DOI: 10.3897/jbcr.e182990

Authors: Supriya Khade, Mohini Mahatme, Neha Meshram, Vikram Bobade

Abstract: Introduction: Artificial Intelligence (AI) has the potential to transform healthcare in various ways. It can turn large amounts of patient data into actionable information, improve public health surveillance, accelerate health responses & produce faster & more targeted research & development. In context of developing countries, the potential of AI in public health needs to be assessed. This study enables a comprehensive exploration of clinicians' views, aiming to identify actionable insights for addressing barriers to AI implementation in healthcare systems.Methodology: It is a cross-sectional study in which a pre-validated questionnaire developed. A purposive sample of 94 clinicians from various specialities taken in the study. Data is collected using a structured questionnaire designed after an extensive literature review & expert consultation. Data were analyzed using the appropriate statistical test.Results: The study identified key challenges hindering AI adoption in healthcare, based on responses from 94 clinicians. The primary barriers include insufficient infrastructure (68.5%), lack of AI-specific training (44.7%) & limited collaboration between healthcare sectors (63.8%). Clinicians' skepticism (58%) about AI’s decision-making accuracy and ethical concerns regarding patient data security (74.5%) were significant obstacles. Fragmented healthcare data systems (70%) further hindered the effective AI integration.Conclusion: While AI has substantial potential to enhance healthcare delivery, particularly in optimizing operations and personalizing treatment, addressing these challenges through comprehensive strategies involving ethical frameworks, robust data management & stakeholder engagement is crucial for successful implementation & acceptance of AI technologies in clinical practice.

HTML

PDF

DOI: 10.3897/jbcr.e142717

Authors: Fagbohun Oyenike Bushirat, Hassan Abdusalam Adewuyi, Sakariyau Waheed Adio, Maryam Nana Musa, Timothy God-Giveth Olusegun, Ayomide Babatunde Ishola, Agumage Idoko, Adeola Victor Kolawole, Adesanmi Adefunmilayo Oluwatuyi, Sarah Ngozi Agwasim

Abstract: Adansonia digitata and Annona muricata are traditionally used medicinal plants with reported pharmacological properties. In this study, we aimed to elucidate the phytochemical composition, antioxidant activity, and antibacterial properties of partition fractions of Adansonia digitata and Annona muricata extracts obtained using chloroform, ethyl acetate, ethanol, and aqueous solvent systems. The plant extracts were successively partitioned using chloroform, ethyl acetate, ethanol, and aqueous solvent systems. Phytochemical analysis was performed using standard methods. Antioxidant activity was evaluated using FRAP and DPPH assays. Antibacterial activity was assessed using agar well diffusion and MIC determination. Phytochemical analysis revealed the presence of alkaloids (10.2-15.6%), flavonoids (8.5-12.1%), and phenolic acids (5.6-9.2%) in all fractions. The ethyl acetate fraction of Annona muricata exhibited the highest antioxidant activity (IC50 = 20.5 μg/mL) in the DPPH assay, while the chloroform fraction of Adansonia digitata showed significant antioxidant activity (IC50 = 35.2 μg/mL) in the FRAP assay. The antibacterial evaluation demonstrated that the chloroform fraction of Adansonia digitata exhibited broad-spectrum antibacterial activity (MIC = 0.5-1.5 mg/mL) against Staphylococcus aureus, Escherichia coli, and Pseudomonas aeruginosa, whereas the ethyl acetate fraction of Annona muricata showed potent antibacterial activity (MIC = 0.25-1.0 mg/mL) against Gram-negative bacteria. Additionally, the ethanol fraction of Adansonia digitata displayed moderate antibacterial activity (MIC = 1.0-2.5 mg/mL) against Gram-positive bacteria, and the aqueous fraction of Annona muricata exhibited weak antibacterial activity (MIC = 2.5-5.0 mg/mL) against all tested bacterial strains. Comparison of antioxidant and antibacterial activities among fractions revealed significant variations, indicating the importance of solvent selection in extracting bioactive compounds. The study validates the traditional use of Adansonia digitata and Annona muricata, highlighting their potential as natural antioxidants and antibacterial agents.

HTML

PDF

DOI: 10.3897/jbcr.e144006

Authors: Georgi Danielov Prandzhev, Grigor Angelov Gortchev, Dobromir Dimitrov Dimitrov, Radoslav Iliev Miltchev, Dimitar Rangelov, Slavcho Tomov Tomov

Abstract: Cervical cancer remains a leading cause of morbidity and mortality among women worldwide, particularly in regions with limited access to advanced medical care. Accurate and timely diagnosis of precancerous changes in the cervix is critical for effective prevention and treatment. This study introduces a deep learning algorithm for colposcopic analysis of the transformation zone of the uterine cervix. Intel & MobileODT Cervical Cancer Screening competition provided a comprehensive dataset designed to advance the application of artificial intelligence (AI) in classifying transformation zones (TZ) of the cervix, a key site where precancerous changes develop due to Human Papillomavirus (HPV) infection. This study highlights the significance of TZ classification for targeted biopsy during colposcopy, a gold-standard diagnostic method. However, challenges such as clinician’s subjectivity and interobserver variability, false negatives and positives interpretations limited accessibility, and resource intensity have spurred the integration of AI into colposcopic evaluations. The dataset comprises diverse cervical images, categorized into three types of TZs, enabling the development of AI models to distinguish between these categories. By leveraging deep learning algorithms, AI has demonstrated potential in enhancing the sensitivity and specificity of colposcopic findings while mitigating subjectivity and observer dependency. This abstract outlines the anatomical basis of cervical pathology, the critical role of colposcopy in diagnosing transformation zone abnormalities, and the transformative potential of AI in improving cervical cancer screening processes. The integration of AI-assisted tools could significantly improve diagnostic accuracy, reduce invasive procedures, and enhance access to cervical cancer prevention measures, particularly in underserved regions.

HTML

PDF