Mutational inactivation of the SWI/SNF chromatin regulator ATRX occurs frequently in gliomas, the most common primary brain tumors. Whether and how ATRX deficiency promotes oncogenesis by epigenomic dysregulation remains unclear, despite its recent implication in both genomic instability and telomere dysfunction. Here we report that Atrx loss recapitulates characteristic disease phenotypes and molecular features in putative glioma cells of origin, inducing cellular motility although also shifting differentiation state and potential toward an astrocytic rather than neuronal histiogenic profile. Moreover, Atrx deficiency drives widespread shifts in chromatin accessibility, histone composition, and transcription in a distribution almost entirely restricted to genomic sites normally bound by the protein. Finally, direct gene targets of Atrx that mediate specific Atrx-deficient phenotypes in vitro exhibit similarly selective misexpression in ATRX-mutant human gliomas. These findings demonstrate that ATRX deficiency and its epigenomic sequelae are sufficient to induce disease-defining oncogenic phenotypes in appropriate cellular and molecular contexts.

BACKGROUND AND OBJECTIVES: General large language models (LLMs), such as ChatGPT (GPT-3.5), have demonstrated the capability to pass multiple-choice medical board examinations. However, comparative accuracy of different LLMs and LLM performance on assessments of predominantly higher-order management questions is poorly understood. We aimed to assess the performance of 3 LLMs (GPT-3.5, GPT-4, and Google Bard) on a question bank designed specifically for neurosurgery oral boards examination preparation. METHODS: The 149-question Self-Assessment Neurosurgery Examination Indications Examination was used to query LLM accuracy. Questions were inputted in a single best answer, multiple-choice format. χ2, Fisher exact, and univariable logistic regression tests assessed differences in performance by question characteristics. RESULTS: On a question bank with predominantly higher-order questions (85.2%), ChatGPT (GPT-3.5) and GPT-4 answered 62.4% (95% CI: 54.1%-70.1%) and 82.6% (95% CI: 75.2%-88.1%) of questions correctly, respectively. By contrast, Bard scored 44.2% (66/149, 95% CI: 36.2%-52.6%). GPT-3.5 and GPT-4 demonstrated significantly higher scores than Bard (both P < .01), and GPT-4 outperformed GPT-3.5 (P = .023). Among 6 subspecialties, GPT-4 had significantly higher accuracy in the Spine category relative to GPT-3.5 and in 4 categories relative to Bard (all P < .01). Incorporation of higher-order problem solving was associated with lower question accuracy for GPT-3.5 (odds ratio [OR] = 0.80, P = .042) and Bard (OR = 0.76, P = .014), but not GPT-4 (OR = 0.86, P = .085). GPT-4's performance on imaging-related questions surpassed GPT-3.5's (68.6% vs 47.1%, P = .044) and was comparable with Bard's (68.6% vs 66.7%, P = 1.000). However, GPT-4 demonstrated significantly lower rates of “hallucination” on imaging-related questions than both GPT-3.5 (2.3% vs 57.1%, P < .001) and Bard (2.3% vs 27.3%, P = .002). Lack of question text description for questions predicted significantly higher odds of hallucination for GPT-3.5 (OR = 1.45, P = .012) and Bard (OR = 2.09, P < .001). CONCLUSION: On a question bank of predominantly higher-order management case scenarios for neurosurgery oral boards preparation, GPT-4 achieved a score of 82.6%, outperforming ChatGPT and Google Bard.

BACKGROUND AND PURPOSE: Differentiating the types of pediatric posterior fossa tumors on routine imaging may help in preoperative evaluation and guide surgical resection planning. However, qualitative radiologic MR imaging review has limited performance. This study aimed to compare different machine learning approaches to classify pediatric posterior fossa tumors on routine MR imaging. MATERIALS AND METHODS:This retrospective study included preoperative MR imaging of 288 patients with pediatric posterior fossa tumors, including medulloblastoma (n ¼ 111), ependymoma (n ¼ 70), and pilocytic astrocytoma (n ¼ 107). Radiomics features were extracted from T2-weighted images, contrast-enhanced T1-weighted images, and ADC maps. Models generated by standard manual optimization by a machine learning expert were compared with automatic machine learning via the Tree-Based Pipeline Optimization Tool for performance evaluation.RESULTS: For 3-way classification, the radiomics model by automatic machine learning with the Tree-Based Pipeline Optimization Tool achieved a test micro-averaged area under the curve of 0.91 with an accuracy of 0.83, while the most optimized model based on the feature-selection method x 2 score and the Generalized Linear Model classifier achieved a test micro-averaged area under the curve of 0.92 with an accuracy of 0.74. Tree-Based Pipeline Optimization Tool models achieved significantly higher accuracy than average qualitative expert MR imaging review (0.83 versus 0.54, P , .001). For binary classification, Tree-Based Pipeline Optimization Tool models achieved an area under the curve of 0.94 with an accuracy of 0.85 for medulloblastoma versus nonmedulloblastoma, an area under the curve of 0.84 with an accuracy of 0.80 for ependymoma versus nonependymoma, and an area under the curve of 0.94 with an accuracy of 0.88 for pilocytic astrocytoma versus non-pilocytic astrocytoma.CONCLUSIONS: Automatic machine learning based on routine MR imaging classified pediatric posterior fossa tumors with high accuracy compared with manual expert pipeline optimization and qualitative expert MR imaging review. ABBREVIATIONS: AUC ¼ area under the curve; AutoML ¼ automatic machine learning; CHSQ ¼ x 2 score; EP ¼ ependymoma; MB ¼ medulloblastoma; ML ¼ machine learning; PA ¼ pilocytic astrocytoma; TPOT ¼ Tree-Based Pipeline Optimization Tool A mong childhood malignancies, pediatric brain tumors are the second most common and the leading cause of death from solid tumors. 1,2 Posterior fossa tumors make up a disproportionate portion of brain tumors in the pediatric population, accounting for 54%-70% of tumors compared with ,20% in the adult population. 3 The most common subtypes of posterior fossa tumors among children are medulloblastoma (MB), pilocytic astrocytoma (PA), and ependymoma (EP). 4,5 Discrimination of these 3 malignancies is important due to the differing natural

No abstract