Objective: To evaluate if artificial intelligence (AI)-based virtual triage and care referral (VTCR) improved care acuity alignment and has the potential to reduce unwarranted, avoidable care costs when integrated into the patient engagement capabilities of an Australian private health insurance company.
Methods: A cross-sectional study compared patient pre- and post-VTCR care intent across 4,471 encounters to evaluate the degree of clinical care acuity re-alignment (or divergence) which occurred and potential associated cost savings.
Results: Overall compliance or alignment with triage recommendations was high (74.0%), and VTCR was effective in educating patients about the most appropriate care to meet their actual clinical needs. One-half of patients (50.5%) changed their care intent. Following VTCR there was a 91.3% reduction of patients with uncertain care intent (39.8 percentage points [PP]); a 56.5% (6.2 PP) increase in intent to engage self-care, and a 35.7% (0.5 PP) decrease in emergency care intent (all p <.05). This yielded a potential $4.27 (8.6%) overall net savings per completed VTCR encounter, with potential savings of $284.55 (72.2%) per completed encounter among patients initially intending to seek emergency care, and 35 unnecessary outpatient visits potentially avoided per 1,000 encounters producing potential savings of $3.39 (6.5%) per completed encounter among patients initially intending to seek outpatient care. Almost 10% of patients intended to book a clinically appropriate telemedicine consultation following VTCR.
Conclusions: VTCR was found to be potentially clinically and cost-effective in re-directing patients who had an initial care intent not supported by their actual clinical acuity, reducing patient care uncertainty and potentially avoidable care utilization. Future research should include clinical validation of patient diagnosis and care services delivered as a primary outcome in order to confirm the potential savings identified in this study.
Objective: To identify key hospital food service attributes that influence patient satisfaction and inform actionable improvements in meal delivery and service quality.
Methods: This cross-sectional study assessed patient satisfaction with hospital food service using a modified SERVQUAL-based survey instrument. Inpatients rated both expectations and experiences across multiple service dimensions. Descriptive statistics and regression analysis were conducted to identify food service features linked to satisfaction.
Results: Food quality, perceived value, empathy, and meal diversity showed strong positive influence, while longer hospital stays and slower service were associated with lower ratings. Responsiveness also played a role in shaping overall satisfaction. These findings highlight actionable opportunities for improving patient-centered care.
Conclusions: Enhancing menu design, staff engagement, and delivery efficiency may elevate meal satisfaction and support broader institutional quality goals.
Background: Global climate change has increased the likelihood of natural disasters, including hurricanes, floods, wildfires, tornadoes, and earthquakes; this increased risk presents acute socioecological disturbances that generate cascading impacts across healthcare systems, social structures, and economic frameworks. Forty-three percent of Atlantic hurricanes that make U.S. landfall hit the southeastern United States, and their increasing intensity threatens the healthcare infrastructure. Hospital cost-to-charge ratios (CCRs) vary between rural and urban facilities, but hurricane risk impacts on hospital financial performance remain poorly understood.
Objective: To examine relationships among hurricane risk, geographic location, and hospital CCRs among southeastern hospitals.
Methods: A cross-sectional analysis was used to merge 2021 CMS Cost Report data with 2023 FEMA National Risk Index data for 1,030 hospitals across eight southeastern states. All hospitals within this region were included except for federally funded hospitals due to their unique funding model. Each hospital self-reports its categorization of urban or rural on the CMS Cost Report. Multivariate regression was used to examine associations among log-transformed CCR and hurricane risk percentile, rural/urban location, and hospital quick ratio.
Results: Among 1,030 hospitals analyzed, 52% were rural and 48% urban. The regression model explained 24.7% of CCR variation (adjusted R2 = 0.2465, F = 85.18, p <.0001). All predictors were statistically significant (p <.0001). Counter to expectations, each 1-point increase in hurricane risk percentile was associated with a 0.1% decrease in CCR, indicating improved cost efficiency in higher-risk areas. LOGCCR = -.75714 -.00840 (NAPCT) -.26551 (RURAL) +.01491 (QUICK) -.00011 (QUICK2). Rural hospitals as indicated by the CMS Cost Report demonstrated 26.5% lower CCR compared to urban hospitals. Hospital quick ratio showed a curvilinear relationship with CCR; at the mean quick ratio (3.819), each 1-unit increase was associated with a 1.4% increase in CCR. No significant multicollinearity was detected among predictor variables.
Conclusions: Hurricane risk is paradoxically associated with lower hospital CCR, suggesting complex financial adaptations in high-risk areas. Rural hospitals maintain more favorable cost structures than urban facilities, and policymakers should consider these geographic variations in disaster preparedness strategies.
Background: Sepsis increases mortality and is a global healthcare concern. In the United States evidence-based early identification and treatment protocols are required in some states. Predictive analytics is one option to meet this requirement.
Objective: The purpose of this system-wide initiative was to develop an interprofessional team to implement, evaluate, and optimize an early alert system for patients at high risk for sepsis utilizing predictive analytics to improve patient outcomes.
Methods: The Sepsis Predictive Model and customized Best Practice Advisory (BPA) were evaluated utilizing a phased-rollout and pilot-testing. Regular meetings were conducted to analyze data and strategize iterative changes. End users were educated.
Results: Pilot tests established the most effective alert-sepsis trigger scores; scores > 5 resulted in a 54% decrease in alerts. The Concordance Statistic (C-Stat) for the system-wide roll out was 0.765. The proportion of patients who had a BPA alert, had sepsis and an intervention (18.83%) was significantly greater than the proportion of patients who had a BPA alert had sepsis, and did not have an intervention (4.35%, p-value <.001). Similar results were found for the proportion of patients with a final diagnosis of infection who had a BPA alert, and an intervention, compared to those who did not. Early warning of potential sepsis resulted in a reduction in sepsis mortality rates not present on admission.
Conclusions: An interprofessional team approach to leveraging established evidence and harnessing predictive analytics, fostered a customized collaborative protocol that improved sepsis care. Predictive analytics, tailored to clinical settings, is a powerful tool for advancing sepsis management.
Objective: Effective interprofessional collaboration (IPC) is a cornerstone of high-quality healthcare delivery. Given the complexity of healthcare systems, optimal patient outcomes depend on the ability of professionals across disciplines to work cohesively. Conversely, weak collaboration among health workers contributes to poor service quality, a challenge evident in Nigeria. This study explored the perceptions and practices of IPC among healthcare professionals at the Federal Medical Centre, Owo, Ondo State, Nigeria.
Methods: A cross-sectional survey was conducted using the validated Assessment of Interprofessional Collaboration Scale questionnaire, rated on a five-point Likert scale. Data analysis involved mean ± standard deviation for continuous variables and proportions/percentages for categorical data.
Results: A total of 185 respondents participated, with the majority (77.3%) aged between 20-39 years. Females accounted for 61.1% of the sample, though gender distribution varied by profession: nursing remained predominantly female (91.2%), while medical laboratory science was male-dominated (87.5%). Among specialists, laboratory scientists (37.5%), physiotherapists (35%), and doctors (33.3%) had the highest proportions. Doctors and nurses recorded the highest mean scores across most IPC domains, particularly role clarity (4.40 and 4.33, respectively) and trust (4.45 and 4.34). Administrators and “others” consistently recorded the lowest scores (3.12-3.74). ANOVA revealed significant differences across all parameters (p <.001). Post-hoc analysis confirmed stronger doctor-nurse collaboration compared to other groups.
Conclusions: Findings revealed that doctors demonstrated the strongest interprofessional collaboration, followed by nurses and pharmacists. In contrast, physiotherapists, laboratory scientists, administrators, and other cadres reported lower levels of collaboration. Notably, doctors consistently rated themselves highly and were similarly rated by other professional groups. Strengthening IPC across all healthcare professions remains essential to improving teamwork and ensuring better patient outcomes.