Skip to main content

Table 2 Definition of derivation and validation cohorts and the distribution of analysis units in the cohorts (evaluated at discharges following the first diagnosis)

From: A framework for feature extraction from hospital medical data with applications in risk prediction

 

Derivation cohort

Validation cohort

Diabetes

Period

2003-2007

2008-2011

Number of patients

4,930

2,101

Number of analysis units

11,897

4,041

COPD

Period

2003-2008

2009-2011

Number of patients

1,816

1,816

Number of analysis units

5,746

5,270

Mental disorders

Period

2003-2009

2010-2011

Number of patients

3,089

1,248

Number of analysis units

10,728

2,232

Pneumonia

Period

2003-2008

2009-2011

Number of patients

3,258

2,264

Number of analysis units

7,817

4,020