Risk Prediction in Healthcare and Cost-Effectiveness Analysis

Introduction:

Within the intricate healthcare sector, clinical guidelines provide a significant contribution to the process of establishing and distributing the most effective practices. For the purpose of directing primary preventative treatments toward individuals who are at the greatest risk, these guidelines are increasingly making use of risk prediction models. Within the context of producing guidelines that promote long-term preventative medicines, we explore the significance of risk prediction modelling and cost-effectiveness analyses. Specifically on the primary prevention of cardiovascular disease (CVD) and osteoporotic fracture.

Understanding Risk Prediction and Competing Mortality Risk:

Risk prediction models are crucial in healthcare, but most don’t account for competing mortality risk. This refers to the scenario where an individual dies of another condition (e.g., lung cancer) before experiencing the event being predicted (e.g., CVD or fracture). This can lead to overprediction of event rates among older individuals and those with multiple health conditions.

Exploring Model-Based Cost-Effectiveness Analysis:

Model-based cost-effectiveness analysis (CEA) does account for competing mortality risk, but whole-population estimates of competing mortality may not be accurate at all levels of risk for CVD and fracture. Current models also fail to account for all harms, notably direct treatment disutility (DTD), which is the disutility arising from the hassles of taking treatments.

Improving Evidence Generation:

The overall aim of this research was to improve the evidence generated from risk prediction models and model-based CEAs to inform decision-making for selecting primary prevention treatments for CVD and osteoporotic fracture. This research followed a systematic approach, involving the validation of various risk prediction tools, deriving and validating new models, and quantifying the magnitude of DTD in the general population. They also examined the effect of accounting for competing risks and DTD on cost-effectiveness in the context of statins and bisphosphonates for the primary prevention of CVD and osteoporotic fracture, respectively.

The authors found that ignoring competing mortality in risk prediction overestimates the risk of CVD and fracture among older people and those with multimorbidity. However, risk prediction is improved by accounting for competing mortality risks.

Implications and Recommendations:

The implications of this study are far-reaching, highlighting the need for more accurate risk prediction models and CEAs. They recommend that modellers consider this issue when designing analyses of preventative treatments. Moreover, decision-makers should review scenarios with and without DTD and highlight its possible impact, enabling prescribers to engage in shared decision-making that gives appropriate weight to individual preferences.

Conclusion:

This research offers valuable insights into the complexities and potential shortcomings of existing risk prediction models and CEAs within the prevention of CVDs and osteoporotic fracture. The findings underscore the importance of incorporating these elements into CEAs and risk prediction models to enhance their accuracy and utility in clinical decision-making. By accounting for competing mortality risks, we can achieve more precise risk prediction, especially among older individuals and those with multiple health conditions. Furthermore, considering DTD can ensure a more comprehensive evaluation of treatment cost-effectiveness, capturing not only the economic implications but also the patient’s experience and quality of life.