Plating versus wiring for fixation of traumatic rib and sternal fractures

[Diagnosis of Rib Fracture Using Artificial Intelligence on Chest CT Images of Patients with Chest Trauma]

Purpose

To determine the pros and cons of an artificial intelligence (AI) model developed to diagnose acute rib fractures in chest CT images of patients with chest trauma.

Materials and Methods

A total of 1209 chest CT images (acute rib fracture [n = 1159], normal [n = 50]) were selected among patients with chest trauma. Among 1159 acute rib fracture CT images, 9 were randomly selected for AI model training. 150 acute rib fracture CT images and 50 normal ones were tested, and the remaining 1000 acute rib fracture CT images was internally verified. We investigated the diagnostic accuracy and errors of AI model for the presence and location of acute rib fractures.

Results

Sensitivity, specificity, positive and negative predictive values, and accuracy for diagnosing acute rib fractures in chest CT images were 93.3%, 94%, 97.9%, 82.5%, and 95.6% respectively. However, the accuracy of the location of acute rib fractures was low at 76% (760/1000). The cause of error in the diagnosis of acute rib fracture seemed to be a result of considering the scapula or clavicle that were in the same position (66%) or some ribs that were not recognized (34%).

Conclusion

The AI model for diagnosing acute rib fractures showed high accuracy in detecting the presence of acute rib fractures, but diagnosis of the exact location of rib fractures was limited.

Assessing outcome measures used after rib fracture: A COSMIN systematic review

PURPOSE

The incidence of invasive treatment of rib fracture has increased significantly over the last decade however the evidence of improved patient outcomes to support this is lacking. A systematic review was performed to identify patient reported outcome measures (PROMs) used in the assessment of outcomes following chest wall injury. The quality of evidence for the psychometric properties of the identified PROMs was graded using the COnsensus-based Standards for the selection of health Measurement INstruments (COSMIN) methodology.

METHODS

Rib fracture studies measuring patient reported outcomes were identified using PubMed/Medline, EMBASE, AMED and PsycINFO. Methodological quality of measurement properties was evaluated with the COnsensus-based Standards for selection of health status Measurement INstruments (COSMIN) checklist.

RESULTS

A total of 64 studies were identified including 19 different PROM instruments. Domains included in the reported PROMs included pain, breathlessness, general health quality of life, physical function and physiological health. No rib fracture specific PROM was identified. The most frequently reported instrument was the SF-36 reporting overall quality of life (HRQoL) although there was very low quality evidence for its content validity. There was low quality evidence to support good content validity for the Medical Research Council (MRC) dyspnoea scale, Brief Pain Index (BPI) and McGill Pain Questionnaire (MPQ). No PROM had undergone validation in a rib fracture population. The overall quality of the PROM development studies was poor. While we were unable to identify a clear "gold standard", based on the limited current evidence, we recommend that the EQ-5D-5L is used in combination with the MRC and BPI or MPQ for future rib fracture studies.

CONCLUSION

The lack of validated outcome measures for rib fracture patients is a significant limitation of the current literature. Further studies are needed to provide validated outcome measures to ensure accuracy of the reported results and conclusions. As interventions for rib fractures have become more common in both research and clinical practice this has become an urgent priority.