Hanene Boussi Rahmouni

Background: The development of osteoarthritis (OA), a whole-joint disorder that is increasingly recognized, depends on subchondral trabecular bone. Variations in the viscoelastic characteristics of trabecular bone have been proposed to affect load distribution and potentially lead to joint degradation. The viscoelastic response of human trabecular bone in both healthy and osteoarthritic situations was investigated using constitutive modeling and stress-relaxation testing. Fifteen tibial trabecular bone specimens were evaluated using Standard Linear Solid (SLS) models and two-branch generalized Maxwell models following uniaxial stress-relaxation testing. Mechanical, energy, and relaxation-related traits were retrieved and compared between groups. Results: Healthy bone tended to relax stress more slowly and to bear mechanical loads over time to a slightly greater extent than osteoarthritic bone, which tended to relax stress more quickly and had poorer mechanical endurance; these differences were not statistically significant. The Generalized Maxwell model suited the experimental data better than the SLS model (R² > 0.98), capturing both short- and long-term relaxation mechanisms. Sensitivity analysis revealed higher parameter variability in OA specimens, suggesting possible differences in mechanical heterogeneity and load-dissipation behavior that require further investigation. Conclusions: Although the observed differences were not statistically significant in this exploratory study, the results suggest potential trends toward altered viscoelastic behavior between healthy and osteoarthritic trabecular bone. Future studies with larger cohorts are needed to further investigate osteoarthritis-related biomechanical alterations. Multi-branch viscoelastic modeling may provide sensitive mechanical descriptors for characterizing the relaxation behavior of subchondral bone.

1. Quantitative linguistics characterizes language structure through mathematical laws, most notably Zipf’s law and related scaling phenomena (Piantadosi, 2014). However, beyond static frequency di...

Background: Lung cancer causes more deaths than any other malignancy worldwide, accounting for 2.2 million new cases and 1.8 million deaths in 2020. Extracting structured clinical knowledge from unstructured French-language oncology records remains methodologically unresolved in Tunisian and Francophone healthcare systems, where validated natural language processing tools do not yet exist. This study examined the effectiveness of transformer-based named-entity recognition for automated clinical annotation of Tunisian lung cancer reports. Aim: The study aimed to (i) establish performance baselines for four transformer-based models on a publicly available thoracic radiology dataset, (ii) evaluate five models, including a French biomedical specialist, on a newly constructed Tunisian clinical corpus, and (iii) demonstrate prototype deployment feasibility for structured clinical decision support. Methods: An initial comparative study evaluated BERT, RoBERTa, BioClinicalBERT, and CamemBERT using the official RadGraph dataset partitions, which natively comprise a total of 600 annotated thoracic radiology reports distributed across a standardized 80/10/10 split. Subsequently, five models were evaluated on 200 manually annotated diagnostic reports from Mami Pneumo-Phthisiology Hospital, Tunis. For the Tunisian corpus, a five-fold cross-validation approach was implemented to ensure robust performance estimation, followed by final evaluation on a dedicated hold-out test set. All models were trained for a maximum of 10 epochs, with a learning rate of 5 × 10⁻⁵ and a batch size of 16. Results: Based on the initial comparative study on the RadGraph dataset, where RoBERTa was the top performer and achieved the highest F1-score of 0.873 (precision: 0.869, recall: 0.877), we evaluated its specialized biomedical variant, DR-BERT, on our Tunisian clinical dataset. DR-BERT demonstrated strong generalization on the hold-out test set with an F1-score of 0.824, outperforming the baseline RoBERTa (test F1: 0.791) and showing competitive performance relative to multilingual BERT (0.843 ± 0.005 in five-fold cross-validation). A prototype interface generated structured clinical summaries encompassing prior conditions, imaging modalities, and TNM staging. Conclusion: Language- and domain-adapted transformer models effectively extract structured clinical entities from French-language Tunisian lung cancer reports. DR-BERT’s superior generalization on unseen data confirms that biomedical pretraining in the target language is a key driver of robust performance in specialized French oncology text. This work establishes foundational infrastructure for NLP-driven oncology data management in Tunisia and comparable Francophone settings.

Background: Nuclear medicine healthcare professionals (NMHP) sustain chronic occupational exposure to iodine-131 (I-131), conferring an elevated risk of radiation-induced solid thyroid cancer. Established radiobiological prediction tools derive risk coefficients from atomic bomb survivor data but are not configured for rapid individualized risk assessment in occupational exposure settings. This study examined whether machine learning algorithms can serve as high-precision computational surrogates for excess relative risk estimation in NMHP. Aim: The study aimed to (i) develop and validate three machine learning algorithms for predicting the excess relative risk per unit absorbed dose for radiation-induced solid thyroid cancer (ERR/Gy.RST), (ii) characterize relationships between dosimetric and demographic features and predicted risk, and (iii) identify the optimal algorithm for deployment in occupational health surveillance. Methods: A dataset of 4657 observations was constructed from Life Span Study-derived ERR/Gy parameters, adapted to occupational low-dose conditions, using a dose-and-dose-rate effectiveness factor of 2.0, per ICRP Publication 103. Five features (gender, age at exposure, current age, distance from the I-131 source, and cumulative absorbed dose in the thyroid) were used to train a decision tree regressor (dtcr), a random forest regressor (rfr), and a multilayer perceptron (MLP) neural network algorithm. Results: Cumulative absorbed dose in the thyroid correlated positively with ERR/Gy.RST (r = 0.63, p < 0.01), while radiation source distance demonstrated a strong inverse association (r = −0.38, p < 0.01). The MLP algorithm achieved R² score = 0.999, MSE = 0.002, and MAE = 0.010, substantially outperforming the rfr (R² score = 0.700, MSE = 0.410, MAE = 0.295) and the dtcr (R² score = 0.510, MSE = 0.654, MAE = 0.289). Conclusions: The MLP algorithm provides a high-fidelity surrogate for established ERR/Gy.RST projection tools in the NMHP context, enabling computationally efficient, feature-integrated occupational radiation-induced thyroid cancer risk quantification. These findings suggest that machine learning-based surrogate modeling is a practical, scalable complement for occupational health practitioners and radiation protection officers to support individualized surveillance of radiation-induced thyroid cancer risk in nuclear medicine departments.

Background: Lung cancer causes more deaths than any other malignancy worldwide, accounting for 2.2 million new cases and 1.8 million deaths in 2020. Extracting structured clinical knowledge from unstructured French-language oncology records remains methodologically unresolved in Tunisian and Francophone healthcare systems, where validated natural language processing tools do not yet exist. This study examined the effectiveness of transformer-based named entity recognition for automated clinical annotation of Tunisian lung cancer reports. Aim: The study aimed to (i) benchmark four transformer-based models on a publicly available thoracic radiology dataset, (ii) evaluate five models, including a French biomedical specialist, on a newly constructed Tunisian clinical corpus, and (iii) demonstrate prototype deployment feasibility for structured clinical decision support. Methods: A benchmarking study evaluated BERT, RoBERTa, BioClinicalBERT, and CamemBERT on the RadGraph dataset (600 annotated thoracic radiology reports). Five models were subsequently fine-tuned on 200 manually annotated initial diagnostic reports from Mami Pneumo-Phthisiology Hospital, Tunis. All models were trained for a maximum of 10 epochs, with a learning rate of 5x10-5, a batch size of 16, and an 80/10/10 train-validation-test split, and evaluated using precision, recall, and F1-score. Results: On RadGraph, RoBERTa achieved the highest F1-score of 0.873 (precision: 0.869, recall: 0.877), followed by BioClinicalBERT (F1: 0.868) and BERT (F1: 0.857). CamemBERT achieved an F1 score of 0.682 on this English dataset. On the Tunisian corpus, DrBERT outperformed all models with an F1-score of 0.811, compared to RoBERTa at 0.79. A prototype interface generated structured clinical summaries encompassing prior conditions, imaging modalities, and TNM staging. Conclusion: Language- and domain-adapted transformer models effectively extract structured clinical entities from French-language Tunisian lung cancer reports. DrBERT's precision advantage confirms that biomedical pretraining in the target language is the primary driver of performance in specialized French oncology text. This work establishes foundational infrastructure for NLP-driven oncology data management in Tunisia and comparable Francophone settings.

Background and objectives: Articular cartilage provides low-friction articulation across joint surfaces, distributes loads, and absorbs stress, all of which are crucial mechanical functions of joints. Changes in the mechanical characteristics of cartilage are among the first signs of degenerative joint disease, and they are especially important for athletes who are subjected to high-impact, high-magnitude loading on a regular basis. The objective of this study was to: (i) compare the mechanical characteristics of tibiofemoral cartilage in healthy and osteoarthritic conditions across medial and lateral anatomical compartments; and (ii) use nonlinear phenomenological viscoelastic modeling in conjunction with unconfined compression testing to characterize compartment-specific viscoelastic behavior. Materials and Methods: Forty-six human tibiofemoral cartilage samples were collected during knee surgeries and classified as healthy (n = 17) or osteoarthritic (n = 29) and as medial (n = 26) or lateral (n = 20). Quasi-static unconfined compression tests were performed at 1 mm/min to obtain stress–strain responses, Young’s modulus, maximum compressive stress, and energy absorption. Viscoelastic behavior was analyzed using a nonlinear phenomenological viscoelastic model. Appropriate parametric or non-parametric statistical tests and effect size measures were applied. Results: Osteoarthritic cartilage’s stiffness and energy absorption were significantly higher than those of healthy tissue (p < 0.05). Medial cartilage exhibited significantly greater stiffness and stress than lateral cartilage (p < 0.001). The nonlinear phenomenological viscoelastic model provided an excellent fit (R² > 0.999). Conclusions: The mechanical profile of osteoarthritic tibiofemoral cartilage is characterized by pathological mechanical remodeling and increased stiffness. Greater mechanical susceptibility in the medial compartment supports the significance of cartilage biomechanical properties as sensitive indicators of early degeneration and osteoarthritis risk in athletic populations.

Background: Hearing loss affects over 466 million individuals globally and is recognized as a major risk factor for Alzheimer’s disease, yet treatment personalization remains limited due to the complexity and diversity of underlying causes. Current diagnostic and therapeutic approaches lack standardized methods to accurately predict the most appropriate intervention for individual patients. The integration of medical ontologies with machine learning offers a promising solution for enhancing diagnostic accuracy and treatment personalization. Aim: Our study aimed to (i) develop a Systematized Nomenclature of Medicine—Clinical Terms (SNOMED CT)-aligned clinical ontology for hearing loss using Semantic Web Rule Language for automated reasoning; (ii) implement a Random Forest classifier trained on ontology-enriched patient data to classify hearing loss types (conductive, sensorineural, mixed, or normal); and (iii) predict optimal personalized treatments based on laterality, severity, audiometric thresholds, and medical history using real-world patient data. Methods: We developed a task ontology using Protégé 5.6.3 with Web Ontology Language (OWL), integrated SNOMED CT terminology alignment, and implemented Semantic Web Rule Language rules executed by the Pellet 2.2.0 reasoner. The framework was trained and evaluated on 3723 adult patients from the 2015–2016 National Health and Nutrition Examination Survey (NHANES) dataset with complete audiometric and clinical data. Random Forest models were developed using an 80–20 train-test split with stratified sampling and five-fold cross-validation. Performance was compared between K-Means clustering-based labeling and ontology-based semantic inference using accuracy, precision, recall, F1-score, and log loss metrics. Results: The ontology successfully generated semantic labels for all 3723 patients, enabling precise classification of hearing loss types, severity levels, and laterality. The Random Forest model with K-Means clustering achieved a test accuracy of 90.2% with a log loss of 0.2766 and a cross-validation mean accuracy of 91.22% (standard deviation 1.2%). Integration of ontology-based semantic enrichment significantly improved performance, achieving a test accuracy of 92.48% with a cross-validation mean accuracy of 92.80% (standard deviation 0.9%). F1-scores improved across all classes, with mixed hearing loss showing a notable increase from 0.86 to 0.92. Feature importance analysis identified audiometric thresholds, ontology-derived severity labels, and medical history as top predictors, enhancing clinical interpretability. Conclusions: This study demonstrates that combining SNOMED CT-aligned ontology with Random Forest classification achieves superior diagnostic accuracy and enables personalized treatment recommendations for hearing loss. The hybrid framework provides clinically interpretable decision support while ensuring semantic interoperability with electronic health records. Multi-institutional validation studies are necessary to assess generalizability across diverse populations before clinical deployment.

Background: Hearing loss affects over 466 million individuals globally and is recognized as a major risk factor for Alzheimer's disease, yet treatment personalization remains limited due to the complexity and diversity of underlying causes. Current diagnostic and therapeutic approaches lack standardized methods to accurately predict the most appropriate intervention for individual patients. The integration of medical ontologies with machine learning offers a promising solution for enhancing diagnostic accuracy and treatment personalization. Aim: Our study aimed to (i) develop a SNOMED CT-aligned clinical ontology for hearing loss using Semantic Web Rule Language for automated reasoning; (ii) implement a Random Forest classifier trained on ontology-enriched patient data to classify hearing loss types (conductive, sensorineural, mixed, or normal); and (iii) predict optimal personalized treatments based on laterality, severity, audiometric thresholds, and medical history using real-world patient data. Methods: We developed a task ontology using Protégé 5.6.3 with Web Ontology Language, integrated SNOMED CT terminology alignment, and implemented Semantic Web Rule Language rules executed by Pellet 2.2.0 reasoner. The framework was trained and evaluated on 3,723 adult patients from the 2015-2016 National Health and Nutrition Examination Survey dataset with complete audiometric and clinical data. Random Forest models were developed using an 80-20 train-test split with stratified sampling and five-fold cross-validation. Performance was compared between K-Means clustering-based labeling and ontology-based semantic inference using accuracy, precision, recall, F1-score, and log loss metrics. Results: The ontology successfully generated semantic labels for all 3,723 patients, enabling precise classification of hearing loss types, severity levels, and laterality. The Random Forest model with K-Means clustering achieved test accuracy of 90.2% with log loss of 0.2766 and cross-validation mean accuracy of 91.22% (standard deviation 1.2%). Integration of ontology-based semantic enrichment significantly improved performance, achieving test accuracy of 92.48% with cross-validation mean accuracy of 92.80% (standard deviation 0.9%). F1-scores improved across all classes, with mixed hearing loss showing notable increase from 0.86 to 0.92. Feature importance analysis identified audiometric thresholds, ontology-derived severity labels, and medical history as top predictors, enhancing clinical interpretability. Conclusion: This study demonstrates that combining SNOMED CT-aligned ontology with Random Forest classification achieves superior diagnostic accuracy and enables personalized treatment recommendations for hearing loss. The hybrid framework provides clinically interpretable decision support while ensuring semantic interoperability with electronic health records. Multi-institutional validation studies are necessary to assess generalizability across diverse populations before clinical deployment.

Background: Anatomopathological reports are largely unstructured, which limits automated data extraction, interoperability, and large-scale research. Manual extraction and standardization are costly and difficult to scale. Objective: We developed and evaluated an automated pipeline for entity extraction and multi-ontology normalization of anatomopathological reports. Methods: A corpus of 560 reports from the Military Hospital of Tunis, Tunisia, was manually annotated for three entity types: sample type, test performed, and finding. The entity extraction utilized BioBERT v1.1, while the normalization combined BioClinicalBERT multi-label classification with retrieval-augmented generation, incorporating both dense and BM25 sparse retrieval over SNOMED CT, LOINC, and ICD-11. The performance was measured using precision, recall, F1-score, and statistical tests. Results: BioBERT achieved high extraction performance (F1: 0.97 for the sample type, 0.98 for the test performed, and 0.93 for the finding; overall 0.963, 95% CI: 0.933–0.982), with low absolute errors. For terminology mapping, the combination of BioClinicalBERT and dense retrieval outperformed the standalone and BM25-based approaches (macro-F1: 0.6159 for SNOMED CT, 0.9294 for LOINC, and 0.7201 for ICD-11). Cohen’s Kappa ranged from 0.7829 to 0.9773, indicating substantial to near-perfect agreement. Conclusions: The pipeline provides robust automated extraction and multi-ontology coding of anatomopathological entities, supporting transformer-based named entity recognition with retrieval-augmented generation. However, given the limitations of this study, multi-institutional validation is needed before clinical deployment.