MHMahmudul Hasan

Mahmudul Hasan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Mahmudul Hasan has a total of 7 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Pre-admission polypharmacy burden and intensive care unit outcomes in patients with sepsis: A retrospective cohort study using the MIMIC-IV-ED linked database

    by Farhana Haque, Mahmudul Hasan

    Purpose: Polypharmacy is highly prevalent among critically ill patients, yet it’s independent impact on intensive care unit (ICU) outcomes in sepsis remains critically unexplored. We aimed to evaluate whether pre-admission polypharmacy independently predicts ICU mortality and provides incremental prognostic value using the medication reconciliation module of the MIMIC-IV-ED linked database. Materials and Methods: We conducted a retrospective cohort study of 3,347 adults admitted to the ICU who met Sepsis-3 criteria. Pre-admission polypharmacy was categorized as none (0-4), standard (5-9), or high (≥10 medications). Multivariable logistic regression, propensity score matching, and reclassification analyses (NRI/IDI) were performed. The primary outcome was in-hospital ICU mortality. Results: High polypharmacy was present in 58.9% of patients. Crude ICU mortality increased sequentially: 18.5% (none), 26.0% (standard), and 27.5% (high; p < 0.001). After multivariable adjustment, high polypharmacy independently predicted in-hospital ICU mortality (aOR 1.45, 95% CI (1.10-1.91)), and 28-day mortality (aOR 1.47). Drug-class analysis identified statins as significantly protective (aOR 0.56), whereas RAS blockers combined with diuretics increased acute kidney injury risk (aOR 1.49). Propensity matching confirmed the primary mortality association (matched aOR 1.28). Conclusions: By utilizing the ED medication reconciliation table, this study proves high polypharmacy represents a distinct ‘pharmacologic frailty’, independent of acute severity. Available instantly at triage, this zero-latency metric provides significant early prognostic value (SOFA NRI = 0.24) and identifies actionable high-risk interactions (e.g., RAS blockers plus diuretics) for immediate, targeted pharmacist-led intervention upon ICU admission.

  • Open Access

    CABLE-Net: Collaborative automated breast lesion evaluation integrating mammography ultrasound fusion with LLM-based radiopathological reporting

    by Mahmudul Hasan, Sharmin R. Ara, Shabnam Akhter, Sharmin Akhter Rupa, Rayhana Awwal, Kamrul Hasan

    Multimodal breast cancer diagnosis remains limited by inter-modal distributional discrepancy between acoustically acquired ultrasound and radiographically acquired mammographic signals, inadequate cross-modal alignment, and the underutilization of structured radiological descriptors as primary inputs. These challenges hinder reliable integration of heterogeneous biomedical signals for accurate breast cancer classification. We propose CABLE-Net, a unified octa-modal end-to-end deep learning framework integrating breast ultrasound images, dual-view mammographic projections, and structured radiological report descriptors from both modalities, operating within a two-stage diagnostic pipeline for simultaneous benign-malignant classification and automated radiopathological report generation. Stage I achieves perfect normal-abnormal separation using ultrasound alone. The architecture combines PopperNet, a falsification-driven convolutional backbone performing per-channel counter-evidence gating to suppress contradictory activations under multi-task gradient interference; a bidirectional spatial cross-attention module for asymmetric feature exchange between CC and MLO views; a transformer-based text feature extractor elevating structured descriptors to primary inputs; a pseudo graph fusion dense network propagating relational cross-modal correlations through residual graph convolutional blocks; a shared-private geometric alignment domain adapter minimizing distributional divergence through polar angular-radial adaptation; and a cross-gated late fusion mechanism dynamically weighting modality contributions via a learned scalar gate. Evaluated on the BUSMIAT dataset of 899 patients under five-fold cross-validation, CABLE-Net achieves 98.84% accuracy on benign-malignant classification, outperforming state-of-the-art multimodal methods by up to 10.91% in accuracy. CABLE-Net demonstrates state-of-the-art performance for multimodal breast imaging analysis and highlights the potential of integrated image-text modeling to improve diagnostic accuracy, streamline radiopathological reporting through LLM-generated BI-RADS-consistent reports, and reduce radiologist workload in resource-limited settings.