NaandamSamuel Naandam
Samuel Naandam
Stephen Edward MooreStephen Edward Moore
Stephen Edward Moore
In this article, we formulate and analyse a novel mathematical model for the co-infection of Hepatitis B virus (HBV) and COVID-19. We investigate the effect of compliance to preventive measures, and massive disturbances due to environmental factors on transmission dynamics. First, we establish the basic reproduction number for HBV only Rs0α, COVID-19 only, Rs0C, and coinfection Rs0αC stochastic models around disease-free equilibrium point. Next, the conditions for stability in the stochastic sense for HBV only, COVID-19 only sub-models, and the co-infection model are established. Furthermore, we devote our attention to sufficient conditions for extinction and persistence using each of these reproductive numbers. Finally, by using the Euler Murayama scheme, we demonstrate the dynamics of the coinfection, COVID-19, HBV and effect of some parameters on disease transmission dynamics by means of numerical simulations.