Project description:Little is known on how to best prioritize various tele-ICU specific tasks and workflows to maximize operational efficiency. We set out to: 1) develop an operational model that accurately reflects tele-ICU workflows at baseline, 2) identify workflow changes that optimize operational efficiency through discrete-event simulation and multi-class priority queuing modeling, and 3) implement the predicted favorable workflow changes and validate the simulation model through prospective correlation of actual-to-predicted change in performance measures linked to patient outcomes.SettingTele-ICU of a large healthcare system in New York State covering nine ICUs across the spectrum of adult critical care.PatientsSeven-thousand three-hundred eighty-seven adult critically ill patients admitted to a system ICU (1,155 patients pre-intervention in 2016Q1 and 6,232 patients post-intervention 2016Q3 to 2017Q2).InterventionsChange in tele-ICU workflow process structure and hierarchical process priority based on discrete-event simulation.Measurements and main resultsOur discrete-event simulation model accurately reflected the actual baseline average time to first video assessment by both the tele-ICU intensivist (simulated 132.8 ± 6.7 min vs 132 ± 12.2 min actual) and the tele-ICU nurse (simulated 128.4 ± 7.6 min vs 123 ± 9.8 min actual). For a simultaneous priority and process change, the model simulated a reduction in average TVFA to 51.3 ± 1.6 min (tele-ICU intensivist) and 50.7 ± 2.1 min (tele-ICU nurse), less than the added simulated reductions for each change alone, suggesting correlation of the changes to some degree. Subsequently implementing both changes simultaneously resulted in actual reductions in average time to first video assessment to values within the 95% CIs of the simulations (50 ± 5.5 min for tele-intensivists and 49 ± 3.9 min for tele-nurses).ConclusionsDiscrete-event simulation can accurately predict the effects of contemplated multidisciplinary tele-ICU workflow changes. The value of workflow process and task priority modeling is likely to increase with increasing operational complexities and interdependencies.

Project description:BackgroundIn Huntington's disease clinical trials, recruitment and stratification approaches primarily rely on genetic load, cognitive and motor assessment scores. They focus less on in vivo brain imaging markers, which reflect neuropathology well before clinical diagnosis. Machine learning methods offer a degree of sophistication which could significantly improve prognosis and stratification by leveraging multimodal biomarkers from large datasets. Such models specifically tailored to HD gene expansion carriers could further enhance the efficacy of the stratification process.ObjectivesTo improve stratification of Huntington's disease individuals for clinical trials.MethodsWe used data from 451 gene positive individuals with Huntington's disease (both premanifest and diagnosed) from previously published cohorts (PREDICT, TRACK, TrackON, and IMAGE). We applied whole-brain parcellation to longitudinal brain scans and measured the rate of lateral ventricular enlargement, over 3 years, which was used as the target variable for our prognostic random forest regression models. The models were trained on various combinations of features at baseline, including genetic load, cognitive and motor assessment score biomarkers, as well as brain imaging-derived features. Furthermore, a simplified stratification model was developed to classify individuals into two homogenous groups (low risk and high risk) based on their anticipated rate of ventricular enlargement.ResultsThe predictive accuracy of the prognostic models substantially improved by integrating brain imaging features alongside genetic load, cognitive and motor biomarkers: a 24 % reduction in the cross-validated mean absolute error, yielding an error of 530 mm3/year. The stratification model had a cross-validated accuracy of 81 % in differentiating between moderate and fast progressors (precision = 83 %, recall = 80 %).ConclusionsThis study validated the effectiveness of machine learning in differentiating between low- and high-risk individuals based on the rate of ventricular enlargement. The models were exclusively trained using features from HD individuals, which offers a more disease-specific, simplified, and accurate approach for prognostic enrichment compared to relying on features extracted from healthy control groups, as done in previous studies. The proposed method has the potential to enhance clinical utility by: i) enabling more targeted recruitment of individuals for clinical trials, ii) improving post-hoc evaluation of individuals, and iii) ultimately leading to better outcomes for individuals through personalized treatment selection.

Project description:BackgroundLeaders play a crucial role in implementing and sustaining changes in clinical practice, yet there is limited evidence on the strategies to engage them in team problem solving and communication.ObjectiveExamine the impact of an intervention focused on facilitating leadership during daily huddles on optimizing team-based care and improving outcomes.DesignCluster-randomized trial using intention-to-treat analysis to measure the effects of the intervention (n = 13 teams) compared with routine practice (n = 16 teams).ParticipantsTwenty-nine primary care clinics affiliated with a large integrated health system in the upper Midwest; representing differing practice types and geographic settings.InterventionFull-day leadership training retreat for team leaders to facilitate of care team huddles. Biweekly coaching calls and two site visits with an assigned coach.Main measuresPrimary outcomes of team development and function were collected, pre- and post-intervention using surveys. Patient satisfaction and quality outcomes were compared pre- and post-intervention as secondary outcomes. Leadership engagement and adherence to the intervention were also assessed.Key resultsA total of 279 pre-intervention and 272 post-intervention surveys were completed. We found no impact on team development (- 0.98, 95% CI (- 3.18, 1.22)), improved team credibility (0.18, 95% CI (0.00, 0.35)), but worse psychological safety (- 0.19, 95% CI (- 0.38, 0.00)). No differences were observed in patient satisfaction; however, results were mixed among quality outcomes. Post hoc analysis within the intervention group showed higher adherence to the intervention was associated with improvement in team coordination (0.47, 95% CI (0.18, 0.76)), credibility (0.28, 95% CI (0.02, 0.53)), team learning (0.42, 95% CI (0.10, 0.74)), and knowledge creation (0.74, 95% CI (0.35, 1.13)) compared to teams that were less engaged.ConclusionsResults of this evaluation showed that leadership training and facilitation were not associated with better team functioning. Additional components to the intervention tested may be necessary to enhance team functioning.Trial registrationClinicaltrials.gov Identifier NCT03062670. Registration Date: February 23, 2017. URL: https://clinicaltrials.gov/ct2/show/NCT03062670.

Project description:BackgroundSepsis costs and incidence vary dramatically across diagnostic categories, warranting a customized approach for implementing predictive models.ObjectiveThe aim of this study was to optimize the parameters of a sepsis prediction model within distinct patient groups to minimize the excess cost of sepsis care and analyze the potential effect of factors contributing to end-user response to sepsis alerts on overall model utility.MethodsWe calculated the excess costs of sepsis to the Centers for Medicare and Medicaid Services (CMS) by comparing patients with and without a secondary sepsis diagnosis but with the same primary diagnosis and baseline comorbidities. We optimized the parameters of a sepsis prediction algorithm across different diagnostic categories to minimize these excess costs. At the optima, we evaluated diagnostic odds ratios and analyzed the impact of compliance factors such as noncompliance, treatment efficacy, and tolerance for false alarms on the net benefit of triggering sepsis alerts.ResultsCompliance factors significantly contributed to the net benefit of triggering a sepsis alert. However, a customized deployment policy can achieve a significantly higher diagnostic odds ratio and reduced costs of sepsis care. Implementing our optimization routine with powerful predictive models could result in US $4.6 billion in excess cost savings for CMS.ConclusionsWe designed a framework for customizing sepsis alert protocols within different diagnostic categories to minimize excess costs and analyzed model performance as a function of false alarm tolerance and compliance with model recommendations. We provide a framework that CMS policymakers could use to recommend minimum adherence rates to the early recognition and appropriate care of sepsis that is sensitive to hospital department-level incidence rates and national excess costs. Customizing the implementation of clinical predictive models by accounting for various behavioral and economic factors may improve the practical benefit of predictive models.

Dataset Information

Risk, Results, and Costs: Optimizing Clinical Trial Efficiency through Prognostic Enrichment.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets