Lessons Learned in Providing Claims-Based Data to Participants in Health Care Innovation Models

Understandings of innovation usually encompass multiple overlapping aspects, putting innovation terminology at risk of vagueness and overuse. However, innovation concepts are expected to remain powerful and useful in healthcare beyond the pandemic and into the future, so clarity will be helpful for effective leadership. To disentangle and disambiguate meanings within innovation, we offer a framework that captures and simplifies foundational substance within innovation concepts. Our method is an overview review of innovation literature from the 5 years preceding COVID-19. 51 sources were sampled and analysed for explicit definitions of healthcare innovation. Drawing on broad themes suggested from previous reviews, and gathering specific themes emergent from this literary dataset, we focused on categorising the nature of innovations (the what) and reasons given for them (the why). We identified 4 categories of what (ideas, artefacts, practice/process and structure) and 10 categories of why (economic value, practical value, experience, resource use, equity/accessibility, sustainability, behaviour change, specific-problem solving, self-justifying renewal and improved health). These categories reflect contrasting priorities and values, but do not substantially interfere or occlude each other. They can freely be additively combined to create composite definitions. This conceptual scheme affords insight and clarity for creating precise meanings, and making critical sense of imprecision, around innovation. Improved communication and clear shared understandings around innovative intentions, policies and practices cannot but improve the chances of enhanced outcomes. The all-inclusive character of this scheme leaves space for considering the limits of innovation, and notwithstanding well-established critiques, provides a basis for clarity in ongoing usage.

show abstract

“…‘Health care innovation models are often focused on changing the behaviour of health care providers and organizations.’(Cohen et al , p234)66…”

Section: Resultsmentioning

confidence: 99%

Capturing what and why in healthcare innovation

Reid

Davis

Gordon

2023

leader

View full text Add to dashboard Cite

show abstract

“…This can lead to dynamic and individualized product pricing (Cather 2018). In another example, using and utilizing claims data for specific diseases like cancer can drive innovation in healthcare models (Cohen et al 2019). When developing innovative products during the pandemic crisis, insurance companies must be able to assess the pandemic risk by creating simulations that include predictions of claims due to the pandemic and other sequential events to calculate other potential losses (Qiu 2020).…”

Section: Conceptual Framework and Development Of Hypothesismentioning

confidence: 99%

Actuarial Risk Management Practices and Firm Performance: The Mediating Role of E-Service Innovation

Widianto,

Arief,

Hamsal

et al. 2024

JRFM

View full text Add to dashboard Cite

Research on actuarial risk management practices (ARMP) and insurance firm performance has revealed inconsistent results. Therefore, a mediating factor such as innovation is needed to bridge between them. Studies exploring the relationship between ARMP and innovation have been largely qualitative. This study offered a quantitative model focusing on the mediating role of e-service innovation between ARMP and firm performance. The hypothesized relationships were tested using a structural equation model (SEM), with a sample from 98 Indonesian insurance companies and WarpPLS 7.0 as the analytical tool. The results indicated that ARMP significantly influenced e-service innovation but was insignificant for firm performance. Furthermore, the findings highlighted the significant role of e-service innovation in insurance firm performance, which implied that e-service innovation acts as a mediator in the relationship between ARMP and firm performance. The practical application of the research findings makes them directly relevant and beneficial to the insurance industry, especially in Indonesia.

show abstract

Development and Internal Validation of an Interpretable Machine Learning Model to Predict Readmissions in a United States Healthcare System

et al. 2023

View full text Add to dashboard Cite

(1) One in four hospital readmissions is potentially preventable. Machine learning (ML) models have been developed to predict hospital readmissions and risk-stratify patients, but thus far they have been limited in clinical applicability, timeliness, and generalizability. (2) Methods: Using deidentified clinical data from the University of California, San Francisco (UCSF) between January 2016 and November 2021, we developed and compared four supervised ML models (logistic regression, random forest, gradient boosting, and XGBoost) to predict 30-day readmissions for adults admitted to a UCSF hospital. (3) Results: Of 147,358 inpatient encounters, 20,747 (13.9%) patients were readmitted within 30 days of discharge. The final model selected was XGBoost, which had an area under the receiver operating characteristic curve of 0.783 and an area under the precision-recall curve of 0.434. The most important features by Shapley Additive Explanations were days since last admission, discharge department, and inpatient length of stay. (4) Conclusions: We developed and internally validated a supervised ML model to predict 30-day readmissions in a US-based healthcare system. This model has several advantages including state-of-the-art performance metrics, the use of clinical data, the use of features available within 24 h of discharge, and generalizability to multiple disease states.

show abstract

Lessons Learned in Providing Claims-Based Data to Participants in Health Care Innovation Models

Cited by 3 publications

References 9 publications

Capturing what and why in healthcare innovation

Capturing what and why in healthcare innovation

Actuarial Risk Management Practices and Firm Performance: The Mediating Role of E-Service Innovation

Development and Internal Validation of an Interpretable Machine Learning Model to Predict Readmissions in a United States Healthcare System

Contact Info

Product

Resources

About