Editorial: Burst fractures
Christoph P. Hofstetter and Michael Y. Wang
Treatment of thoracolumbar trauma by short-segment percutaneous transpedicular screw instrumentation: prospective comparative study with a minimum 2-year follow-up
Petr Vanek, Ondrej Bradac, Renata Konopkova, Patricia de Lacy, Jiri Lacman, and Vladimir Benes
The main aim of this study was to compare clinical and radiological outcomes after stabilization by a percutaneous transpedicular system and stabilization from the standard open approach for thoracolumbar spine injury.
Thirty-seven consecutive patients were enrolled in the study over a period of 16 months. Patients were included in the study if they experienced 1 thoracolumbar fracture (A3.1–A3.3, according to the AO/Magerl classification), had an absence of neurological deficits, had no other significant injuries, and were willing to participate. Eighteen patients were treated by short-segment, minimally invasive, percutaneous pedicle screw instrumentation. The control group was composed of 19 patients who were stabilized using a short-segment transpedicular construct, which was performed through a standard midline incision. The pain profile was assessed by a visual analog scale (VAS), and overall satisfaction by a simple 4-stage scale relating to performance of daily activities. Working ability and return to original occupation were also monitored. Radiographic follow-up was defined by the vertebral body index (VBI), vertebral body angle (VBA), and bisegmental Cobb angle. The accuracy of screw placement was examined using CT.
The mean surgical duration in the percutaneous screw group was 53 ± 10 minutes, compared with 60 ± 9 minutes in the control group (p = 0.032). The percutaneous screw group had a significantly lower perioperative blood loss of 56 ± 17 ml, compared with 331 ± 149 ml in the control group (p < 0.001). Scores on the VAS in patients in the percutaneous screw group during the first 7 postoperative days were significantly lower than those in the control group (p < 0.001). There was no significant difference between groups in VBI, VBA, and Cobb angle values during follow-up. There was no significant difference in screw placement accuracy between the groups and no patients required surgical revision. There was no significant difference between groups in overall satisfaction at the 2-year follow-up (p = 0.402). Working ability was insignificantly better in the percutaneous screw group; previous working position was achieved in 17 patients in this group and in 12 cases in the control group (p = 0.088).
This study confirms that the percutaneous transpedicular screw technique represents a viable option in the treatment of preselected thoracolumbar fractures. A significant reduction in blood loss, postoperative pain, and surgical time were the main advantages associated with this minimally invasive technique. Clinical, functional, and radiological results were at least the same as those achieved using the open technique after a 2-year follow-up. The short-term benefits of the percutaneous transpedicular screw technique are apparent, and long-term results have to be studied in other well-designed studies evaluating the theoretical benefit of the percutaneous technique and assessing whether the results of the latter are as durable as the ones achieved by open surgery.
Boosting phase-contrast MRI performance in idiopathic normal pressure hydrocephalus diagnostics by means of machine learning approach
Aleš Vlasák, Václav Gerla, Petr Skalický, Arnošt Mládek, Vojtěch Sedlák, Jiří Vrána, Helen Whitley, Lenka Lhotská, Vladimír Beneš Sr., Vladimír Beneš Jr., and Ondřej Bradáč
Phase-contrast MRI allows detailed measurements of various parameters of CSF motion. This examination is technically demanding and machine dependent. The literature on this topic is ambiguous. Machine learning (ML) approaches have already been successfully utilized in medical research, but none have yet been applied to enhance the results of CSF flowmetry. The aim of this study was to evaluate the possible contribution of ML algorithms in enhancing the utilization and results of MRI flowmetry in idiopathic normal pressure hydrocephalus (iNPH) diagnostics.
The study cohort consisted of 30 iNPH patients and 15 healthy controls examined on one MRI machine. All major phase-contrast parameters were inspected: peak positive, peak negative, and average velocities; peak amplitude; positive, negative, and average flow rates; and aqueductal area. The authors applied ML algorithms to 85 complex features calculated from a phase-contrast study.
The most distinctive parameters with p < 0.005 were the peak negative velocity, peak amplitude, and negative flow. From the ML algorithms, the Adaptive Boosting classifier showed the highest specificity and best discrimination potential overall, with 80.4% ± 2.9% accuracy, 72.0% ± 5.6% sensitivity, 84.7% ± 3.8% specificity, and 0.812 ± 0.047 area under the receiver operating characteristic curve (AUC). The highest sensitivity was 85.7% ± 5.6%, reached by the Gaussian Naive Bayes model, and the best AUC was 0.854 ± 0.028 by the Extra Trees classifier.
Feature extraction algorithms combined with ML approaches simplify the utilization of phase-contrast MRI. The highest-performing ML algorithm was Adaptive Boosting, which showed good calibration and discrimination on the testing data, with 80.4% accuracy, 72.0% sensitivity, 84.7% specificity, and 0.812 AUC. Phase-contrast MRI boosted by the ML approach can help to determine shunt-responsive iNPH patients.