Glioblastoma and malignant melanoma: Serendipitous or anticipated association?

We describe a patient who had primary glioblastoma (GB) and malignant melanoma (MM). A 78-year-old man presented with several weeks to months of history of gait disturbance, confusion, memory disturbance, and worsening speech. Imaging studies performed on admission revealed a large frontotemporal lobe mass associated with the surrounding zone of vasogenic edema. Given the patient's medical history of incomplete biopsy of a midback tumor performed three weeks before, the presumptive clinical diagnosis was metastatic MM. Pathological examination of frozen sections of fragmented specimens obtained at stereotactic biopsy performed on admission revealed a high-grade malignant neoplasm characterized by discohesive cells in a blue myxoid background and abundant foci of tumor necrosis. Given these features, in conjunction with the abovementioned pathological report, the frozen section diagnosis by the neuropathologist was "neoplasm identified, favor melanoma." Due to the paucity of lesional tissue, a limited immunohistochemistry performed on the permanent sections revealed positive staining of lesional cells for Sox10 alone using a multiplex MART1/Sox10 immunostain and S-100 protein, an immunohistochemical profile supporting the presumptive frozen section diagnosis. A tumor debulk procedure, performed two weeks later, revealed histopathologic features most compatible with GB, IDH wild-type. Thus, additional immunohistochemistry on the permanent sections revealed positive staining of glial fibrillary acidic protein (GFAP), Sox10, and S-100 protein as well as negative staining of gp100, a complex carbohydrate matrix protein in embryonic melanosomes, using a specific antibody HMB45. The concomitant occurrence of MM and GB in our patient underscores the association between these two entities. Our literature review suggests that the sporadic co-occurrence of these two conditions is likely not serendipitous.

AI-based differential diagnosis of dementia etiologies on multimodal data.

Differential diagnosis of dementia remains a challenge in neurology due to symptom overlap across etiologies, yet it is crucial for formulating early, personalized management strategies. Here, we present an artificial intelligence (AI) model that harnesses a broad array of data, including demographics, individual and family medical history, medication use, neuropsychological assessments, functional evaluations and multimodal neuroimaging, to identify the etiologies contributing to dementia in individuals. The study, drawing on 51,269 participants across 9 independent, geographically diverse datasets, facilitated the identification of 10 distinct dementia etiologies. It aligns diagnoses with similar management strategies, ensuring robust predictions even with incomplete data. Our model achieved a microaveraged area under the receiver operating characteristic curve (AUROC) of 0.94 in classifying individuals with normal cognition, mild cognitive impairment and dementia. Also, the microaveraged AUROC was 0.96 in differentiating the dementia etiologies. Our model demonstrated proficiency in addressing mixed dementia cases, with a mean AUROC of 0.78 for two co-occurring pathologies. In a randomly selected subset of 100 cases, the AUROC of neurologist assessments augmented by our AI model exceeded neurologist-only evaluations by 26.25%. Furthermore, our model predictions aligned with biomarker evidence and its associations with different proteinopathies were substantiated through postmortem findings. Our framework has the potential to be integrated as a screening tool for dementia in clinical settings and drug trials. Further prospective studies are needed to confirm its ability to improve patient care.

AI-based differential diagnosis of dementia etiologies on multimodal data.

Differential diagnosis of dementia remains a challenge in neurology due to symptom overlap across etiologies, yet it is crucial for formulating early, personalized management strategies. Here, we present an AI model that harnesses a broad array of data, including demographics, individual and family medical history, medication use, neuropsychological assessments, functional evaluations, and multimodal neuroimaging, to identify the etiologies contributing to dementia in individuals. The study, drawing on 51,269 participants across 9 independent, geographically diverse datasets, facilitated the identification of 10 distinct dementia etiologies. It aligns diagnoses with similar management strategies, ensuring robust predictions even with incomplete data. Our model achieved a micro-averaged area under the receiver operating characteristic curve (AUROC) of 0.94 in classifying individuals with normal cognition, mild cognitive impairment and dementia. Also, the micro-averaged AUROC was 0.96 in differentiating the dementia etiologies. Our model demonstrated proficiency in addressing mixed dementia cases, with a mean AUROC of 0.78 for two co-occurring pathologies. In a randomly selected subset of 100 cases, the AUROC of neurologist assessments augmented by our AI model exceeded neurologist-only evaluations by 26.25%. Furthermore, our model predictions aligned with biomarker evidence and its associations with different proteinopathies were substantiated through postmortem findings. Our framework has the potential to be integrated as a screening tool for dementia in various clinical settings and drug trials, with promising implications for person-level management.

Adjuvant treatments for ependymomas.

Ependymomas are rare primary central nervous system tumors occurring in children and young adults. They can be indolent or locally aggressive depending on location, histology, and extent of resection. Treatment involves maximal surgical resection and usually focal radiation therapy, depending on the presence of residual disease and tumor grade. Chemotherapy has been studied for both adults and children but do not have an established role in adjuvant therapy. In both age groups, treatment with mainly cisplatin based regimens can be considered in the setting of residual disease after surgery or for salvage therapy when surgery or further radiation is not indicated. In children, chemotherapy can be considered in very young children to delay radiation or to increase the likelihood of complete resection in second look surgery. Targeted agents such as bevacizumab and lapatinib do not have a role in adjuvant therapy for ependymomas but are being explored for recurrent disease. This review discusses adjuvant therapy in both adult and child populations.