Urinary tract infections (UTIs) are among the most common bacterial infections worldwide, requiring timely and accurate diagnosis to guide appropriate therapy and reduce antimicrobial resistance. Although urine culture remains the diagnostic gold standard, its prolonged turnaround time and susceptibility to pre-analytical variability limit its clinical efficiency. Recent advances in artificial intelligence (AI) have positioned urinalysis as a promising alternative diagnostic approach, utilizing machine learning and deep learning algorithms for automated analysis and prediction. This review synthesizes current evidence on AI applications in urinalysis for UTI diagnosis, examining computational techniques, diagnostic performance, clinical integration, limitations, and future directions. The literature demonstrates that AI-powered urinalysis can achieve diagnostic accuracy comparable to urine culture, with high sensitivity and specificity while reducing diagnostic time. Integration of AI into clinical workflows has the potential to enhance decision-making, streamline laboratory processes, and support antimicrobial stewardship. However, challenges related to data heterogeneity, algorithm interpretability, validation, and regulatory requirements remain significant barriers to widespread adoption. Overall, AI-driven urinalysis represents a transformative opportunity to complement the existing diagnostic standard and advance more rapid, efficient, and personalized approaches to UTI management.

Human ; Artificial Intelligence ; Urinalysis ; Urinary Tract Infections ; Machine Learning ; Deep Learning

BACKGROUND

The COVID-19 pandemic disrupted education worldwide, prompting a rapid shift to emergency remote teaching that challenged students’ learning and mental health. Nursing students, in particular, faced heightened pressures due to the suspension or online adaptation of essential clinical experiences, alongside the need to master theoretical and practical competencies. Emerging evidence indicates that such stressors adversely affect students’ emotional and psychological well-being, potentially influencing academic outcomes. Understanding the relationship between mental health and academic performance among nursing students is crucial for developing targeted interventions that support their well-being and professional readiness.

OBJECTIVE

This study analyzed the mental health status and academic performance of graduating nursing students during the challenging period of remote learning amid the pandemic in a government school in Leyte.

METHODS

The study utilized a descriptive correlational design to explore the relationships between mental health status and academic performance among nursing students. A modified self-administered questionnaire was utilized to gather data. Ethical approval from Eastern Visayas Health Research and Development ConsortiumEthics Review with ERC number 2023-024 was secured, and data collection occurred through various methods. Data analysis used SPSS version 24, emphasizing the importance of understanding these relationships in educational settings.

RESULTS

The study assessed the demographic profile, online learning attributes, mental health status, and academic performance of 20 nursing students during the pandemic. All students passed their courses, despite reporting moderate emotional loneliness and irritability, but minimal fear of COVID-19. Significant correlations were found between demographic factors and mental health indicators. The null hypothesis, suggesting no relationship between demographic factors and mental health, is void, as significant associations were identified. Recommendations include enhancing mental health support in nursing education to address these challenges.

CONCLUSION

This study highlights the experiences of 20 nursing students from a government college in Leyte during the COVID-19 pandemic. Predominantly young women from rural, low-income backgrounds, these students faced challenges like poor internet access but successfully completed their academic requirements, showcasing resilience. While they reported low fear of COVID-19, moderate emotional loneliness and irritability indicated underlying mental health issues. The findings stress the need for educational institutions to provide mental health support and address the digital divide to enhance student well-being and success.

Human ; Male ; Female ; Young Adult: 19-24 Yrs Old ; Adult: 25-44 Yrs Old ; Statistics As Topic ; Psychological Well-being ; Indicators And Reagents ; Students, Nursing ; Suspensions ; Academic Performance ; Learning ; Pandemics ; Nursing ; Education, Nursing ; Covid-19 ; Mental Health

Abstract Intestinal ultrasound (IUS) is increasingly recognized as a vital, non-invasive tool for managing inflammatory bowel disease (IBD) due to its real-time assessment capabilities and patient comfort. However, the lack of standardized training pathways remains a significant barrier to its widespread adoption, particularly in low- and middle-income settings. This editorial evaluates the implementation of a mastery learning-based workshop in Indonesia designed to enhance IUS skills among physicians. The mastery learning framework—incorporating flipped learning, deliberate practice, and real-time feedback led to significant improvements in technical performance with large effect sizes. Despite these gains, only about two-thirds of participants achieved competency in sigmoid colon scanning, and only half met the standard for terminal ileum assessment. This suggests that while short-term intensive workshops are effective for early skill acquisition, they may be insufficient for ensuring consistent proficiency in technically demanding tasks. Mastery learning offers a structured and reproducible approach to gastroenterology procedural training. To translate these initial educational gains into durable clinical expertise, future programs should consider longitudinal curricula that include sustained practice, mentorship, and ongoing assessment.
Intestinal ultrasound ; mastery learning ; Inflammatory bowel disease ; medical education ; competency-based training ; gastroenterology

Breast cancer (BC) is the most frequently diagnosed malignancy worldwide and a leading cause of death in women. Machine learning (ML) enables data-driven risk stratification and outcome prediction, potentially improving screening, treatment choices, and overall care. This scoping review cataloged ML models used to predict BC risk and post-treatment outcomes. A PubMed search using MeSH terms (“breast neoplasms,” “breast cancer,” “machine learning,” and “predictive value of tests”) retrieved 44 records, with 9 added by manual searching; 24 studies were included. We excluded 29 reports limited to imaging/radiomics or biomolecular/omics, plus other ineligible items. Model usage among included studies: 13 random forest (RF); 13 support vector machine; 7 decision tree; 5 k-nearest neighbors; 4 deep learning; 3 naïve Bayes; 2 artificial neural networks. Average RF accuracy surpassed 90% in most reports, indicating RF is both common and consistently strong for predictive modeling, supporting targeted clinical translation.
breast neoplasm ; machine learning ; predictive value of tests

OBJECTIVE

This meta-analysis aimed to evaluate the diagnostic capability of machine learning (ML) models in predicting stone-free status following percutaneous nephrolithotomy (PCNL).

METHODS

A comprehensive literature search was conducted across MEDLINE, Embase, Scopus, Cochrane, Google Scholar and supplementary databases was undertaken until June 2023. Inclusion criteria were English publications assessing the sensitivity and specificity of ML in predicting post PCNL stone-free status. Studies on non-human subjects or with incomplete data sets were excluded. Quality assessment utilized the Cochrane Risk of Bias Tool. Pooled sensitivity, specificity, and other diagnostic metrics were calculated using Meta-Disc 1.4 software.

RESULTS

Of the 65 initial articles, 5 met the inclusion criteria, representing a total of 1,773 participants. The accuracy of ML models ranged from 44% to 94.8%. The pooled sensitivity and specificity were 0.60 (95% CI [0.57, 0.63]) and 0.87 (95% CI [0.84, 0.89]), respectively. The pooled positive likelihood ratio was 4.69 (95% CI [3.82, 5.77]) and the negative likelihood ratio was 0.45 (95% CI [0.41, 0.48]). The diagnostic odds ratio was 10.93 (95% CI [8.35, 14.33]). The area under the curve (AUC) stood at 0.9372, signifying an excellent diagnostic performance.

CONCLUSION

Machine learning models demonstrate significant potential in accurately predicting stone-free status post-PCNL. However, the small number of included studies, retrospective designs, and heterogeneity in ML approaches limit generalizability. Standardized definitions, larger multicenter datasets, and prospective validation are required before routine clinical adoption.

Human ; Male ; Female ; Meta-analysis ; Artificial Intelligence ; Machine Learning ; Nephrolithotomy, Percutaneous

BACKGROUND

Outcomes-Based Education (OBE) in the Philippines has shifted perioperative training from numeric case quotas toward demonstrated competencies, with simulation increasingly used to address limited operating room (OR) exposure.

OBJECTIVE

This study determined the level of perioperative clinical performance among senior (4th year) nursing students and had also examined associations with four influencing domains: teaching–learning, interpersonal, student-related, and environmental.

METHODS

A descriptive–correlational study was conducted in AY 2023–2024 across higher education institutions in Eastern Visayas. A universal sample of 280 fourth-year BSN students who met minimum perioperative case requirements participated via online and paper surveys. Aresearcher-developed, expert-validated instrument that was anchored on CHED outcomes and PRC–BON guidelines was used to assess 11 competence domains in order to perceive influencing factors. Internal consistency was excellent (performance α = .987; factors α = .944). Descriptive statistics summarized competence; while Fisher’s Exact Test was used to assess associations (p < .05).

RESULTS

Competence was strongest in aseptic technique, patient safety, teamwork, documentation, and ethical–legal responsibilities. Lower ratings were noted for surgical skin preparation, anesthesia assistance, patient transport, medication safety, health education, and quality improvement. Among the four domains, only environmental factors (resources, workflow support, safety culture) were significantly associated with performance (Fisher’s Exact, p = .013).

CONCLUSION

Senior nursing students demonstrated strong technical and ethical perioperative competence but showed persistent gaps in less-frequent and higher-order competencies. Environmental supports in the OR decisively shaped performance. Programs should scale simulation for under-practiced tasks, strengthen mentorship, and explicitly integrate health education and quality improvement within perioperative training.

Human ; Learning ; Education ; Students, Nursing ; Mental Competency

Practice-based learning is the key objective of postgraduate education. COVID-19 has revealed that medical institutions may need to adopt adaptive strategies to guide their students. The aim of this study is to describe the perception of Philippine medical clerks towards their surgical preparedness with an Enriched Virtual Mode (EVM)-Hybrid Learning during the pandemic. A cross-sectional survey was conducted among 176 fourth-year students using a 21-item 4-point-Likert questionnaire. Descriptive analysis showed that students sustained a strong enthusiasm for surgery (composite mean = 2.83 ± 0.62), with the highest ratings given to skill-oriented subjects, such as practical minors (3.05 ± 0.82) and clinical surgery (3.03 ± 0.78). Preparedness was similarly high (3.17 ± 0.46): practice was regarded as essential (3.50 ± 0.68) and operating-room exposure useful (3.22 ± 0.68), though time for hands-on practice was adequate (2.84 ± 0.74). Preference scores revealed a desire for richer tactile experience (3.36 ± 0.37), with scrubbing, suturing and live surgery observation receiving most support (>3.50). Overall satisfaction reached a moderate-to-high level (2.99 ± 0.48) but lagged behind interest and preparedness, indicating that limited physical immersion tempered fuller contentment. These suggest that while a blended curriculum can preserve enthusiasm and sense of readiness, emphasis on protected skills laboratories and increased exposure to the operating room may be needed to translate conceptual competence into experiential fulfillment.

Human ; Male ; Female ; Young Adult: 19-24 Yrs Old ; Cross-sectional Studies ; Education ; Curriculum ; Perception ; Observation ; Schools, Medical ; Personal Satisfaction ; Learning ; Mental Competency ; Laboratories ; Pandemics

BACKGROUND

Hypertension is a major contributor to cognitive decline, and dementia is an increasing public health concern in the Philippines. Despite evidence linking these conditions, the awareness of dementia risk remains limited. Broader modifiable factors—such as nutrition, physical activity, smoking, alcohol use and sleep—also influence dementia risk but are not consistently emphasized in health education for hypertensive adults.

OBJECTIVE

To comprehensively assess the dementia risk awareness of hypertensive Filipino adults residing in the Philippines.

METHODS

An adapted questionnaire will gather data on dementia risk awareness among hypertensive Filipino adults. Phase I involves distributing the questionnaire via Google Forms on social media and collecting informed consent, the Personal Data Sheet (PDS), Dementia Knowledge Assessment Scale (DKAS) responses and self-reported modifiable risk factors from the McCance Brain Care Score (BCS). Phase II consists of quantitative analysis using descriptive statistics, including sub-analyses assessing correlations between dementia risk awareness and secondary measures.

EXPECTED RESULTS

At least 384 responses from hypertensive Filipino adults are anticipated, allowing classification into dementia risk–aware or dementia risk–unaware groups using DKAS thresholds. Exploratory analyses will describe potential associations between dementia risk awareness and selected modifiable risk factors

Human ; Male ; Female ; Adolescent: 13-18 Yrs Old ; Young Adult: 19-24 Yrs Old ; Adult: 25-44 Yrs Old ; Middle Aged: 45-64 Yrs Old ; Adult ; Awareness ; Dementia ; Learning ; Philippines ; Risk

Artificial Intelligence (AI) is transforming the landscape of pathology, particularly in resource-constrained settings like the Philippines. This narrative review explores the applications, challenges, and future potential of AI in digital image analysis for pathology practices. By synthesizing peer-reviewed literature from 2019 to 2024, the review highlights the role of machine learning (ML) and deep learning (DL) algorithms in enhancing diagnostic accuracy, workflow efficiency, and clinical decision-making. AI-driven tools such as convolutional neural networks (CNNs) and transfer learning models have demonstrated significant success in tumor detection, biomarker evaluation, and predictive analytics, paving the way for personalized medicine. However, barriers such as limited annotated datasets, privacy concerns, and model interpretability hinder widespread adoption. The review emphasizes the need for ethical frameworks, workforce training, and infrastructure development to ensure equitable and effective integration of AI into pathology practices. By addressing these challenges, AI has the potential to improve diagnostic precision, expand access to healthcare, and modernize pathology services in the Philippines.

Human ; Artificial Intelligence ; Pathology ; Philippines ; Deep Learning ; Machine Learning

OBJECTIVES: To evaluate the performance of a multi-constraint representation learning classification model for identifying ovarian cancer with missing laboratory indicators. METHODS: Tabular data with missing laboratory indicators were collected from 393 patients with ovarian cancer and 1951 control patients. The missing ovarian cancer laboratory indicator features were projected to the latent space to obtain a classification model using the representational learning classification model based on discriminative learning and mutual information coupled with feature projection significance score consistency and missing location estimation. The proposed constraint term was ablated experimentally to assess the feasibility and validity of the constraint term by accuracy, area under the ROC curve (AUC), sensitivity, and specificity. Cross-validation methods and accuracy, AUC, sensitivity and specificity were also used to evaluate the discriminative performance of this classification model in comparison with other interpolation methods for processing of the missing data. RESULTS: The results of the ablation experiments showed good compatibility among the constraints, and each constraint had good robustness. The cross-validation experiment showed that for identification of ovarian cancer with missing laboratory indicators, the AUC, accuracy, sensitivity and specificity of the proposed multi-constraints representation-based learning classification model was 0.915, 0.888, 0.774, and 0.910, respectively, and its AUC and sensitivity were superior to those of other interpolation methods. CONCLUSIONS The proposed model has excellent discriminatory ability with better performance than other missing data interpolation methods for identification of ovarian cancer with missing laboratory indicators.
Female ; Humans ; Ovarian Neoplasms/diagnosis* ; Machine Learning ; ROC Curve