Computer Vision News Computer Vision News 38 Datasets through the L king-Glass to a predefined list. Checklists are widely used in medical settings, making them familiar to clinicians. Their study utilizes the MIMIC-IV dataset for vital series data; the MIMIC-CXR dataset, which includes radiology images and reports; and the chest imagenome dataset. Their goal is phenotype classification of intensive care unit patients. One interesting finding is that incorporating fairness constraints helps the model rely less on spurious features. For details on how the predictive checklist is learned, refer to the video above. ③ Malihe Alikhani is an Assistant Professor at Northeastern University’s Khoury College of Computer Sciences and a member of the Northeastern Ethics Institute. Resmi Ramachandranpillai is a Postdoctoral Research Associate at the Institute for Experiential AI at Northeastern University. The last talk explored bias in automated clinical decision-making using Electronic
RkJQdWJsaXNoZXIy NTc3NzU=