Skip to main content

Table 4 Logistic regression models for NETS and SENSS after model updating

From: External validation of inpatient neonatal mortality prediction models in high-mortality settings

SENSS:

 Linear predictor (LPSENSS) =  − 3.4635 + 2.8734 * ELBW + 1.7696 * VLBW + 0.3352 * LBW − 0.2396 * macrosomia − 0.0685 * male + 0.6400 * difficulty feeding + 0.5300 * convulsions + 1.5078 * indrawing + 1.0633 * cyanosis + 0.9583 * floppy unable to suck

NETS:

 Linear predicator (LPNETS) =  − 3.5246 + 4.2077 * ELBW + 2.6112 * VLBW + 0.8759 * LBW + 0.000 * macrosomia − 0.0667 * male + 0.5962 * antibiotics + 0.8095 * fluids − 1.2843 * feeds + 0.1522 * oxygen + 1.1303 * phenobarbital

  1. For each variable, the presence of the indicator takes a value of 1, and the absence takes a value of 0. The coefficients are summated to give the linear predictor, which is then converted to the predicted probability of in-hospital mortality
  2. ELBW Extremely low birth weight, LBW Low birth weight, LP Linear predictor, NETS Neonatal Essential Treatment Score, SENSS Score of Essential Neonatal Symptoms and Signs, VLBW Very low birth weight
Back to article page

BMC Medicine

ISSN: 1741-7015

Contact us