Value-based and data-driven vestibular schwannoma care

Abstract

Vestibular schwannoma care is a complex, multidisciplinary field that requires careful decision-making and continuous quality improvement. The thesis examines how value-based care principles, such as shared decision-making and patient-reported outcomes, can optimize treatment outcomes for patients, focusing on long-term quality of life and employment rates. Additionally, two innovative artificial intelligence (AI) tools were developed: one for automating the analysis of patient experience surveys (AI-PREM) and another for measuring tumor volumes on MRI scans. These tools improve care by streamlining quality assessments and enhancing the accuracy of tumor monitoring. Although AI technologies can reduce clinicians' workload and support decision-making, human validation remains crucial. The integration of these tools into clinical practice is key to their success. The research underscores the importance of a customized approach in applying value-based and data-driven care, as not all aspects fit every medical condition.