Sofia Ira Ktena
Papers
1
Total Citations
2
H-Index
1
About
Sofia Ira Ktena is a researcher at the forefront of machine learning for healthcare and multimodal data analysis. Her work centers on developing intelligent systems that can actively acquire and integrate information from diverse temporal sources—a critical challenge in clinical settings where data collection is costly and time-sensitive. Ktena introduced the challenging decision-making task of active acquisition for multimodal temporal data (A2MT), pioneering methods to train agents that strategically decide which features to request at what time to maximize predictive performance while minimizing acquisition costs. This foundational contribution addresses a key bottleneck in real-world AI deployment, particularly in medical diagnostics where every data point carries significant resource implications. Her research has garnered attention for its practical relevance, with her most cited work accumulating citations that underscore its impact on the field. Ktena's work bridges the gap between theoretical reinforcement learning and applied healthcare challenges, offering a principled framework for building more efficient, cost-aware AI systems that can operate effectively under real-world constraints.
Research Focus
Key Achievements
Top Papers
- 1