000			03378cam a22003857 4500
001			w26168
003			NBER
005			20211020104042.0
006			m o d
007			cr cnu||||||||
008			210910s2019 mau fo 000 0 eng d
100	1		_aMullainathan, Sendhil. _917242
245	1	0	_aDiagnosing Physician Error: _bA Machine Learning Approach to Low-Value Health Care / _cSendhil Mullainathan, Ziad Obermeyer.
260			_aCambridge, Mass. _bNational Bureau of Economic Research _c2019.
300			_a1 online resource: _billustrations (black and white);
490	1		_aNBER working paper series _vno. w26168
500			_aAugust 2019.
520	3		_aWe use machine learning to study how physicians make decisions, in particular whether to test a patient for heart attack. We build an algorithmic model of patient risk, and identify cases where physician choices deviate from its predictions. To judge who was right, the algorithm or the physician, we use actual outcome data. Three findings emerge. First, many patients are tested who should not be: at typical cost-effectiveness thresholds, 62% of all tests would be cut. Second, many patients who should be tested are not. These patients go on to suffer adverse health events (including death) at rates exceeding clinical guidelines. A natural experiment using shift-to-shift testing variation confirms these findings: increased testing improves health and reduces mortality, but only for high-risk patients. We estimate the under-tested set to be 61% of the size of the tested population. Machine learning, by measuring value at the patient level rather than population level, is crucial for uncovering under- and over-testing. The simultaneous existence of both cannot easily be explained by physician incentives alone, and instead suggests physician errors. Third, we provide suggestive evidence on why physicians err: (i) they use too simple a model of risk, suggesting bounded rationality; (ii) they over-weight salient information; and (iii) they over-weight representative symptoms--those that fit the stereotype of heart attack. Together, these results suggest the need for health care models and policies to incorporate not just physician incentives, but also physician mistakes.
530			_aHardcopy version available to institutional subscribers
538			_aSystem requirements: Adobe [Acrobat] Reader required for PDF files.
538			_aMode of access: World Wide Web.
588	0		_aPrint version record
690		7	_aC55 - Large Data Sets: Modeling and Analysis _2Journal of Economic Literature class.
690		7	_aD8 - Information, Knowledge, and Uncertainty _2Journal of Economic Literature class.
690		7	_aD84 - Expectations • Speculations _2Journal of Economic Literature class.
690		7	_aD9 - Micro-Based Behavioral Economics _2Journal of Economic Literature class.
690		7	_aI1 - Health _2Journal of Economic Literature class.
690		7	_aI13 - Health Insurance, Public and Private _2Journal of Economic Literature class.
700	1		_aObermeyer, Ziad.
710	2		_aNational Bureau of Economic Research.
830		0	_aWorking Paper Series (National Bureau of Economic Research) _vno. w26168.
856	4	0	_uhttps://www.nber.org/papers/w26168
856			_yAcceso en línea al DOI _uhttp://dx.doi.org/10.3386/w26168
942			_2ddc _cW-PAPER
999			_c321954 _d280516