Pan-drug-resistant Acinetobacter baumannii (PDR-AB) causes severe infections and constitutes a threat in several geographic regions. Little is known about the differential effectiveness of last-resort regimens, frequently used in this setting. We compared the effectiveness of two literature-proposed regimens against PDR-AB infections consisting of colistin, ampicillin-sulbactam, and either meropenem (regimen A) or tigecycline (regimen B). This is a retrospective analysis of prospectively collected data from 12 centers on adult patients with hospital-acquired pneumonia (HAP) or bloodstream infection (BSI), who had received definitive treatment with either regimen A or regimen B. The primary outcome was clinical failure, defined as any of the following occurring by day 14 from infection onset: death, initiation of salvage treatment, treatment withdrawal due to toxicity, persistent bacteremia for BSI patients and failure to improve oxygenation for HAP patients before and after propensity matching. Eighty-three patients were included in the primary analysis; 60 had received regimen A and 23 regimen B. Regimen B was significantly associated with clinical failure before and after propensity matching (odds ratios [OR]: 3.11; 95% confidence interval [CI]: 1.10-8.84 vs OR: 3.83; 95% CI: 1.26-11.63), respectively. Salvage therapy and treatment discontinuation due to toxicity were more frequent in patients treated with regimen B. In multivariable analysis, regimen B was independently associated with 28-day mortality before (hazard ratio [HR]: 2.53; 95% CI: 1.08-5.94) but not after propensity matching (HR: 2.64; 95% CI: [0.99-7.02]). Treatment with colistin, ampicillin-sulbactam, and meropenem against severe PDR-AB infections was associated with favorable outcomes compared to colistin, ampicillin-sulbactam, and tigecycline.

Background: Pandrug-resistant (PDR) Acinetobacter baumannii represents a major therapeutic challenge in regions where carbapenem-resistant A. baumannii (CRAB) is endemic. Whether the PDR phenotype independently worsens clinical outcomes beyond the effects of disease severity and therapeutic limitations remains uncertain. This study compared the characteristics, management, and outcomes of severe infections caused by PDR and carbapenem-resistant, colistin-susceptible A. baumannii. Methods: We conducted a retrospective analysis of prospectively collected data across 11 tertiary-care hospitals in Greece (February 2022-June 2024). Consecutive adults with bloodstream infection or hospital-acquired/ventilator-associated pneumonia caused by CRAB or PDR A. baumannii were enrolled. The primary outcome was 14-day clinical failure; secondary outcomes included 28-day mortality, microbiological eradication, organ dysfunction, and organ-support-free days. Multivariable logistic and Cox regression analyses, before and after propensity score matching, were performed to adjust for confounding. Results: Among 142 patients, 91 (64%) had PDR and 51 (36%) had carbapenem-resistant, colistin-susceptible infections. Clinical failure occurred in 41% of patients and did not differ significantly between PDR and CRAB infections (39% vs. 45%; p = 0.440). Twenty-eight-day mortality was 33% and 22%, respectively (p = 0.139). After adjustment, the PDR phenotype was not independently associated with clinical failure or mortality. Higher APACHE II score and pneumonia independently predicted clinical failure, whereas sulbactam-containing therapy was associated with lower odds of failure (OR 0.24, 95% CI 0.07-0.79). Older age, higher SOFA score, impaired lactate clearance, and tigecycline-containing therapy independently predicted 28-day mortality. In matched analysis, PDR showed a non-significant upward trend in 28-day mortality (HR 2.36, 95% CI 0.97-5.76; p = 0.059). Conclusions: In severe A. baumannii infections, the PDR phenotype was not an independent determinant of clinical failure or short-term mortality. Patient severity and antimicrobial strategy were major outcome correlates; treatment associations should be interpreted cautiously given the observational design.

PURPOSE:To characterise the pharmacokinetics (PK) of ceftazidime-avibactam (CAZ-AVI) and explore the dynamics of a broad blood immune biomarker panel in critically ill patients with hospital-acquired (HAP) or ventilator-associated pneumonia (VAP) caused by Klebsiella pneumoniae. METHODS:Population PK (PopPK) models were developed for CAZ and AVI individually and jointly, evaluating covariate effects and correlations at interindividual (IIV) and residual unexplained variability (RUV) levels. Biomarker turnover dynamics in blood were modelled, and exposure-biomarker relationships were assessed. RESULTS:The dataset included 266 drug plasma concentration measurements and 48-87 observations per biomarker, collected from ten critically ill patients. CAZ and AVI PK were well-described by two-compartment models, with estimated creatinine clearance (eCrCL) as a key covariate on clearance. Joint modelling revealed significant correlations between the two drugs at both IIV and RUV levels, supporting coherent patient-specific simulations. Turnover dynamics were characterised for 32 biomarkers. The most pronounced biomarker changes over the course of treatment were decreases in IL6, CRP and AREG, and increases in DCBLD2, LAMP3 and TRIM21. A significant exposure-response relationship was identified between CAZ plasma concentrations and CRP turnover, with higher CAZ levels associated with inhibition of CRP production. CONCLUSIONS:The joint PopPK model confirmed eCrCL as a key covariate for clearance. Changes in 32 immune response biomarkers were quantified, with CRP showing a clear exposure-response relationship. These findings provide a foundation for prioritising biomarkers for future studies to guide therapeutic strategies in critically ill patients with HAP or VAP.

Background: Multiple Sclerosis (MS) is a chronic autoimmune disease of the central nervous system with a propensity to inflict severe neurological disability. Accurate and early prediction of MS progression is extremely crucial for its management and treatment. Methods: In this paper, we compare a number of self-labeled semi-supervised learning methods used to predict MS from labeled and unlabeled medical data. Specifically, we compare the performance of Self-Training, SETRED, Co-Training, Co-Training by Committee, Democratic Co-Learning, RASCO, RelRASCO, CoForest, and TriTraining in different labeled ratios. The data contain clinical, imaging, and demographic features, allowing for a detailed comparison of each method's predictive ability. Results and Conclusions: The experimental results demonstrate that several self-labeling semi-supervised learning (SSL) algorithms perform competitively in the task of Multiple Sclerosis (MS) prediction, even when trained on as little as 30-40% of the labeled data. Notably, Co-Training by Committee, CoForest, and TriTraining consistently deliver high performance across all metrics (accuracy, F1-score, and MCC).

Optical Coherence Tomography (OCT) has become an indispensable imaging modality in ophthalmology, providing high-resolution cross-sectional images of the retina. Accurate classification of OCT images is crucial for diagnosing retinal diseases such as Age-related Macular Degeneration (AMD) and Diabetic Macular Edema (DME). This study explores the efficacy of various deep learning models, including convolutional neural networks (CNNs) and Vision Transformers (ViTs), in classifying OCT images. We also investigate the impact of integrating metadata (patient age, sex, eye laterality, and year) into the classification process, even when a significant portion of metadata is missing. Our results demonstrate that multimodal models leveraging both image and metadata inputs, such as the Multimodal ResNet18, can achieve competitive performance compared to image-only models, such as DenseNet121. Notably, DenseNet121 and Multimodal ResNet18 achieved the highest accuracy of 95.16%, with DenseNet121 showing a slightly higher F1-score of 0.9313. The multimodal ViT-based model also demonstrated promising results, achieving an accuracy of 93.22%, indicating the potential of Vision Transformers (ViTs) in medical image analysis, especially for handling complex multimodal data.

Background: The global COVID-19 pandemic has significantly disrupted healthcare systems, inadvertently influencing the epidemiology of antimicrobial resistance (AMR). Among the most critical AMR threats are carbapenem-resistant organisms (CROs), which include carbapenem-resistant Enterobacterales, Acinetobacter baumannii, and Pseudomonas aeruginosa. This review explores the pandemic’s impact on carbapenem resistance patterns worldwide. Objectives: This study aimed to assess the effects of the COVID-19 pandemic on carbapenem resistance trends, identify key drivers, and discuss implications for clinical practice and public health policy. Methods: A comprehensive review of peer-reviewed literature, national surveillance reports, and WHO/ECDC data from 2019 to 2025 was conducted, with emphasis on hospital-acquired infections, antimicrobial use, and infection control practices during the pandemic. Results: The pandemic has led to increased use of broad-spectrum antibiotics, including carbapenems, often in the absence of confirmed bacterial co-infections. Overwhelmed healthcare systems and disruptions in infection prevention and control (IPC) measures have facilitated the spread of carbapenem-resistant organisms, particularly in intensive care settings. Surveillance data from multiple countries show a measurable increase in CRO prevalence during the pandemic period, with regional variations depending on healthcare capacity and stewardship infrastructure. Conclusions: COVID-19 has accelerated the emergence and dissemination of carbapenem resistance, underscoring the need for resilient antimicrobial stewardship and IPC programs even during public health emergencies. Integrating pandemic preparedness with AMR mitigation strategies is critical for preventing further escalation of resistance.

The effective management of Emergency Department (ED) overcrowding is essential for improving patient outcomes and optimizing healthcare resource allocation. This study validates hospital admission prediction models initially developed using a small local dataset from a Greek hospital by leveraging the comprehensive MIMIC-IV dataset. After preprocessing the MIMIC-IV data, five algorithms-Linear Discriminant Analysis (LDA), K-Nearest Neighbors (KNN), Random Forest (RF), Recursive Partitioning and Regression Trees (RPART), and Support Vector Machines (svmRadial)-were evaluated. Among these, RF demonstrated superior performance, achieving an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.9999, sensitivity of 0.9997, and specificity of 0.9999 when applied to the MIMIC-IV data. These findings underscore the robustness of RF in handling complex datasets for admission prediction, establishing MIMIC-IV as a valuable benchmark for validating models based on smaller local datasets and providing actionable insights for steering ED management strategies in the right direction.

Antibiotic resistance is a global health crisis exacerbated by the misuse of antibiotics in healthcare, agriculture, and the environment. In an intensive care unit (ICU), where high antibiotic usage, invasive procedures, and immunocompromised patients converge, resistance risks are amplified, leading to multidrug-resistant organisms (MDROs) and poor patient outcomes. The human microbiome plays a crucial role in the development and dissemination of antibiotic resistance genes (ARGs) through mechanisms like horizontal gene transfer, biofilm formation, and quorum sensing. Disruptions to the microbiome balance, or dysbiosis, further exacerbate resistance, particularly in high-risk ICU environments. This study explores microbiome interactions and antibiotic resistance in the ICU, highlighting machine learning (ML) as a transformative tool. Machine learning algorithms analyze high-dimensional microbiome data, predict resistance patterns, and identify novel therapeutic targets. By integrating genomic, microbiome, and clinical data, these models support personalized treatment strategies and enhance infection control measures. The results demonstrate the potential of machine learning to improve antibiotic stewardship and predict patient outcomes, emphasizing its utility in ICU-specific interventions. In conclusion, addressing antibiotic resistance in the ICU requires a multidisciplinary approach combining advanced computational methods, microbiome research, and clinical expertise. Enhanced surveillance, targeted interventions, and global collaboration are essential to mitigate antibiotic resistance and improve patient care.

Abstract Background Minocycline has made a comeback in the drug armamentarium as a treatment option for infections due to Acinetobacter baumannii. Although, it has been launched in the 1960s, scarce pharmacokinetic studies have been published. This open-label, prospective clinical study was conducted in critical ill patients with documented infections, mainly VAP-associated pneumonia, attributed to extensively-drug or pan-drug resistant Acinetobacter baumannii, susceptible-or intermediate susceptible to minocycline strains, treated with oral minocycline as a combination therapy. PTA of 200mg and 400mg of minocycline for a range of MICs after a Monte Carlo simulation of 10000 AUC values Methods The PK study population consisted of 20 patients, hospitalized in the ICU of a tetriary Hospital in Athens, Greece. The minimum inhibitory concentration was determined using broth microdilution and a susceptibility breakpoint of ≤ 4mg/L was applied for interpretation, according to the Clinical and Laboratory Standards Institute (CLSI). All patients were given a loading dose of 200mg of minocycline followed by 100mg every 12 hours. Plasma PK samples were collected predose and at 13,14,18,21.5, 59.5,61, 64,68 and 71.5 hours after commencement of minocycline. Minocycline quantification in patient serum sample was conducted using HPLC-PDA, Shimadzu Prominence system (Shimadzu, Kyoto, Japan). A population pharmacokinetic model was developed in Monolix 2023 R1. Monte Carlo simulations were carried out, assuming protein binding of 76%. The probability of target attainment was calculated for each MIC value to achieve an fAUC/MIC ratio of above 25 for daily doses of 200mg and 400mg. Results MInocycline PK parameters in critical ill adult patients were best described using a one-compartment model. The PTA values for various MICs are shown in Figure 1, which indicates that an oral dosage of 200mg and 400mg daily, could cover infections, due to Acinetobacter baumannii strains exhibiting MICs of 0.125mg/L and 0.25 mg/L ,respectively, with a PTA >90%. Conclusion These findings suggest that current oral treatment may be suboptimal for treating such infections, at least as a monotherapy. Further research is needed in order to explore possible dose elevations and synergistic combinations that could enhance its efficacy in combatting XDR, and PDR Acinetobacter baumannii infections. Disclosures All Authors: No reported disclosures

OBJECTIVES:Multidrug-resistant Acinetobacter baumannii (MDR-A. baumannii) has become an emerging pathogen, causing ventilator-associated pneumonia (VAP), with limited treatment options available. MIN has re-emerged as a potential treatment option for MDR pathogens. However, evidence regarding MIN pharmacokinetic properties in critically ill patients is scarce and primarily limited to IV administration. To address the knowledge gap in regions where IV MIN is unavailable, a prospective, open-label study was conducted to describe the pharmacokinetic properties of orally administered MIN. METHODS:The study included 24 critically ill patients with MDR-A. baumannii VAP. A population PK (popPK) model was developed and the PTA for different MICs was assessed by Monte Carlo simulations. A one-compartment model with first-order absorption and linear elimination best described the data. RESULTS:The values of the estimated population parameters were found equal to 183.3 L, 6.55 L/h and 1.66 h⁻¹, for the apparent volume of distribution (V/F), the apparent clearance (CL/F) and the absorption rate constant (ka), respectively (F representing oral bioavailability). PTA analysis showed that for a daily dose of 400 mg, adequate exposure [free AUC/MIC (fAUC/MIC > 25)] was achieved only for MICs ≤ 0.25 mg/L, while for the ratio of fAUC/MIC = 13.75, high PTA values are calculated up to MIC = 0.5 mg/L. CONCLUSIONS:This study provides a popPK model for oral MIN in critically ill adults. The developed popPK model contributes to a better understanding of MIN's PK and can inform dosing strategies and future studies on MIN use in critical care settings.

Metabolic disorders, including type 2 diabetes mellitus (T2DM), obesity, and metabolic syndrome, are systemic conditions that profoundly impact the skin microbiota, a dynamic community of bacteria, fungi, viruses, and mites essential for cutaneous health. Dysbiosis caused by metabolic dysfunction contributes to skin barrier disruption, immune dysregulation, and increased susceptibility to inflammatory skin diseases, including psoriasis, atopic dermatitis, and acne. For instance, hyperglycemia in T2DM leads to the formation of advanced glycation end products (AGEs), which bind to the receptor for AGEs (RAGE) on keratinocytes and immune cells, promoting oxidative stress and inflammation while facilitating Staphylococcus aureus colonization in atopic dermatitis. Similarly, obesity-induced dysregulation of sebaceous lipid composition increases saturated fatty acids, favoring pathogenic strains of Cutibacterium acnes, which produce inflammatory metabolites that exacerbate acne. Advances in metabolomics and microbiome sequencing have unveiled critical biomarkers, such as short-chain fatty acids and microbial signatures, predictive of therapeutic outcomes. For example, elevated butyrate levels in psoriasis have been associated with reduced Th17-mediated inflammation, while the presence of specific Lactobacillus strains has shown potential to modulate immune tolerance in atopic dermatitis. Furthermore, machine learning models are increasingly used to integrate multi-omics data, enabling personalized interventions. Emerging therapies, such as probiotics and postbiotics, aim to restore microbial diversity, while phage therapy selectively targets pathogenic bacteria like Staphylococcus aureus without disrupting beneficial flora. Clinical trials have demonstrated significant reductions in inflammatory lesions and improved quality-of-life metrics in patients receiving these microbiota-targeted treatments. This review synthesizes current evidence on the bidirectional interplay between metabolic disorders and skin microbiota, highlighting therapeutic implications and future directions. By addressing systemic metabolic dysfunction and microbiota-mediated pathways, precision strategies are paving the way for improved patient outcomes in dermatologic care.

Background/Objectives: Melanoma, an aggressive form of skin cancer, accounts for a significant proportion of skin-cancer-related deaths worldwide. Early and accurate differentiation between melanoma and benign melanocytic nevi is critical for improving survival rates but remains challenging because of diagnostic variability. Convolutional neural networks (CNNs) have shown promise in automating melanoma detection with accuracy comparable to expert dermatologists. This study evaluates and compares the performance of four CNN architectures—DenseNet121, ResNet50V2, NASNetMobile, and MobileNetV2—for the binary classification of dermoscopic images. Methods: A dataset of 8825 dermoscopic images from DermNet was standardized and divided into training (80%), validation (10%), and testing (10%) subsets. Image augmentation techniques were applied to enhance model generalizability. The CNN architectures were pre-trained on ImageNet and customized for binary classification. Models were trained using the Adam optimizer and evaluated based on accuracy, area under the receiver operating characteristic curve (AUC-ROC), inference time, and model size. The statistical significance of the differences was assessed using McNemar’s test. Results: DenseNet121 achieved the highest accuracy (92.30%) and an AUC of 0.951, while ResNet50V2 recorded the highest AUC (0.957). MobileNetV2 combined efficiency with competitive performance, achieving a 92.19% accuracy, the smallest model size (9.89 MB), and the fastest inference time (23.46 ms). NASNetMobile, despite its compact size, had a slower inference time (108.67 ms), and slightly lower accuracy (90.94%). Performance differences among the models were statistically significant (p < 0.0001). Conclusions: DenseNet121 demonstrated a superior diagnostic performance, while MobileNetV2 provided the most efficient solution for deployment in resource-constrained settings. The CNNs show substantial potential for improving melanoma detection in clinical and mobile applications.

The COVID-19 pandemic has posed unprecedented challenges to global health, necessitating rapid advancements in our understanding of the factors that influence disease outcomes. This study delves into the relationship between pre-infection physical activity (PA) levels and the efficacy of various COVID-19 treatments within a Greek adult population. Employing the ExtraTreesClassifier, an ensemble learning method, our study achieved a predictive accuracy of 72.56%, underscoring the importance of anthropometric measurements in treatment outcomes. The clustering analysis revealed distinct subgroups within the patient data, suggesting a potential protective effect of higher PA levels against severe COVID-19 outcomes. The findings possibly advocate for public health strategies that promote active lifestyles as a preventive measure against severe COVID-19 outcomes. Beyond certain limitations, the study's insights underscore the promise of machine learning in healthcare, paving the way for personalized treatment strategies and improved patient care.

(1) Background: Predictive modeling is becoming increasingly relevant in healthcare, aiding in clinical decision making and improving patient outcomes. However, many of the most potent predictive models, such as deep learning algorithms, are inherently opaque, and their decisions are challenging to interpret. This study addresses this challenge by employing Shapley Additive Explanations (SHAP) to facilitate model interpretability while maintaining prediction accuracy. (2) Methods: We utilized Gradient Boosting Machines (GBMs) to predict patient outcomes in an emergency department setting, with a focus on model transparency to ensure actionable insights. (3) Results: Our analysis identifies “Acuity”, “Hours”, and “Age” as critical predictive features. We provide a detailed exploration of their intricate interactions and effects on the model’s predictions. The SHAP summary plots highlight that “Acuity” has the highest impact on predictions, followed by “Hours” and “Age”. Dependence plots further reveal that higher acuity levels and longer hours are associated with poorer patient outcomes, while age shows a non-linear relationship with outcomes. Additionally, SHAP interaction values uncover that the interaction between “Acuity” and “Hours” significantly influences predictions. (4) Conclusions: We employed force plots for individual-level interpretation, aligning with the current shift toward personalized medicine. This research highlights the potential of combining machine learning’s predictive power with interpretability, providing a promising route concerning a data-driven, evidence-based healthcare future.

In an era increasingly focused on integrating Artificial Intelligence (AI) into healthcare, the utility and user satisfaction of AI applications like ChatGPT have become pivotal research areas. This study, conducted in Greece, engaged 193 doctors from various medical departments who interacted with ChatGPT 4.0 through a custom web application. The participants, representing a diverse range of medical specialties, received responses from the specific chatbot tailored to their specific departmental inquiries. Their satisfaction was gauged using a validated form featuring a 1-to-5 rating scale. The results highlighted a possible correlation between the doctors' medical departments and their satisfaction levels with ChatGPT 4.0. Significantly, doctors from certain departments (like General Surgery and Cardiology) reported lower satisfaction scores, ranging from 2.73 to 2.80 out of 5, in contrast to their colleagues from departments like Biopathology and Orthopedics, who scored between 4.00 and 4.46 out of 5. This variation in satisfaction levels underscores the diverse needs within different medical specialties and illuminates both the potential of ChatGPT and the areas needing improvement, especially in delivering department-specific medical information. Despite its limitations, ChatGPT version 4.0 is emerging as a valuable tool in the medical community, indicating potential future advancements and more extensive integration into healthcare practices. The study's findings are crucial in understanding the distinct preferences and requirements of healthcare professionals across various medical departments, thereby guiding the future development of AI tools in healthcare.

In this AI-focused era, researchers are delving into AI applications in healthcare, with ChatGPT being a primary focus. This Greek study involved 182 doctors from various regions, utilizing a custom web application connected to ChatGPT 4.0. Doctors from diverse departments and experience levels engaged with ChatGPT, which provided tailored responses. Over a month, data was collected using a form with a 1-to-5 rating scale. The results showed varying satisfaction levels across four criteria: clarity, response time, accuracy, and overall satisfaction. ChatGPT's response speed received high ratings (3.85/5.0), whereas clarity of information was moderately rated (3.43/5.0). A significant observation was the correlation between a doctor's experience and their satisfaction with ChatGPT. More experienced doctors (over 21 years) reported lower satisfaction (2.80-3.74/5.0) compared to their less experienced counterparts (3.43-4.20/5.0). At the medical field level, Internal Medicine showed higher satisfaction in evaluation criteria (ranging from 3.56 to 3.88), compared to other fields, while Psychiatry scored higher overall, with ratings from 3.63 to 5.00. The study also compared two departments: Urology and Internal Medicine, with the latter being more satisfied with the accuracy, and clarity of provided information, response time, and overall compared to Urology. These findings illuminate the specific needs of the health sector and highlight both the potential and areas for improvement in ChatGPT's provision of specialized medical information. Despite current limitations, ChatGPT, in its present version, offers a valuable resource to the medical community, signaling further advancements and potential integration into healthcare practices.

Background/Objectives: Carbapenem resistance poses a significant threat to public health by undermining the efficacy of one of the last lines of antibiotic defense. Addressing this challenge requires innovative approaches that can enhance our understanding and ability to combat resistant pathogens. This review aims to explore the integration of machine learning (ML) and epidemiological approaches to understand, predict, and combat carbapenem-resistant pathogens. It examines how leveraging large datasets and advanced computational techniques can identify patterns, predict outbreaks, and inform targeted intervention strategies. Methods: The review synthesizes current knowledge on the mechanisms of carbapenem resistance, highlights the strengths and limitations of traditional epidemiological methods, and evaluates the transformative potential of ML. Real-world applications and case studies are used to demonstrate the practical benefits of combining ML and epidemiology. Technical and ethical challenges, such as data quality, model interpretability, and biases, are also addressed, with recommendations provided for overcoming these obstacles. Results: By integrating ML with epidemiological analysis, significant improvements can be made in predictive accuracy, identifying novel patterns in disease transmission, and designing effective public health interventions. Case studies illustrate the benefits of interdisciplinary collaboration in tackling carbapenem resistance, though challenges such as model interpretability and data biases must be managed. Conclusions: The combination of ML and epidemiology holds great promise for enhancing our capacity to predict and prevent carbapenem-resistant infections. Future research should focus on overcoming technical and ethical challenges to fully realize the potential of these approaches. Interdisciplinary collaboration is key to developing sustainable strategies to combat antimicrobial resistance (AMR), ultimately improving patient outcomes and safeguarding public health.

The intersection of COVID-19 and pulmonary embolism (PE) has posed unprecedented challenges in medical diagnostics. The critical nature of PE and its increased incidence during the pandemic underline the need for improved detection methods. This study evaluates the effectiveness of advanced deep learning techniques in enhancing PE detection in post-COVID-19 patients through Computed Tomography Pulmonary Angiography (CTPA) scans. Using a dataset of 746 anonymized CTPA images from 25 patients, we fine-tuned the state-of-the-art Ultralytics YOLOv8 object detection model, which was trained on 676 images with 1,517 annotated bounding boxes and validated on 70 images with 108 bounding boxes. After 200 epochs of training, which lasted approximately 1.021 hours, the YOLOv8 model demonstrated significant diagnostic proficiency, achieving a mean Average Precision (mAP) of 0.683 at an IoU threshold of 0.50 and a mAP of 0.246 at the IoU range of 0.50:0.95 in the validation dataset. Notably, the model reached a maximum precision of 0.85949 and a maximum recall of 0.81481, though these metrics were observed in separate epochs. These findings emphasize the model's potential for high diagnostic accuracy and offer a promising direction for deploying AI tools in clinical settings, significantly contributing to healthcare innovation and patient care post-pandemic.