Combined Military Hospital

Nearly two billion chest X-rays (CXRs) are performed annually, making them the most used imaging technique in radiology for the diagnosis of pulmonary disorders. The accompanying report with the findings from a chest X-ray forms a crucial part of the examination. By providing an accurate report, healthcare professionals can be enabled to make better decisions about the care being provided. To this end, we propose an end-to-end radiology report generation framework built on transformers trained on text reports in conjunction with visual characteristics of the chest X-ray to generate a reliable report that astutely describes the findings from a single CXR taken either from the Anterior-Posterior or Posterior-Anterior position. A foundation model is utilised to perform Knowledge Distillation (KD) in conjunction with the Encoder which is fine-tuned during the training phase. In addition, using a large corpus of radiology reports to pre-train the foundation model in an unsupervised manner is shown to improve the performance on smaller datasets. This training methodology results in comparable performance to architectures that employ a lot more parameters. The proposed framework is evaluated on multiple datasets including the Indiana University dataset, MIMIC dataset, MIMIC-PRO dataset, and BRAX dataset. The incorporation of KD results in an increase of BLEU-1 score for Indiana dataset by 4% and BERTScore by 7.5%. Similarly, pre-training on larger datasets in combination with KD, further increases BLEU-1 score for Indiana dataset by 7.2% and BERTScore by 3%. For MIMIC dataset, comparable performance is achieved for the Findings and the Impression sections of the report while the proposed framework outperforms other techniques when both of these sections are combined. For MIMIC-PRO dataset, an semb score of 0.4069 while a RadGraph F1 score of 0.1165 is achieved outperforming other techniques in the literature. Finally, the proposed framework is also evaluated on locally gathered dataset and BRAX subset without any re-training or fine-tuning resulting in BLEU-1 score of 0.3827 and a BERTScore of 0.4392 for the former and BLEU-1 score 0.1671 of and a BERTScore of 0.2186 for latter showing generalisation ability.

BACKGROUND & OBJECTIVE: Neonatal hyperbilirubinemia is common and requires timely detection to prevent bilirubin-induced neurological dysfunction. Serum total bilirubin (STB) is the diagnostic gold standard but is invasive and time-consuming, whereas transcutaneous bilirubin (TcB) offers a rapid, non-invasive screening alternative. To evaluate the correlation and agreement between TcB and STB in late preterm and term neonates and to assess the reliability of TcB as a NICU screening tool. METHODOLOGY:It is a Cross-sectional analytical study. A study was conducted at the Neonatal ICU, Combined Military Hospital Kharian, Pakistan, from June to August 2025. A total of 159 jaundiced neonates (35–37 weeks) were included. TcB values obtained with the Dräger JM-105 were compared with simultaneous STB measurements. Data were stratified by gestational and postnatal age. Statistical tests included Shapiro–Wilk, Pearson/Spearman correlation, Intraclass Correlation Coefficient (ICC), and Bland–Altman analysis. RESULTS: Mean TcB was 267.14 ± 77.84 µmol/L, and STB was 276.78 ± 80.12 µmol/L. All subgroups showed strong positive correlations (r/ρ > 0.78, p < 0.01). ICC values ranged from 0.757 to 0.952. Bland–Altman analysis showed a mean bias of –9.64 µmol/L, with limits of agreement from –49.1 to +29.8 µmol/L. CONCLUSIon: TcB demonstrates strong correlation and good agreement with STB and can serve as a reliable screening tool in resource-limited NICUs. However, consistent underestimation and wide limits of agreement limit its use as a stand-alone diagnostic test. STB confirmation is recommended when values approach treatment thresholds.

Background: Primary extracranial meningiomas are rare neoplasms that may arise without intracranial or dural involvement and are frequently misdiagnosed as benign scalp lesions. Lack of routine histopathological evaluation of excised scalp masses may delay diagnosis of rare tumors. Case Presentation: We report a 28-year-old woman with a recurrent left parieto-occipital scalp mass associated with positional headache and intermittent vertigo. She had undergone prior excision of a similar lesion five months earlier without histopathological examination and was lost to follow-up. Examination revealed a firm, mobile subcutaneous mass. Contrast-enhanced magnetic resonance imaging demonstrated a well-circumscribed extracranial lesion without intracranial extension or dural attachment. The patient underwent complete en bloc excision. Intraoperatively, the lesion was highly vascular. Histopathology confirmed a World Health Organization Grade I meningothelial meningioma with epithelial membrane antigen and progesterone receptor positivity and a low Ki-67 index (~2%). At one-year follow-up, the patient remained recurrence-free with complete symptom resolution. Conclusion: This case highlights a diagnostic pitfall in which the omission of histopathological evaluation following initial excision led to the delayed diagnosis of a primary extracranial scalp meningioma. It emphasizes that imaging alone is insufficient to exclude rare neoplasms and underscores the need for routine pathological examination of all excised scalp lesions to prevent misdiagnosis and recurrence.

Introduction Placenta praevia is a recognized pregnancy complication characterized by the placenta implanting partially or completely within the lower uterine segment, and it is associated with significant maternal and perinatal morbidity. Antepartum hemorrhage is a cardinal sign of placenta praevia, and it is unusual for a woman with placenta praevia to reach the late third trimester without vaginal bleeding. Many risk factors, i.e., age >30 years, previous caesarean section, history of dilatation and curettage, history of assisted reproductive techniques (ARTs), multiple pregnancies, and history of placenta praevia in previous pregnancies, need to be addressed so that a confirmed diagnosis can be made in the antenatal period, and women who are at increased risk for this condition can be managed or referred to a setup where proper and vigilant care is provided to both mother and baby. This study aims to identify the risk factors unique to our population and to stratify antenatal patients into high-risk and lower-risk pregnancy groups.  Methods The study was conducted in the Obstetrical Department of Ayub Teaching Hospital, Abbottabad, Pakistan, after approval of the topic and completion of all prerequisites, for a period of three months from July 1, 2025, to September 30, 2025. Women diagnosed with placenta praevia, including low-lying placenta praevia, through ultrasound examinations after 32 completed weeks of gestation were included in the case group. A total of 30 patients were included in the case group. Similarly, 60 women with normal placental localization were included in the control group (case:control ratio, 1:2). Detailed history was taken and recorded in a predefined proforma. For qualitative data, the Chi-square test was used, and a p-value of <0.05 was considered significant. Results In our study, several factors were associated with placenta previa. Women older than 30 years were more likely to develop placenta previa, with nearly four times higher odds compared to younger women (odds ratio (OR) 3.92, 95% confidence interval (CI): 1.55-9.93; p = 0.0064). A history of previous cesarean section also increased the risk, with cases showing six times higher odds than controls (OR: 6.00, 95% CI: 2.28-15.77; p = 0.00037). Similarly, women who had previously undergone dilatation and curettage had over five times higher odds of placenta previa (OR: 5.20, 95% CI: 1.97-13.70; p = 0.00095), and those who conceived through ARTs were nearly four times more likely to develop the condition (OR: 3.80, 95% CI: 1.49-9.67; p = 0.0037). Notably, a previous history of placenta previa was the strongest predictor of recurrence, with affected women facing markedly higher odds of developing the condition again (OR: 11.0, 95% CI: 3.23-37.42; p = 0.0001).  Conclusion Our study highlights several key risk factors for placenta previa, including advanced maternal age, previous cesarean section, history of dilatation and curettage, ARTs, and prior placenta previa. Identifying these factors early can help clinicians recognize women at higher risk and implement careful monitoring to prevent complications. While our findings align with larger studies, they provide additional insight by examining these associations within a focused case-control setting. Overall, these results emphasize the importance of individualized risk assessment and proactive management to improve maternal and fetal outcomes in pregnancies complicated by placenta previa.

Coronary artery calcium (CAC) scoring has emerged as a valuable tool for cardiovascular risk assessment, yet its role in asymptomatic individuals at low-to-intermediate risk remains an area of ongoing investigation. This systematic review aimed to evaluate the prognostic value of CAC scoring for predicting hard cardiovascular events and its utility in risk reclassification beyond traditional risk models. A comprehensive literature search was conducted across PubMed/MEDLINE, Embase, and the Cochrane Library for studies published between 2000 and 2025. Prospective cohort studies assessing CAC in asymptomatic adults without established cardiovascular disease and reporting hard coronary outcomes were included. A total of eight studies met the inclusion criteria. Across these studies, CAC demonstrated a consistent and graded association with incident coronary heart disease events, independent of conventional risk factors. Higher CAC scores were associated with significantly increased risk, with several studies reporting markedly elevated risk at CAC ≥100, including hazard ratios approaching 4.6 in low-risk populations, while a CAC score of zero was consistently linked to very low short- to intermediate-term event rates. Importantly, CAC improved risk stratification, particularly among individuals initially classified as intermediate risk, with studies reporting substantial risk reclassification and net reclassification improvement values of approximately 0.25. Evidence also suggested that CAC is more strongly predictive of coronary events than stroke, supporting its role as a coronary-specific risk marker. Although the review included only eight studies and demonstrated methodological heterogeneity in CAC categorization, comparator models, and outcome definitions, findings were directionally consistent across diverse populations and study designs. These results indicate that CAC scoring provides incremental prognostic value and may serve as a clinically useful tool to refine risk assessment and guide individualized preventive strategies in asymptomatic adults at low-to-intermediate cardiovascular risk.