5 articles found
An Entropy-Based Approach to Decision Tree Analysis in Emergency Medicine: Optimization of Diagnostic Tool Selection to Thoracic Aortic Dissection
Title
An Entropy-Based Approach to Decision Tree Analysis in Emergency Medicine: Optimization of Diagnostic Tool Selection to Thoracic Aortic Dissection
Authors & Affiliations
Daerin Hwang, Abdel Badih el Ariss1, Norawit Kijpaisalratana1, Paul Chong2, Pedram Safari4, David Chen3, Ahmad Hassan1
1 Massachusetts General Hospital, Harvard Medical School
2 Campbell university
3 Temerty Faculty of Medicine, University of Toronto
4 MGH Institute of Health Professions
CHARACTER COUNT: 2050 / 2050
Introduction
Shannon entropy is a key concept in both machine learning and information theory, significantly influencing decision tree modeling. In emergency medicine, the utilization of testing and imaging tools to reduce uncertainty is vital for enhancing medical decision-making, especially in time-sensitive scenarios. While sensitivity and specificity assess test accuracy, entropy provides insight into how much a test clarifies the overall clinical picture, which is crucial in time-sensitive situations like thoracic aortic dissection. The aim of this study is to evaluate and compare the effectiveness of entropy and entropy reduction against conventional metrics of sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV), in the diagnostic evaluation of thoracic aortic dissection.
Methodology
We gathered diagnostic metrics, including true positives and negatives, as well as false positives and negatives, from a well-established online diagnostic accuracy database known as "Get the Diagnosis" for thoracic aortic dissection. Data collection took place from November 17, 2022, to January 22, 2023. This dataset allowed us to compute sensitivities, specificities, negative predictive values (NPVs), and positive predictive values (PPVs). A decision tree representing the diagnostic tool was created and examined for Shannon entropy and entropy reduction across the various child nodes. The decision tree was based on 2x2 diagnostic tables, covering total cases (N), true positives (TP), false positives (FP), false negatives (FN), and true negatives (TN).
Results
Using a helical CT scan for thoracic aortic dissection, we observed a sensitivity of 97.64% and a specificity of 98.90%, whereas MRI exhibited a lower sensitivity (93.33%) but a higher specificity (99.30%). However, entropy removal calculations revealed that the helical CT scan removed 87.23%
of entropy associated with thoracic aortic dissection, while MRI removed 81.36%. Within these populations studied, this suggests helical CT scan may provide greater reduction in diagnostic uncertainty than MRI in thoracic aortic dissection assessment and underscores the unique insights offered by entropy removal, which sensitivity and specificity fail to provide.
Conclusion
Unlike sensitivity and specificity, entropy captures the inherent variability and uncertainty in diagnostic data, especially in complex medical scenarios where it accommodates individual variability in patient responses and disease manifestations.A Qualitative Assessment of the Feasibility, Usability, and Clinical Impact of the Keva365 Remote Patient Monitoring Platform for Asthma Management
Background
Remote Patient Monitoring (RPM) has emerged as a promising approach to managing chronic conditions like asthma, particularly during the COVID-19 pandemic. However, limited research exists on the use of qualitative analysis to capture patient feedback and experiences in RPM programs. This study extends a quantitative observational study that explored the impact of RPM on patients with moderate-to-severe asthma.
Objective
The aim of this study was to evaluate the feasibility and usability of Keva365, a digital therapeutic platform designed for remote asthma management, and to explore its impact on patient-provider relationships, asthma management, patient compliance, and engagement.
Methods
A purposeful sample of six patients with moderate-to-severe persistent asthma participated in the study. Over a nine-month period, participants were interviewed once using an open-ended question guide to collect qualitative data. The interviews were recorded, transcribed, and analyzed thematically using NVivo software. Data were used to assess the feasibility of the RPM intervention, its usability, and its impact on patient experiences. Written consent to publish these details has been obtained from all participants that were included in this research.
Results
Thematic analysis identified key themes related to patients' experiences with the app, their compliance and engagement with the program, their relationships with providers, and asthma management. All participants reported positive experiences with the program, noting the app’s usability, efficiency, and impact on their relationships with healthcare providers. Participants expressed high levels of satisfaction and a willingness to recommend the program to others. Feedback from the interviews contributed to near real-time modifications of the RPM application, enhancing its usability and navigation.
Conclusions
The study found that integrating patient feedback is essential for improving the usability of RPM platforms. Continuous iterative refinement based on patient experiences can lead to more patient-centered digital health solutions, enhancing both patient compliance and the overall care experience. The findings suggest that RPM programs can effectively support asthma management while fostering positive patient-provider relationships. make a scope statement for Conduct Science journal that focuses on current and latest research that focuses on shaping the future of medicine.Humanizing Critical Care: Transforming ICUs Through Empathy and Innovation
Background:
Intensive Care Units (ICUs) in resource-limited settings face persistent challenges, including high infection rates, staffing shortages, and inconsistent patient-family engagement. Standardized ICU audits provide a structured approach to assessing and improving infection control, staff preparedness, and patient-centered care. This study evaluates CritiCore, a structured ICU audit framework innovation piloted and applied longitudinally over three sequential cycles at a single center, designed to drive iterative, evidence-based quality improvements through targeted intervention cycles.
Methods:
CritiCore was implemented at Evercare Hospital Lahore, Pakistan, across three cycles: baseline audit (November 2024), first re-audit (January 2025), and second re-audit (April 2025). Each cycle included structured observational assessments, infection-surveillance review, and multidisciplinary stakeholder interviews with ~20 ICU professionals (physicians, nurses, infection control specialists, and administrative staff). Findings from each audit informed targeted interventions focusing on real-time infection surveillance, simulation-based staff training, and standardized patient-family engagement strategies (Empatheon).
Results:
The initial audit revealed elevated hospital-acquired infection rates (≈40–50%), linked to inconsistent hand hygiene and ventilation gaps. Staffing continuity was affected by reliance on locum personnel and limited simulation-based training. Patient-family engagement was inconsistent, with unclear visitation policies and fragmented communication. By the first re-audit, adherence to infection-control protocols improved, simulation training participation increased, and structured family communication and visitation protocols were adopted. By the second re-audit, most improvements were sustained, with additional gains in simulation training coverage, consistency of family engagement, and environmental control measures. Infection control adherence remained markedly higher than baseline, and staffing continuity improvements were maintained.
Conclusion:
This three-cycle ICU audit from Lahore demonstrates the feasibility and sustained impact of a structured, iterative quality-improvement framework in an LMIC private hospital. The same CritiCore approach was subsequently rolled out at Evercare hospitals in Nigeria (twice) and Kenya (once), supporting adaptability across diverse settings; a formal multi-site analysis is planned.
Keywords: critical care transformation; Evercare hospitals; ICU audit; infection surveillance; LMICs; patient-family engagement; quality improvement; staff training; Empatheon.
Money as Medicine: Beyond the Monetary Value of Cash Assistance Programs
Social determinants of health (SDOH)—the root causes of health disparities—often fall outside the scope of traditional clinical care. In this discussion, we argue that financial interventions, particularly cash assistance programs, play a transformative role in improving health outcomes by addressing SDOH. Drawing on lessons from established public health approaches, we explore the concept of "Money as Medicine," which reframes cash assistance not just as economic relief but as a vital component of healthcare, directly impacting physical and mental well-being.1 To build healthier communities, we recommend integrating cash assistance programs into the healthcare system to reduce emergency department (ED) utilization, enhance mental health, and promote overall health stability. We explore key evidence, highlight successful models, such as the nonprofit Link Health, and propose pathways for integration. 
