Kaur, Anmol

The intersection between radiomics, the computational analysis of imaging data, and machine learning (ML) may lead to new developments in the diagnosis, prognosis, and management of diseases. For spinal tumors specifically, applications of these fields appear promising. In this educational narrative review, we provide a summary of the current advancements in radiomics and artificial intelligence (AI), as well as applications of both fields in the diagnosis and management of spinal tumors. We also provide a suggested workflow of radiomics and machine learning analysis of spinal tumors for researchers, including a list and description of commonly used radiomic features. Future directions in the field of radiomics and machine learning applications to spinal tumors may involve validating already proposed algorithms with larger datasets, ensuring that all computational applications to patient care maintain high ethical standards, and continuing work in developing novel and highly accurate computational techniques to enhance patient outcomes.

e13162 Background: BRCA1/2 mutations impair homologous recombination repair, forcing cancer cells to rely on alternative DNA repair pathways, such as those mediated by poly(ADP-ribose) polymerase (PARP). PARP inhibitors (PARPis), like iniparib, olaparib, talazoparib, niraparib, and veliparib, exploit this dependency, inducing lethality in cells of BRCA-mutated, HER2-negative breast cancers (BRCAm, HER2-BC). Only 2 PARPis, talazoparib and olaparib, are FDA-approved for BRCAm, HER2-BC. However, the treatment with the highest efficacy remains unclear. We conducted a network meta-analysis (NMA) of randomised controlled trials (RCTs) to compare the efficacy of PARPis in treating BRCAm, HER2-BC. Methods: We systematically searched PubMed, Cochrane CENTRAL, SCOPUS, and ClinicalTrials.gov (up to December 2024) for randomized controlled trials (RCTs) following PRISMA-NMA guidelines. Primary outcome was overall survival(OS), with hazard ratios (HRs) and 95% confidence intervals (CIs). Secondary outcome was progression-free survival (PFS). Survival times were converted to HRs under the assumption of exponential distribution. Standard of care (SOC) was defined as taxane/anthracycline-based regimens with additional platinum-based chemotherapy. Physician's choice chemotherapy (PCT) included capecitabine, eribulin, gemcitabine, or vinorelbine. A frequentist approach with random-effects modeling was used to pool estimates, and P-scores ranked treatment efficacy. Heterogeneity and inconsistency were assessed using τ², I², and Q-statistics. Analyses were conducted in R version 4.4.1. Results: 8 studies including 4432 participants incorporating 8 pairwise comparisons and 7 treatments were analyzed for OS. Compared to SOC (reference), HRs of OS were significantly reduced with talazoparib+SOC (HR = 0.49, 95% CI: 0.32–0.74; P = 0.64), olaparib+SOC (HR = 0.46, 95% CI: 0.36–0.59; P = 0.69), niraparib+SOC (HR = 0.44, 95% CI: 0.26–0.76; P = 0.76), and veliparib+SOC (HR = 0.38, 95% CI: 0.29–0.48; P = 0.91). No heterogeneity or inconsistency was detected (τ² = 0; I² = 0; Q = 1.27, p = 0.53). For PFS, iniparib/gemcitabine, talazoparib, olaparib, and niraparib showed significant reduction in HR with increasing order of P-scores, in combination with SOC. Conclusions: Veliparib combined with SOC showed the highest OS improvement, while niraparib ranked highest for PFS, followed by talazoparib and olaparib. Further trials are needed to confirm these findings and refine treatment strategies for BRCAm, HER2-BC.