Patient-specific risk scores are used to identify individuals at elevated risk for cardiovascular disease. Typically, risk scores are based on patient habits and medical history - age, sex, race, smoking behavior, and prior vital signs and diagnoses. We explore an alternative source of information, a patients raw electrocardiogram recording, and develop a score of patient risk for various outcomes. We compare models that predict adverse cardiac outcomes following an emergency department visit, and show that a learned representation (e.g. deep neural network) of raw EKG waveforms can improve prediction over traditional risk factors. Further, we show that a simple model based on segmented heart beats performs as well or better than a complex convolutional network recently shown to reliably automate arrhythmia detection in EKGs. We analyze a large cohort of emergency department patients and show evidence that EKG-derived scores can be more robust to patient heterogeneity.

Patient-specific risk scores are used to identify individuals at elevated risk for cardiovascular disease. Typically, risk scores are based on patient habits and medical history - age, sex, race, smoking behavior, and prior vital signs and diagnoses. We explore an alternative source of information, a patient's raw electrocardiogram recording, and develop a score of patient risk for various outcomes. We compare models that predict adverse cardiac outcomes following an emergency department visit, and show that a learned representation (e.g. deep neural network) of raw EKG waveforms can improve prediction over traditional risk factors. Further, we show that a simple model based on segmented heart beats performs as well or better than a complex convolutional network recently shown to reliably automate arrhythmia detection in EKGs. We analyze a large cohort of emergency department patients and show evidence that EKG-derived scores can be more robust to patient heterogeneity.

That one-quarter of Medicare spending in the United States occurs in the last year of life is commonly interpreted as waste. But this interpretation presumes knowledge of who will die and when. Here we analyze how spending is distributed by predicted mortality, based on a machine-learning model of annual mortality risk built using Medicare claims. Death is highly unpredictable. Less than 5% of spending is accounted for by individuals with predicted mortality above 50%. The simple fact that we spend more on the sick-both on those who recover and those who die-accounts for 30 to 50% of the concentration of spending on the dead. Our results suggest that spending on the ex post dead does not necessarily mean that we spend on the ex ante "hopeless."

Health systems rely on commercial prediction algorithms to identify and help patients with complex health needs. We show that a widely used algorithm, typical of this industry-wide approach and affecting millions of patients, exhibits significant racial bias: At a given risk score, Black patients are considerably sicker than White patients, as evidenced by signs of uncontrolled illnesses. Remedying this disparity would increase the percentage of Black patients receiving additional help from 17.7 to 46.5%. The bias arises because the algorithm predicts health care costs rather than illness, but unequal access to care means that we spend less money caring for Black patients than for White patients. Thus, despite health care cost appearing to be an effective proxy for health by some measures of predictive accuracy, large racial biases arise. We suggest that the choice of convenient, seemingly effective proxies for ground truth can be an important source of algorithmic bias in many contexts.