Citations

Institution: Mayo Clinic Clear

Showing 10 of 108152 citations.

CT pulmonary angiography in the inpatients: A 5-year retrospective view at the end of COVID-19 public health emergency
Mugu, Vamshi , Parikh, Riddhi S. , Carr, Brendan M. , Khandelwal, Ashish , Mugu, Vamshi K

Medicine | November 11, 2024 | Volume: 103 | Issue: 45 | Pages: e40351

10.1097/md.0000000000040351 | PMID 39533597 Get It

To retrospectively evaluate the trends in utilization and results of computed tomography pulmonary angiography (CTPA study) for detection of acute pulmonary embolism (PE) in the hospital inpatients during different phases of COVID-19 public health emergency. We conducted an Institutional Review Board (IRB)-approved retrospective review of CTPA studies for our hospital inpatients in the years from 2019 to 2023, ranging from the prepandemic year (2019) to the year coinciding with the end of public health declarations (2023). Collected characteristics included patient age, patient sex, and result of the study. The utilization of CTPA studies for inpatients was higher in 2020 to 2023, compared to 2019 (3.8% in 2023 compared to 2.4% in 2019, P < .001). The increase in utilization was also statistically significant in each group, when stratified by age and sex (OR = 1.46 for female, OR = 1.71 for male, OR = 1.93 for elderly, and OR = 1.29 for non-elderly inpatients in 2023, compared to 2019). The positivity rate of acute PE in the inpatients was overall higher in 2021, 2022, and 2023, compared to 2019 (for example, 18.5% in 2023 compared to 14.3% in 2019, P = .01). When stratified by age and sex, only the non-elderly patients continued to have a significantly higher rate of acute PE in 2023, compared to 2019 (OR = 1.39). While studies spanning longer time frames and involving multiple institutions are needed to understand and generalize this conclusion, we conclude that the utilization and positivity rates of CTPA studies in inpatients remains high at the end of the COVID-19 pandemic public health emergency.
TMIC-60. BRATS-PATH: ASSESSING HETEROGENEOUS HISTOPATHOLOGIC REGIONS IN GLIOBLASTOMA
Thakur, Siddhesh , Moassefi, Mana , Baid, Ujjwal , Innani, Shubham , Baheti, Bhakti , Albrecht, Jacob , Karargyris, Alexandros , Kassem, Hasan, Nasrallah, MacLean P. , Gubbiotti, Maria A. , López, Giselle Y. , Miller, Michael L. , Cooper, Lee , Bell, William R. , Faghani, Shahriar , Moassefi, Mana , Chung, Verena , Pati, Sarthak , Ahrendsen, Jared T. , Barresi, Valeria , Lucas, Calixto‐Hope G. , Miller, Michael, Huse, Jason T. , Bakas, Spyridon

Neuro-Oncology | November 11, 2024 | Volume: 26 | Issue: Supplement_8 | Pages: viii312-viii312

10.1093/neuonc/noae165.1238 Get It

Abstract Glioblastoma, the most common malignant primary adult brain tumor, poses significant diagnostic and treatment challenges due to its heterogeneous molecular and micro-environmental profiles. To this end, we organize the BraTS-Path challenge to provide a public benchmarking environment and a comprehensive dataset to develop and validate AI models for identifying distinct histopathologic glioblastoma sub-regions in H&E-stained digitized tissue sections. We identified 188 multi-institutional diagnostic slides of glioblastoma (IDH-wt, Gr.4) cases, from the TCGA-GBM and TCGA-LGG data collections, following their reclassification according to the 2021 WHO classification criteria. Sub-regions were selected according to distinctive morphology of histopathologic features and included aggressive tumor biology and areas consistent with potential treatment effect. Selected sub-region annotations included cellular tumor, geographic necrosis, cortical infiltration, pseudopalisading necrosis, microvascular proliferation, white matter penetration, regions dense with macrophages, leptomeningeal infiltration, and presence of lymphocytes. We obtained 107,340 patches of size 512x512 from the 9 sub-regions. A global network of board-certified expert neuropathologists defined and followed a systematic annotation protocol based on clinical definitions and only delineated sub-regions with high confidence, thus ensuring high-quality standardized data. Each tissue section was assigned to an annotator-approver pair, with the annotator delineating sub-regions and the approver ensuring the consistency of the annotations. By crowdsourcing annotations, the BraTS-Path challenge harnesses the collective expertise of clinical neuropathologists and fosters a collaborative environment to advance the neuro-oncology field. The anticipated developed algorithms are expected to integrate state-of-the-art computational methods, achieving high accuracy in identifying diverse histopathologic features and advancing clinical decision-making processes. The BraTS-Path challenge aims to bridge the gap between research and clinical practice by promoting the development of AI-driven tools for precise tumor characterization. This collaborative effort can significantly enhance our understanding of glioblastoma, improve diagnostic accuracy, and inform treatment strategies, thereby contributing to better patient outcomes.
TMIC-67. EMERGING ROLE OF EXTRACELLULAR MATRIX STIFFNESS AS A HALLMARK OF GLIOBLASTOMA: INSIGHT TO MECHANICAL MEMORY FORMATION AND PROLONGED INVASION IN THE TUMOR PERIPHERY
Meade, Paola Suarez, Whitehead, Rachel, Teeter, Caroline, Aramburu, Manuela, Chaichana, Kaisorn L. , Rosenfeld, Steven S. , Kenchappa, Rajappa S., Hwang, Tae Hyun , Quiñones‐Hinojosa, Alfredo , Whitehead, Rachel, Clemenceau, Jean R. , Norton, Emily S. , Kulkarni, Tanmay , Hong, Changjin , Guerrero‐Cazares, Hugo , Schiapparelli, Paula , Κωνσταντόπουλος, Κωνσταντίνος

Neuro-Oncology | November 11, 2024 | Volume: 26 | Issue: Supplement_8 | Pages: viii313-viii313

10.1093/neuonc/noae165.1245 Get It

Abstract The extracellular matrix (ECM) plays a critical role in cancer progression, with its biophysical properties influencing cancer behavior. ECM stiffness can induce long-lasting adaptations in cancer cells, promoting sustained invasion through a process known as “mechanical memory” (MM). Glioblastoma (GBM) exhibits spatial heterogeneity in stiffness, with stiffer ECM found at the tumor periphery where invasive cells reside and promote recurrence. We hypothesize that increased stiffness at the tumor periphery primes GBM cells for sustained invasion through MM. METHODS Cell lines were established from image-guided human GBM samples from tumor margin and core (n=10 patients, 20 cell lines). Cells from random locations were conditioned in physiologically relevant extracellular matrices for two weeks. Human organotypic assay (n=3), Migration Assays, Atomic Force Microscopy (AFM), Immunocytochemistry, Western Blot, and RNA-sequencing (n=6) were performed. RESULTS GBM cells at higher stiff surfaces displayed increased migration (p&lt;0.01). Magnetic Resonance Elastography (n=9) confirmed GBM heterogeneity, with softer cores (0.2-0.5kPa) transitioning to stiffer margins (&gt;2kPa). Organotypic scaffolds mimicking the tumor margin promoted enhanced migration of GFP-labeled GBM cells. Margin cells and cells conditioned on stiffer matrices demonstrated higher migratory potential compared to their core and soft-conditioned counterparts (p&lt;0.05). These trends persist over time and across multiple passages. ECM stiffness exposure causes nanomechanical, cytoskeletal, and transcriptional adaptations. AFM shows that cells from the margin (n=6) are softer (p&lt;0.01) and more deformable (p&lt;0.01). RNAseq identified upregulation of MM-specific genes in GBM margin cells. The mechanosensitive transcription factor YAP1 emerged as a key driver of MM. Notably, YAP1 is targetable by the FDA-approved drug Verteporfin. YAP1 expression was elevated in margin and stiff-conditioned cells (p&lt;0.05). Stiff-conditioned cells and margin cells displayed increased sensitivity to Verteporfin treatment (p&lt;0.05), with treatment significantly reducing margin migration compared to the core (p&lt;0.001). CONCLUSION Stiffer GBM margins promote the formation of aggressive phenotypes through MM. Targeting YAP1 with Verteporfin, a readily available drug, presents a promising strategy to halt GBM invasion and improve patient outcomes.
TMIC-68. DEEP LEARNING OF THE SPATIAL IMMUNE ENGAGEMENT IN GLIOBLASTOMA UNDER TEMOZOLOMIDE TREATMENT
Gupta, Pravesh , Kannan, Kasthuri , Castillo, Simón P. , Jahedi, Afrooz , Huse, Jason T. , Yuan, Yinyin , Bhat, Krishna

Neuro-Oncology | November 11, 2024 | Volume: 26 | Issue: Supplement_8 | Pages: viii313-viii314

10.1093/neuonc/noae165.1246 Get It

Abstract Effective immune synapses are a prerequisite for desirable immune surveillance and control of tumour growth. Cell-to-cell interactions form the basis of immune synapses, resulting in either immunoprotected or immunosuppressed manifestations in the tumour brain that could explain glioblastoma (GBM) recurrence. Using state-of-the-art multiplex imaging, spatial statistics, and spatially aware deep learning tools in 14 patient-matching tissues from primary and recurrent GBM, we detected spatial immune networks (SINets). SINets across 105 regions of interest comprising 2.3 million cells show stronger spatial engagement between myeloid and lymphoid lineages at recurrence. SINets’ architecture in primary tumours is associated with relapse timing. Patients, where the SINets are more modular, recur sooner than patients with denser SiNets. In addition, this association presents sexual dimorphism in our cohort (N=3 females, and N=4 males). Phenotype-to-phenotype spatial coexistence also contributes to enhancing phenotype prediction. A spatial-aware deep learning model trained with single-cell data from primary tumours reaches an average balanced accuracy of 0.76 in primary tumour cellular communities unseen during training, compared to a spatial-agnostic model that reached an average balanced accuracy of 0.69. In summary, we detected a distinct spatial engagement in glioblastoma undergoing chemo-radiation treatment. The spatial patterns of coexistence represent ecological niches that contribute to defining cell occurrence and may underpin effective immune synapses. Overall, the spatiotemporal elements provide a newer approach for dissecting glioblastoma’s complexity and discovering opportunities for stratifying patients by harnessing spatial information encoded in multicellular niches.
NCOG-32. RELATIONSHIPS BETWEEN INTRAOPERATIVE TASK-BASED GAMMA BAND ELECTROCORTICOGRAMS, DIRECT ELECTRICAL STIMULATION, AND COGNITIVE-LINGUISTIC OUTCOME FOLLOWING AWAKE BRAIN TUMOR RESECTION
Noll, Kyle R. , Tasnim, Israt , Asman, Priscella , Swamy, Chandra, Connelly, Katherine , Muir, Matthew , Ince, Nuri F. , Prabhu, Sujit S. , Muir, Matthew T. , Hall, Matt , Pellizzer, Giuseppe

Neuro-Oncology | November 11, 2024 | Volume: 26 | Issue: Supplement_8 | Pages: viii231-viii231

10.1093/neuonc/noae165.0914 Get It

Abstract BACKGROUND As an adjunct to direct electrical stimulation (DES), intraoperative electrocorticography (ECoG) can aid detection of language-eloquent cortex. However, it is unclear how surgical impact upon mapping findings relates to cognitive-linguistic outcomes. METHODS Ten patients underwent awake craniotomy for tumor resection with ECoG and DES language mapping. Mapping utilized iPad stimulus presentation coupled to an electrode array capable of both recording ECoG activity and delivering DES. Time-frequency gamma band activations were visualized (Early, Long, Late, Double Peak) for 3 naming paradigms (Object, Action, Auditory). DES was also conducted for each task. Mapping results were overlayed on postoperative MRI to examine proximity to parenchymal trauma (cavity, sulcal displacement). Patients completed cognitive-linguistic testing [WAB-R (N=3) or Neuropsychological Assessment (N=7)] prior to surgery and &lt;2 months postoperatively. Patients with persisting aphasia at 6-month follow-up were also identified. RESULTS Postoperative language decline was found in 50% of patients, with 30% showing worsening (&gt;1SD) in Naming and Phonemic Fluency, and 60% in Semantic Fluency. Surgery impacted ECoG features in 60% of patients and DES arrest sites in 30%. A trend was observed where Early and Late Object naming ECoG features were associated with Semantic Fluency decline [rpb(5)=-.69, p=.067]. Arrest during Auditory naming DES &lt;1 cm of surgical effect was associated with decline in Abstraction [rpb(5)=-.83, p=.042; FET, p=.029] and Semantic Fluency [rpb(5)=-.87, p=.012; FET, p=.024]. Excluding the 3 transsulcal surgeries, arrest during Auditory naming DES &lt;1 cm of resection was associated with general language decline [FET, p=.047]. All 3 patients with persisting aphasia had Auditory naming arrest &lt;1 cm of resection and 2/3 patients had Object naming ECoG features resected. CONCLUSIONS While preliminary, results suggest that surgical proximity to ECoG and DES mapping results may inform risk of surgically-acquired cognitive-linguistic decline. Findings support the potential of multimethod-multitask intraoperative language mapping.
NCOG-34. CORRESPONDENCE BETWEEN INTRAOPERATIVE GAMMA BAND ELECTROCORTICOGRAMS AND DIRECT ELECTRICAL STIMULATION ACROSS DIVERSE NAMING TASKS IN PATIENTS WITH LANGUAGE-ELOQUENT BRAIN TUMORS
Noll, Kyle R. , Tasnim, Israt , Asman, Priscella , Swamy, Chandra, Connelly, Katherine , Muir, Matthew , Hall, Matthew J. , Ince, Nuri F. , Prabhu, Sujit S. , Muir, Matthew T. , Hall, Matthew, Pellizzer, Giuseppe

Neuro-Oncology | November 11, 2024 | Volume: 26 | Issue: Supplement_8 | Pages: viii232-viii232

10.1093/neuonc/noae165.0916 Get It

Abstract BACKGROUND Few studies have examined concordance between intraoperative electrocorticography (ECoG) and direct electrical stimulation (DES) language mapping, especially across varied naming tasks. METHODS Twelve patients (Mdn age=59; 75% HGG) underwent awake craniotomy with ECoG and DES language mapping. Mapping utilized iPad stimulus presentation coupled to a 4x8 electrode array for both ECoG and DES. Time-frequency ECoG gamma band activity (Early and Late) was visualized for 3 naming paradigms (Object, Action, Auditory). Bipolar DES was also conducted for each task at each electrode pair. ECoG activations and DES hits were overlayed on preoperative MRI. DES hits represented ground truth for eloquence. ECoG accuracy was examined for each task with 3 different criteria: exact (identical electrodes for ECoG activation and DES hits), adjacent (ECoG &lt;1cm of DES hits), and adjacent within a predefined peritumoral region of interest (&lt;2 cm from boundaries). RESULTS 32 DES hits (40% Auditory, 32% Action, 28% Obj) were observed across patients. Exact ECoG-DES accuracy ranged from 78%-90% [Object: Sens=11%, Spec=91%, PPV=6%, NPV=95%; Action: Sens=40%, Spec=93%, PPV=24%, NPV=97%; Auditory: Sens=69%, Spec=78%, PPV=19%, NPV=78%]. Adjacent ECoG-DES accuracy ranged from 82%-91% [Object: Sens=33%, Spec=92%, PPV=18%, NPV=97%; Action: Sens=44%, Spec=93%, PPV=25%, NPV=97%; Auditory: Sens=91%, Spec=81%, PPV=37%, NPV=99%]. When restricted to the peritumoral region, adjacent ECoG-DES accuracy ranged from 94%-97% [Object: Sens=14%, Spec=99%, PPV=25%, NPV=97%; Action: Sens=25%, Spec=99%, PPV=25%, NPV=99%; Auditory: Sens=100%, Spec=94%, PPV=54%, NPV=100%]. For patients with DES hits (N=10), all had at least 1 task activation &lt;1 cm of DES hits, with 7/10 having convergence of activations across at least 2 tasks. CONCLUSIONS Negative ECoG mapping is strongly predictive of non-eloquence confirmed by DES for all naming tasks. Additionally, gamma band activation elicited by auditory naming within the peritumoral region is strongly predictive of eloquence. Findings support task-based ECoG language mapping for prediction of eloquence and identification of targets for DES confirmation.
TMIC-41. RBBP4/P300 COMPLEX CONTROLS GENES MODULATING ANGIOGENESIS AND IMMUNOSUPPRESSION IN GLIOBLASTOMA MICROENVIRONMENT
Mapunda, Josephine, Htee, Hser, Mortazavifarsani, Seyedehsahar, Suzuki, Yuta , Kitange, Gaspar J. , Wang, Li , Verma, Vivek , Hoeppner, Luke H. , Sarkaria, Jann N.

Neuro-Oncology | November 11, 2024 | Volume: 26 | Issue: Supplement_8 | Pages: viii307-viii307

10.1093/neuonc/noae165.1219 Get It

Abstract The RBBP4/p300 complex was recently shown to control genes critical for DNA damage repair and may play a role in glioblastoma (GBM) therapy responsiveness, especially to temozolomide (TMZ). However, the role of this complex in the modulation of the GBM tumor microenvironment (GBM-TME) remains elusive. Because pro-tumorigenic GBM-TME is primarily due to angiogenesis and immune tolerance, we evaluated whether the RBBP4/p300 complex may control these critical processes. To that end, we used shRNA to silence each RBBP4/p300 complex member in GBM43 cells and RNAseq to identify angiogenesis and immune genes regulated by this complex. Our data demonstrated that silencing RBBP4 or p300 suppressed the expression of HIF1α and several other hypoxia response genes, including VEGFA and DDIT4, suggesting that RBBP4/p300 complex may regulate angiogenesis. Consistent with a role in regulating angiogenesis, culture medium conditioned by GBM43 cells expressing the control non-targeting shRNA (shNT) significantly induced angiogenic tube formation by human umbilical vein endothelial cells (HUVEC). In contrast, this effect was blocked by the medium conditioned by the shRBBP4 or shp300 expressing cells. Both shRBBP4 and shp300 expressing cells failed to activate HIF1α accumulation and other signaling in response to hypoxia. Additionally, the control shNT-conditioned medium inhibited IFN-γ production while the medium conditioned by the shRBBP4 or shp300 expressing cells supported IFN-ɣ production from CD8+ T cells. Intriguingly, silencing RBBP4 or p300 also suppressed the expression of CCL2 and PD-L1 (CD274). CCL2 protein is a chemokine that promotes TME infiltration by myeloid-derived suppressor cells (MDSCs), while PD-L1 interacts with PD1 to suppress cytotoxic CD8+ T cell activation. Although this is an ongoing investigation, we conclude that RBBP4/p300 complex mediates the expression of hypoxia response genes, including HIF1α, and immunosuppressive genes, including PD-L1, and this activity may enhance angiogenic and immunosuppressed GBM-TME, making this complex a potential target for GBM therapy.
TMIC-44. ANDROGEN LOSS WEAKENS ANTI-TUMOR IMMUNITY AND ACCELERATES BRAIN TUMOR GROWTH
Lathia, Justin D. , Chung, Yoon-Mi, Sharifi, Nima , Swanson, Kristin R. , Swanson, Kristin R , Lee, Juyeun , Curtin, Lee

Neuro-Oncology | November 11, 2024 | Volume: 26 | Issue: Supplement_8 | Pages: viii308-viii308

10.1093/neuonc/noae165.1222 Get It

Abstract Many cancers, including glioblastoma (GBM), exhibit a male-biased incidence and outcome disparity. The underlying reasons for this sex bias are unclear but likely involve differences in tumor cell state and immune response. This effect is further influenced by sex hormones, including androgens, which have been shown to inhibit anti-tumor T cell immunity in other solid tumors. Using a series of pre-clinical models, we observed that androgens drive anti-tumor immunity in brain tumors, contrasting with their effect in other tumor types. Upon castration, tumor growth was accelerated in GBM and brain tumor models, while the opposite effect was observed when tumors were located outside the brain. This castration effect could be reversed by testosterone administration. Flow cytometry revealed decreased T cell function, indicated by reduced anti-tumor cytokines (IFNγ and TNFα), and increased T cell exhaustion in both tumors and peripheral tissues in castrated mice, suggesting systemic immunosuppression. Indeed, the survival difference was completely abrogated in T cell deficient mice (RAG1 knockout). Mechanistically, increased hypothalamus-pituitary-adrenal (HPA) axis activity in castrated mice was responsible for the observed systemic immunosuppression, particularly in those with brain tumors. Blocking glucocorticoid receptors reversed the accelerated tumor growth in castrated mice, indicating that elevated glucocorticoid signaling mediated the castration effect. This mechanism was brain-specific rather than GBM-specific, as hyperactivation of the HPA axis was also observed with intracranial implantation of non-GBM tumors. Neuroinflammation caused by brain tumors was stronger in castrated mice, and proinflammatory cytokines like IL-1 and TNF induced HPA axis hyperactivation. Together, these findings highlight that brain tumors drive distinct endocrine-mediated mechanisms in the androgen-deprived setting and highlight the importance of organ-specific effects on anti-tumor immunity.
DISP-07. CURRENT NEURO-ONCOLOGY CAPACITY IN SUB-SAHARAN AFRICAN COUNTRIES: A QUESTIONNAIRE-BASED SURVEY
Ghomsi, Nathalie , Kabare, Gloria , Eckel‐Passow, Jeanette E. , Jenkins, Robert B. , Kitange, Gaspar J. , Akinjo, Andrea O , Badmos, Kabir, Idowu, Olufemi, Karekazi, Claire, Darko, Kwadwo, Edrick, Elias, Katasi, Victoria Mwebe , Magambo, Margreth, Magoha, Michael, Ngaiza, Advera , Higgins, Dominique, Okenwa, Minda, Osei‐Tutu, Lawrence, Petershie, Bernard, Yevudza, W Elorm , Anunobi, C C , Tiamiyu, Liadi, Gankpé, Gbètoho Fortuné, Heronima, Kashaigili, Shroeder, Kristin, Teddy, Totimeh, Cheserem, Beverly , Gankpé, Fortuné Gbètoho , Odukoya, Lateef A , Kamson, David , Bankole, Olufemi , Darko, Kwadwo , Ekhator, Chukwuyem , Lachance, Daniel Honore , Brown, Desmond , Huse, Jason T. , LLEWELLYN, HENRY J. , Nyalundja, Arsène Daniel , Fonkem, Ekokobe , Balogun, James , Zerd, Francis

Neuro-Oncology | November 11, 2024 | Volume: 26 | Issue: Supplement_8 | Pages: viii148-viii148

10.1093/neuonc/noae165.0581 Get It

Abstract Brain tumors constitute significant morbidity and mortality in sub-Saharan Africa (SSA). There is no previous large-scale effort focusing on brain tumor genetics in SSA. This project aims to map out the current neuro-oncology capacity in terms of workforce and available services in SSA. This is an ongoing online survey among a cross section of neuro-oncology practitioners spread across SSA countries to capture information on the distribution, number of available neuro-oncology care practitioners, capacity for neuropathology and molecular diagnosis, management of brain tumors, cancer registration, and tumor biobanking. The survey was disseminated by the Society for Neuro-oncology in SSA (SNOSSA). There were 83 respondents representing 15 countries and 52 health institutions: 46 tertiary, 4 secondary, 1 private and 1 other. Here, we present data on the 52 institutions. The prevalence of specialties was 87% neurosurgery, 75% anatomic pathology, 69% medical oncology, 64% neurology, 60% radiation oncology, and 39% neuropathology. For radiologic evaluation, 81% of institutions were reported to have both CT and MRI, 17% CT only, and one institution neither. For molecular testing, 46% have access to IHC or NGS testing, whereas 52% were reported to have neither. A neuro-oncology tumor board was reported at 58% of institutions. A general cancer registry is available in 64% of institutions, 31% have a brain tumor specific registry and 10% have a brain tumor biorepository. This study shows that SSA has substantial potential in neuro-oncology care practice capacity and facilities. Most significant gaps remain in areas such as neuropathology and molecular testing, which makes widespread implementation of the WHO 2021 diagnosis challenging. Understanding the prevalence of CNS tumor subtypes is also difficult due to low number of brain tumor registries and biobanks in SSA. The present findings reveal strategic opportunities, especially in neuropathology, tumor registries, biobanks, and infrastructure for IHC and NGS in SSA.
DISP-05. SUPERVISED MACHINE LEARNING PREDICTION OF THERAPEUTIC CLINICAL TRIAL ENROLLMENT FOR MINORITY PATIENTS AND WOMEN IN NEURO-ONCOLOGY
Mehari, Mulki , Warrier, Gayathri , Dada, Abraham , Kabir, Aymen , Reihl, Sheantel , Jackson, Joshua , González, Ariel, Reason, Ellery H, Dalton, Tara , Negussie, Mikias , Gonzales, Cesar Nava, Chukwueke, Ugonma , Molinaro, Annette M, Porter, Alyx B. , Hervey‐Jumper, Shawn L. , Warrier, Gayathri , Haskell-Mendoza, Aden , Reason, Ellery , Flusché, Ann Marie , Fecci, Peter E.

Neuro-Oncology | November 11, 2024 | Volume: 26 | Issue: Supplement_8 | Pages: viii147-viii147

10.1093/neuonc/noae165.0579 Get It

Abstract BACKGROUND Despite changes in national policy, women and minority patients remain under-accrued in glioma clinical trials. Supervised machine learning may serve as a novel approach to understanding which variables and their complex interplay most influence enrollment for underrepresented patients. We aimed to design and externally validate machine learning models to predict therapeutic clinical trial enrollment for a) all patients, b) women, and c) NIH-designated minority patients with low- and high-grade glioma. METHODS In a 20-year retrospective cohort of 1042 adult patients with low- and high-grade glioma, boosted neural network (BNN) models for the whole, women, and minority cohorts were used to analyze the combined effects of demographic, socioeconomic, and oncologic variables on clinical trial enrollment. These models were validated using an external cohort (n=103). RESULTS In the development cohort (445 [42.7%] women; 151 [14.5%] minorities; median age, 51.5 [interquartile range: 39.4-62.5] years), 350 patients (33.6%) enrolled in a therapeutic clinical trial. The whole cohort BNN (AUC: 0.827, misclassification rate (MR): 0.175), the women cohort BNN (AUC: 0.895, MR: 0.125), and the minority cohort BNN (AUC: 0.983, MR: 0.053) models accurately predicted trial enrollment on external validation. For the whole cohort and women models, several demographic (race, ethnicity, minority status, sex), socioeconomic (insurance, employment status), and oncologic variables (seizure, chemotherapy, KPS, WHO grade, tumor lobe) were equally influential (Main effect (ME): 1.000, Total effect (TE): 1.000) on enrollment. For the minority model, socioeconomic variables including insurance status (ME: 0.089, TE: 0.417) and occupation classification (ME: 0.087, TE: 0.381) drove enrollment. CONCLUSION We designed and externally validated the first machine learning model for predicting therapeutic clinical trial enrollment for patients with diffuse glioma. Model features driving trial enrollment varied for underrepresented patients. These results may help prioritize personalized patient-specific initiatives to address barriers to equitable patient accrual.