Aim The aim was to compare the performances of the World Health Organization (WHO) and population‐based (PB) references in the screening for hydrocephalus in infants aged <2 years. Methods We collected 341 longitudinal head circumference (HC) measurements of hydrocephalic infants and 120 181 measurements of 15 145 healthy infants from primary care. The measurements were converted into z‐scores, and a new screening parameter, change in HC standard deviation score (SDS) over time (ΔHC SDS), was calculated. Comparisons were made using receiver operating characteristics analysis and linear mixed models. Results The mean HC SDSWHO was 3.5 and the mean HC SDSPB was 2.9 in the hydrocephalic infants, and in healthy children, those numbers were 1.0 SDSWHO and 0 SDSPB, respectively. The best screening accuracy was obtained with the PB reference in combination with the ΔHC SDS parameter (AUC 0.89). The accuracy of the WHO standard could be improved to a similar level by customising the screening cut‐offs of HC SDS according to the population and combining screening parameters. Conclusions Auxology alone was not sufficient for the screening of hydrocephalus. The WHO standard should be validated in the population, and population‐specific cut‐offs for normality defined before its introduction.