Objectives: Hypertension, commonly known as high blood pressure, is a prevalent and serious condition affecting a significant portion of the adult population globally. It is a chronic medical issue that, if left unaddressed, can lead to severe health complications, including kidney problems, heart disease, and stroke. This study aims to develop a feature selection model using the XGBoost algorithm to identify specific single nucleotide polymorphisms (SNPs) as biomarkers for detecting hypertension risk. Methods: We propose using the high dimensionality of genetic variations (i.e., SNPs) to build a classifier model for prediction. In this study, SNPs were used as markers for hypertension in patients. We utilized the OpenSNP dataset, which includes 19,697 SNPs from 2,052 samples. Extreme gradient boosting (XGBoost) is an ensemble machine learning method employed here for feature selection, which incrementally adjusts weights in a series of steps. Results: The experimental results identified 292 SNPs that exhibited high performance, with an F1-score of 98.55%, precision of 98.73%, recall of 98.38%, and overall accuracy of 98%. This study provides compelling evidence that the XGBoost feature selection method outperforms other representative feature selection methods, such as genetic algorithms, analysis of variance, chi-square, and principal component analysis, in predicting hypertension risk, demonstrating its effectiveness. Conclusions We developed a model for predicting hypertension using the SNPs dataset. The high dimensionality of SNP data was effectively managed to identify significant features as biomarkers using the XGBoost feature selection method. The results indicate high performance in predicting the risk of hypertension.

Objectives: Hypertension, commonly known as high blood pressure, is a prevalent and serious condition affecting a significant portion of the adult population globally. It is a chronic medical issue that, if left unaddressed, can lead to severe health complications, including kidney problems, heart disease, and stroke. This study aims to develop a feature selection model using the XGBoost algorithm to identify specific single nucleotide polymorphisms (SNPs) as biomarkers for detecting hypertension risk. Methods: We propose using the high dimensionality of genetic variations (i.e., SNPs) to build a classifier model for prediction. In this study, SNPs were used as markers for hypertension in patients. We utilized the OpenSNP dataset, which includes 19,697 SNPs from 2,052 samples. Extreme gradient boosting (XGBoost) is an ensemble machine learning method employed here for feature selection, which incrementally adjusts weights in a series of steps. Results: The experimental results identified 292 SNPs that exhibited high performance, with an F1-score of 98.55%, precision of 98.73%, recall of 98.38%, and overall accuracy of 98%. This study provides compelling evidence that the XGBoost feature selection method outperforms other representative feature selection methods, such as genetic algorithms, analysis of variance, chi-square, and principal component analysis, in predicting hypertension risk, demonstrating its effectiveness. Conclusions We developed a model for predicting hypertension using the SNPs dataset. The high dimensionality of SNP data was effectively managed to identify significant features as biomarkers using the XGBoost feature selection method. The results indicate high performance in predicting the risk of hypertension.

Objectives: Hypertension, commonly known as high blood pressure, is a prevalent and serious condition affecting a significant portion of the adult population globally. It is a chronic medical issue that, if left unaddressed, can lead to severe health complications, including kidney problems, heart disease, and stroke. This study aims to develop a feature selection model using the XGBoost algorithm to identify specific single nucleotide polymorphisms (SNPs) as biomarkers for detecting hypertension risk. Methods: We propose using the high dimensionality of genetic variations (i.e., SNPs) to build a classifier model for prediction. In this study, SNPs were used as markers for hypertension in patients. We utilized the OpenSNP dataset, which includes 19,697 SNPs from 2,052 samples. Extreme gradient boosting (XGBoost) is an ensemble machine learning method employed here for feature selection, which incrementally adjusts weights in a series of steps. Results: The experimental results identified 292 SNPs that exhibited high performance, with an F1-score of 98.55%, precision of 98.73%, recall of 98.38%, and overall accuracy of 98%. This study provides compelling evidence that the XGBoost feature selection method outperforms other representative feature selection methods, such as genetic algorithms, analysis of variance, chi-square, and principal component analysis, in predicting hypertension risk, demonstrating its effectiveness. Conclusions We developed a model for predicting hypertension using the SNPs dataset. The high dimensionality of SNP data was effectively managed to identify significant features as biomarkers using the XGBoost feature selection method. The results indicate high performance in predicting the risk of hypertension.

BACKGROUND

Acne vulgaris is one of the common skin diseases prompting dermatologic consult. Although prevalent worldwide, knowledge of the public about acne is still lacking. Due to this, content related to acne vulgaris has been a topic of choice on social media platforms.

A cross-sectional study was conducted among 120 patients diagnosed with acne vulgaris aged 18-50 years-old consulting via teledermatology and face-to-face consultation at the Rizal Medical Center. Patients completed a self-administered questionnaire and global acne severity was assessed.

A total of 120 newly d iagnosed patients with acne vulgaris were included in the study, with a mean age of 23.25 years, with a female predominance, household average monthly income less than PhP 10,957 and with mild to moderate acne severity. Majority of the participants used social media to look for treatment options and to gain more knowledge about the disease. The most used platforms were Youtube, Facebook and Tiktok. Short videos were viewed more often and content from dermatologists were preferred. Most commonly tried products are over-the-counted non-pharmaceutical topical products. There was a significant association between the use of social media with age and educational attainment. Furthermore, a significant association between self-medication practices and average household monthly income was seen. No association was seen between acne severity, social media use and self-medication practices.

In summary, the use of social media to access acne-related content was prevalent among young female patients, of lower socioeconomic status diagnosed with mild-moderate acne severity at a tertiary hospital in the Philippines.

Acrodermatitis continua of Hallopeau (ACH) is a rare, chronic, and recalcitrant inflammatory disorder classified as a localized variant of pustular psoriasis. Patients usually present with relapsing episodes of subungual pustules, nail dystrophy, and scaling. We report a case of ACH in a 32-year-old female, which developed following a nail infection and exacerbated during pregnancy, with no medication for 2 years. She presented at the clinic with severe manifestations of anonychia and multiple bone resorption on the distal phalanges. The patient was started on topical medication of combination corticosteroid and vitamin D analogue and oral methotrexate initially at l0mg/week then increased to 15mg/week due to poor response. Despite compliance to medications and avoidance of possible irritants, the patient still had relapse of pustules on the nails.

Several treatment options for ACH are available such as topical steroids, vitamin D analogue, systemic biologics, and non-biologics such as methotrexate and cyclosporine. However, systemic biologics are considered the most efficacious for ACH but financial constraints often limit their use in resource-poor settings.

Problem: In September 2024, an illegal toxic waste dumping incident along the Tebrau River in Johor State, Malaysia, raised widespread health concerns in Johor Bahru and Kulai districts. The pollution released a strong, unpleasant odour, resulting in acute symptoms among exposed individuals, including sore throat, dizziness and coughing. Context: The Tebrau River is a vital waterway supporting urban populations in Johor. This was not the first chemical pollution event in the region, as previous incidents, including the Kim Kim River crisis in 2019, highlighted the region’s vulnerability to such events. The involvement of multiple districts and agencies during the response presented challenges in coordination and data sharing. Action: The Johor Bahru District Health Office promptly deployed a rapid assessment team to assess the affected areas and implement both active and passive case detection. Community engagement targeted vulnerable populations, such as schoolchildren, to minimize exposure risks. Additional dumping sites identified along the Tebrau River prompted expanded surveillance and a state-level response to coordinate efforts across districts and all health-care facilities. Outcome: A total of 484 individuals were exposed to the pollution, 334 of whom developed symptoms related to chemical exposure. Timely public health actions consisted of actions to mitigate the impact. Health facilities were placed on high alert and community trust was maintained through proactive engagement. However, gaps in cross-district coordination and challenges accessing environmental data underscored areas for improvement. Discussion: This incident highlighted the importance of rapid assessment, cross-sector collaboration, community engagement and integrated data systems. It also showed that effective public health action is possible despite environmental data limitations. The strengthening of communication, standardized protocols and real-time data sharing will be critical to improving future chemical pollution events.

BACKGROUND

Intraoperative transfusion for gynecologic surgery, when appropriately used, can improve patient outcomes. However, when utilized incorrectly, blood transfusion can worsen patient outcomes and increase patient cost. This study aimed to evaluate the blood transfusion practices of tertiary hospitals in the Philippines.

The study utilized a cross-sectional design wherein prospective data were gathered through multiple sources across seven tertiary-level hospitals. Women admitted to undergo gynecologic surgery were recruited based on a set of criteria. A chart review was conducted, and blood utilization indices were calculated. Outcomes were compared between public versus private facilities and transfused versus nontransfused patients.

Among 514 patients, 79.7% underwent cross-matching and 75.1% received transfusions. Adverse events were rare, with no transfusion-related deaths. The overall crossmatch-to-transfusion ratio (C/T ratio) was 2.8, exceeding the 2.5 optimal benchmark; all public hospitals recorded a C/T ratio >2.5, whereas private centers had more efficient usage. Six hospitals met acceptable benchmarks for transfusion probability and transfusion index. Open abdominal procedures, particularly hysterectomy, accounted for the most blood used. Transfused patients had longer operative times, greater blood loss, lower preoperative hemoglobin, and more frequently involved resident physicians in training. Public hospitals recorded higher cross-match and transfusion rates, greater resident physician participation, and broader use of general anesthesia.

Results of the study highlight the importance of monitoring blood transfusion parameters to optimize blood utilization. The observed differences between public and private institutions in the country highlight the urgent need for standardized and evidence-based practice to ensure efficient transfusion protocols nationwide.

OBJECTIVE

This study assessed the correlation of macular pigment optical density (MPOD) and varying levels of exposure to video display terminals (VDT) among young adult Filipinos.

This cross-sectional, analytical, single-center study compared the MPOD, measured using the Zeiss VISUCAM 500, between two groups of individuals aged 20 to 35 years old with differing VDT exposure. The more exposed group consisted of individuals who spent at least 8 hours per day on VDTs for the past 1 year, while the less exposed group spent less than 6 hours per day. Student’s t-test and chi-square test were used to compare the two groups, while Pearson's r coefficient was utilized to determine the relationship between MPOD and VDT exposure.

A total of 80 individuals (40 in each group) were included in the study. Both groups had similar profiles, except for refractive errors, which were significantly higher in the prolonged VDT exposure group (p = 0.02). The prolonged exposure group averaged 10 hours of VDT use per day, compared to 3 hours in the low VDT exposure group. The MPOD level, particularly the maximum optical density (Max OD), was significantly lower in the prolonged VDT exposure group (0.2034 DU) compared to the low VDT exposure group (0.2467 DU) (p = 0.0051). A negative weak correlation was observed between the VDT exposure hours and MPOD levels (Max OD r = –0.387, p = 0.0005).

This study found a weak but significant negative correlation between prolonged VDT exposure and lower MPOD levels, suggesting that extended screen time may contribute to reduced macular pigment density. While the correlation was weak (r = –0.387), these findings underscore the potential risk of diminished macular health with increased VDT use. The results highlight the importance of promoting protective strategies, such as reducing screen time and encouraging dietary or lifestyle changes that support eye health, especially among individuals with high VDT exposure.

Objective:To determine the sensitivity, specificity and positive predictive value of the STOP BANG questionnaire in diagnosing Obstructive Sleep Apnea (OSA) in adults admitted for polysomnography at the Rizal Medical Center from January 2019 to June 2024

Methods:
Design:Review of Records
Setting:Tertiary Government Training Hospital
Participants:166 adult patients

Results:A total of 166 patient records were included with an average age of 35.6 ± 12 years, BMI of 29.3 ± 6.44 and 67% were male. The STOP-BANG questionnaire had a sensitivity of 77% to screen for all (AHI ≥ 5), mild (AHI = 5-14.9), moderate (AHI = 15-19.9), and severe OSA (AHI > 30), respectively. The specificity was 62% and the area under the curve was 0.717 for all, mild, moderate and severe OSA

Conclusion:A STOP-BANG score of 3/8 can predict the presence of OSA with a sensitivity of 77% and specificity of 62% with AUC of 0.717. The increase in score does not predict the severity. Further research can be done to identify other co-morbidities associated with OSA.

Objective:To describe the radiologic dimensions of the Eustachian tube (pre-tympanic diameter, tubo-tympanic angle, and Eustachian tube angle) among normal ears, ears with chronic otitis media (COM) with and without cholesteatoma, in a sample of Filipino adults with COM; and to compare the dimensions of the three variables.

Methods:
Design:Retrospective Review of Records
Setting:Tertiary Government Training Hospital
Participants:The study included 69 CT scans of adults with COM, with images of 23 ears for each variable (normal ears, COM with and without cholesteatoma formation).

Results:In normal ears, the average pre-tympanic diameter was 3.976 ± 0.78 mm, the average tubo-tympanic angle was 41.529 ± 5.85 degrees, and the average Eustachian tube Angle (Reid Plane) was 27.077 ± 4.62 degrees. In patients with COM without cholesteatoma, the mean pre tympanic diameter was 4.002 ± 1.13 mm, the mean tubo-tympanic angle was 141.994 ± 6.30 degrees, and the mean measurement of the Reid plane was 24.649 ± 3.10 degrees. In ears with COM with cholesteatoma, the mean pre-tympanic diameter was 4.1993 ± 0.50mm, the mean tubo-tympanic angle was 138.789 ± 7.13 degrees, and the mean Reid plane was 26.483 ± 3.86 degrees. P-values for the pre-tympanic diameter, tubo-tympanic angle, and ET angle were .617, .198, and .098 respectively, indicating that there were no statistically significant differences in the ET dimensions of the ears with COM with cholesteatoma, without cholesteatoma and normal ears.

Conclusion:In our investigation, we found no statistically significant differences in Eustachian tube dimensions among individuals with normal ears and COM with or without cholesteatoma. This suggests that the Eustachian tube dimensions may not serve as a primary etiological factor for COM among our patients.