SearcharxivSearch

arXiv subjects

Md Fantacher Islam

Publications and source records attributed to Md Fantacher Islam.

3 recordsLinked to original sources

A Digital Twin for Individualized Treatment Effects of Non-Invasive Respiratory Support Strategies (DINIRS)

Objective: Choosing between noninvasive respiratory support (NIRS) and invasive mechanical ventilation (IMV) for acute respiratory failure is a time-sensitive decision. Although guidelines provide population-level guidance, it remains unclear who benefits more from NIRS than IMV. The standard outcome, ventilator-free days at 28 days (VFD-28), scores death and prolonged ventilation equally, and current estimators do not distinguish between them. We developed and validated a censoring-aware Digital Twin framework for Individualized Treatment Effects of Non-Invasive Respiratory Support (DINIRS) to estimate individualized treatment effects (ITEs) that capture both mortality and ventilation duration. Materials and Methods: We emulated a target trial in 5,336 MIMIC-IV patients and trained DINIRS on 23 baseline clinical variables measured during the first 24 ICU hours. A transformer encoder with a survival attention gate decomposed VFD-28 into survival probability and conditional ventilation duration. A cross-fitted, doubly robust learner estimated ITEs. We externally validated DINIRS in 2,540 patients from the multi-site eICU-CRD dataset without retraining. Results: The DINIRS policy achieved a mean benefit of 2.07 ventilator-free days per patient (207 per 100 patients) compared with observed practice. Predicted NIRS benefit was higher among patients with less organ dysfunction (88.4% versus 49.0%) and persisted across hypoxemia severity. External validation reproduced this pattern. Discussion: The NIRS benefit stemmed from shorter ventilation among survivors rather than from reduced mortality, indicating that avoiding intubation-associated complications was the primary mechanism. Conclusion: Prospective validation is needed before these estimates inform treatment decisions. The decomposition framework can be extended beyond respiratory support to any zero-inflated composite outcome.

q-bio.QM

Development and Evaluation of an Ontology for Non-Invasive Respiratory Support in Acute Care

Managing patients with respiratory failure increasingly involves noninvasive respiratory support (NIRS) strategies to support respiration, often preventing the need for invasive mechanical ventilation. However, despite the rapidly expanding use of NIRS, there remains a significant challenge to its optimal use across all medical circumstances. It lacks a unified ontological structure, complicating guidance on NIRS modalities across healthcare systems. This study introduced NIRS ontology to support knowledge representation in acute care settings by providing a unified framework that enhances data clarity and interoperability, laying the groundwork for future clinical decision-making. We developed NIRS ontology using the Web Ontology Language (OWL) and Protege to organize clinical concepts and relationships. To enable rule-based clinical reasoning beyond hierarchical structures, we added Semantic Web Rule Language (SWRL) rules. We evaluated logical reasoning by adding a sample of 6 patient scenarios and used SPARQL queries to retrieve and test targeted inferences. The ontology has 145 classes, 11 object properties, and 18 data properties across 949 axioms that establish concept relationships. To standardize clinical concepts, we added 392 annotations, including descriptive definitions based on controlled vocabularies. SPARQL query evaluations across clinical scenarios confirmed the ontology ability to support rule based reasoning and therapy recommendations, providing a foundation for consistent documentation practices, integration into clinical data models, and advanced analysis of NIRS outcomes. In conclusion, we unified NIRS concepts into an ontological framework and demonstrated its applicability through the evaluation of patient scenarios and alignment with standardized vocabularies.

q-bio.OT

Characterizing Fungal Infections in the All of Us Research Program

Fungal infections, such as Coccidioidomycosis, Aspergillosis, and Histoplasmosis, represent a growing public health concern in the United States. The rising incidence of these mycoses is linked to climate shifts, demographic changes, and social determinants of health. However, the actual burden of these infections is often underestimated by traditional surveillance methods. Therefore, this study aims to characterize these infections within the All of Us Research Program and evaluate the quality of clinical and health data related to fungal infections. We constructed three fungi cohorts of Coccidioidomycosis (n=1,173), Aspergillosis (n=687), and Histoplasmosis (n=345) among over 400,000 participants using electronic health record data. We analyzed geographic and sociodemographic distributions and performed a data quality assessment on ten key laboratory biomarkers to evaluate data completeness, unit conformance, and measurement concordance within a 90-day window of diagnosis. Our analysis confirmed known epidemiological patterns, including the geographic distributions of Coccidioidomycosis in the Southwest and Histoplasmosis in the Midwest. Fungal infections disproportionately affected older adults, males, and White non-Hispanic individuals. The data quality assessment revealed high completeness for general hematology markers (e.g., Hemoglobin > 70%) but limited availability for biomarkers, such as Beta 1,3 Glucan (< 15%). While measurement concordance was strong (e.g., hemoglobin-hematocrit correlation, r = 0.94), unit conformance was poor for key inflammatory markers, such as erythrocyte sedimentation rate. In conclusion, the All of Us dataset is a valuable resource for characterizing fungal infections. However, significant data quality issues related to completeness and conformance for specialized biomarkers must be addressed to enhance their applicability for robust clinical research.

q-bio.QM