Here prediction refers to model-based estimation of an observation's value, regardless of its timing.ĭiagnoses are recorded on claims in the United States using the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM). Expected costs are then summed to yield an expected annual cost for the entire enrollment ( Fowles et al. In capitation-setting applications, risk-adjustment models are used to estimate an expected annual cost for each patient to be enrolled in a prepaid health plan. 1996 Thomas, Grazier, and Ward 2004a Robinson, Zeger, and Forrest 2006). Comparisons of observed and expected costs are then aggregated across a provider's patient sample to yield an overall assessment of provider performance ( Powe et al. In provider profiling applications, risk-adjustment models are used to estimate an expected cost for each of a provider's patients, to be compared with each patient's observed cost. Models that use diagnoses from claims to risk-adjust health care cost predictions are widely employed by health services researchers and public and private payers.
0 kommentar(er)
