A comparison of tympanic and rectal temperatures in term Nigerian neonates

Background: Tympanic thermometry has come as a suitable alternative to traditional thermometry because of its safety and ease of use. However, it is still yet to gain wide acceptance in African settings due to conflicting results on its accuracy, thus rectal thermometry remains the gold standard in the newborn. The aim of this study was to compare tympanic and rectal temperatures in term Nigerian neonates. Methods: Rectal and tympanic temperatures were measured simultaneously in 300 consecutive term neonates between the ages of 37 and 42 weeks gestation using mercury-in-glass and the Infrared tympanic thermometers respectively. Paired t test, Pearson correlation coefficient and the Bland-Altman plot were used to compute data. Using rectal thermometry as gold standard, the sensitivity, specificity and predictive values of tympanic thermometry at various rectal temperature cut-offs were determined. Receiver Operating Curves (ROC) were constructed and the Areas Under the Curves (AUC) were compared. Results: The mean rectal temperature (37.34 +/- 0.55 degrees C) was significantly higher than the mean tympanic temperature (37.25 +/- 0.56 degrees C) (p < 0.001) with a mean difference of 0.09 degrees C +/- 0.24 degrees C (95% CI: 0.06, 0.12). There was a strong positive correlation between the two measurements (r = 0.9; p < 0.001). Tympanic thermometry showed sensitivities ranging from 65% to 86% and specificities of 95% to 99% at rectal temperature cut-offs of 37.5 degrees C to 38 C. The positive and negative predictive values of the tympanic temperatures at the various temperature cut-offs ranged from 82% to 93% and 80% to 98% respectively. Accuracy was noted to increase with higher temperatures as shown by the Receiver Operating Curves with the highest accuracy at the temperature cut-off of 38 C and AUC of 0.91. Conclusions: The sensitivity of tympanic thermometry was relatively low in detecting rectal temperatures despite the good correlation and agreement between them. The specificities and predictive values of tympanic temperatures in detecting rectal temperatures were high and accuracy increased with higher temperatures. Though using the tympanic route for measuring temperature in the newborn is relatively safe and non-invasive, its low sensitivity limits its use. Further studies would be required to further assess the accuracy of tympanic temperature measurements in the newborn.