Application of machine learning methodology to assess the performance of DIABETIMSS program for patients with type 2 diabetes in family medicine clinics in Mexico

You, Yue; Doubova, Svetlana V.; Pinto-Masis, Diana; Pérez-Cuevas, Ricardo; Borja-Aburto, Víctor  Hugo; Hubbard, Alan

doi:10.1186/s12911-019-0950-5

BMC Medical Informatics and Decision Making

Table 3 Associations of DIABETIMSS program and glycemic control indicator by clinic and pooled over all clinics

From: Application of machine learning methodology to assess the performance of DIABETIMSS program for patients with type 2 diabetes in family medicine clinics in Mexico

Clinic	DIABETIMSS	n	Unadjusted logistic regression	Adjusted logistic regression	TMLE
			HbA1c < 7% (95% CI)	HbA1c < 7% (95% CI)	HbA1c < 7% (95% CI)
A	No	4778	0.3599 (0.3517, 0.3680)	0.3692 (0.3574, 0.3810)	0.3694 (0.3577, 0.3812)
	Yes	573	0.4122 (0.3864, 0.4381)	0.3907 (0.3564, 0.4249)	0.3997 (0.3665, 0.4329)
	RD		0.0524 (0.0252, 0.0795)	0.0215 (−0.0141, 0.0570)	0.0302 (−0.0131, 0.0736)
B	No	6335	0.4027 (0.3950, 0.4103)	0.4028 (0.3918, 0.4138)	0.4034 (0.3926, 0.4143)
	Yes	2324	0.3901 (0.3777, 0.4025)	0.4530 (0.4368, 0.4693)	0.4598 (0.4444, 0.4752)
	RD		-0.0125 (−0.0271, 0.0020)	0.0502 (0.0312, 0.0693)	0.0564 (0.0334, 0.0794)
C	No	11535	0.3419 (0.3369, 0.3470)	0.3285 (0.3222, 0.3349)	0.3291 (0.3228, 0.3354)
	Yes	3269	0.3713 (0.3612, 0.3814)	0.3694 (0.3554, 0.3833)	0.3815 (0.3673, 0.3957)
	RD		0.0293 (0.0181, 0.0406)	0.0408 (0.0255, 0.0561)	0.0524 (0.0310, 0.0737)
D	No	3500	0.3067 (0.2982, 0.3151)	0.2911 (0.2801, 0.3022)	0.2917 (0.2809, 0.3026)
	Yes	2208	0.3446 (0.3330, 0.3563)	0.3382 (0.3252, 0.3513)	0.3385 (0.3257, 0.3513)
	RD		0.0380 (0.0236, 0.0523)	0.0471 (0.0307, 0.0635)	0.0468 (0.0272, 0.0663)
E	No	1050	0.1570 (0.1483, 0.1657)	0.1624 (0.1503, 0.1746)	0.1623 (0.1501, 0.1744)
	Yes	229	0.1717 (0.1514, 0.1919)	0.1860 (0.1551, 0.2169)	0.1781 (0.1493, 0.2069)
	RD		0.0147 (−0.0073, 0.0367)	0.0236 (−0.0095, 0.0567)	0.0158 (−0.0239, 0.0555)
F	No	1160	0.2049 (0.1944, 0.2154)	0.2370 (0.2219, 0.2520)	0.2376 (0.2226, 0.2527)
	Yes	337	0.2590 (0.2352, 0.2828)	0.3073 (0.2753, 0.3393)	0.3169 (0.2844, 0.3494)
	RD		0.0542 (0.0281, 0.0802)	0.0703 (0.0351, 0.1056)	0.0793 (0.0360, 0.1226)
All	No	28325	0.3278 (0.3247, 0.3309)	0.3225 (0.3184, 0.3266)	0.3227 (0.3185, 0.3268)
	Yes	8940	0.3548 (0.3489, 0.3608)	0.3692 (0.3617, 0.3768)	0.3716 (0.3639, 0.3794)
	RD		0.027 (0.0204, 0.0337)	0.0467 (0.0383, 0.0552)	0.0490 (0.0377, 0.0602)

The estimates displayed in this table represent the proportion of subjects with HbA1c < 7% within each group (DIABETIMSS Yes/No) as well as the difference of these proportions in the two groups. We show three estimators as discussed in text: unadjusted, adjusted within a logistic regression and finally using targeted maximum likelihood estimation (TMLE)

Back to article page

ISSN: 1472-6947

Contact us

General enquiries: journalsubmissions@springernature.com