National Institute of Cancer Research and Hospital

Background: Conventional screening methods for cervical cancer, such as visual inspection with acetic acid (VIA), have limited specificity. The Swede score, a structured colposcopic scoring system, may improve detection and triage of cervical intraepithelial neoplasia (CIN) in VIA-positive women. Methods: This cross-sectional study was conducted in the Department of Obstetrics and Gynecology at a tertiary-level hospital in Bangladesh from October 2023 to July 2024. A total of 60 VIA-positive women meeting the selection criteria were consecutively enrolled after providing informed consent. Socio-demographic information and detailed medical history were recorded. All participants underwent colposcopic assessment using the Swede score, followed by colposcopy-guided biopsy. Data were analyzed using Stata (version 17). Results: The mean age was 41.7 ± 8.1 years, with 41.7% aged 40–49 and 48.3% having below-secondary education. Chronic cervicitis was found in 50%, while 30% had CIN1 and 18.3% had CIN2+. The mean Swede score was 5.3 ± 2.0. Notably, 96.6% of women with abnormal histopathology had Swede scores of 5–10, while 61.3% of those with normal histology scored 0–4. A Swede score cut-off of 6 demonstrated high sensitivity (82.8%) and specificity (96.8%) for CIN1+ (PPV 96.0%, NPV 85.7%). For CIN2+, a cut-off of 7 achieved perfect sensitivity (100%) and high specificity (85.7%), with an NPV of 100%. Multivariate analysis showed that each unit increase in Swede score increased the risk of CIN by 39-fold (AOR: 39.14, 95% CI: 2.33–658.33). Conclusion: The Swede score is a reliable tool for detecting CIN among VIA-positive women, supporting its use for targeted biopsies and “see-and-treat” strategies in low-resource settings.

INTRODUCTION:Hydatidiform mole (HM) is a gestational trophoblastic disease characterized by abnormal proliferation of trophoblastic tissue. Accurate subclassification into complete hydatidiform mole (CHM) and partial hydatidiform mole (PHM) is essential, as CHM carries a higher risk of persistent trophoblastic disease and choriocarcinoma. Histopathology alone may be inconclusive due to overlapping features and interobserver variability. p57 immunohistochemistry has emerged as a valuable ancillary tool in differentiating CHM from PHM. This study aimed to evaluate p57 expression across histopathologically diagnosed cases of HM and determine its usefulness as a diagnostic marker. MATERIALS AND METHODS:A cross-sectional observational study was conducted on 57 cases diagnosed as complete, partial, or indeterminate HM from the Bangladesh Medical University (BMU) and private laboratories in Dhaka. All cases were re-evaluated based on defined histopathological criteria. p57 immunohistochemistry was performed in the Department of Pathology, BMU, and staining results were compared across diagnostic groups. Statistical analysis was performed using SPSS Statistics version 22.0 for Windows (IBM Corp., Armonk, NY, USA). A p value <0.05 was considered significant.  Results: Of 57 cases, 36 were histologically diagnosed as CHM, 13 as PHM, and eight as indeterminate. Among CHM, 32 (88.9%) showed negative p57 expression, while four (11.1%) were positive. In PHM cases, nine (69.2%) showed positive expression, and four (30.8%) were negative. Among indeterminate cases, six showed negative expression, and two were positive. p57 expression demonstrated a statistically significant association with final diagnosis, leading to reclassification of cases to 42 CHM and 15 PHM. CONCLUSION:p57 immunostaining significantly enhances diagnostic accuracy and reduces ambiguity in differentiating complete from partial HM. Incorporation of p57 evaluation alongside histopathology is recommended for reliable subclassification of HM.

Abstract Background and Objective Early and reliable disease prediction from structured clinical data remains challenging when datasets are small, highly imbalanced, and contain limited positive disease cases. Conventional machine learning (ML) and deep learning approaches often struggle to capture clinically meaningful relationships under such low-data representation conditions due to weak statistical associations between features and prediction targets. This study proposes a clinically grounded Distil GPT2-based table-to-text framework for disease prediction using structured healthcare datasets, motivated by the contextual reasoning capability of GPT models to better capture clinically meaningful relationships when statistical learning alone becomes insufficient due to limited data availability. Methods & Materials Structured clinical records were transformed into physician-style textual descriptions and enriched through GPT4-generated medical paraphrasing to improve minority-class representation while preserving clinical meaning. Both the original and generated clinical texts were used to fine-tune a Distil GPT2 model across four public healthcare datasets, including heart disease, heart failure, chronic kidney disease, and thyroid cancer recurrence. Gradient-based explainable AI analysis was additionally incorporated to identify clinically important features influencing prediction outcomes. Results The proposed framework demonstrated consistently strong predictive performance across four clinical datasets, achieving average precision, specificity, sensitivity, and F1-score of 0.96, 0.97, 0.96, and 0.96, respectively. The model achieved improved sensitivity, stronger generalization, and more stable predictive behavior compared with traditional ML, deep learning, transformer-based, and GAN-augmented approaches. Importantly, the framework consistently emphasized clinically meaningful variables even under severe class imbalance, where conventional ML and neural network models often struggled to identify key clinically relevant relationships. Conclusions The proposed Distil GPT2-based table-to-text framework provides a practical and clinically interpretable approach for disease prediction from limited structured healthcare data. By integrating contextual clinical reasoning with explainable prediction mechanisms, the framework suggests strong potential for early risk detection, transparent clinical decision support, and reliable deployment in real-world data-scarce healthcare settings.

Abstract Background: Bangladesh faces a rapidly increasing cancer burden, yet radiotherapy infrastructure remains critically inadequate. High-volume centers like Ahsania Mission Cancer and General Hospital (AMCGH) struggle to deliver timely treatment due to limited machines and overwhelming patient demand. The aim of this study is to evaluate waiting-time for starting radiotherapy and workflow performance in a resource-limited tertiary cancer center, comparing inpatient and outpatient pathways, documenting emergency care timelines, and assessing treatment interruptions. Materials and Methods: A retrospective observational study was conducted at AMCGH between March and June 2025. Records of 80 consecutive patients receiving external beam radiotherapy (EBRT) were reviewed. Workflow intervals—including referral, consultation, CT-simulation, treatment start, and completion—were extracted from electronic and manual logs. Descriptive statistics and comparative analyses were performed to evaluate waiting times and interruptions. Results: Of 80 patients, 40 were inpatients and 40 were outpatients. Radiotherapy was delivered with curative intent in 72 patients (90%) and palliative intent in 8 (10%). Inpatients were more likely to start radiotherapy within recommended timelines: 60% began within one month of prior treatment, compared with outpatients, 22.5% of whom presented to AMCGH three months after completion of their last treatment. From simulation to treatment, 62.5% of outpatients, initiated radiotherapy within 1–1.5 months, though cumulative delays were substantial. Treatment interruptions occurred in 28 patients (35%), predominantly due to machine downtime and toxicities from treatment. Emergency cases were prioritized with reserved slots, ensuring timely initiation. Conclusion: Despite infrastructure constraints, AMCGH demonstrates resilience in delivering radiotherapy, achieving acceptable timelines for many inpatients through integrated scheduling and prioritization of emergencies. However, prolonged delays among outpatients highlight systemic gaps in national radiotherapy capacity and referral. Expansion of modern radiotherapy infrastructure, strengthened referral pathways, and preventive maintenance strategies are urgently needed to reduce waiting times and improve cancer outcomes in Bangladesh. Keywords: Radiotherapy; Resource-limited settings; Bangladesh

Objectives In Bangladesh, where healthcare financing heavily relies on out-of-pocket expenditure (OOPE), access to palliative care remains limited, fragmented, and economically burdensome for many families. This study aims to estimate the cost of inpatient hospital-based palliative care for cancer patients and identify the major cost components contributing to this burden. Methods This prospective, multicenter study was conducted in 2 palliative care centers—one government-run and one privately operated by a trust—in Dhaka, Bangladesh. A total of 151 adult cancer patients receiving inpatient palliative care were enrolled. Data were collected from hospital records and patient interviews, and costs were categorized into direct and indirect components. Statistical analysis included descriptive statistics, decomposition analysis, and gamma generalized linear regression models with log link. Results The average cost of inpatient hospital-based palliative care was 41 170 BDT (≈339 USD). OOPE accounted for 73.5% of the total cost. Medication and patient wage loss were the highest contributors to direct and indirect costs respectively. Economic status and hospital type significantly influenced cost burdens. Higher income was linked to higher total and OOPE, with wealthier patients preferring high-cost private facilities. Conclusion Inpatient hospital-based palliative care in Bangladesh imposes a substantial financial burden on patients, driven largely by high OOPE. These findings provide evidence to support long-term efforts for financial protection, medicine access, and equitable palliative care, informing future policy and subsequent research.