Week 7 - Trustworthy AI

Required Reading

• “Why Should I Trust You?”: Explaining the Predictions of Any Classifier
• Explainable machine-learning predictions for the prevention of hypoxaemia during surgery
• The false hope of current approaches to explainable artificial intelligence in health care

Optional Reading

• AI Can Outperform Doctors. So Why Don’t Patients Trust It?
• Towards trustable machine learning
• From local explanations to global understanding with explainable AI for trees
• Dissecting racial bias in an algorithm used to manage the health of populations
• Machine Bias, ProPublica, May 23, 2016
• Bias In Medicine: Last Week Tonight with John Oliver, Aug 18, 2019
• Fitbits and other wearables may not accurately track heart rates in people of color, Stat News, July 24, 2019
• We should treat algorithms like prescription drugs, Quartz, Feb 14, 2019
• Word embeddings quantify 100 years of gender and ethnic stereotypes
• AI could worsen health disparities, New York Times, Jan 31, 2019
• Fairness and machine learning