Computed Tomography Does Not Improve Intra- and Interobserver Agreement of Hertel Radiographic Prognostic Criteria

Background and Objectives: Proximal humerus fractures are the second most frequent site of avascular necrosis (AVN), occurring in up to 16% of cases. The Hertel criteria have been used as a reference for the prediction of humerus head ischemia. However, these are based solely on the use of radiographs, which can make interpretation extremely difficult due to several reasons, such as the overlapping fragments, severity of the injury, and noncompliant acute pain patients. The objectives of the study were to evaluate the role of computed tomography (CT) in the interpretation of the Hertel criteria and to evaluate the intra- and interobserver agreement of orthopedic surgeons, comparing their area of expertise. Materials and Methods: The radiographs and CT scans of 20 skeletally mature patients who had fractures of the proximal humerus were converted to jpeg and mov, respectively. All images were evaluated by eight orthopedic surgeons (four trauma surgeons and four shoulder surgeons) in two different occasions. The intra- and interobserver agreement was assessed by using the Kappa coefficient. The level of significance was 5%. Results: There was a weak-to-moderate intraobserver agreement (kappa < 0.59) for all examiners. Only the medial metaphyseal hinge greater than 2 mm was identified by 87.5% of evaluators both in the radiographic and CT examinations in the two rounds of the study (p < 0.05). There was no significant interobserver agreement (kappa < 0.19), as it occurred only in some moments of the second round of evaluation. Conclusions: The prognostic criteria for humeral head ischemia evaluated in this study showed weak intra- and interobserver agreement in both the radiographic and tomographic evaluation. CT did not help surgeons in the primary interpretation of Hertel prognostic criteria used in this study when compared to the radiographic examination.