Development of a predictive model for integrated medical and long-term care resource consumption based on health behaviour: application of healthcare big data of patients with circulatory diseases

Table 2 Predictor of integrated medical and long-term care resource consumption

Health behaviour		Broad adherence	No.
Secondary prevention	→	Secondary prevention (Integrated)	1
Health check-ups, number per year		*
Items of check-ups, number per year		*
Tertiary prevention
Rehabilitation intensity, units/year	→	Rehabilitation intensity	2
Guidance (e.g. lifestyle-related disease), number per year	→	Guidance	3
PDC, %	→	PDC	4
Overlapping outpatient service
Outpatients visits, number per year	→	Overlapping outpatient visits	5
Clinical laboratory and physiological tests, number per year	→	Overlapping clinical laboratory and physiological tests	6
Medical attendance behaviour	→	Medical attendance (Integrated)	7
Inpatient days, days per year		**
Outpatients visits, number per year		**
Dispensing, number per year		**
Public behaviour
Generic drug rate, %	→	Generic drug rate	8
		(Complementary Indicators)
		Age
		Sex
		Follow-up period

Integrated into an adherence 1* or adherence 7** index by machine learning (see Table 1)
Abbreviations: PDC proportion of days covered

ISSN: 1741-7015