A randomized trial examining the effect of predictive analytics and tailored interventions on the cost of care

Nikolova-Simons, Mariana; Golas, Sara; Buijs, Jorn op den; Palacholla, Ramya; Garberg, Gary; Orenstein, Allison; Kvedar, Joseph C.

doi:10.1038/s41746-021-00449-w

Cited by 3 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Preventing rehospitalization is only one application; others include prevention of sepsis 7 or acute kidney injury 8 . While not a substitute for randomized trials 9 , simulation modeling can provide initial answers and insights for all stakeholders involved, including researchers developing prediction algorithms, administrators optimizing clinical workflows, executives evaluating business models, and regulators seeking to understand performance in context.…”

mentioning

confidence: 99%

Beyond performance metrics: modeling outcomes and cost for clinical machine learning

2021

Self Cite

View full text Add to dashboard Cite

Advances in medical machine learning are expected to help personalize care, improve outcomes, and reduce wasteful spending. In quantifying potential benefits, it is important to account for constraints arising from clinical workflows. Practice variation is known to influence the accuracy and generalizability of predictive models, but its effects on cost-effectiveness and utilization are less well-described. A simulation-based approach by Mišić and colleagues goes beyond simple performance metrics to evaluate how process variables may influence the impact and financial feasibility of clinical prediction algorithms.

show abstract

mentioning

confidence: 99%

Beyond performance metrics: modeling outcomes and cost for clinical machine learning

2021

Self Cite

View full text Add to dashboard Cite

show abstract

Exploring the feasibility of an mHealth application to enhance physical activity and an active healthy lifestyle in community-dwelling older adults (Preprint)

Daniels,

Vonck,

Robijns

et al. 2024

Preprint

View full text Add to dashboard Cite

BACKGROUND Advancements in smartphone technology have paved the way for innovative interventions aimed at promoting physical activity (PA). OBJECTIVE The main objective of this feasibility study is to thoroughly assess the feasibility, usability, and acceptability of the MIA, a specifically developed app, in promoting PA among healthy older adults. METHODS Our study utilized a mixed methods approach to evaluate the MIA app’s acceptability, feasibility, and usability. First, a "think-aloud" method was used to provided immediate feedback during initial app use. Participants then integrated the app into their daily activities for five weeks. Behavioral patterns, such as user session duration, feature usage frequency, and navigation paths were analyzed, focusing on engagement metrics and user interactions. User satisfaction was assessed using the System Usability Scale (SUS), User Experience Questionnaire (UEQ), Net Promoter Score (NPS) and the Customer Satisfaction Score (CSAT). Qualitative data from focus groups, performed after the five-week intervention, helped gather insights into user experiences. Recruitment targeted healthy, native Dutch-speaking older adults over 65 without severe illnesses. RESULTS The study involved 30 participants. The app received positive ratings, with a sustainable usability scale of 77.4 and a customer satisfaction score of 86.6%. Analysis showed general satisfaction with the app’s workout videos and broad acceptance of its content. Qualitative feedback suggested improvements in navigation and content relevance. CONCLUSIONS Mobile health apps offer promise for promoting PA in older adults. Tailoring technology that suits individual needs is crucial to ensure user-friendly, relevant, sustainable, and agile solutions. Future enhancements should focus on personalization and integration with wearable devices to provide real-time health data, which can optimize activity recommendations and health monitoring. Furthermore, incorporating robust social networking features and predictive analytics could enhance user engagement. CLINICALTRIAL The study was preregistered with ClinicalTrials.gov (NCT05650515).

show abstract

Clinical Data for Parametrization of In Silico Bone Models Incorporating Cell-Cytokine Dynamics: A Systematic Review of Literature

Ledoux

Boaretti

Sachan

et al. 2022

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

In silico simulations aim to provide fast, inexpensive, and ethical alternatives to years of costly experimentation on animals and humans for studying bone remodeling, its deregulation during osteoporosis and the effect of therapeutics. Within the varied spectrum of in silico modeling techniques, bone cell population dynamics and agent-based multiphysics simulations have recently emerged as useful tools to simulate the effect of specific signaling pathways. In these models, parameters for cell and cytokine behavior are set based on experimental values found in literature; however, their use is currently limited by the lack of clinical in vivo data on cell numbers and their behavior as well as cytokine concentrations, diffusion, decay and reaction rates. Further, the settings used for these parameters vary across research groups, prohibiting effective cross-comparisons. This review summarizes and evaluates the clinical trial literature that can serve as input or validation for in silico models of bone remodeling incorporating cells and cytokine dynamics in post-menopausal women in treatment, and control scenarios. The GRADE system was used to determine the level of confidence in the reported data, and areas lacking in reported measures such as binding site occupancy, reaction rates and cell proliferation, differentiation and apoptosis rates were highlighted as targets for further research. We propose a consensus for the range of values that can be used for the cell and cytokine settings related to the RANKL-RANK-OPG, TGF-β and sclerostin pathways and a Levels of Evidence-based method to estimate parameters missing from clinical trial literature.

show abstract

A randomized trial examining the effect of predictive analytics and tailored interventions on the cost of care

Cited by 3 publications

References 20 publications

Beyond performance metrics: modeling outcomes and cost for clinical machine learning

Beyond performance metrics: modeling outcomes and cost for clinical machine learning

Exploring the feasibility of an mHealth application to enhance physical activity and an active healthy lifestyle in community-dwelling older adults (Preprint)

Clinical Data for Parametrization of In Silico Bone Models Incorporating Cell-Cytokine Dynamics: A Systematic Review of Literature

Contact Info

Product

Resources

About