Predicción del riesgo individual de alto coste sanitario para la identificación de pacientes crónicos complejos
Two articles appear on the same topic, published at the same time, in Canada and Catalonia (I am coauthor of the latter). The results of both studies are similar. Their goal is to identify those patients that will belong to the highest spenders next year.
Canada results:
If the top 5% patients at risk of becoming HCUs are followed, the achieved sensitivity and specificity is 42.2% and 97%, respectively. These values suggest very reasonable predictive power, indicating that the model picks up 42.2% of all high-cost healthcare users and correctly identifies 97% of those who are not high users.Catalonia results:
En el modelo, todas las variables fueron estadísticamente significativas excepto el sexo. Se obtuvo una sensibilidad del 48,4% (intervalo de confianza [IC]: 46,9%-49,8%), una especificidad del 97,2% (IC: 97,0%-97,3%), un VPP del 46,5% (IC: 45,0%-47,9%) y un AUC de 0,897 (IC: 0,892-0,902).The models are slightly different, while the results are close.
I suggest you have a look at them, predictive modeling is one of the main current topics of health services research. Some people consider that it is under the umbrella of Big Data, although it was born before such a term was created.
PS. A must read. Bob Evans, and The Undisciplined Economist: Waste, Economists and American Healthcare
PS. In memoriam: Gary S. Becker, 1930-2014. The Becker-Posner blog is terminated.