MSMounia Serraj

Mounia Serraj

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mounia Serraj has a total of 39 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    NSCLC EGFR Mutation Prediction via Random Forest Model: A Clinical–CT–Radiomics Integration Approach

    by Anass Benfares, Badreddine Alami, Sara Boukansa, Mamoun Qjidaa, Ikram Benomar, Mounia Serraj, Ahmed Lakhssassi, Mohammed Ouazzani Jamil, Mustapha Maaroufi, Hassan Qjidaa

    Non-small cell lung cancer (NSCLC) is the leading cause of cancer-related mortality worldwide. Accurate determination of epidermal growth factor receptor (EGFR) mutation status is essential for selecting patients eligible for tyrosine kinase inhibitors (TKIs). However, invasive genotyping is often limited by tissue accessibility and sample quality. This study presents a non-invasive machine learning model combining clinical data, CT morphological features, and radiomic descriptors to predict EGFR mutation status. A retrospective cohort of 138 patients with confirmed EGFR status and pre-treatment CT scans was analyzed. Radiomic features were extracted with PyRadiomics, and feature selection applied mutual information, Spearman correlation, and wrapper-based methods. Five Random Forest models were trained with different feature sets. The best-performing model, based on 11 selected variables, achieved an AUC of 0.91 (95% CI: 0.81–1.00) under stratified five-fold cross-validation, with an accuracy of 0.88 ± 0.03. Subgroup analysis showed that EGFR-WT had a performance of precision 0.93 ± 0.04, recall 0.92 ± 0.03, F1-score 0.91 ± 0.02, and EGFR-Mutant had a performance of precision 0.76 ± 0.05, recall 0.71 ± 0.05, F1-score 0.68 ± 0.04. SHapley Additive exPlanations (SHAP) analysis identified tobacco use, enhancement pattern, and gray-level-zone entropy as key predictors. Decision curve analysis confirmed clinical utility, supporting its role as a non-invasive tool for EGFR-screening.


  • Open Access

    Nomogram Based on the Most Relevant Clinical, CT, and Radiomic Features, and a Machine Learning Model to Predict EGFR Mutation Status in Non-Small Cell Lung Cancer

    by Anass Benfares, Abdelali Yahya Mourabiti, Badreddine Alami, Sara Boukansa, Ikram Benomar, Nizar El Bouardi, Moulay Youssef Alaoui Lamrani, Hind El Fatimi, Bouchra Amara, Mounia Serraj, et al.

    Background: This study aimed to develop a nomogram based on the most relevant clinical, CT, and radiomic features comprising 11 key signatures (2 clinical, 2 CT-based, and 7 radiomic) for the non-invasive prediction of the EGFR mutation status and to support the timely initiation of tyrosine kinase inhibitor (TKI) therapy in patients with non-small cell lung cancer (NSCLC) adenocarcinoma. Methods: Retrospective real-world data were collected from 521 patients with histologically confirmed NSCLC adenocarcinoma who underwent CT imaging and either surgical resection or pathological biopsy for EGFR mutation testing. Five Random Forest classification models were developed and trained on various datasets constructed by combining clinical, CT, and radiomic features extracted from CT image regions of interest (ROIs), with and without feature preselection. Results: The model trained exclusively on the most relevant clinical, CT, and radiomic features demonstrated superior predictive performance compared to the other models, with strong discrimination between EGFR-mutant and wild-type cases (AUC = 0.88; macro-average = 0.90; micro-average = 0.89; precision = 0.90; recall = 0.94; F1-score = 0.91; and accuracy = 0.87). Conclusions: A nomogram constructed using a Random Forest model trained solely on the most informative clinical, CT, and radiomic features outperformed alternative approaches in the non-invasive prediction of the EGFR mutation status, offering a promising decision-support tool for precision treatment planning in NSCLC.


  • Open Access

    Quality of life and its determinants in patients with chronic respiratory diseases in the Fes-Meknes region, Morocco

    by Nassiba Bahra, Bouchra Amara, Hind Bourkhime, Soukaina El Yaagoubi, Nada Othmani, Nabil Tachfouti, Mohamed Berraho, Mounia Serraj, Mohamed Chakib Benjelloun, Samira El Fakir

    Chronic respiratory diseases (CRDs) pose a serious public health issue, affecting social functioning and psychological well-being and leading to a deterioration in the quality of life. The aim of this study was to assess the quality of life of patients with CRDs and determine the factors associated with their impairment in Morocco. A cross-sectional study was conducted in the Pulmonology Department of the Hassan II University Hospital in Fez in 2021. Data collection was carried out using an anonymous questionnaire containing sociodemographic, clinical, and therapeutic information. We employed the Moroccan version of the 12-item short-form (SF-12) scale to assess the mental and physical quality of life of patients. Bivariate analysis was performed to investigate the association between various factors and quality of life, using tests appropriate to the types of variables studied. Subsequently, multivariate analysis through multiple linear regression was employed to determine factors associated with quality of life, taking into account confounding factors. The threshold for inclusion in the model was set at 20%. Significant associations are presented as β values along with their 95% confidence intervals (CI). Our study included 209 patients, with 50.7% being female and 74.2% aged over 50 years. The most frequent clinical symptom was coughing. The average physical quality of life was estimated at 34.45±13.78, and the mental quality of life was 33.72±19.79. Multivariate analysis revealed that the deterioration of physical quality of life was associated with marital status (single) [β=-6.84; 95% CI (-11.43; -2.25); p=0.004], stage II dyspnea on the Modified Medical Research Council scale [β=-4.94; 95% CI (-9.41; -0.52); p=0.029], and the presence of cyanosis [β=-9.65; 95% CI (-15.64; -3.67); p=0.002]. The factors negatively associated with mental health in our patients were age ≥50 [β=-7.84; 95% CI (-15.05; -0.62); p=0.033], marital status (single) [β=-7.81; 95% CI (-15.14; -0.48); p=0.037], and presence of cyanosis [β=-10.70; 95% CI (-20.08; -1.32); p=0.026]. The SF-12 calculation reflected an impairment in the quality of life of patients with CRDs. It is imperative to integrate the assessment of quality of life into the management strategy for this pathology.


  • Open Access

    Unexpected pulmonary tumor: metastasis from a benign uterine leiomyoma in a post-menopausal woman: a case report

    by Boubacar Efared, Gabrielle Atsame-Ebang, Rabiou Sani, Layla Tahiri, Ibrahim Sory Sidibe, Fatimazahra Erregad, Nawal Hammas, Mohamed Smahi, Mounia Serraj, Laila Chbani, et al.

    The occurrence of lung metastasis from benign uterine leiomyomas is rarely reported especially in post menopausal women. The pathogenesis of these metastatic benign tumors still remains a subject of various speculations. A 57-year-old woman presented with a chronic cough and dyspnea. She had undergone 8 years previously, hysterectomy for benign leiomyomas. A chest computed tomography scan showed a 4 cm solitary nodular parenchymal tumor that increased in size after 12 months. The histological analysis of the biopsy from this nodule showed a benign tumor with regular spindle cells disposed in intersected fascicles. At immunohistochemical analysis, the tumor cells were positive for smooth muscle markers and oestrogen-progesterone receptors with a low mitotic index assessed by Ki-67. These features were consistent with a benign metastasizing uterine leiomyoma. At the multidisciplinary meeting, prescription of an aromatase inhibitor has been decided for the patient. Benign metastasizing uterine leiomyomas of the lung are very rare tumors. Although extremely rare in post menopausal women, their diagnosis should be considered in symptomatic patients with a history of hysterectomy for leiomyomas.


  • Open Access

    The diagnostic value of the bronchoalveolar lavage in interstitial lung diseases

    by Boubacar Efared, G. Ebang-Atsame, Sani Rabiou, Abdoulsalam S. Diarra, Layla Tahiri, Nawal Hammas, Mohamed Smahi, Bouchra Amara, Mohamed C. Benjelloun, Mounia Serraj, et al.

    Bronchoalveolar lavage (BAL) is a diagnostic tool often used during the management of interstitial lung diseases (ILD). However, its diagnostic value in discrimination between entities comprising the very heterogenous group of ILD, is still a controversial issue. The objective of our study is to assess the diagnostic value of BAL in the management of ILD, by comparing the cytological findings in BAL fluid among the different diseases of this group. It was a retrospective, observational study of 151 patients between January 2012 and December 2015. BAL fluid cytology was performed to analyse the distribution of leucocytes population subsets in patients with ILD. The mean age was 52.78 years; 74.83% were women. The analysis of the following main groups of diseases was performed : sarcoïdosis (n = 30), idiopathic pulmonary fibrosis (IPF; n = 22), other idiopathic interstitial pneumonia (non specific interstitial pneumonia, cryptogenic organising pneumonia and respiratory bronchiolitis interstitial lung disease; n = 20) and connective tissue disease (n = 14). Overall, out of 141 patients, 22% had sarcoïdosis, 15.6% had idiopathic pulmonary fibrosis (IPF), 14.18% had other idiopathic interstitial pneumonia (IIP) and 9.9% had connective tissue disease (CTD). Mixed alveolitis was common in the 4 groups, sarcoïdosis had higher proportion of lymphocytes and IPF had higher neutrophils count. However, there was no significant statistical difference of BAL cellular count among these diseases (p > 0.05). Also, the prevalence of studied diseases did not change with variation of BAL cellular count (p > 0.05). Alone, the BAL cytological analysis has a limited value to provide substantial information that could lead to discriminate between diseases that form ILD. Thus, it must be always associated with other diagnostic methods.