Improving Clinical Proficiency Using a 3-Dimensionally Printed and Patient-Specific Thoracic Spine Model as a Haptic Task Trainer

Background and Objectives Advanced haptic simulators for neuraxial training are expensive, have a finite life, and are not patient specific. We sought to demonstrate the feasibility of developing a custom-made, low-cost, 3-dimensionally printed thoracic spine simulator model from patient computed tomographic scan data. This study assessed the model's practicality, efficiency as a teaching tool, and the transfer of skill set into patient care. Methods A high-fidelity, patient-specific thoracic spine model was used for the study. Thirteen residents underwent a 1-hour 30-minute training session prior to performing thoracic epidural analgesia (TEA) on patients. We observed another group of 14 residents who were exposed to the traditional method of training during their regional anesthesia rotation for thoracic epidural placement. The TEA was placed for patients under the supervision of attending anesthesiologists, who were blinded to the composition of the study and control groups. As a primary outcome, data were collected on successful TEAs, which was defined as a TEA that provided full relief of sensation across the entire surgical area as assessed by both a pinprick and temperature test. Secondary outcomes included whether any assistance from the attending physician was required and failed epidurals. Results A total of 27 residents completed the study (14 in the traditional training, 13 in the study group). We found that the residents who underwent training with the simulator had a significantly higher success rate (11 vs 4 successful epidural attempts, P = 0.002) as compared with the traditional training group. The control group also required significantly more assistance from the supervising anesthesiologist compared with the study group (5 vs 1 attempt requiring guidance). The number needed to treat (NNT) for the traditional training group was 1.58 patients over the study period with a 95% confidence interval of 1.55 to 1.61. Conclusions By using patient-specific, 3-dimensionally printed, thoracic spine models, we demonstrated a significant improvement in clinical proficiency as compared with traditional teaching models.