相关文章推荐
失眠的刺猬  ·  You have JVM property ...·  1 月前    · 
失眠的刺猬  ·  supervisor 启动 celery ...·  11 月前    · 
失眠的刺猬  ·  Spring ...·  12 月前    · 
失眠的刺猬  ·  [译] Android ...·  12 月前    · 
失眠的刺猬  ·  Build More Engaging ...·  1 年前    · 
失眠的刺猬  ·  Diagnosing Physician ...·  1 年前    · 
腼腆的炒粉  ·  Supervised Learning ...·  51 分钟前    · 
要出家的吐司  ·  工具 | ...·  1小时前    · 
留胡子的煎饼  ·  类似 这种 ZMQ_DONTWAIT ...·  3 小时前    · 
Mobile Enter search term C21 - Cross-Sectional Models; Spatial Models; Treatment Effect Models; Quantile Regressions C23 - Panel Data Models; Spatio-temporal Models C26 - Instrumental Variables (IV) Estimation C31 - Cross-Sectional Models; Spatial Models; Treatment Effect Models; Quantile Regressions; Social Interaction Models C32 - Time-Series Models; Dynamic Quantile Regressions; Dynamic Treatment Effect Models; Diffusion Processes; State Space Models C35 - Discrete Regression and Qualitative Choice Models; Discrete Regressors; Proportions D72 - Political Processes: Rent-seeking, Lobbying, Elections, Legislatures, and Voting Behavior D73 - Bureaucracy; Administrative Processes in Public Organizations; Corruption D74 - Conflict; Conflict Resolution; Alliances; Revolutions D78 - Positive Analysis of Policy Formulation and Implementation D91 - Role and Effects of Psychological, Emotional, Social, and Cognitive Factors on Decision Making D92 - Intertemporal Firm Choice, Investment, Capacity, and Financing E01 - Measurement and Data on National Income and Product Accounts and Wealth; Environmental Accounts E02 - Institutions and the Macroeconomy E03 - Behavioral Macroeconomics E24 - Employment; Unemployment; Wages; Intergenerational Income Distribution; Aggregate Human Capital; Aggregate Labor Productivity E25 - Aggregate Factor Income Distribution E42 - Monetary Systems; Standards; Regimes; Government and the Monetary System; Payment Systems E43 - Interest Rates: Determination, Term Structure, and Effects E44 - Financial Markets and the Macroeconomy G32 - Financing Policy; Financial Risk and Risk Management; Capital and Ownership Structure; Value of Firms; Goodwill G33 - Bankruptcy; Liquidation G34 - Mergers; Acquisitions; Restructuring; Corporate Governance G38 - Government Policy and Regulation H24 - Personal Income and Other Nonbusiness Taxes and Subsidies; includes inheritance and gift taxes H25 - Business Taxes and Subsidies H26 - Tax Evasion and Avoidance J14 - Economics of the Elderly; Economics of the Handicapped; Non-Labor Market Discrimination J15 - Economics of Minorities, Races, Indigenous Peoples, and Immigrants; Non-labor Discrimination J16 - Economics of Gender; Non-labor Discrimination J18 - Public Policy L16 - Industrial Organization and Macroeconomics: Industrial Structure and Structural Change; Industrial Price Indices L19 - Other Q15 - Land Ownership and Tenure; Land Reform; Land Use; Irrigation; Agriculture and Environment Q16 - R&D; Agricultural Technology; Biofuels; Agricultural Extension Services Q56 - Environment and Development; Environment and Trade; Sustainability; Environmental Accounts and Accounting; Environmental Equity; Population Growth Q58 - Government Policy R23 - Regional Migration; Regional Labor Markets; Population; Neighborhood Characteristics R28 - Government Policy R41 - Transportation: Demand, Supply, and Congestion; Travel Time; Safety and Accidents; Transportation Noise R48 - Government Pricing and Policy N3 - Labor and Consumers, Demography, Education, Health, Welfare, Income, Wealth, Religion, and Philanthropy Enter search term Mobile Enter search term Enter search term

Abstract

We use machine learning as a tool to study decision making, focusing specifically on how physicians diagnose heart attack. An algorithmic model of a patient’s probability of heart attack allows us to identify cases where physicians' testing decisions deviate from predicted risk. We then use actual health outcomes to evaluate whether those deviations represent mistakes or physicians’ superior knowledge. This approach reveals two inefficiencies. Physicians overtest: predictably low-risk patients are tested, but do not benefit. At the same time, physicians undertest: predictably high-risk patients are left untested, and then go on to suffer adverse health events including death. A natural experiment using shift-to-shift testing variation confirms these findings. Simultaneous over- and undertesting cannot easily be explained by incentives alone, and instead point to systematic errors in judgment. We provide suggestive evidence on the psychology underlying these errors. First, physicians use too simple a model of risk. Second, they overweight factors that are salient or representative of heart attack, such as chest pain. We argue health care models must incorporate physician error, and illustrate how policies focused solely on incentive problems can produce large inefficiencies.

 
推荐文章