nadirah ghenimi

Dr. nadirah ghenimi

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
27 December 2023 in PLOS ONE
Verified
Journal Article
Open access
PDF file
WKWasif Khan
Wasif Khan
NZNazar Zaki
Nazar Zaki
NGnadirah ghenimi
nadirah ghenimi
AAAmir Ahmad
Amir Ahmad
JBJiang Bian
Jiang Bian
LALuai A Ahmed
Luai A Ahmed
Preterm birth (PTB) presents a complex challenge in pregnancy, often leading to significant perinatal and long-term morbidities. “While machine learning (ML) algorithms have shown promise in PTB prediction, the lack of interpretability in existing models hinders their clinical utility. This study aimed to predict PTB in a pregnant population using ML models, identify the key risk factors associated with PTB through the SHapley Additive exPlanations (SHAP) algorithm, and provide comprehensive explanations for these predictions to assist clinicians in providing appropriate care. This study analyzed a dataset of 3509 pregnant women in the United Arab Emirates and selected 35 risk factors associated with PTB based on the existing medical and artificial intelligence literature. Six ML algorithms were tested, wherein the XGBoost model exhibited the best performance, with an area under the operator receiving curves of 0.735 and 0.723 for parous and nulliparous women, respectively. The SHAP feature attribution framework was employed to identify the most significant risk factors linked to PTB. Additionally, individual patient analysis was performed using the SHAP and the local interpretable model-agnostic explanation algorithms (LIME). The overall incidence of PTB was 11.23% (11 and 12.1% in parous and nulliparous women, respectively). The main risk factors associated with PTB in parous women are previous PTB, previous cesarean section, preeclampsia during pregnancy, and maternal age. In nulliparous women, body mass index at delivery, maternal age, and the presence of amniotic infection were the most relevant risk factors. The trained ML prediction model developed in this study holds promise as a valuable screening tool for predicting PTB within this specific population. Furthermore, SHAP and LIME analyses can assist clinicians in understanding the individualized impact of each risk factor on their patients and provide appropriate care to reduce morbidity and mortality related to PTB.

WKWasif Khan
Wasif Khan
NZNazar Zaki
Nazar Zaki
AAAmir Ahmad
Amir Ahmad
Jiang BianJiang Bian
Jiang Bian
LALuqman Ali
Luqman Ali
LALuai A. Ahmed
Luai A. Ahmed
Low Birth weight (LBW) infants pose a serious public health concern worldwide in both the short and long term for infants and their mothers. Infant weight prediction prior to birth can help to identify risk factors and reduce the risk of infant morbidity and mortality. Although many Machine Learning (ML) algorithms have been proposed for LBW prediction using maternal features and produced considerable model performance, their performance needs to be improved so that they can be adapted in real-world clinical settings. Existing algorithms used for LBW classification often fail to capture structural information from the tabular dataset of patients with different complications. Therefore, to improve the LBW classification performance, we propose a solution by transforming the tabular data into a knowledge graph with the aim that patients from the same class (normal or LBW) exhibit similar patterns in the graphs. To achieve this, several features related to each node are extracted such as node embedding using node2vec algorithm, node degree, node similarity, nearest neighbors, etc. Our method is evaluated on a real-life dataset obtained from a large cohort study in the United Arab Emirates which contains data from 3453 patients. Multiple experiments were performed using the seven most commonly used ML models on the original dataset, graph features, and a combination of features, respectively. Experimental results show that our proposed method achieved the best performance with an area under the curve of 0.834 which is over 6% improvement compared to using the original risk factors without transforming them into knowledge graphs. Furthermore, we provide the clinical relevance of the proposed model that are important for the model to be adapted in clinical settings.

20 August 2024 in Children
Verified
Journal Article
Open access
PDF file
SASohrab Amiri
Sohrab Amiri
NMNailah Mahmood
Nailah Mahmood
RYRahemeen Yusuf
Rahemeen Yusuf
NGnadirah ghenimi
nadirah ghenimi
SJSyed Fahad Javaid
Syed Fahad Javaid
Moien AB KhanMoien AB Khan
Moien AB Khan
(1) Objectives: The impact of abnormal body mass index (BMI) on health is extensive, and various risk factors contribute to its effects. This study aimed to examine the association between adverse childhood experiences (ACEs) and BMI categories, including underweight, overweight, obesity, severe obesity, and morbid obesity; (2) Methods: Three databases were searched: Web of Science, PubMed, and Scopus. Manual searches were conducted using Google Scholar and ResearchGate. Odds ratios (ORs) and 95% confidence intervals (CIs) were calculated to assess the association between ACEs and BMI. A random-effects model was used to combine the ORs and CIs across studies; (3) Results: This meta-analysis included 71 studies. The pooled ORs for the relationship between ACEs and obesity was 1.42 (95% CI: 1.24–1.63, Z = 4.96, p < 0.001), indicating a significant association. ACEs showed a positive association with overweight (OR = 1.16, 95% CI: 1.06–1.27, Z = 3.24, p = 0.001). Specifically, ACEs ≥ 4 were strongly associated with obesity (OR = 2.06, 95% CI: 1.27–3.36, Z = 2.90, p = 0.004). Sexual abuse was also found to be significantly associated with obesity (OR = 1.46, 95% CI: 1.29–1.65, Z = 5.98, p < 0.001); (4) Conclusion: This study finds that individuals who have experienced ACEs are more likely to have a higher BMI in adulthood. Therefore, ACEs should be considered a factor associated with abnormal BMI.

9 August 2025 in AI & SOCIETY
Verified
Journal Article
Open access
PDF file
NGnadirah ghenimi
nadirah ghenimi
RGRomona Govender
Romona Govender
KMKeymanthri Moodley
Keymanthri Moodley
The integration of artificial intelligence (AI) into healthcare has transformed patient care through advanced diagnostics, personalized treatment plans, and predictive analytics. However, this technological evolution presents a paradox when juxtaposed with narrative-based medicine (NBM), which emphasizes the patient’s story and human experience in healthcare delivery. The integration of AI into the NBM raises questions regarding its clinical applicability, resistance from patients and physicians, emotional considerations, time constraints, and ability to balance psychosocial and biomedical care. This critical review explores the challenges and potential of combining AI with NBM, aiming to enhance patient care by leveraging the strengths of both approaches.

13 September 2024 in Healthcare
Verified
Journal Article
Open access
PDF file
YSYauhen Statsenko
Yauhen Statsenko
DSDarya Smetanina
Darya Smetanina
GSGillian Lylian Simiyu
Gillian Lylian Simiyu
MBMaroua Belghali
Maroua Belghali
NGnadirah ghenimi
nadirah ghenimi
MLMilos Ljubisavljevic
Milos Ljubisavljevic
The rationale for the current study is the sparsity of data on the combined effect of the environmental and individual risks of obesity and sedentary lifestyle in children of different races/ethnicities from different regions. An effective weight management strategy is hard to design due to insufficient evidence. This work was initiated to study race, ethnicity, and geography as determinants of excessive weight and low physical activity in the pediatric population. To achieve this aim, we systematically review publications on daily length of physical activity of light, moderate, and vigorous intensity, as well as sedentary time and BMI and its dynamics in children of different races/ethnicities and geographies. The extracted data are stratified into six major geographic regions and six races/ethnicities. Then, a random-effects meta-analysis is used to calculate the pooled mean of each outcome measure. A ridge regression is constructed to explore age-related change in BMI. A Kruskal–Wallis H test is applied to compare the pooled duration of physical activity and sedentary time in the subgroups. Finally, we calculate paired correlation coefficients between BMI and physical activity/inactivity for each group. The findings can be further used in public health surveillance to clarify the epidemiology of obesity, to guide priority setting and planning, and to develop and evaluate public health policy and strategy.

27 March 2026
Verified
Thesis
Closed access
NGnadirah ghenimi
nadirah ghenimi
Un ensemble des données cohérentes de la littérature plaide en faveur d'une relation entre une baisse d'activité de la voie de signalisation de la vitamine A, des altérations de la plasticité synaptique et des déficits mnésiques spécifiques associés au vieillissement. Une diminution de l'activité de cette voie de signalisation est également évoquée dans les processus neurodégénératifs caractéristiques de la maladie d'Alzheimer. Dans ce contexte, les objectifs de ce travail étaient de mieux comprendre les conséquences neuro-anatomiques et fonctionnelles d'une baisse d'activité de la voie de signalisation de la vitamine A. Notre approche expérimentale a mis en œuvre 2 modèles animaux, un modèle de carence vitaminique A qui induit spécifiquement une baisse d'activité de sa voie de signalisation et un modèle d'hypothyroïdie dont il a été montré qu'il induit aussi une hypoactivité de la voie de signalisation de la vitamine A. La démarche expérimentale conduite chez les rats carencés en vitamine A comporte deux volets : (i) un volet mettant en œuvre l’imagerie et la spectroscopie RMN, (ii) un volet moléculaire consacrée à l’étude de l’expression de gènes cibles des rétinoïdes impliqués dans le processus amyloïdogène. Les mesures ont été réalisées, d'une part, chez des animaux soumis à un régime dépourvu en vitamine A pendant 10 semaines et d'autre part, chez des animaux soumis à ce même régime pendant une durée de 13 ou 14 semaines. Une partie des animaux carencés a été traitée par de l'AR. Les résultats montrent que dès 10 semaines de carence, les animaux présentent une altération du métabolisme et de son action cellulaire de la vitamine A qui se traduit par (i) une diminution significative du taux de vitamine A sérique, (ii) une diminution du taux d'ARNm codant pour les récepteurs RAR, dans le cerveau entier, le striatum, l'hippocampe et de manière moins prononcée le cortex des animaux. Après 10 semaines de régime dépourvu en vitamine A, des modifications métaboliques ont été mises en évidence essentiellement dans le cortex. Elles se traduisent par une hausse du (i) NAA/Cr, marqueur de la densité neuronale corrigée par une administration d'AR, et (ii) du GSH/Cr, indicateur du potentiel antioxydant cellulaire dans cette structure. Au plan anatomique, un ralentissement de la croissance cérébrale a été observé dés la 7ème semaine de régime. Une diminution du volume hippocampique et une augmentation des espaces ventriculaires ont été observées à partir de 11 semaines de carence. Au plan moléculaire, aucune modification de l'expression du gène codant pour APP, ou du rapport APP770-751/APP695, considéré comme un indicateur précoce de la MA n'a été observée après 10 semaines de carence. Après 14 semaines de régime dépourvu en vitamine A, de profondes modifications métaboliques sont observées dans les trois structures à savoir le cortex, l’hippocampe et le striatum. Au plan moléculaire, les principaux résultats suggèrent un basculement du processus biochimique de dégradation de la protéine APP en faveur de la voie amyloïdogénique dans le cortex, et par voie de conséquence en faveur de la formation du peptide Aß. Cependant, aucune modification du taux protéique des peptides Aß n'a été mise en évidence dans le cortex et l'hippocampe des rats carencés. Le modèle d'hypothyroïdie que nous avons mis en oeuvre entraine bien une hypoactivité de la voie de signalisation de la T3, observée dans l'hippocampe des animaux et une diminution du taux d'ARNm codant pour RARß observée dans le cortex des rats hypothyroïdiens. Au plan moléculaire, l'augmentation du rapport APP770-751/APP695 a été observée chez les rats rendus hypothyroïdiens par rapport aux rats témoins. Comme chez les rats carencés en vitamine A, les indicateurs de la voie physiologique ne sont que très faiblement affectés chez les rats rendus hypothyroïdiens.