Producers report bovine respiratory disease (BRD) and diarrhea as the 2 most common diseases in preweaned calves, both of which can affect calf performance and welfare. Group housing has the potential to improve calf welfare, but only if producers are able to detect disease. To reduce time evaluating individual calves, there is a need for a group level health-screening tool to identify potentially sick calves that require further examination. The objective of this study was to develop a screening tool using behavioral measures to detect disease in preweaned group-housed dairy calves. This cross-sectional study included the evaluation of preweaned group-housed calves (n = 206) on 4 farms in Wisconsin. Calves were scored for behaviors that were hypothesized to be indicative of illness: abnormal posture when lying or standing, isolation, lethargy, and the willingness to approach a stationary person (2 approach tests were performed and each was scored separately). Each behavior category was scored as normal (0 points) or abnormal (1 point) and then categories were summed to obtain a total behavior score for each calf. Following the behavior scoring, calves underwent an individual health assessment for BRD, diarrhea, and umbilical infections. Total behavior scores ranged from 0 (normal) to 5 (severely abnormal) and reflect the number of abnormal behaviors observed. The highest sensitivity and specificity of the behavior score for disease identification occurred at score cut points of 2 and 3. Therefore, scores of 2 or greater or scores of 3 or greater were considered a positive test result for disease and were further examined. Outcomes of a positive or negative behavior score for cut points of 2 and 3 were analyzed using PROC LOGISTIC in SAS and all models were controlled for calf age and farm. A score of 2 or greater tended to be significant for the detection of diarrhea (P = 0.05), but was not significant for BRD (P > 0.05). At a cut point of 3 or greater, calves without BRD were 0.24 (95% CI: 0.10 to 0.59) times as likely to have a positive behavior score, compared with calves with BRD (P < 0.01). Utilizing a cut point of 3 or greater on this behavior-based screening tool may be useful to identify calves with BRD.