National Institute of Cancer Research & Hospital (NICRH) is dedicated to cancer patient management, education and research. This is the only tertiary level center of the country engaged in multidisciplinary cancer patient management.It started its activity in a tin-shade building of Dhaka Medical College and Hospital in 1982, soon it is shifted to the present location at Mohakhali in 1986. According to a Memorandum of Understanding signed between the Ministry of Health and the Rotary Club of Dhaka the latter built the Rotary Cancer Detection Unit (RCDU) and the Cancer Institute started working as an outdoor cancer detection unit only. In 1991, 50 bed indoor facilities incorporated. In 1994 the cancer institute renamed as National Institute of Cancer Research & Hospital (NICRH) and the first radiation treatment was applied to a patient in 1995 with a Cobalt 60 Teletherapy machine.With the provision of support from the Saudi Fund for Development (SFD), the up-gradation works of this Institute to 300 bedded Center has been completed. In April 2015 it was upgraded to a 300-bed hospital. In 2019 the Hon'ble Health Minister Mr. Jahid Maleque M.P. consented to convert NICRH as a 500-bed hospital and the work is almost completed.
Background: Mutation in the TP53 suppressor gene and accumulation of p53 protein are the common genetic events in gastric carcinomas. This mutation has been associated with abnormalities in cell cycle regulation, DNA repair and synthesis, apoptosis, and is suggested to be implicated in the prognosis of gastric carcinoma. Objective: The purpose of the present study was to assess the immunohistochemical expression of p53 protein in gastric adenocarcinoma and to study the association between p53 protein expression and tumour staging, including depth of invasion and regional lymph node involvement. Methodology: In this cross-sectional observational study, 60 paraffin blocks of gastric adenocarcinoma were re-evaluated, and depth of invasion and regional lymph node involvement were assessed. The p53 expression in the tumour cell nucleus of the submitted blocks was assessed by the standard immunoperoxidase method. Appropriate positive control were run for each batch of slides. Results: In this study, out of 60, forty cases (66.67%) showed high expression of p53 protein. Our study showed a statistically significant association of p53 protein expression with depth of invasion of tumour (p < 0.001) and regional lymph node involvement (p < 0.001). Conclusion: There was a significant association between immunohistochemical expression of p53 protein and tumour staging, including depth of invasion of tumour and regional lymph node involvement. These results indicate that immunohistochemical expression of p53 protein is an important prognostic factor of gastric carcinoma, allowing the selection of a group of patients with an extensive therapeutic indication. Journal of National Institute of Neurosciences Bangladesh, January 2026;12(1):110-114
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.
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 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 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 with 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. Conclusions: The proposed 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 demonstrates strong potential for early risk detection, transparent clinical decision support, and reliable deployment in real-world low-resource healthcare environments. ### Competing Interest Statement The authors have declared no competing interest. ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: UC Irvine Machine Learning Repository Link: https://archive.ics.uci.edu/ I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes UC Irvine Machine Learning Repository