We conducted a 5-month-long screening of Anaplasma spp. and Anaplasma ovis infection in sheep from central Tunisia. During this longitudinal study, we investigated the infection dynamics using both direct and indirect assessments validated with a polymerase chain reaction (PCR) as the gold standard method. The experimental design included 84 male lambs aged from 6 to 8 months, and 32 ewes, both chosen randomly from June to November with a periodicity of 2 weeks approximately between June and September, and 1 month between September and November. A total of 9 field visits were carried out in this period during which animals were clinically examined and biological samples were extracted. Thus, a total of 716 blood smears, 698 sera from the nine sampling dates, as well as 220 blood samples from the first and the ninth sampling dates were collected from apparently healthy lambs and ewes, respectively, and analyzed by competitive enzyme-linked immunosorbent assay (cELISA) and polymerase chain reaction (PCR) assay, for the detection of Anaplasma antibodies and A. ovis DNA, respectively. Sera were analyzed by competitive enzyme-linked immunosorbent assay (cELISA) and PCR, for the detection of Anaplasma antibodies and A. ovis DNA, respectively. The Anaplasma spp. initial seroprevalence rate was 33.3% in lambs and 100% in ewes, and it then flowed in an upward trend to reach a maximum of 52.6% in lambs, whereas in ewes, the Anaplasma spp. seroprevalence rate remained unchanged and equal to 100%. Meanwhile, the A. ovis initial molecular prevalence was 22.6% at the first visit and 26.3% at the last visit in lambs, whereas in ewes, the molecular prevalence rates of A. ovis were higher in both the first and the last visit estimated at 100% and 85.7%, respectively. The Kappa coefficient between cELISA and PCR indicated a moderate level of agreement on the first sampling date (0.67) and a low agreement level on the last (0.43). Furthermore, an exploratory data analysis using a multimodal machine learning approach highlighted the underlying pattern of each analytical technique used in this study. In this prospect, we were able to establish the performance of each technique at detecting Anaplasma spp. in sheep. The combination of these approaches should improve the field assessment while promoting a data-based decision in precision epidemiology. The genetic follow-up test relevant to A. ovis msp4 sequences revealed three different genotypes, two of which were previously described in Italy.

Hematology plays a critical role in diagnosing and managing a wide range of blood-related disorders. The manual interpretation of blood smear images, however, is time-consuming and highly dependent on expert availability. Moreover, it is particularly challenging in remote and resource-limited settings. In this study, we present an AI-driven system for automated blood cell anomaly detection, combining computer vision and machine learning models to support efficient diagnostics in hematology and telehealth contexts. Our architecture integrates segmentation (YOLOv11), classification (ResNet50), transfer learning, and zero-shot learning to identify and categorize cell types and abnormalities from blood smear images. Evaluated on real annotated samples, the system achieved high performance, with a precision of 0.98, recall of 0.99, and F1 score of 0.98. These results highlight the potential of the proposed system to enhance remote diagnostic capabilities and support clinical decision making in underserved regions.

Antibiotics are frequently used in the poultry industry, which has led to the emergence of bacterial strains that are resistant to antimicrobial treatments. The main objectives of this research were to conduct a multimodal risk assessment, to determine the extent of contamination of chicken meat with Escherichia coli, assess the prevalence of strains resistant to extended-spectrum cephalosporins (ESC), and characterise the genes associated with resistance and virulence. A standardised procedure involving enrichment in buffered peptone water and isolation of E. coli on MacConkey agar was carried out on 100 chicken carcasses. Subsequently, the sensitivity of the strains was tested against 21 antibiotic discs. Additionally, ESBL production was detected using a double synergy test. Specific PCRs were employed to identify resistance to critical antibiotics in human medicine (such as cephalosporins, carbapenems, fluoroquinolones, and colistin), as well as the presence of virulence genes. The contamination rate of chicken meat with E. coli was 82%. The prevalence of ESC-resistant isolates was 91.2%. Furthermore, 76.5% of the isolates exhibited ESBL production, with the different beta-lactamase genes (bla_CTXM, bla_TEM, and bla_SHV). The mcr-1 gene, associated with colistin resistance, was detected in four strains (5.9%). Some isolates also carried resistance genes such as sul1, sul2, sul3, tetA, tetB, qnrB, and qnrS. In addition, several virulence genes were detected. In our study, we were able to link the expression of AMR to the iron metabolic regulatory elements using a multimodal machine learning approach; this mechanism could be targeted to mitigate the bacteria virulence and resistance. The high prevalence of ESBL-producing and multi-resistant E. coli strains in poultry presents significant human health risks, with the focus on antibiotic-resistant uropathogenic strains since poultry meat could be an important source of uropathogenic strains, underscoring the danger of hard-to-treat urinary tract infections, stressing the need for controlled antibiotic use and thorough monitoring.