Citations

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.

Abstract BACKGROUND Central nervous system (CNS) tumors are frequently characterized by physical disabilities, and treatment is often associated with side effects, as well as financial toxicity and loss of income owing to disease-related neurological deficits. Treatment at centers with specialized neuro-oncology care is associated with an overall survival benefit. However, access to such centers can be limited for many patients. Telehealth services represent an option for improving access to specialized care. During the COVID-19 pandemic public health emergency (PHE), regulatory and reimbursement changes provided patients improved access to neuro-oncology by telehealth. METHODS We retrospectively analyzed our institutional utilization of telehealth visits in the neuro-oncology vs solid tumor oncology practice after the COVID-19 pandemic. RESULTS Between July 2020 and April 2021, telehealth represented 24.1% of all neuro-oncology visits compared to 13.3% for all solid tumor groups. Between May 2021 and April 2023, telehealth visits remained frequent in neuro-oncology compared to solid tumor groups (34.6% vs 15.2%). Utilization rates declined across the practice in the year following expiration of the COVID-19 PHE in May 2023, though remained high for neuro-oncology at 34.1% vs 15.2% for solid tumor groups. Overall, telehealth visit utilization for neuro-oncology has remained more than double that of the oncology practice as a whole. CONCLUSIONS The striking difference between telehealth visit utilization in neuro-oncology compared with general medical oncology indicates that patients with CNS tumors, and those that provide care for these patients, have come to depend on this mode of care delivery. Even after expiration of the COVID-19 PHE, telehealth use remains high in neuro-oncology at our institution. Prospective evaluation to determine the safety of and clinical outcomes associated with telehealth visits for individuals with CNS tumors are critically needed. Such data may promote regulatory and reimbursement reform enabling broader adoption, service sustainability, and improved access to specialized care.

Abstract Glioblastoma (GBM) presents as a highly aggressive and malignant brain tumor with limited treatment options. Despite the availability of existing therapies, the invasive characteristics of GBM frequently result in tumor recurrence and poor prognosis. We previously developed a B-cell-based therapy (BVax) that has shown promising results in its ability to induce therapeutic responses in preclinical models of GBM. Our research revealed potency of BVax can be attributed to its robust antigen-presenting capability, cognate antigen specificity with T cells, and ability to generate tumor-reactive antibodies. The present study aims to characterize the unique antigenic reactivity of BVax-derived antibodies by evaluating their immunological effects and therapeutic potential in both murine models and GBM patient-specific samples. Leveraging CD45.1 and CD45.2 congenic mouse models, we first revealed that BVax preferentially migrated to glioma-bearing brains upon intravenous injection, resulting in a CD38+CD20-CD19+ plasmablast phenotype. To further characterize the reactivity of BVax-derived immunoglobulins (Ig), we utilized proteomic analysis and identified preferential targets of Gelsolin, Fibronectin, Versican, Fibrinogen, and collagen type IV alpha, commonly associated with cell motility and the extracellular matrix. Microdialysis data confirmed the increased presence of many of these BVax-derived Igs-recognized antigens in tumor regions compared to normal brain regions in GBM patients. Utilizing purified BVax-derived antibodies from patient specimen, in vitro cell motility assays demonstrated a significant prevention of the invasion and migration of cell lines from patient derived xenograft (PDX). In this study, we concluded that BVax elicits antitumor activity through targeted migration to tumor-bearing regions, differentiation into plasmablasts, and robust secretion of specific Igs that retain the ability to inhibit functionalities associated with cell invasion and migration. Here, we present the first in-depth study that characterizes GBM patients’ antibody reactivity, specifically a subset of inflammatory B cells (BVax) with therapeutic effects that offer an indication for a new direction of immunotherapies.

Abstract Targeted gene expression profiling improves risk stratification for meningiomas, but the utility of this approach for low grade meningiomas is incompletely understood. To address this, 466 meningiomas that were initially used to validate a 34-gene expression biomarker were combined with 270 previously unpublished samples for an analysis of biomarker performance in newly diagnosed (n=691) or recurrent (n=45) WHO grade 1 meningiomas treated with gross total (GTR) or subtotal resection (STR), and newly diagnosed WHO grade 2 meningiomas treated with GTR. Prediction of local freedom from recurrence (LFFR) or overall survival (OS) was measured using Cox proportional hazards models and the Kaplan-Meier method. The cohort included 736 patients, 69.4% female, with a median age at diagnosis of 58 years. There were 635 WHO grade 1 meningiomas, 498 with GTR and 133 with STR, and 101 WHO grade 2 meningiomas with GTR. The median follow-up was 4.6 years, the local recurrence rate was 12.0% and the rate of death was 8.4%. The biomarker classified 51.5% of meningiomas as intermediate risk and 9.6% as high risk. Combining the biomarker with extent of resection identified 19.7% as unfavorable (intermediate molecular risk with STR or high molecular risk), including 7.4% of newly diagnosed WHO grade 1 meningiomas with GTR. The risk score was prognostic for LFFR overall (hazard ratio per 0.1 increase in risk score 1.89, 95% confidence interval 1.58-2.25) and across WHO grades, extents of resection, and newly diagnosed or recurrent settings. Gene expression risk groups were prognostic for LFFR, with improved outcomes among low molecular risk compared to intermediate molecular risk (Log-rank, p=0.0002) and high molecular risk meningiomas (Log-rank, p<0.0001). These data suggest that a targeted gene expression biomarker can identify low grade meningiomas that are more likely to recur after surgery, possibly changing management for approximately one-fifth of cases.

AbstractPurposeTo systematically review the literature regarding machine learning in leg length discrepancy (LLD) and to provide insight into the most relevant manuscripts on this topic in order to highlight the importance and future clinical implications of machine learning in the diagnosis and treatment of LLD.MethodsA systematic electronic search was conducted using PubMed, OVID/Medline and Cochrane libraries in accordance with Preferred Reporting Items for Systematic Review and Meta‐Analysis guidelines. Two observers independently screened the abstracts and titles of potential articles.ResultsA total of six studies were identified in the search. All measurements were calculated using standardized anterior‐posterior long‐leg radiographs. Five (83.3%) of the studies used measurements of the femoral length, tibial length and leg length to assess LLD, whereas one (16.6%) study used the iliac crest height difference to quantify LLD. The deep learning models showed excellent reliability in predicting all length measurements with intraclass correlation coefficients ranging from 0.98 to 1.0 and mean absolute error (MAE) values ranging from 0.11 to 0.45 cm. Three studies reported measurements of LLD, and the convolutional neural network model showed the lowest MAE of 0.13 cm in predicting LLD.ConclusionsMachine learning models are effective and efficient in determining LLD. Implementation of these models may reduce cost, improve efficiency and lead to better overall patient outcomes.Clinical RelevanceThis review highlights the potential of deep learning (DL) algorithms for accurate and reliable measurement of lower limb length and leg length discrepancy (LLD) on long‐leg radiographs. The reported mean absolute error and intraclass correlation coefficient values indicate that the performance of the DL models was comparable to that of radiologists, suggesting that DL‐based assessments could potentially be used to automate the measurement of lower limb length and LLD in clinical practice.Level of EvidenceLevel IV.

Background and Aims: Sarcopenia is highly prevalent in patients with liver cirrhosis and is associated with adverse clinical outcomes, including HE. Androgen receptor agonists, androgen receptor agonists, can address these conditions through multimodal mechanisms of action; however, their safety and efficacy in patients with cirrhosis have not been well established. Approach and Results: In this multicenter, double-blind, phase 2 trial, men with sarcopenia and cirrhosis awaiting liver transplant were randomized 1:1 to receive either oral Androgen Receptor Agonist LPCN 1148 or placebo for 24 weeks (NCT04874350). The primary end point was the change from baseline to 24 weeks in skeletal muscle index measured by a CT scan of the L3 region, analyzed with a prespecified modified intent-to-treat population. The secondary end point was the number of overt HE events. Twenty-nine participants (mean age=59 y, MELD=17) received at least 1 dose of LPCN 1148 (n=15) or placebo (n=14). Baseline characteristics were similar between groups. Primary end point analysis demonstrated an increase in L3-skeletal muscle index measured by a CT scan of the L3 region in the LPCN 1148 group (n=15) compared to placebo (n=10), with a mean group difference of 4.4 cm2/m2 (95% CI: 1.3–7.4 cm2/m2, p=0.007). Participants in LPCN 1148 experienced fewer episodes of overt HE (Common Terminology Criteria for Adverse Events grade ≥2; p=0.02) than placebo. The number and severity of treatment-emergent adverse events were similar between arms. Conclusions: LPCN 1148 treatment improved sarcopenia and reduced the number of overt HE episodes in men with cirrhosis and sarcopenia awaiting liver transplant. These findings support additional research on the efficacy of LPCN 1148 in treating sarcopenia and preventing HE recurrence.

Abstract Background Multianalyte assays with algorithmic analysis (MAAAs), such as the Prostate Health Index (phi), are increasingly utilized for generating disease risk scores. Currently, imprecision and bias in phi are not directly monitored by quality control (QC) assessment of the index but rather by QC assessment of individual components. This may not be adequately controlling for imprecision and bias in the calculated multicomponent phi value itself. Methods Inter- and intra-assay phi precision was compared to precision of the individual component assays. QC measurements from total prostate-specific antigen (PSA), free PSA, and p2PSA were used to calculate a single calculated phi QC metric (PHIc). The frequency of QC failure of PHIc, relative to individual components QC by Westgard rules (13S and 22S), was determined. The effects of varying analyte component assay bias on the resulting PHIc metric were also examined. Results Average measured phi imprecision (6.7% CV) was higher than individual phi analyte component imprecision (3.9–4.5% CV) across 2 Beckman Coulter Unicel DxI 800 instruments. A retrospective examination of PHIc QC over 84 quality control determinations was concurrently carried out for both PHIc and component assay failure patterns, which were dependent on SDs utilized for Westgard evaluation. Finally, reinforcing nonlinear changes in PHIc were observed in select cases of introduced simulated bias of individual component measurements. Conclusions An additional calculated phi QC measure can be introduced to monitor MAAA precision/bias, and in principle calculated index controls may represent a complementary supplemental QC method that could be applied to other MAAA indices.

Background Acute ischemic stroke arising from medium vessel occlusions (MeVO) poses substantial challenges in treatment and management. This study aims to elucidate the outcomes and factors contributing to achieving excellent recanalization (modified Thrombolysis in Cerebral Infarction [mTICI] 2c–3) versus successful recanalization (mTICI 2b) in patients with MeVO stroke undergoing mechanical thrombectomy (MT). Methods We conducted a multinational study analyzing data from the MAD‐MT (Multicenter Analysis of Distal Medium Vessel Occlusions: Effect of Mechanical Thrombectomy) registry, encompassing 37 centers across North America, Asia, and Europe, collected between September 2017 and July 2023. The study included acute ischemic stroke patients with MeVO treated with MT, with or without intravenous thrombolysis, who achieved mTICI 2b–3 post‐MT. Results Among 1463 patients with successful recanalization (mTICI 2b–3), 523 achieved mTICI 2b recanalization, and 940 achieved mTICI 2c–3. Distal occlusions exhibited higher odds of excellent recanalization compared with proximal MeVO vessel occlusions (odds ratio, 1.58; 95% CI, 1.17–2.15; P = 0.003). Cardioembolic stroke pathogenesis was associated with a higher likelihood of excellent recanalization (1.67; 95% CI, 1.07–2.59; P = 0.018). Patients achieving mTICI 2c–3 recanalization demonstrated lower initial National Institutes of Health Stroke Scale scores, significant improvements in postprocedural National Institutes of Health Stroke Scale shift, and a higher percentage of favorable 90‐day outcomes compared with those with mTICI 2b. However, no significant difference in 90‐day mortality rates was observed. Conclusion This study underscores that among patients with MeVO stroke with successful recanalization (mTICI 2b–3) there is higher likelihood of achieving excellent recanalization (mTICI 2c–3) in distal occlusions and cardioembolic pathogenesis. mTICI 2c–3 scores post‐MT correlate with improved clinical outcomes compared with mTICI 2b, affirming the superiority of excellent recanalization over successful recanalization in patients with MeVO stroke. Further prospective studies and randomized controlled trials are warranted for validation.