Cross-population evaluation of cervical cancer risk prediction algorithms.

BACKGROUND: Cervical cancer is a preventable disease, despite being one of the most common types of female cancers worldwide. Integrating existing programs for cervical cancer screening with personalized risk prediction algorithms can improve population-level cancer prevention by enabling more targeted screening and contrive preventive healthcare innovations. While algorithms developed for cervical cancer risk prediction have shown promising performance in internal validation on more homogeneous populations, their ability to generalize to external populations remains to be assessed. METHODS: To address this gap, we perform a cross-population comparative study of personalized prediction algorithms for more personalized cervical cancer screening. Using data from the Norwegian and Estonian populations, the algorithms are validated on internal and external datasets to study their potential biases and limitations when applied to different populations. We evaluate the algorithms in predicting progression from low-grade precancerous cervical lesions, simulating a clinically relevant application of more personalized risk stratification. RESULTS: As expected, our numerical experiments show that algorithm performance varies depending on the population. However, some algorithms show strong generalization capacity across different data sources. Using Kaplan-Meier estimates, we demonstrate the strengths and limitations of the algorithms in detecting cancer progression over time by comparing to the trends observed from data. We assess their overall discrimination performance in personalized risk predictions by analyzing the accuracy and confidence in individual risk estimates. DISCUSSION AND CONCLUSION: This study examines the effectiveness of personalized prediction algorithms across different populations. Our results demonstrate the potential for generalizing risk prediction algorithms to external populations. These findings highlight the importance of considering population diversity when developing risk prediction algorithms.

Estonia: Health System Review.

This analysis of the Estonian health system illustrates recent developments in organization and governance, health financing, health care provision, health reforms and health system performance. In general, Estonia spends less per capita on health than the European Union average, although public expenditure has been growing steadily, with an increasing role of government budget transfers towards the social health insurance model. Despite these efforts, more than a fifth of current health expenditure comes from out-of-pocket payments, creating pressure to develop new and strengthen existing financial protection instruments. Life expectancy in Estonia has increased rapidly over the past decade, but not fast enough to meet the targets set in strategic documents. The first years of the COVID-19 pandemic were marked by a decline in life expectancy and high excess mortality, which set back progress. Despite this, Estonia's gains in population health were more pronounced in 2022. Overall, health inequalities between socioeconomic groups remain high, prompting policymakers to take steps to increase equity in access to care. The outstanding challenges for the Estonian health system include: addressing the shortage of primary and mental health experts, especially given the growing burden of chronic conditions and other needs of the ageing population; minimizing stark socioeconomic inequalities in health outcomes; renewing the outdated public health framework; and further improving integration and coordination of care and clinical decision-making.

Lessons learned from the Baltic countries' response to the first wave of COVID-19.

The Baltic countries of Estonia, Latvia, and Lithuania shared a similar response to the first wave of the COVID-19 pandemic. Using the information available on the COVID-19 Health System Response Monitor platform, this article analyzed measures taken to prevent transmission, ensure capacity, provide essential services, finance the health system, and coordinate their governance approaches. All three countries used a highly centralized approach and implemented restrictive measures relatively early, with a state of emergency declared with fewer than 30 reported cases in each country. Due to initially low COVID-19 incidence, the countries built up their capacities for testing, contact tracing, and infrastructure, without a major stress test to the health system throughout the spring and summer of 2020, yet issues with accessing routine health care services had already started manifesting themselves. The countries in the Baltic region entered the pandemic with a precarious starting point, particularly due to smaller operational budgets and health workforce shortages, which may have contributed to their escalated response aiming to prevent transmission during the first wave. Subsequent waves, however, were much more damaging. This article focuses on early responses to the pandemic in the Baltic states highlighting measures taken to prevent virus transmission in the face of major uncertainties.