Chen Dun

Objective: Value-based care (VBC) represents a fundamental shift from volume-driven reimbursement to models focused on improving patient outcomes and reducing costs. Informatics plays an essential, but often underappreciated, role in enabling VBC. Traditional discussions of informatics emphasize data and technology; however, a broader sociotechnical view highlights how people, organizations, workflows, and policies interact with technology to influence the success of VBC initiatives. In this article, we apply the Informatics Stack as a heuristic framework to examine how informatics shapes VBC across 4 phases: research, policy setting, healthcare implementation, and local assessment within learning health systems. Materials and Methods: We applied the Informatics Stack as a heuristic framework to analyze VBC across four phases: research, policy setting, healthcare implementation, and local assessment. To provide a grounded analysis, the study focused on the Healthcare Implementation phase, utilizing vascular claudication management as a primary illustrative case to demonstrate how high-level VBC policies are converted into granular clinical workflows and algorithms. Results: We present “As-Is” characterizations of informatics in VBC at multiple levels of the Stack, ranging from world-level regulatory forces to organizational values, to business processes, workflows, information systems, modules, algorithms, data, and underlying technologies. We also outline “To-Be” opportunities, including computable clinical guidelines, interoperable data platforms, algorithm performance monitoring, and integration of multimodal data streams into decision support. To provide a grounded analysis, we narrow our focus to the Healthcare Implementation phase, using vascular claudication management as our primary illustrative case. Managing claudication in a VBC model requires preventing low-value care, such as early, aggressive peripheral vascular interventions, while optimizing patient-specific outcomes. We will used this clinical example to walk down the levels of the Stack, demonstrating how informatics converts high-level VBC policy into granular clinical workflows and algorithm. Discussion: In this article, we apply the Informatics Stack as a heuristic framework to examine how informatics shapes VBC across four phases, specifically focusing on the Healthcare Implementation phase using vascular claudication management as an illustrative case. We present “As-Is” characterizations of the current state of informatics alongside “To-Be” opportunities, including computable clinical guidelines, interoperable data platforms, and algorithm performance monitoring. Concluding that VBC requires a socio-technical perspective beyond mere data and technology, we propose the Stack as a diagnostic tool for health leaders and offer a “VBC Informatics Gap Analysis Toolkit” to help organizations identify alignment gaps in their implementation strategies. Conclusion: In teaching informatics and in generating an assessment of where a problem or a field is at any point in time, we have found the Stack to help students, universally, and many alumni, to apply in their work. However, for the health system leader attempting to implement VBC, the Stack must be more than a theoretical model; it must be a diagnostic tool. It does not prescribe specific software purchases, but rather points out to an organization where they may have inconsistencies in their conception of their informatics infrastructure or frank gaps in that conceptualization.

Objective: The purpose of this study was to assess the impact of racial/ethnic disparities and other variables in 30‐day Emergency Department (ED) visits due to post‐hysterectomy complications. Methods: We conducted a retrospective cohort study of patients who underwent hysterectomy between 2017 and 2021 in Florida and Maryland using Healthcare Cost and Utilization Project (HCUP) databases. Multivariable logistic regression models estimated associations between race/ethnicity and 30‐day ED visits, including interaction terms for state, surgery route, and setting. Generalized linear modeling was used to assess surgery costs. Results: Black patients had significantly higher odds of 30‐day ED visits compared to White patients (odds ratio [OR] 1.16, 95% confidence interval [CI] 1.12–1.20, P < 0.001), while Asian or Pacific Islander patients had lower odds (OR 0.86, CI: 0.76–0.98, P = 0.020). Racial disparities differed by state. For example, the increased risk of 30‐day ED visits among Hispanic patients was attenuated in Maryland compared to Florida (OR 0.85, CI: 0.73–0.98, P = 0.024). Black patients had consistently higher odds in both inpatient and outpatient settings, whereas elevated risk among Hispanic patients was limited to outpatient procedures. Racial compositions also varied by primary payer group. Total charges for index hysterectomy and 30‐day ED utilization were lower in Maryland compared to Florida (OR 0.21, CI: 0.21–0.21, P < 0.001). Conclusion: Significant racial disparities in 30‐day ED visits persist following hysterectomy. These disparities are associated with geographic, clinical, and socioeconomic factors. These findings highlight the necessity for interventions focused on promoting health equity.

Introduction: Economic evaluations are essential for informed healthcare decision-making but often face challenges due to inconsistent reporting and methodological complexity. Large Language Models (LLMs) offer a scalable alternative for evaluating adherence to such standards. Building on Hileas, a previously developed tool, this study assesses the accuracy of LLM-generated evaluations compared with human reviewers, aiming to quantify reliability, identify limitations, and advance automated, but assistive quality assessment methods in health economic research. Methods: In all, 110 peer-reviewed economic evaluation papers were evaluated using the CHEERS checklist through structured LLM prompts and scored by 2 human reviewers on a 0-4 ordinal scale. Interrater agreement and LLM performance were measured using Cohen’s kappa, sensitivity, specificity, and area under the curve. LLM outputs were compared against human consensus ratings, and usability of the review platform was assessed with the System Usability Scale. Results: Among 2860 item-level evaluations, 25.3% showed disagreement between human reviewers, with generally low interrater reliability (kappa=−0.07 to 0.43). Compared with human consensus, the LLM achieved 72.3% to 94.7% agreement, with areas under the curve up to 0.96 but variable performance across checklist items. At the paper level, LLM-assigned CHEERS scores (median, 17) were consistently lower than human-reviewed scores (median, 18-21). Conclusion: This study demonstrated an exploratory proof-of-concept application of LLMs to research quality evaluation. Our results suggests that the LLM was generally able to provide well-reasoned evaluations that closely aligned with human assessments, although with some limitations in fully supporting its judgments.

Introduction: Economic evaluations are essential for informed healthcare decision-making but often face challenges due to inconsistent reporting and methodological complexity. Large Language Models (LLMs) offer a scalable alternative for evaluating adherence to such standards. Building on Hileas, a previously developed tool, this study assesses the accuracy of LLM-generated evaluations compared with human reviewers, aiming to quantify reliability, identify limitations, and advance automated, but assistive quality assessment methods in health economic research. Methods: In all, 110 peer-reviewed economic evaluation papers were evaluated using the CHEERS checklist through structured LLM prompts and scored by 2 human reviewers on a 0-4 ordinal scale. Interrater agreement and LLM performance were measured using Cohen’s kappa, sensitivity, specificity, and area under the curve. LLM outputs were compared against human consensus ratings, and usability of the review platform was assessed with the System Usability Scale. Results: Among 2860 item-level evaluations, 25.3% showed disagreement between human reviewers, with generally low interrater reliability (kappa=−0.07 to 0.43). Compared with human consensus, the LLM achieved 72.3% to 94.7% agreement, with areas under the curve up to 0.96 but variable performance across checklist items. At the paper level, LLM-assigned CHEERS scores (median, 17) were consistently lower than human-reviewed scores (median, 18-21). Conclusion: This study demonstrated an exploratory proof-of-concept application of LLMs to research quality evaluation. Our results suggests that the LLM was generally able to provide well-reasoned evaluations that closely aligned with human assessments, although with some limitations in fully supporting its judgments.

Cesarean sections are commonly performed in the United States, including among patients for whom vaginal delivery may be clinically feasible. This study aimed to evaluate rates and factors associated with cesarean section use and inpatient cost among low-risk deliveries in selected U.S. states. This was a retrospective, cross-sectional analysis using Healthcare Cost and Utilization Project (HCUP) State Inpatient database for Maryland, Florida, and Wisconsin between January 1, 2017, and December 31, 2020. American Hospital Association (AHA) data and median household income quartiles based on the Agency for Healthcare Research and Quality's (AHRQ) 2018 estimates were included in this study to assess hospital and patient neighborhood characteristics. AHA data was linked to HCUP data using the hospital identifier number. Median household income quartiles were linked to HCUP using ZIP codes. A multivariable generalized estimating equations regression model including a random intercept for hospitals was used to identify patient- and hospital-level characteristics associated with the use of cesarean section. 245,383 women who underwent a delivery between 2017 and 2020 were included in the analysis. Of these women, 8.1% had cesarean section and 91.9% had vaginal delivery. Mean age was 26.9 (SD ± 4.41) years for cesarean section and 26.9 (SD± 4.37) years for vaginal delivery. An increasing rate of cesarean section was detected during the study period. Higher rates of cesarean section were found among Black and Hispanic women compared to White and Asian, and among women with lower income. Hospitals in Florida had the highest cesarean section rate of 9.4% among low-risk women while Maryland and Wisconsin had rates of 6.3% and 5.3%, respectively. Being Hispanic or Black, having private insurance, and giving birth in a for-profit hospital were associated with higher cesarean section utilization after controlling patient- and hospital-level factors. A range of clinical and policy interventions have been implemented over the past decade to reduce cesarean sections among low-risk deliveries; however, we still identified an increasing rate of cesarean section among low-risk women between 2017 and 2020 in select U.S. states. There is an emergent need to revisit policies and interventions that impact cesarean section in these states. Women with low socioeconomic status were more vulnerable to have cesarean sections. Identifying variation in cesarean delivery rates among low-risk populations may inform future efforts to improve maternal care quality.

Purpose: To assess trends in prevalence and patient/surgeon characteristics of intraocular lens (IOL) exchange surgery in the United States and to evaluate the surgical complication rates. Setting: Medicare beneficiaries. Design: Retrospective cross-sectional analysis. Methods: Medicare beneficiaries aged 65 years or older who underwent IOL exchange surgery between 2011 and 2020 were identified from 100% Medicare fee-for-service carrier claims data. Main exclusion criteria: missing demographic information and incomplete follow-up data. Main outcomes: incidence of IOL exchange, patient-level and surgeon-level factors, and postoperative complication rates. Results: 52 583 IOL exchanges were performed on 48 967 patients. The annual number of IOL exchanges increased from 4621 in 2011 to 6114 in 2019. Most patients were White (n = 47 228, 89.8%), resided in urban locations (n = 44 095, 84.0%), and had a Charlson comorbidity index of ≤2 (n = 41 556, 79.0%). Of 7493 surgeons, most were male (n = 6308, 84.2%), practiced in urban locations (n = 6907, 92.2%), and had an average of 24.7 ± 11.2 years between medical school graduation and the last surgery they performed during the study period. The most common surgical indications were mechanical lens failure (n = 22 252, 51.4%) and lens displacement (n = 9155, 21.1%). The most common complications were epiretinal membrane (ERM) (n = 531, 6.8%), mechanical lens complication (n = 460, 5.9%), and dislocation of the replacement IOL (n = 385, 4.9%). Conclusions: The number of IOL exchange procedures performed among Medicare beneficiaries increased over the past decade. Male ophthalmologists in urban locations performed the majority of IOL exchanges. The most common postoperative complication was ERM. The rates of corneal decompensation, retinal detachment, and endophthalmitis were low.

BACKGROUND: The accuracy of contemporary administrative claims codes to discriminate between different phenotypes of peripheral artery disease is not well defined. We aimed to validate a predefined set of International Classification of Diseases, Tenth Revision , codes used to distinguish between claudication and chronic limb-threatening ischemia (CLTI) and to optimize their diagnostic accuracy using a supervised machine-learning approach. METHODS: We included all patients who underwent a peripheral vascular intervention for claudication or CLTI in the US Medicare-matched VQI-VISION (Vascular Quality Initiative Vascular Implant Surveillance and Interventional Outcomes Network) registry database between January 2016 and December 2019. Gold standard claudication and CLTI diagnoses were determined using VQI (Vascular Quality Initiative) registry data. These diagnoses were compared with a predetermined set of International Classification of Diseases, Tenth Revision , codes in the Medicare-matched data set. We used traditional logistic regression modeling and 6 machine-learning models to distinguish claudication from CLTI. We evaluated the sensitivity, specificity, total agreement, and area under the curve for all models, implementing grid search cross-validation to boost machine-learning model performance. RESULTS: Of 54 180 patients who underwent a peripheral vascular intervention (mean age, 71.9±10.0 years; 41.0% female; 74.2 non-Hispanic White), 20 769 (38.3%) had claudication and 33 411 (61.7%) had CLTI per gold standard registry definitions. The predefined set of International Classification of Diseases, Tenth Revision , codes had high sensitivity (80.9%), specificity (81.9%), and total agreement (81.3%) for distinguishing claudication versus CLTI. Traditional logistic regression improved sensitivity to 96.2%, but with a substantial drop in specificity (41.8%) and an area under the curve of 0.785. Of the machine-learning models, gradient boosting classifier performed the best (area under the curve, 0.892), improving sensitivity to 88.6% and total agreement to 84.2% with minimal drop in specificity (77.1%). CONCLUSIONS: International Classification of Diseases, Tenth Revision , codes can be used to discriminate between claudication and CLTI in claims data. Our defined set of claims codes can be used by investigators to accurately distinguish between these 2 peripheral artery disease phenotypes.