Current jobs related to Multiple PhDs and postdocs on evaluation metrics for multimodal health data - Copenhagen, Copenhagen - ELLIS
-
Copenhagen, Copenhagen, Denmark beBee Careers Full timePhD and Postdoc Positions: Evaluating Teams and Algorithms for Multimodal Health DataThe IT University of Copenhagen invites highly motivated individuals to apply for a PhD or 2-year Postdoc position.Machine learning competitions in healthcare face limitations in real-world applications. They often result in similar algorithms that excel on specific accuracy...
-
Multimodal Health Data Evaluation Metrics
5 days ago
Copenhagen, Copenhagen, Denmark beBee Careers Full timeThe IT University of Copenhagen invites highly motivated individuals to apply for PhD or Postdoc positions. The project, funded by the Novo Nordisk Foundation, aims to develop novel evaluation metrics for multimodal health data. This will involve designing competitions with multiple metrics, both in what the metric measures and which subgroups of patients it...
-
Copenhagen, Copenhagen, Denmark PARETO SECURITIES AS Full timeMultiple PhD and postdoc positions on evaluation metrics for multimodal health data at the IT University of Copenhagen The PURRlab (Pattern Recognition Revisited lab) at the IT University of Copenhagen invites highly motivated individuals to apply for a PhD or a 2 year Postdoc position starting late 2025 or in 2026. The earliest possible start date is 1...
-
Copenhagen, Copenhagen, Denmark ELLIS Full timeA PhD or 2-year postdoc position is available at the IT University of Copenhagen, focusing on evaluating multimodal health data.ContextMachine learning competitions are often touted as drivers of algorithm development in healthcare but face limitations in real-world applications.Competition may deter underrepresented groups in computer science from entering...
-
Copenhagen, Copenhagen, Denmark beBee Careers Full timeSeeking experts in multimodal health data evaluation to join our research team. The ideal candidate will have a strong background in machine learning and experience working with diverse data types.Job DescriptionWe are looking for two PhD students and two postdocs to work on evaluating metrics for multimodal health data. This project aims to design...
-
Copenhagen, Copenhagen, Denmark beBee Careers Full timeJob OverviewWe are seeking highly motivated and experienced professionals to join our research team in evaluating metrics for multimodal health data.The selected candidates will work on designing competitions with multiple metrics, including what the metric measures and which subgroups of patients it measures on.Project AimsThe project focuses on two...
-
Copenhagen, Copenhagen, Denmark beBee Careers Full timeMultiple PhD and postdoc positions are available at the IT University of Copenhagen. These positions aim to hire 2 PhD students and 2 postdocs to work on developing novel evaluation metrics for multimodal health data. The project involves designing competitions with multiple metrics to evaluate algorithm robustness and generalizability.Candidates will have...
-
Copenhagen, Copenhagen, Denmark beBee Careers Full timeEvaluation Metrics for Advancing HealthcareWe are seeking a highly motivated individual to join our team in designing evaluation metrics for multimodal health data. The goal is to promote more diverse and robust algorithm development in machine learning competitions, particularly in healthcare.Project OverviewThe project CHEETAH: Challenges of Evaluating...
-
Copenhagen, Copenhagen, Denmark ELLIS Full timeJoin us in exploring the challenges of evaluating teams and algorithms in healthcare.About the ProjectFunded by the Novo Nordisk Foundation Data Science Ascending Investigator grant, our research aims to develop novel methods for evaluating multimodal health data.Key ObjectivesDesign competitions with multiple metrics to capture algorithm robustnessEvaluate...
-
Evaluating Teams and Algorithms
5 days ago
Copenhagen, Copenhagen, Denmark beBee Careers Full timeThe PURRlab team at the IT University of Copenhagen invites applications for PhD or Postdoc positions. The project involves developing novel evaluation metrics for multimodal health data, including designing competitions with multiple metrics. This will involve developing novel methods to evaluate and increase the diversity of the evaluation data, as well as...
Multiple PhDs and postdocs on evaluation metrics for multimodal health data
2 weeks ago
The PURRlab (Pattern Recognition Revisited lab) at the IT University of Copenhagen invites highly motivated individuals to apply for a PhD or a 2-year Postdoc position starting late 2025 or in 2026. The earliest possible start date is 1 October 2025.
The project is funded by the Novo Nordisk Foundation Data Science Ascending Investigator grant titled "CHEETAH: CHallenges of Evaluating Teams and Algorithms" and is led by Associate Professor Veronika Cheplygina.
Machine learning (ML) competitions are often touted as drivers of algorithm development in healthcare but face limitations in real-world applications. An example competition is detecting lung cancer in chest images, where the team correctly identifying the most images with cancer wins the competition. Such competitions attract many international teams with monetary or prestigious incentives. While competitions are said to spur innovation, they often result in too similar algorithms that only excel on a specific accuracy metric, but are not robust and fail to generalize to diverse, real-world data.
I posit that a single performance metric such as accuracy is insufficient to capture algorithm robustness, for example how the algorithm performs on rare patient cases. Having a single performance metric also leads to too similar algorithms which do not bring added value despite their high training costs and carbon footprint. Furthermore, as research on women and other underrepresented groups in computer science shows, competition may deter them from entering or staying in the field.
I therefore propose to design competitions with multiple metrics, both in what the metric measures (e.g., accuracy or sensitivity) and which subgroups of patients this is measured on. My team will focus on two multimodal disease (risk) prediction data: chest x-rays with radiology reports and retinal images with tabular clinical measurements. Inspired by techniques like generative models, transfer learning, and data distillation we will first develop novel methods to evaluate and increase the diversity of the evaluation data. We will then design how to evaluate similarity of algorithms, and develop methods to combine and reuse (parts of) them, such that robustness can be increased without the disproportionate carbon footprint. Finally, we will organize competitions in education and at conferences, where we will study how the novel design affects underrepresented groups in data science.
#J-18808-Ljbffr