Brachytherapy outcome modeling in cervical cancer patients: A predictive machine learning study on patient-specific clinical, physical and dosimetric parameters.

PURPOSE: To predict clinical response in locally advanced cervical cancer (LACC) patients by a combination of measures, including clinical and brachytherapy parameters and several machine learning (ML) approaches. METHODS: Brachytherapy features such as insertion approaches, source metrics, dosimetric, and clinical measures were used for modeling. Four different ML approaches, including LASSO, Ridge, support vector machine (SVM), and Random Forest (RF), were applied to extracted measures for model development alone or in combination. Model performance was evaluated using the area under the curve (AUC) of receiver operating characteristics curve, sensitivity, specificity, and accuracy. Our results were compared with a reference model developed by simple logistic regression applied to three distinct clinical features identified by previous papers. RESULTS: One hundred eleven LACC patients were included. Nine data sets were obtained based on the features, and 36 predictive models were built. In terms of AUC, the model developed using RF applied to dosimetric, physical, and total BT sessions features were found as the most predictive [AUC; 0.82 (0.95 confidence interval (CI); 0.79 -0.93), sensitivity; 0.79, specificity; 0.76, and accuracy; 0.77]. The AUC (0.95 CI), sensitivity, specificity, and accuracy for the reference model were found as 0.56 (0.52 ...0.68), 0.51, 0.51, and 0.48, respectively. Most RF models had significantly better performance than the reference model (Bonferroni corrected p-value < 0.0014). CONCLUSION: Brachytherapy response can be predicted using dosimetric and physical parameters extracted from treatment parameters. Machine learning algorithms, including Random Forest, could play a critical role in such predictive modeling.

Clinical and radiological outcomes after decompression and posterior fusion in patients with degenerative scoliosis.

OBJECTIVE: The prevalence of degenerative scoliosis (DS) increases with age and an overall increase is seen due to the aging population. This study aims to evaluate the clinical and radiological outcomes after decompression and posterior fusion in patients with DS. METHODS: In this is prospective study, 43 patients with DS, aged 37 to 70 years, were eligible to undergo decompression and posterior fusion. Primary outcomes were low back pain (LBP) with or without radicular pain, which was evaluated preoperatively and at 12 and 24 months after surgery with the use of a visual analog scale (VAS), and the quality of life (QOL), which was assessed at the same time periods by the Oswestry Disability Index (ODI) questionnaire. The Cobb's method was used to measure the degree of scoliosis in each patient preoperatively and at 24 hours, 12 and 24 months after the surgery. RESULTS: VAS scores improved significantly from a mean of 8.18 preoperatively to 4.48 at 12 months and 3.07 at 24 months postoperatively (P < .001). The mean radicular pain scores also decreased significantly (P < .001). At postoperative 12 months, the mean ODI score was significantly lower than the mean preoperative ODI score (47.81 ± 16.06 vs. 72.18 ± 12.28; P = .001). ODI score at 24 months postoperatively was significantly better than the preoperative ODI (15.53 ± 7.21 vs. 72.18 ± 12.28; P = .016). The mean Cobb angle changed significantly from 31.4° ± 4.88 preoperatively to 3.28° ± 2.10 at 24 months postoperatively (P < .001). CONCLUSIONS: Our findings suggest that decompression and posterior fusion in the patients with DS is an effective surgical method which is associated with satisfying clinical results in terms of improvement of postoperative LBP, radicular pain, and QOL, and correction of Cobb angle at 12 and 24 months after the surgery and restoration of sagittal alignment at 2 months postoperatively.

Comparison Between Acrylic Cage and Polyetheretherketone (PEEK) Cage in Single-level Anterior Cervical Discectomy and Fusion: A Randomized Clinical Trial.

STUDY DESIGN: Prospective, single-blind randomized-controlled clinical study. OBJECTIVE: To compare polyetheretherketone (PEEK) cage with a novel Acrylic cage to find out which fusion cage yielded better clinical outcomes following single-level anterior cervical discectomy and fusion (ACDF). SUMMARY OF BACKGROUND DATA: ACDF is considered a standard neurosurgical treatment for degenerative diseases of cervical intervertebral disks. There are many options, including bone grafts, bone cement, and spacers made of titanium, carbon fiber, and synthetic materials, used to restore physiological disk height and enhance spinal fusion, but the ideal device, which would provide immediate structural support and subsequent osteointegration and stability, has not been identified yet. To overcome this, we designed a new, inexpensive Acrylic cage. MATERIALS AND METHODS: A total of 64 patients were eligible to participate and were randomly allocated to undergo ACDF either with Acrylic interbody fusion cage filled with bone substitute (n=32) or PEEK cage (n=32). Nurick's grading was used for quantifying the neurological deficit. Clinical and radiologic outcome was assessed preoperatively, immediately after surgery, and subsequently at 2, 6, and 12 months of follow-up using Odom's criteria and dynamic radiographs (flexion-extension) and computed tomography scans, respectively. RESULTS: There was a statistically significant improvement in the clinical outcomes of the Acrylic cage group compared with the PEEK cage group (mean difference: -0.438; 95% confidence interval, -0.807 to -0.068; P=0.016). There was a statistically significant difference in disk space height increase between the 2 groups at the 6- and 12-month follow-up. The Acrylic cage achieved higher fusion rate (good fusion) than the PEEK cage (96.9% vs. 93.8%). Intervertebral angle demonstrated a significant difference among the 2 treated groups throughout the follow-up period. CONCLUSION: This study suggests that the use of Acrylic cage is associated with good clinical and radiologic outcomes and it can be therefore a good substitute for bone graft and other cages in ACDF.