Skip to main content

Table 4 Final models developed by simplified logistic regression

From: Development and validation of prediction models for gestational diabetes treatment modality using supervised machine learning: a population-based cohort study

Level 1  − 0.856 to 0.005 * history of GDM + 0.741 * BMI obese + 0.800 * prediabetes before pregnancy
Levels 1–2  − 1.001 + 0.572 * history of GDM + 0.579 * pre-pregnancy obesity + 0.774 * prediabetes before pregnancy
 + 0.733 * screening valuea − 0.323 * history of GDM * pre-pregnancy obesity − 0.577 * history of GDM * screening
valuea + 0.480 * pre-pregnancy obesity * screening valuea
Levels 1–3  − 4.468 + 0.074 * oral glucose tolerance testb − 0.063 * week of gestational agec − 1.435 diagnosis by C–C criteriad
Levels 1–4  − 2.645 to 0.810 * meeting glycemic control goale + 0.167 * number of SMBG tests taken − 0.076 * week of gestational
agec + 0.044 * oral glucose tolerance testb − 0.234 * meeting glycemic control goale * number of SMBG tests taken
  1. BMI, body mass index; GDM, gestational diabetes mellitus; SMBG, self-monitored blood glucose
  2. The outcome is in log odds form, and coefficients have been rounded to the third decimal point
  3. aGlucose levels at 50-g, 1-h glucose challenge test for GDM screening (≥ 200 mg/dL)
  4. bFasting glucose value at 100-g, 3-h oral glucose tolerance test
  5. cGestational week at GDM diagnosis (continuous)
  6. dGDM diagnosis by Carpenter-Coustan criteria (versus by fasting hyperglycemia)
  7. eSMBG control status for the fasting test measured during first week after GDM diagnosis