64 papers
A retrospective analysis of New York City hospitalizations reveals that the high rate of sickle cell disease patients leaving against medical advice, which is strongly associated with subsequent readmissions, serves as a critical indicator of unmet care needs and systemic barriers rather than solely patient responsibility.
This study validates rule-based registry indicators for monitoring postdiagnostic antibiotic decisions in pediatric febrile urinary tract infections, demonstrating that while these measures capture overall prescribing patterns, they underestimate guideline concordance and require calibration against clinician-reviewed data to improve accuracy for antimicrobial stewardship.
This qualitative study of English primary care clinicians reveals that while Advice and Guidance (A&G) is utilized to support decision-making and manage complex cases, its effectiveness is heavily contingent on timely, clinically relevant responses and the resolution of barriers such as delayed feedback and concerns over equitable workload distribution.
This study demonstrates that applying targeted R Shiny optimization strategies to the NEST-IT digital health dashboard significantly reduced latency and improved system reliability, thereby enabling timely access to critical neonatal care data in resource-constrained hospitals across sub-Saharan Africa.
This qualitative case study of Nakuru County, Kenya, demonstrates that enhancing health facility financial autonomy through budgeting capacity building requires a sustained, multi-year, and adaptive approach that tailors support to facility levels, combines training with standardized tools, and embeds strong monitoring and leadership mechanisms.
This study developed and validated a Large Language Model pipeline that successfully drafts high-quality Statistical Analysis Plans from clinical trial protocols, demonstrating strong performance on descriptive content while highlighting the continued necessity for human oversight in complex statistical reasoning tasks.
This study of nearly 48,000 German melanoma patients demonstrates that treatment in certified cancer centres is associated with significantly improved overall and disease-free survival compared to non-certified hospitals, highlighting the value of evidence-based quality standards while underscoring the need to expand access to such high-quality care.
This paper proposes a three-step, causally informed framework that integrates domain knowledge, graph-theoretic rules, and empirical validation to improve the robustness and generalizability of neurobiomedical machine learning models by rigorously addressing confounding while cautioning against causal misinterpretation of associative predictions.
Utilizing 2021-22 Ethiopia Service Provision Assessment data and principal component analysis, this study reveals significant regional and facility-level disparities in reproductive, maternal, newborn, and child health service readiness, highlighting critical gaps in resources, staffing, and infrastructure that necessitate targeted investments to ensure equitable access to quality care.
This paper proposes a GDPR-compliant, FHIR DK-standardized microservice architecture for Region Hovedstaden to securely integrate continuous wearable health data into the national electronic health record, addressing interoperability gaps and building on stakeholder-identified trust factors to enable safe data sharing.
This reflexive thematic analysis of 36 stakeholders in a regionalized Canadian health system reveals that while localized care for brain tumors demonstrates strengths like responsive palliative integration and provider commitment, systemic fragmentation at the interfaces between tertiary centers and community services creates critical barriers to care continuity, highlighting the urgent need for standardized pathways and cross-organizational coordination to serve geographically dispersed populations.
This comparative survey of 200 healthcare risk managers in the United States and United Kingdom reveals significant differences in risk assessment techniques and organizational practices, highlighting a need for stronger institutional support and a shift toward prospective, multidisciplinary approaches to improve patient safety.
This experimental study demonstrates that a telehealth-enabled multi-sensory environment significantly reduces both physiological stress markers and subjective anxiety levels in young adults following a stress-inducing task, while also identifying key design preferences to guide future implementations in educational settings.
This study utilized latent class analysis on a randomized controlled trial to identify distinct high-need patient subgroups, revealing that tailored intensive care management significantly reduced readmissions and emergency visits for specific profiles, thereby suggesting that segmenting patients by medical, behavioral, and social risk factors can enhance the effectiveness of complex care interventions.
In a study of 8,774 postpartum patients, traditional logistic regression outperformed automated machine learning and ensemble methods in predicting 14-day readmissions, demonstrating that threshold optimization rather than algorithmic complexity is the key driver of clinical utility, though all models showed modest discrimination using only sociodemographic variables.
This implementation research demonstrates that a co-created digital monitoring and action planning tool, piloted in Lahore, Pakistan, effectively strengthens routine immunisation systems by enhancing real-time data visibility, improving decision-making for zero-dose and under-immunised children, and fostering stakeholder ownership to address coverage inequities.
This mixed-methods study protocol outlines a comprehensive plan to assess AI awareness, attitudes, and educational needs among Qatar's primary healthcare workforce, aiming to develop an evidence-based readiness framework and training roadmap to facilitate the effective and ethical integration of artificial intelligence in primary care.
This study demonstrates that the absence of routine orientation assessment within 24 hours in ICU patients with low acute physiologic derangement is a powerful, independent predictor of mortality, suggesting it serves as a critical objective marker for unmeasured care process failures that current severity scores and infrastructure often miss.
This study of health sciences academics in Germany reveals that institutional norms privileging continuous productivity and availability drive both external exclusion and self-exclusion, creating a self-reinforcing cycle of social homogeneity that can only be broken by challenging the structural conditions defining academic success.
This study of Sri Lankan colorectal carcinoma patients demonstrates that right-sided tumors exhibit distinct clinicopathological features associated with microsatellite instability, and while the MsPath score shows a significant correlation with mismatch repair deficiency, immunohistochemistry using a PMS2 and MSH6 panel remains the most feasible and reliable method for screening in resource-limited settings.