Abstract We use machine learning as a tool to study decision making, focusing specifically on how physicians diagnose heart attack. An algorithmic model of patient’s probability attack allows us identify cases where physicians' testing decisions deviate from predicted risk. then actual health outcomes evaluate whether those deviations represent mistakes or physicians’ superior knowledge. This a...

Medical Journal of AustraliaVolume 215, Issue 3 p. 101-103.e1 Perspectives Low value care is a health hazard that calls for patient empowerment Ian A Scott, Corresponding Author Scott [email protected] orcid.org/0000-0002-7596-0837 Princess Alexandra Hospital, Brisbane, QLD University Queensland, Correspondence [email protected] more papers by this authorAdam G Elshaug...

Research into the prevalence and impact of low-value medical practices has evolved substantially over the past two decades. However, despite international efforts, many challenges still remain with regards to progress in this field, including limits in the capacity to identify and prioritize low-value care practices and to systematically appraise clinical and policy attempts at redressing low-v...