Citations

Background: Reports have concluded that platelet-rich plasma (PRP) is an effective and safe biological approach in the treatment of knee osteoarthritis (OA). However, no consensus has been established regarding the number of injections required to observe a therapeutic effect. Purpose: To compare the clinical effectiveness reported in randomized controlled trials (RCTs) of single versus multiple PRP injections in the treatment of knee OA. Study Design: Systematic review; Level of evidence, 1. Methods: A comprehensive search was conducted for RCTs published between 1970 and 2019 that compared the effect of single versus multiple PRP injections on pain and functionality in patients with knee OA. Searched databases included MEDLINE, Scopus, Embase, Web of Science, and the Cochrane Central Register of Controlled Trials. A data extraction form was designed to obtain bibliographic information of the study as well as patient, intervention, comparison, and outcomes of interest data. A random-effects model was used to pool quantitative data from the primary outcomes. Results: We included 5 clinical trials with a low-moderate risk of bias that reported data for 301 patients. Meta-analysis showed that, at 6 months after the intervention, single and multiple (double or triple) injections had similar pain improvement, with no significant differences (standardized mean difference [SMD], 0.61 [95% CI, −1.09 to 2.31]; I 2 = 97%; P = .48). A significant improvement in knee functionality was observed in favor of multiple injections (SMD, 2.29 [95% CI, 0.45-4.12]; I 2 = 97%; P = .01). Subanalysis showed that the significant improvement was only evident for the results of single versus triple injections (SMD, 3.12 [95% CI, 0.64-5.60]; I 2 = 97%; P = .01). Conclusion: According to our results, a single injection was as effective as multiple PRP injections in pain improvement; however, multiple injections seemed more effective in joint functionality than a single injection at 6 months. We consider that the available evidence is still insufficient, and future research on this specific topic is needed to confirm our results.

128 Background: Treatment for neoplastic fevers and sweating (NFS) is usually accomplished successfully with non-steroidal drugs (NSAIDs) such as naproxen, but such therapies may be contraindicated in some patients due to drug interactions, bleeding diathesis, renal disease, or cirrhosis. Options for treating NFS in such patients are limited. Methods: We report the first use of oxybutynin (OxyB), commonly used for hyperhidrosis and increasingly used for hormonally mediated hot flashes (Smith TJ, NEJM 2018; Leon-Ferre R, SABCS 2018, under review in JNCI Cancer Spectrum, for NFS in NSAID-ineligible or refractory patients. Results: Two patients with NFS were treated. The first was a 70 year old (yo) woman with cholangiocarcinoma with 3 months of NFS for whom naproxen was ineffective and who was starting chemotherapy. Within 2 hours after 2.5 mg OxyB q12h her sweating was gone, and her fever, which had been up to 100.4F, never resumed. The second was a 52 yo male with cirrhosis and hepatocellular carcinoma who was prescribed 2.5 mg q12h OxyB with lysis of his fever within hours and cessation of his sweating. To date, over one month has passed with no reduction in efficacy. Conclusions: OxyB may be a successful treatment modality for patients with NFS who cannot be treated with or are refractory to NSAIDs. Further research is warranted to ensure stability of results over time and to monitor for side effects.

Abstract Introduction: There have been substantial advances in treatment options for multiple myeloma (MM) over the past 15 years, yet little real-world evidence is available to describe the recent trends in MM treatment costs and outcomes. This study aimed to examine the trends in novel therapy use, total healthcare costs, and survival outcomes among newly diagnosed MM patients in the US since 2000. Methods: Patients aged ≥18 years who had ≥ 2 medical claims with MM (ICD-9 diagnosis code 203.0x) at least 30 days apart between January 2000 and September 2015 were identified in the Truven Health MarketScan Research Databases. Date of the first medical claim for MM was designated as index date. Patients were required to have 12-month pre-index and 3-month post-index continuous enrollment, and those with claims for MM treatment (including autologous stem-cell transplantation) in the pre-index period were excluded. Controls were selected from a pool of patients without MM and matched 1:1 with MM patients on index year, age, gender and geographic region. Patients whose death event could be obtained from the Social Security Administrations Master Death File were included in the survival outcomes analysis. Total healthcare costs were defined as sum of health-plan and patient paid costs for prescriptions and medical services, including inpatient admissions, emergency room, and physician office visits, and other outpatient services. MM treatment-related drug costs included outpatient pharmacy prescription costs and costs from outpatient services for infused products. Survival time was measured as time from index date to the date of death. Results: 19,417 newly diagnosed MM patients were included (mean± SD age at diagnosis 65.9±12.3 years, 44.9% female), of which 18,260 patients were matched to controls. The percentage of MM patients using novel therapies (pomalidomide, carfilzomib, bortezomib, lenalidomide, or thalidomide) continuously increased from 8.7% in 2000 to 61.3% in 2014. Overall, 28% of MM patients did not receive any treatment within 1-year after diagnosis during the study period. Total per-patient-per-month (PPPM) all-cause healthcare costs increased from $3,263 in 2000 to $14,656 in 2014 among newly diagnosed MM patients, which were primarily driven by costs of outpatient services (Figure 1). Hospitalization costs accounted for 21.5% of total costs in 2000, which increased to 32.7% in 2014. MM treatment-related drug costs accounted for 10.6% of total costs in 2000, 23.6% in 2009, and 28.5% in 2014. Compared with MM patients diagnosed earlier, those diagnosed after 2010 had higher rates of novel therapy use and significantly better survival outcomes (Figure 2); patients diagnosed in 2012 were 1.25 times more likely to survive two years than patients diagnosed in 2006 while two-year survival among controls was fairly stable over the study period (94-97%). MM patients also showed improved survival outcomes over the study period, with the two-year survival gap between MM patients and their matched controls decreasing at a rate of 3% per year. Conclusions: Findings from this study corroborate clinical data suggesting a paradigm shift in MM treatment over the past 15 years that is associated with substantial survival gains. Total healthcare costs among newly diagnosed MM patients have increased steadily since 2000 due to increases in all healthcare cost categories. However, the relative contribution of drug costs has remained fairly stable since 2009 despite new novel therapies coming to market in this time period. Future studies should focus on the impact of specific novel agents on patient survival, the value of clinical benefit engendered, and overall healthcare costs to better inform decision making in this setting. Disclosures Fonseca: Celgene, BMS, Bayer, Novartis, Sanofi, Janssen, Millennium a Takeda Company and AMGEN: Consultancy; Applied Bioscience: Consultancy; FISH: Patents & Royalties: Dr Fonseca has received a patent for the prognostication of MM based on genetic categorization by FISH of the disease. Abouzaid:Celgene Corporation: Employment, Equity Ownership, Research Funding. Bonafede:Truven Health: Other: I am an employee of Truven Health, which received a research contract to conduct this study with Seattle Genetics. . Cai:Truven Health Analytics: Other: I am an employee of Truven Health, which received a research contract to conduct this study with Seattle Genetics. , Research Funding. Parikh:Celgene Corporation: Employment, Equity Ownership, Research Funding. Cosler:Celgene: Consultancy. Richardson:Gentium S.p.A., Jazz Pharmaceuticals: Research Funding; Celgene, Novartis, Millennium Takeda, Gentium S.p.A., Jazz Pharmaceuticals: Membership on an entity's Board of Directors or advisory committees.

Multiple myeloma (MM) is a neoplasm thought to arise from a damaged germinal center B-cell that progresses to a plasma cell clone arising in bone marrow. MM comprises 20% of all hematologic cancer deaths. Persons of African ancestry (AA) have a 1.5 to 2-fold higher risk compared to individuals of European ancestry (EA). Genetically driven differences in hematopoiesis may lead to variation in the levels white blood cell (WBC) subsets which could, in turn, be associated with MM etiology. There are differences in genetic determinants of WBC traits between EA and AA populations, with possible implications for the racial disparity in risk. We tested the above hypothesis using Mendelian randomization (MR), an approach that leverages genetic determinants of specific traits (i.e. WBC counts) to estimate their effects on the risk of an outcome; and a transcriptome-wide association study (TWAS), which utilizes genetic predictors of gene expression to identify susceptibility genes. These analytic approaches were applied to data from the African American Multiple Myeloma Study (AAMMS) consisting of 1813 cases and 8871 AA cancer-free controls to examine how differences in heritable WBC gene expression profiles influence MM risk. Genetic determinants of variation in WBC subsets in AA were obtained from the literature and supplemented with new genome-wide association findings in AA subjects from the UK Biobank cohort (n=6108). Odds ratios (OR) for MM per 1 standard deviation (SD) increase in each WBC phenotype were estimated using independent (linkage disequilibrium (LD) r2<0.10) variants with P<10-6 as genetic instruments. Analyses based on variants associated with WBC traits in AA populations did not identify any statistically-significant associations between MM risk and WBC overall (p=0.81, using 15 SNPs) or subsets (lymphocytes, monocytes, eosinophils, neutrophils and basophils, p>0.05 for each). However, when we applied genetic determinants of WBC identified in 330,000 cancer-free EA UK Biobank participants (P<10-8, replication P<0.05, LD r2<0.05), a statistically significant inverse relationship emerged between increasing lymphocyte counts and MM risk (OR=0.80, 95% CI: 0.66-0.97, p=0.02, using 385 SNPs), as well as increasing basophil counts (OR=0.63, 95% CI: 0.41-0.96, p=0.03, using 140 SNPs). Next, we examined the association between WBC gene expression profiles and MM risk in AAMMS data. We applied published and validated ancestry-specific models developed using the PrediXcan approach, which leverage germline genetic and transcriptomic data from the Multi-Ethnic Study of Atherosclerosis (MESA) (Mogil et al. PMID: 30096133). The primary TWAS used gene expression models trained in AA subjects (n=233), with sensitivity analyses using models developed in AA and Hispanic subjects (n=585). The TWAS significance threshold was based on the number of genes with significant germline prediction models (p<0.05 and R2 ≥0.05) in AA, corresponding to P < 0.05/2700 = 1.85×10-5. The expression of two genes was significantly associated with MM risk: KANK1at 9p24.3 (P = 1.01×10-5) and DNAJC27at 2p23.3 (P = 1.56×10-5). KANK1is a candidate tumor suppressor gene for renal cell carcinoma and has recently been associated with MM risk in AA [Du, Blood 2017 130:3058]. Here we provide additional evidence for its role in MM etiology via gene expression-mediated mechanisms. DNAJC27 (previously known as RBJ) is a novel MM risk gene linked to constitutive activation of ERK in solid tumors. We also identified two suggestively associated genes: PRR14 (P = 1.34×10-4; combined AA-Hispanic sample: P = 1.56×10-6), which has been linked to MM risk in EA populations, and PARP16 (P = 9.46×10-5). To our knowledge this is the first study to comprehensively examine variation in WBC traits and gene expression profiles with respect to MM risk in AA. Our TWAS analysis leveraged data from the largest collection of genetic and gene expression data in AA, enabling ancestry-matched inference and identification of two novel risk genes. Although the limited availability of genetic instruments for WBC limited the power of MR analysis, findings using variants identified in European populations may offer some insight into trans-ethnic etiologic pathways and contribute to risk stratification strategies using genetic and blood cell count biomarkers. Future studies, particularly with MGUS-free controls, are needed to validate these results. Disclosures Song: Millennium Pharmaceuticals Inc: Employment. Rand:Ancestry.com: Employment. Ailawadhi:Cellectar: Research Funding; Janssen: Consultancy, Research Funding; Celgene: Consultancy; Pharmacyclics: Research Funding; Amgen: Consultancy, Research Funding; Takeda: Consultancy. Nooka:Takeda: Honoraria, Other: advisory board participation; Janssen: Honoraria, Other: advisory board participation; GSK: Honoraria, Other: advisory board participation; Spectrum pharmaceuticals: Honoraria, Other: advisory board participation; Adaptive technologies: Honoraria, Other: advisory board participation; Amgen: Honoraria, Other: advisory board participation; Celgene: Honoraria, Other: advisory board participation; BMS: Honoraria, Other: advisory board participation. Singhal:Bureau of Millennium/Takeda, Celgene, Janssen, Celgene, Bristol-Myers Squibb and Bluebird: Speakers Bureau. van Rhee:Takeda: Consultancy; Sanofi Genzyme: Consultancy; Castleman Disease Collaborative Network: Consultancy; EUSA: Consultancy; Adicet Bio: Consultancy; Kite Pharma: Consultancy; Karyopharm Therapeutics: Consultancy. Mehta:Millennium/Takeda, Celgene; stock in Celgene, Bristol-Myers Squibb and Bluebird: Speakers Bureau. Wolf:Takeda: Consultancy; Celgene: Consultancy; Novartis: Consultancy; Janssen: Consultancy; Amgen: Consultancy. Martin:Roche and Juno: Consultancy; Amgen, Sanofi, Seattle Genetics: Research Funding. Fiala:Incyte: Research Funding. Terebelo:Jannsen: Speakers Bureau; Celgene: Honoraria; Newland Medical Asociates: Employment. Anderson:Bristol-Myers Squibb: Other: Scientific Founder; Oncopep: Other: Scientific Founder; Amgen: Consultancy, Speakers Bureau; Janssen: Consultancy, Speakers Bureau; Takeda: Consultancy, Speakers Bureau; Celgene: Consultancy, Speakers Bureau; Sanofi-Aventis: Other: Advisory Board. Vij:Bristol-Myers Squibb: Honoraria, Research Funding; Celgene: Honoraria, Research Funding; Genentech: Honoraria; Janssen: Honoraria; Karyopharm: Honoraria; Sanofi: Honoraria; Takeda: Honoraria, Research Funding. Bernal-Mizrachi:TAKEDA: Research Funding; Kodikas Therapeutic Solutions, Inc: Equity Ownership; Winship Cancer Institute: Employment, Patents & Royalties. Morgan:Amgen, Roche, Abbvie, Takeda, Celgene, Janssen: Honoraria, Membership on an entity's Board of Directors or advisory committees; Celgene: Other: research grant, Research Funding. Zonder:Celgene Corporation: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Takeda: Membership on an entity's Board of Directors or advisory committees; Amgen: Consultancy, Membership on an entity's Board of Directors or advisory committees; Intellia: Consultancy, Membership on an entity's Board of Directors or advisory committees; Caelum: Consultancy, Membership on an entity's Board of Directors or advisory committees; Alnylam: Consultancy, Membership on an entity's Board of Directors or advisory committees; BMS: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Research Funding; Janssen: Consultancy, Membership on an entity's Board of Directors or advisory committees; Oncopeptides: Consultancy, Membership on an entity's Board of Directors or advisory committees. Huff:Member of Safety Monitoring Board for Johnson and Johnson: Membership on an entity's Board of Directors or advisory committees; Karyopharm, Sanofi, MiDiagnostics: Consultancy. Lonial:Karyopharm: Consultancy; Takeda: Consultancy, Research Funding; Amgen: Consultancy; BMS: Consultancy; Janssen: Consultancy, Research Funding; GSK: Consultancy; Celgene Corporation: Consultancy, Research Funding; Genentech: Consultancy. Orlowski:Poseida Therapeutics, Inc.: Research Funding.

Introduction: Most patients with newly diagnosed FL treated with rituximab (R) alone or R + chemotherapy will experience prolonged progression-free survival and overall survival (OS), but it remains unclear what factors have the greatest influence on FL-associated and other causes of death in this patient population. We utilized individual patient data from 13 first-line randomized clinical trials from the FLASH database to perform a comprehensive multistate survival analysis to examine and quantify the relationships between clinical characteristics, treatment response, and early, intermediate, and late FL outcomes. Methods: The multistate survival analysis model defined states for "Alive after beginning Induction Treatment (TX)", "Alive after beginning Maintenance TX", "Death due to FL", and "Death from Other Causes" (Figure 1). We used the Aalen-Johansen estimator, a generalization of the Kaplan-Meier estimator, to calculate the likelihood of being in each model state and estimate the course of FL over time. Making no assumptions on the probability distributions and capable of coping with censored observations, the Aalen-Johansen estimator is a convenient and reliable nonparametric estimator for clinical data. Results: Among 7,465 FL patients with median age 56 (range 18-90) years, 49.2% were female; 28.7% Stage I-III, 71.3% Stage IV, and FLIPI was 0-1 (20.0%), 2 (36.8%), ≥ 3 (43.2%). Following initiation of induction treatment, 2-, 5- and 10-year death rates were 1.7%, 3.8%, and 5.8% due to FL, and 0.7%, 2.1%, and 4.8% from other causes (Figure 2). Death rates at 2, 5, and 10 years due to FL and other causes for subgroups based on clinical characteristics and treatment response are shown in Table 1. Notably, patients > 70 years and patients with FLIPI ≥ 3 had worse outcomes and patients achieving CR at 18, 24, and 30 months experienced improved outcomes. Conclusion: This is the largest study using data from randomized trials to quantify the impact of clinical factors on early, intermediate and late mortality by cause of death. We demonstrated that age > 70 years and FLIPI ≥ 3 were linked to increased FL-associated death and response to TX distinguished patients with favorable and poor outcomes. Future analyses should quantify the impact of predictors on the rate/time of FL outcomes in multivariable models. Disclosures Salles: Roche, Janssen, Gilead, Celgene: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Other: Educational events; Amgen: Honoraria, Other: Educational events; BMS: Honoraria; Merck: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees; Novartis, Servier, AbbVie, Karyopharm, Kite, MorphoSys: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Other: Educational events; Epizyme: Consultancy, Honoraria; Autolus: Consultancy, Membership on an entity's Board of Directors or advisory committees; Takeda: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees, Other: Educational events. Hoster:Janssen: Research Funding; Roche Pharma AG: Other: Travel Support. Hiddemann:Bayer: Research Funding; Gilead: Consultancy, Honoraria; Vector Therapeutics: Consultancy, Honoraria; Janssen: Consultancy, Honoraria, Research Funding; Roche: Consultancy, Honoraria, Research Funding; Celgene: Consultancy, Honoraria. Herold:Roche: Honoraria, Research Funding; Janssen: Consultancy, Honoraria; Gilead: Honoraria; Celgene: Honoraria. Morschhauser:Servier: Consultancy; Gilead: Consultancy; Janssen: Honoraria; Roche/Genentech: Consultancy; BMS: Honoraria; Celgene: Honoraria. Rummel:Roche Pharma AG: Honoraria, Research Funding; Celgene: Honoraria; Janssen: Honoraria; Sandoz: Honoraria. Kimby:AbbVie,: Membership on an entity's Board of Directors or advisory committees; Celgene: Membership on an entity's Board of Directors or advisory committees; Roche: Membership on an entity's Board of Directors or advisory committees; Jansen: Membership on an entity's Board of Directors or advisory committees; Gilead: Other: educational lectures. Vitolo:Abbvie: Membership on an entity's Board of Directors or advisory committees, Speakers Bureau; Kite: Membership on an entity's Board of Directors or advisory committees, Speakers Bureau; Celgene: Membership on an entity's Board of Directors or advisory committees, Speakers Bureau; Janssen: Membership on an entity's Board of Directors or advisory committees, Speakers Bureau; Gilead: Membership on an entity's Board of Directors or advisory committees, Speakers Bureau; Juno Therapeutics: Membership on an entity's Board of Directors or advisory committees; F. Hoffmann-La Roche: Speakers Bureau; Novartis: Membership on an entity's Board of Directors or advisory committees, Speakers Bureau. Gyan:Pfizer: Honoraria. Ladetto:Celgene: Honoraria; Roche: Honoraria; Janssen: Honoraria; Abbvie: Honoraria; Acerta: Honoraria; Sandoz: Honoraria. Nielsen:F. Hoffmann-La Roche Ltd: Employment, Equity Ownership. Flowers:AstraZeneca: Consultancy; BeiGene: Consultancy, Research Funding; Eastern Cooperative Oncology Group: Research Funding; Burroughs Wellcome Fund: Research Funding; AbbVie: Consultancy, Research Funding; Optimum Rx: Consultancy; V Foundation: Research Funding; Pharmacyclics/Janssen: Consultancy, Research Funding; Bayer: Consultancy; Gilead: Consultancy, Research Funding; TG Therapeutics: Research Funding; Denovo Biopharma: Consultancy; Acerta: Research Funding; National Cancer Institute: Research Funding; Millenium/Takeda: Research Funding; Genentech, Inc./F. Hoffmann-La Roche Ltd: Consultancy, Research Funding; Celgene: Consultancy, Research Funding; Spectrum: Consultancy;

Abstract Pathogenic sequence variants (PSV) in BRCA1 or BRCA2 (BRCA1/2) are associated with increased risk and severity of prostate cancer. We evaluated whether PSVs in BRCA1/2 were associated with risk of overall prostate cancer or high grade (Gleason 8+) prostate cancer using an international sample of 65 BRCA1 and 171 BRCA2 male PSV carriers with prostate cancer, and 3,388 BRCA1 and 2,880 BRCA2 male PSV carriers without prostate cancer. PSVs in the 3′ region of BRCA2 (c.7914+) were significantly associated with elevated risk of prostate cancer compared with reference bin c.1001-c.7913 [HR = 1.78; 95% confidence interval (CI), 1.25–2.52; P = 0.001], as well as elevated risk of Gleason 8+ prostate cancer (HR = 3.11; 95% CI, 1.63–5.95; P = 0.001). c.756-c.1000 was also associated with elevated prostate cancer risk (HR = 2.83; 95% CI, 1.71–4.68; P = 0.00004) and elevated risk of Gleason 8+ prostate cancer (HR = 4.95; 95% CI, 2.12–11.54; P = 0.0002). No genotype–phenotype associations were detected for PSVs in BRCA1. These results demonstrate that specific BRCA2 PSVs may be associated with elevated risk of developing aggressive prostate cancer. Significance: Aggressive prostate cancer risk in BRCA2 mutation carriers may vary according to the specific BRCA2 mutation inherited by the at-risk individual.

Abstract Determining effective therapies for patients with recurrent glioblastoma remains difficult especially in small early phase clinical trials. Currently utilized estimators of treatment response rely on two-dimensional measurements of tumor progression (e.g. RANO, RECIST, MacDonald) that have often fallen short in reliably connecting patients who respond with positive survival outcomes. This has prompted consideration of advanced imaging and volumetric measurements by the RANO working group and others. Our proposed approach, Days Gained (DG), uses volumetric measurements to calculate a personalized response metric based on change in tumor growth characteristics pre/post-treatment. DG has shown promise for connecting imageable treatment response with clinically meaningful (statistically significant) survival benefit when applied in upfront and recurrent therapy settings, even in the context of coincident bevacizumab treatment. In this study, we seek to consider a new cohort of patients receiving bevacizumab in combination with other novel therapies to distinguish any subpopulation of patients with meaningful response. In this work, we identified a subset of 16 patients from bevacizumab clinical trials with data available for DG analysis requiring serial imaging (T1Gd and FLAIR) prior to and after the first cycle of therapy. Each trial evaluated bevacizumab alone versus bevacizumab plus either dasatinib or TRC105 in recurrent disease. Discrimination of time to progression (TTP) was evaluated at DG thresholds identified from our prior analysis of patients treated with bevacizumab. Using previously identified DG thresholds for clinically significant treatment benefit, in our cohort, DG measured by serial FLAIR imaging was significant in predicting longer TTP (120 DG, p=0.014), but T1Gd DG scores did not attain significance (p=0.630). Given the limited insights in connecting response metrics to accurately predicted outcomes, these data further support the use of DG as a burgeoning marker of treatment response (or lack of response) that may be useful for more routine integration into clinical trials.

Abstract INTRODUCTION The quantification of intratumoral heterogeneity – through radiomics-based approaches - can help resolve the regionally distinct genetic drug targets that may co-exist within a single Glioblastoma (GBM) tumor. While this offers potential diagnostic value under the paradigm of individualized oncology, clinical decision-making must also consider the degree of uncertainty associated with each model. In this study, we evaluate the performance of a novel machine-learning (ML) algorithm, called Gaussian Process (GP) modeling, that can quantify the impact of multiple sources of uncertainty in ML model development and prediction accuracy, including variabilities in the copy number measurement, radiomics features, training sample characteristics, and training sample size. METHOD We collected 95 image-localized biopsies from 25 primary GBM patients. We coregistered stereotactic locations with preoperative multi-parametric MRI features (conventional MRI, DSC perfusion, Diffusion Tensor Imaging) to generate spatially matched pairs of MRI and copy number variants (CNV) for for each biopsy. We developed a Gaussian Process (GP) model to predict CNV for Epidermal Growth Factor Receptor (EGFR) based on MRI radiomic features in each patient. We used leave-one-patient-out cross validation to quantify prediction accuracy and model uncertainty. Spatial prediction and uncertainty (p-value) maps were overlaid to help visualize regional genetic variation of EGFR and uncertainty of the radiomic predictions. RESULT: The initial GP radiomics model for EGFR amplification (CNV > 3.5) produced a sensitivity of 0.8 and specificity of 0.8. Samples/regions associated with high uncertainty (p-value >0.05) correlated with either 1) extrapolation of radiomic features from the training set-defined feature space or 2) insufficient training samples in the feature space. CONCLUSION We present a ML-based model that quantifies spatial genetic heterogeneity in GBM, while also estimating model uncertainties that result from multi-source data variabilities. This approach lays the groundwork for prospective clinical integration of modeling-based diagnostic approaches in the paradigm of individualized medicine.