The adulteration of sesame oil poses significant challenges for public health, food safety, and environmental sustainability, requiring advanced analytical and decision-making tools for detection. This study presents an integrated framework combining Fourier Transform Infrared (FTIR) spectroscopy, δ13C isotope ratio mass spectrometry, and artificial intelligence within an environmental engineering perspective. FTIR spectra were processed using an unsupervised deep autoencoder, producing a Spectral Deviation Index (SDI) with excellent discriminatory power (AUC = 1.00). In parallel, a Box-Behnken design quantified δ13C isotopic responses, while machine learning models, including Random Forest (R2 = 0.93) and symbolic regression, accurately predicted adulteration patterns even at low levels. Symbolic regression provided interpretable equations supporting traceability and quantitative decision-making. The hybrid methodology is rapid, non-destructive, and automatable, offering a scalable pathway for sustainable food quality control and environmental monitoring.
This study applies quantitative decision-making and numerical modeling to analyze interactions between dietary behavior, obesity, and perceived stress among 1,036 students at Ibn Tofail University, Morocco. Using binary and multinomial logistic regression models, key determinants were identified for adopting a balanced diet, developing obesity, and experiencing high stress. Age, home-prepared meals, and health awareness increased the likelihood of a balanced diet, whereas sugary drinks and long engagement time reduced it. Regular physical activity and better nutritional knowledge lowered obesity risk, while prolonged daily engagement increased it. Obesity strongly predicted high perceived stress, supported by an E-value of 6.075, indicating robust associations. These findings highlight the relevance of numerical analysis in understanding student health dynamics and support evidence-based decision-making for targeted university health interventions.
Antimicrobial resistance (AMR) poses a major global health challenge driven by behavioral, clinical, and environmental factors within the One Health continuum. This chapter examines antibiotic-related behaviors among patients and prescribing practices among physicians at Azzamouri Provincial Hospital in Kenitra, Morocco, revealing limited knowledge, frequent self-medication, and structural barriers that contribute to irrational antibiotic use. It also highlights socioeconomic constraints, cognitive biases, and clinical pressures such as diagnostic uncertainty that influence inappropriate prescribing. The chapter explores the potential of scientifically supported herbal medicine, rooted in Morocco's ethnopharmacological heritage, as a culturally accepted complementary approach for managing mild infections and reducing unnecessary antimicrobial exposure.Integrating behavioral insights, stronger stewardship, and validated phytotherapy, it proposes an integrated One Health model to improve public awareness, support rational prescribing, and promote sustainable strategies to mitigate AMR.
This chapter presents an explainable artificial intelligence framework for detecting trace-level adulteration in sesame oil using Fourier Transform Infrared spectroscopy. Due to its high economic value, sesame oil is often adulterated with cheaper oils or paraffin, creating significant challenges for reliable detection. The proposed approach integrates multivariate spectral analysis with machine learning techniques to improve both predictive performance and model interpretability. Principal Component Analysis and Partial Least Squares Discriminant Analysis are used for spectral exploration, while XGBoost identifies key discriminatory infrared bands. Symbolic regression generates explicit mathematical equations describing adulteration patterns, and a one-dimensional convolutional neural network with self-attention extracts complex spectral features for classification tasks. The results demonstrate high sensitivity in fraud detection and reliable identification of adulterant types, highlighting the potential of combining spectroscopy and explainable AI for food authenticity assessment.
This chapter critically examines the assumption of algorithmic neutrality in healthcare artificial intelligence (AI). Although AI is often promoted as a driver of accuracy, efficiency, and equity, evidence shows that it can reinforce disparities through biases in data, model design, and implementation. Based on a review of biomedical, computational, and policy literature from 2017 to 2025, the chapter highlights how underrepresentation of marginalized populations, limited validation across contexts, opaque algorithms, and weak stakeholder engagement contribute to inequitable outcomes. It argues that technical bias mitigation alone is insufficient without addressing structural inequalities. Emphasis is placed on participatory and justice-oriented frameworks, transparent audits, accountable governance, and inclusive design. Embedding equity and accountability across the AI lifecycle is presented as essential for ensuring digital innovation advances health justice.
This chapter explores eating disorders among students in Moroccan higher education as a growing public health concern linked to healthcare reform, digital transformation, and leadership in health policy. Based on a cross-sectional study at the Higher Institute of Nursing and Health Techniques (ISPITS) of Kenitra, a synthetic Eating Disorder Risk Score (EDRS) was validated, revealing social pressure and body dissatisfaction as key predictors, with academic stress as a mediating factor. The chapter discusses the economic burden of untreated disorders—productivity loss, absenteeism, and academic dropout—and highlights the need for preventive, cost-effective strategies. It advocates for integrating mental health and nutrition into national health reform through innovative “phygital” approaches that combine digital awareness, institutional counseling, and social marketing. Finally, it underscores the importance of academic leadership in advancing inclusive, evidence-based, and sustainable student health reform in the digital age.