Citations

Background/Objectives: The burden of scoliosis care extends beyond treatment costs and includes missed school for patients and lost income for parents. Chronic absenteeism, defined as more than 18 days of missed school, can have a significant impact on a child’s educational progression, but missed school and work due to scoliosis treatment are not well quantified in the literature. This study investigates absenteeism among scoliosis patients and their caregivers. Methods: We conducted a retrospective comparative study of survey results based on surgery timing and surgery type. Patients and caregivers presenting for clinic visits for scoliosis treatment at a single large tertiary care center from 2014 to 2022 were queried. Results: We collected 2772 surveys from 1104 unique patients. Of these, 223 surveys from 132 patients were within one year of surgery: 140 post-fusion surveys, 71 post-nonfusion surveys, and 11 post-halo/multistage surgery surveys. A total of 2280 surveys were from 1022 nonoperatively treated patients. School absenteeism was significantly higher for surgeries during the school year compared to summer in both the fusion and nonfusion groups, though work absenteeism showed no significant differences. Halo/multistage surgery patients had the highest rates of absenteeism. Conclusions: This study highlights the impacts of scoliosis surgery timing and type on absenteeism among patients and their caregivers. Surgery during summer breaks reduces school absenteeism and academic disruption. Halo/multistage surgery patients face the greatest risk of chronic absenteeism from school, indicating a need for targeted interventions. Optimized surgical timing and planning can help families navigate the educational and financial challenges of scoliosis treatment.

Abstract Background Etrasimod is an oral, once daily (QD), selective sphingosine 1-phosphate1,4,5 receptor modulator for the treatment of moderately to severely active ulcerative colitis (UC). We assessed the benefit of etrasimod monotherapy and the impact of concomitant corticosteroids (CS) and/or 5-aminosalicylates (5-ASA) therapy. Methods In ELEVATE UC 52 and ELEVATE UC 12, patients with moderately to severely active UC were randomized 2:1 to etrasimod 2 mg QD or placebo for 52 and 12 weeks, respectively. Oral CS or 5-ASA were allowed at baseline. Patients in the monotherapy subgroup received etrasimod or placebo without concomitant CS and/or 5-ASA at baseline. Predefined primary (clinical remission) and key secondary efficacy endpoints aligned with those from both trials and were assessed at Week 12 and Week 52. Safety was assessed up to Week 52. Results Clinical remission rates at Weeks 12 and 52 were significantly higher for etrasimod compared with placebo in patients receiving monotherapy (Week 12: 26.2% vs 4.8%; Week 52: 35.7% vs 4.0%). Differences vs placebo were statistically significant for all predefined endpoints at both time points in patients receiving monotherapy or etrasimod with concomitant 5-ASA only (all P < .05); numerical differences, due to small sample sizes, vs placebo were observed for all endpoints in the CS only and CS + 5-ASA subgroups. Safety was consistent with the overall population. Conclusions Etrasimod monotherapy showed consistent efficacy and safety vs placebo; no apparent benefit was observed with concomitant CS and/or 5-ASA in patients receiving etrasimod. Clinical trial registration NCT03945188; NCT03996369.

Abstract Chemotherapy regimens for triple-negative breast cancer (TNBC) combine agents without knowing which agents drive response. Consequently, predictors derived from multi-agent regimens cannot be assumed to generalize to individual drugs or other regimens, motivating development of treatment-matched predictors. Here, we used TNBC patient-derived xenografts (PDXs) treated with carboplatin, docetaxel, or the combination to deconvolute drug-specific responses and identify associated molecular features. Combination treatment rarely improved upon the best single agent, with enhanced responses in only 13% of PDXs and antagonism in a comparable fraction. Proteogenomic analyses identified high cytokeratin-5 (KRT5) as a general marker of chemotherapy responsiveness and KRT5 immunohistochemistry discriminated responsive PDXs (AUROC, 0.83). To train treatment-specific predictors, we integrated these data with independent PDX and clinical cohorts with responses assessed after anthracycline-free platinum, taxane, or platinum-taxane therapy, ensuring response corresponded to the modeled treatment. Four feature selection strategies yielded largely nonoverlapping biomarker panels converging on treatment-relevant pathways. On independent test data, RNA-based predictors of complete response (CR) to platinum-based (carboplatin or cisplatin) and taxane-based (docetaxel or paclitaxel) chemotherapy achieved AUROCs of 0.80 and 0.86, respectively. For platinum-taxane regimens (carboplatin plus docetaxel or paclitaxel), proteomic-guided feature selection generated a 10-biomarker, protein- informed RNA predictor of pathologic complete response (pCR) that outperformed RNA-only feature selection and achieved an AUROC of 0.85 in an independent clinical cohort, while retaining practicality as an RNA-based assay. Treatment-matched integration of multi-omic PDX and clinical datasets provides a framework for chemotherapy-specific predictors with clinically relevant performance, supporting biomarker-guided precision selection and treatment optimization for patients with TNBC. Statement of significance Integration of multi-omic data from patient-derived xenografts with treatment-matched clinical cohorts yielded three retrospectively validated predictors of platinum, taxane, and platinum+taxane response, enabling biomarker-guided chemotherapy selection for patients with triple-negative breast cancer.

Background: Hypomethylating agents (HMA) with venetoclax (VEN) have shown encouraging clinical efficacy in single arm clinical trials for patients with myelodysplastic syndrome (MDS) (Garcia JS et al. ASH 2023, Zeidan AM et al. Am J Hematol. 2023). Many centers have started utilizing HMA-VEN in the clinical management of MDS due to unmet need, pending results of the ongoing phase 3 randomized clinical trial (VERONA) using this combination. However, real world studies with large sample size investigating the use of these agents in MDS, practice patterns and clinical outcomes are lacking. Methods: This is a multicenter retrospective study of 13 US academic medical centers. We included contemporary cohorts of adults (age≥18 years) with MDS who were treated with upfront combination of HMA-VEN, upfront HMA monotherapy, or VEN added after inadequate response or progression on HMA (post-HMA failure VEN). Outcomes analyzed includes clinical response, adverse events (AE) of interest, dose administration and survival. Descriptive statistics were used for baseline characteristics. Overall survival and event free survival (EFS: progression, leukemic transformation, death as events) analysis was conducted using Kaplan-Meier method. Determinants of outcomes were analyzed using multivariable regression models. All analyses were conducted at a significance level of p<0.05. Results: Among 454 patients included, 258 patients received VEN in combination with HMA [upfront HMA-VEN (n=175), post-HMA failure VEN (n=83)] and 196 patients received HMA monotherapy. Median age was 69 (59-77) years and majority of patients had MDS with excess blasts (75%), high risk (31.9%) or very-high (41.8%) risk disease by IPSS-R, 23.7% had therapy related disease, 33% had deletion17p or TP53 mutation and 40.9% underwent allogeneic stem cell transplantation. VEN was predominantly started in outpatient setting (78.6%) with tumor lysis syndrome (TLS) prophylaxis and VEN doses ranged from 70-400mg, adjusted for concomitant antifungal drugs. Incidence of TLS was minimal (No TLS- 92.9%, lab-only TLS 6.2%, 1 pt with clinical TLS). Neutropenic fever was the main AE noted [upfront VEN-HMA (34.2%), HMA monotherapy (22.5%), post-HMA VEN (44.5%)]. In the upfront setting, response rate was significantly higher with HMA-VEN than HMA monotherapy (CR: 33% vs 12%; marrow CR: 40% vs 27%, p<.001). VEN given in the post HMA failure setting also resulted in encouraging response rates (CR 10%, marrow CR 32%). After adjusting for covariates in multivariable analysis, patients treated with HMA-VEN in the upfront setting had significantly improved event free survival as compared to HMA monotherapy (HR 0.59, HR 0.44-0.78, p<0.01), but overall survival did not reach statistical significance (overall survival HR 0.77, 95%CI 0.57-1.04, p=0.08). Conclusions: In this large multicenter retrospective analysis from US academic medical centers, we found that VEN in combination with HMA resulted in encouraging clinical outcomes and was effectively administered in the outpatient setting with minimal TLS. Infection risk management and supportive measures would be important to improve the ability to use this treatment widely, pending results of the ongoing phase 3 randomized clinical trial. Updated results with additional variables will be available at the main meeting.

Introduction: Pembrolizumab Gemcitabine Vinorelbine and Liposomal Doxorubicin (P-GVD) has become a commonly employed regimen for the treatment of relapsed or refractory classical Hodgkin lymphoma (CHL), often preceding autologous stem cell transplant in patients with good response. The utilization of P-GVD is based on a 38-evaluable patient prospective trial (Moskowitz et al. JCO 2021). There remains minimal data regarding the efficacy of this regimen in a larger, real-world cohort. Methods:Patients with CHL who received P-GVD at 9 United States centers were retrospectively evaluated to estimate efficacy and safety, with a focus on the second line use of this regimen. Demographic and clinical data were extracted from medical records. Responses reflected Lugano criteria per local investigator assessment. Study objectives were overall response rates (ORR), complete response rates (CRR), progression free survival (PFS), overall survival (OS), and safety. PFS and OS were estimated by Kaplan-Meier. Results: Patients and Treatment: We identified 65 CHL patients who received P-GVD between July 2019 and June 2024, including 43 who were treated in the second line. Enrolled patients included a median age of 31 years (range 17-69 years), 36.9% (24) females, 75.4% (49) nodular sclerosing subtype, and 60% (39) stage III-IV at diagnosis. Patients included 64.6% (42) White and non-Hispanic, 15.4% (10) Hispanic or White and Hispanic, 10.8% (7) Black, 3.1% (2) Asian/Pacific Islander, 3.1% (2) other, and 3.1% (2) unknown. The median number of prior regimens was 1 (range 0-12); these included 3.1% (2) who had prior checkpoint inhibitor (CPI), 50.8% (33) who had prior brentuximab vedotin (BV), and 3.1% (2) who had prior transplant. Patients with primary refractory disease [no initial complete response (CR)] comprised 58.5% (38), and 35.4% (23) had relapse within 1 year of completing initial therapy. The median number of cycles received was 3 (range 1-5). Treatment in a community practice setting was noted for 21.5% (14) patients. Efficacy: At a median follow up of 17.7 months, ORR and CRR after P-GVD were 95% (62/65) and 74% (48/65), respectively. This increased to 95% ORR and 81% CRR when limited to 43 patients who were treated 2nd line. Responses by line included: 1st [n=1; 100% ORR and CRR]; 3rd [n=15; 100% ORR, 73.3% CRR], 4th [n=3; 100% ORR, 33.3% CRR], 5th [n=2; 100% ORR, 0% CRR], and 13th [n=1; SD]. CRR in BV- and CPI-exposed patients were 60.6% and 50%, respectively. Ninety one percent (39) of 2nd line treated patients proceeded to autologous transplant, as well as all 3 patients > age 60. Among 41 response-evaluable second-line patients, CR was achieved in 94% (30/32) who received 2 or 3 cycles of P-GVD, and 56% (5/9) who received 4 cycles of P-GVD. For the entire cohort at 12 and 24 months after starting P-GVD, PFS was 95% (95% CI: 89-100%), 91% (95% CI: 83-100%) and OS was 98% (95% CI: 94-100%), 94% (95% CI: 86-100%), respectively. Ninety five percent (41) of 2nd line transplanted patients remain alive and in remission at a median of 18.5 months (range 3.5-38.7 months). In the primary refractory subset, PFS and OS at 24 months were 91% and 97%, respectively. For the cohort with 2 or more prior lines of therapy, PFS and OS at 24 months were 91% and 94%, respectively. Safety: Immune-related adverse events (IRAEs) were reported in 20% (13) of patients, of which grade 3 IRAEs per NCCN criteria version 1.2024 comprised 38.5%; all others were grades 1-2. Non-IRAE grade 3-4 toxicities per CTCAE version 5.0 were reported in 22% (14) patients. Of 29 patients evaluable for treatment-related interruptions, 7% (2) had therapy discontinued, and 34% (10) had holds, dose reductions, and/or delays. No deaths were attributed to P-GVD treatment. Conclusions:This retrospective study confirms the utility of P-GVD in treating relapsed/refractory CHL in a real-world population. Though fewer CRs and higher rates of grade 3 adverse events were observed, the vast majority of patients were able to proceed to transplant, and outcomes to date are highly encouraging.

Background: Patients with immunocompromising conditions, including those affected by hematologic malignancies, have a disproportionately high burden of morbidity and mortality related to COVID-19 compared to individuals without such conditions.Clinical practice guidelines (CPGs) recommend the use of remdesivir, a broad-spectrum antiviral, for treatment of mild to severeCOVID-19 in immunocompetent patients not requiring invasive mechanical ventilation. While the CPGs issued by the World Health Organization (WHO, 2023), National Institutes of Health (NIH, 2023) and the Infectious Diseases Society of America (IDSA, 2022) also recommended the use of remdesivir in patients with immunocompromising conditions at high risk for severe disease, there was limited evidence available at the time the recommendations were communicated, more than two years after the start of the pandemic. The European Conference on Infections in Leukemia (ECIL, 2022) guidelines include remdesivir among the treatment options for mild to moderate COVID-19 patients with hematologic malignancies. The lack of evidence for treatment efficacy and safety in patients with immunocompromising conditions, a population underrepresented or excluded from clinical trials, was mentioned in CPGs as a knowledge gap and as need for further research. In this research, we summarize the evidence for remdesivir efficacy and safety for treatment of COVID-19 in hospitalized patients with hematologic malignancies accumulated since the start of the pandemic. Methods: We systematically searched MEDLINE, Embase and Cochrane Library databases from January 2019 through December 2023 for interventional and observational studies examining remdesivir efficacy and safety. Case reports and case studies were excluded. A dual-reviewer approach was used for screening and data extraction. Results: Of the 7,654 references retrieved through the implementation of the extensive search strategy 59 (0.8%) reporting on patients with hematologic malignancies, unspecified cancers, or immunodeficiencies were identified and reviewed in full text. Only eight unique studies (8 of 59) were conducted in patients with hematologic malignancies, of which two reported remdesivir use in a minority of participants (n<5) and were excluded from further analyses. The remaining six studies, of which four were peer-reviewed original articles, one was a letter to editor and the last was a conference abstract, used a retrospective cohort design and reported efficacy outcomes for a combined total of 1,579 individuals across the studies. Three of the six studies were conducted during the pre-Omicron variant era (November 2021) while the remaining three started data collection in December 2021. There were four studies reporting number of deaths or the mortality rate, while a fifth study based on medical chart reviews of 313 patients in Israel found a significantly reduced risk of mortality among remdesivir recipients compared to patients not receiving remdesivir (OR: 0.297; 95% CI: 0.105, 0.834). In addition, a study including 466 patients from the Spanish Hematopoietic Stem Cell Transplantation and Cell Therapy Registry reported mortality among remdesivir treated group related to baseline disease progression, use of corticosteroids for COVID-19 therapy and the presence of coinfections while B-cell malignancy as underlying disease, severe COVID-19, late antiviral initiation (≥5 days after first positive PCR) and longer treatment duration (≥5 days) were factors significantly associated with prolonged viral shedding. The same Spanish study reported safety outcomes indicating that adverse events of grade 3 or above were rare, occurring in 0.5% of remdesivir treated patients. Conclusion: Despite the call for research to fill the knowledge gap signaled by the CPGs, our comprehensive systematic literature review identified only a few publications conducted since the start of the pandemic in patients with hematological malignancies. In the current endemic era, these patients are among the most at risk for severe outcomes and COVID-19 related hospitalizations. While the limited evidence suggests that remdesivir use can reduce mortality in patients with hematologic malignancies, additional research will be instrumental to inform development and updating of evidence-based recommendations to support and guide clinical management of oncology patients.

Background: Chemoimmunotherapy using rituximab, cyclophosphamide, doxorubicin hydrochloride (hydroxydaunomycin), vincristine sulfate (Oncovin), and prednisone (R-CHOP) has been the standard of care treatment of DLBCL for over 20 years. Despite its widespread usage, there is no accepted standard for the dose of prednisone in this setting which varies from fixed-dose (100 mg daily for 5 days) to different levels of BSA-adjusted dosage (ranging from 40-100 mg/m2 daily for 5 days). BSA-adjusted dosage results in high doses of prednisone administered to patients with increased body surface area which may lead to significant adverse events. We performed a systematic review and meta-analysis to determine if fixed-dose prednisone during R-CHOP therapy results in equivalent outcomes compared to BSA-adjusted dosing. Methods: A comprehensive search of several databases from each database's inception to April 29th, 2024, English language, was conducted. The databases included Ovid MEDLINE and Epub Ahead of Print, In-Process & Other Non-Indexed Citations, and Daily, Ovid EMBASE, Ovid Cochrane Central Register of Controlled Trials, Ovid Cochrane Database of Systematic Reviews, and Scopus. The search strategy was designed and conducted by an experienced librarian with input from the study's principal investigator. Controlled vocabulary supplemented with keywords was used to search for prospective clinical studies of R-CHOP for adult patients with untreated DLBCL. Search results were reviewed independently by 2 members of the study team for final inclusion. Discrepancies were adjudicated by a third member and reviewed by the senior author. Prednisone dosage and clinical outcomes were abstracted from the available public data. Meta-analysis was performed using the metafor package in R version 4.2.2 by applying a mixed-effects model to combine results from the multiple studies. The analysis was first conducted overall to determine the general effect, and then stratified by prednisone dose (fixed- vs. BSA-adjusted) to explore dose-dependent variations in outcomes. Results: Our search resulted in 2287 entries which were individually reviewed by the study team. A total of 30 studies with a combined sample size of 3573 treated patients fulfilled the inclusion criteria and were included in the final analysis set. Nineteen (63%) studies with a combined sample size of 1930 patients (median 155, range 12-399) used fixed-dose prednisone. Eleven (37%) studies with a combined sample size of 1643 patients (median 70, range 9-439) used BSA-adjusted dosing. Overall survival (OS) at 2 years data were available for 11 (37%) of the studies. Progression free survival (PFS) at 2 years data were available for 8 studies (27%). Overall response rate (ORR) and complete response rate (CRR) data were available for 16 (54%) and 14 (47%) of the included studies, respectively. OS at 2 years for all studies was 84% (SD 78%-91%) and did not differ between fixed-dose (88%, SD 79%-97%) and BSA-adjusted dose (82%, 73%-91%). PFS at 2 years for all studies was 77% (SD 68%-85%) and did not differ between fixed-dose (80%, SD 68%-93%) and BSA-adjusted dose (74%, SD 62%-86%). ORR for all studies was 86% (SD 79%-92%) and did not differ between fixed-dose (86%, SD 76%-96%) and BSA-adjusted dosage (84%, SD 80%-88%). CRR for all studies was 70% (SD 61%-80%) and did not differ between fixed-dose (67%, SD 54%-81%) and BSA-adjusted dose (77%, SD 64%-89%). Heterogeneity tests performed according to available clinical outcomes yielded results between 0% and 76%. Conclusion: The result of our systematic review and meta-analysis combining 30 prospective studies and a total of 3573 patients with newly diagnosed DLBCL treated with frontline R-CHOP found no difference in clinical outcomes between patients treated with fixed-dose and BSA-adjusted dose prednisone. Our findings provide scientific evidence for the widespread practice of capping prednisone at the maximum dose of 100 mg daily for 5 days, potentially avoiding unnecessary adverse effects from BSA-adjusted dosing.

ABSTRACT A total of 1,925 Corynebacterium isolates were tested for antimicrobial susceptibility at the Mayo Clinic Microbiology laboratory (Rochester, Minnesota) from January 2012 to March 2023, with C. striatum (35.6%) and C. amycolatum (24.4%) identified as the predominant species. Species known to potentially carry diphtheria toxin were excluded. Common sources of isolation included skin and soft tissue (56.8%), bone and/or native joint synovial fluid (14.2%), urine (13.1%), sputum (6.1%), and blood (5.9%). For penicillin, susceptibility decreased from 47.5% (58 of 122) in 2012 to 20.6% (14 of 68) in 2023. Isolates also showed a decrease in susceptibility to erythromycin from 22.4% (26 of 116) in 2012 to 13.2% (9 of 68) in 2023. Susceptibility to trimethoprim-sulfamethoxazole averaged around 50% throughout the period. Notably, linezolid and vancomycin were universally effective in vitro against all species. The highest susceptibility rates among tested oral agents were to linezolid and doxycycline for non- C . striatum species. Daptomycin minimal inhibitory concentrations (MICs) of >256 µg/mL were observed for one C. amycolatum isolate, one C. tuberculostearicum isolate, and for seven C. striatum isolates, all from patients with prior daptomycin exposure. Daptomycin MICs of 2 µg/mL (nonsusceptible) were observed in one C. striatum isolate recovered from a daptomycin-naïve patient and in six C. jeikeium isolates, from both daptomycin-exposed and non-exposed patients. Significant variation in susceptibility profiles across different Corynebacterium species underscores the importance of performing antimicrobial susceptibility testing to guide effective treatment. Moreover, multidrug resistance observed in C. striatum poses substantial therapeutic challenges especially in patients requiring prolonged or chronic antibiotic suppression.

Background: As machine learning becomes increasingly utilized in orthopaedic clinical research, the application of machine learning methodology to cohort data from the Multicenter ACL Revision Study (MARS) presents a valuable opportunity to translate data into patient-specific insights. Purpose: To apply novel machine learning methodology to MARS cohort data to determine a predictive model of revision anterior cruciate ligament reconstruction (rACLR) graft failure and features most predictive of failure. Study Design: Cohort study; Level of evidence, 3. Methods: The authors prospectively recruited patients undergoing rACLR from the MARS cohort and obtained preoperative radiographs, surgeon-reported intraoperative findings, and 2- and 6-year follow-up data on patient-reported outcomes, additional surgeries, and graft failure. Machine learning models including logistic regression (LR), XGBoost, gradient boosting (GB), random forest (RF), and a validated ensemble algorithm (AutoPrognosis) were built to predict graft failure by 6 years postoperatively. Validated performance metrics and feature importance measures were used to evaluate model performance. Results: The cohort included 960 patients who completed 6-year follow-up, with 5.7% (n = 55) experiencing graft failure. AutoPrognosis demonstrated the highest discriminative power (model area under the receiver operating characteristic curve: AutoPrognosis, 0.703; RF, 0.618; GB, 0.660; XGBoost, 0.680; LR, 0.592), with well-calibrated scores (model Brier score: AutoPrognosis, 0.053; RF, 0.054; GB, 0.057; XGBoost, 0.058; LR, 0.111). The most important features for AutoPrognosis model performance were prior compromised femoral and tibial tunnels (placement and size) and allograft graft type used in current rACLR. Conclusion: The present study demonstrated the ability of the novel AutoPrognosis machine learning model to best predict the risk of graft failure in patients undergoing rACLR at 6 years postoperatively with moderate predictive ability. Femoral and tibial tunnel size and position in prior ACLR and allograft use in current rACLR were all risk factors for rACLR failure in the context of the AutoPrognosis model. This study describes a unique model that can be externally validated with larger data sets and contribute toward the creation of a robust rACLR bedside risk calculator in future studies. Registration: NCT00625885 (ClinicalTrials.gov identifier).

Abstract Clinical management of IDH wildtype glioblastoma (GBM) and tumefactive multiple sclerosis (tMS) is drastically different. GBM requires maximal safe resection followed by chemoradiation, while tMS outcome is worsened by surgery and radiotherapy. Noninvasive methods are needed to help with accurate diagnosis of tumor and non-tumor etiologies. To develop an MRI-based classification model, tMS subjects diagnosed prior to January 1, 2020, were matched to tMS by age at diagnosis, sex, index MRI date, and 2D/3D acquisition. Inclusion criteria included one cm minimal lesion size and pre-operative post-contrast T1 and T2 images available for analysis. A 3D-DenseNet121 was used to develop a classification model using prespecified parameters: 650 epochs, batch size 16, learning rate 10-3, cross-entropy loss, and AdamW optimizer. The stopping rule was defined as three sequential differences in epoch cross-entropy loss <0.02. Models were developed using both T1gd and T2, as well as from only T1gd and only T2. Training included 220 subjects (110 GBM, 110 tMS). A 2-stage validation design was used, which included both retrospective and prospective cohorts. Stage 1 consisted of 272 retrospective GBM (diagnosed prior to January 1, 2020). Stage 2 consisted of 69 and 34 prospective (diagnosed after January 1, 2020) GBM and tMS, respectively. External validation on the 272 retrospective GBM demonstrated accuracy of 91%, 84%, and 78% for T1gd+T2, T1gd only, and T2 only, respectively. External validation on the 69 prospective GBM demonstrated an accuracy of 87%, 64%, and 67% for T1gd+T2, T1gd only, and T2 only, respectively. The 34 prospective tMS demonstrated accuracy of 76%, 76%, and 82% for T1gd+T2, T1gd only, and T2 only, respectively. This shows the feasibility of deep learning to aid in differential diagnosis of brain lesions. Future work entails the integration of germline variants into the classification model, including variants associated with the risk of glioma or MS.