Christensen, Jacob Haaber

PURPOSE Patients diagnosed with advanced-stage Hodgkin lymphoma (aHL) have historically been risk-stratified using the International Prognostic Score (IPS). This study investigated if a machine learning (ML) approach could outperform existing models when it comes to predicting overall survival (OS) and progression-free survival (PFS). PATIENTS AND METHODS This study used patient data from the Danish National Lymphoma Register for model development (development cohort). The ML model was developed using stacking, which combines several predictive survival models (Cox proportional hazard, flexible parametric model, IPS, principal component, penalized regression) into a single model, and was compared with two versions of IPS (IPS-3 and IPS-7) and the newly developed aHL international prognostic index (A-HIPI). Internal model validation was performed using nested cross-validation, and external validation was performed using patient data from the Swedish Lymphoma Register and Cancer Registry of Norway (validation cohort). RESULTS In total, 707 and 760 patients with aHL were included in the development and validation cohorts, respectively. Examining model performance for OS in the development cohort, the concordance index (C-index) for the ML model, IPS-7, IPS-3, and A-HIPI was found to be 0.789, 0.608, 0.650, and 0.768, respectively. The corresponding estimates in the validation cohort were 0.749, 0.700, 0.663, and 0.741. For PFS, the ML model achieved the highest C-index in both cohorts (0.665 in the development cohort and 0.691 in the validation cohort). The time-varying AUCs for both the ML model and the A-HIPI were consistently higher in both cohorts compared with the IPS models within the first 5 years after diagnosis. CONCLUSION The new prognostic model for aHL on the basis of ML techniques demonstrated a substantial improvement compared with the IPS models, but yielded a limited improvement in predictive performance compared with the A-HIPI.

Purpose: Improved predictive tools are desired in classic Hodgkin lymphoma (cHL) to improve prognostication and to better risk stratify patients (pts) for clinical trials. In younger pts who tolerate intensive therapies, focus has been on limiting late treatment toxicity through risk-adapted, PET-guided treatment strategy. In older pts, acute treatment toxicities are limiting factors for optimal disease control. Due to these fundamental differences, predictive tools may perform differently in younger and older pts. In particular, tools developed in younger pts may be suboptimal in older populations and vice versa. The primary objective of this study was to assess the performance of the A-HIPI (development was limited to 18-65 years of age) against the international prognostic score (IPS) for modelling overall survival (OS) and progression-free survival (PFS) in younger and older pts with cHL. Methods: This study utilized data from the population-based, nationwide Danish National Lymphoma registry. Pts with advanced-stage cHL (Ann Arbor stage III-IV or IIB with extra nodal disease) were included and categorized by age in two groups: ages ≤65 years vs. >65 years. In the primary analysis, all pts regardless of therapy were included. A sensitivity analysis restricting to pts starting on BEACOPP or ABVD was performed (Only ABVD in the >65 cohort). Concordance index (C-index) and calibration were used to assess model performance and generalizability. Calibration was visualized using calibration plots and quantified by calibration in the large (CITL) and calibration slope (CS) at 5-years post diagnosis. Results: A total of 893 advanced-stage HL pts fulfilled the inclusion criteria (634 in the ≤65 cohort and 259 in the >65 cohort). The 5-year OS and PFS in the >65-year cohort were 44% (Confidence intervals (CI); 37-51%) and 35% (CI; 30-42%), respectively. Fifty-six pts in the >65 cohort were classified as low-intermediate-risk (IPS; 1-2), 128 intermediate-risk (IPS; 3-4), and 75 high-risk (IPS; 5-7). For the ≤65 cohort, the 5-year OS and PFS was 88% (CI; 85-90%) and 76% (CI; 73-80%), respectively. Twenty-three pts were classified as low-risk (IPS; 0), 244 low-intermediate-risk, 286 intermediate-risk, and 81 high-risk. The A-HIPI had a C-index of 0.74 and 0.63 for OS and PFS, respectively in the ≤65 years cohort vs. 0.65 and 0.64 for OS and PFS, respectively, in the >65 cohort. The IPS had a C-index in the ≤65 cohort of 0.66 and 0.60 for OS and PFS, respectively, vs. 0.58 and 0.59 for OS and PFS, respectively, in the >65 cohort (i.e., the IPS performed better in the ≤65 cohort in terms of OS and PFS but was inferior to the A-HIPI). When restricting to pts treated with ABVD or BEACOPP, the A-HIPI C-index in the >65 cohort (116 pts) were reduced to 0.55 for OS and 0.54 for PFS. For the ≤65 cohort (595 pts), the A-HIPI C-index was stable at 0.75 and 0.62 for OS and PFS, respectively. In terms of A-HIPI calibration in the >65 cohort, CITL and CS were -0.78 and 0.39 for OS vs. -0.98 and 0.80 for PFS. In the ≤65 cohort, CITL and CS were -0.06 and 0.99 for OS vs. 0.21 and 1.18 for PFS. Visual inspection of the calibration plot (Figure 1) for the >65 cohort showed that the A-HIPI underestimated the observed proportion for both OS and PFS (i.e., the observed events were higher than the predicted). Calibration plot for the ≤65 cohort (Figure 2) indicated that the A-HIPI accurately modelled the observed proportion for both OS and PFS (i.e., the predicted probability was consistent with the observed proportion). Conclusion: The newly developed A-HIPI was validated in a large population-based cohort of Danish pts with advanced-stage cHL. Performance of the A-HIPI was high in the ≤65 cohort and superior to the IPS for OS prediction. Calibration of A-HIPI was excellent in pts ages ≤65 years. However, A-HIPI performed significantly worse among pts >65 years and attained poor performance in pts receiving ABVD or BEACOPP, which is not surprising since patients older than 65 were not included in the development. This study emphasizes the importance of further efforts to develop or update models that apply specifically in older individuals. The inclusion of additional variables reflecting comorbidities and pts fitness into a prognostic model may be necessary to effectively deliver accurate prognoses and risk assessments for the older pt.

SummaryNon‐endemic Burkitt lymphoma (BL) is a rare germinal centre B‐cell‐derived malignancy with the genetic hallmark of MYC gene translocation and with rapid tumour growth as a distinct clinical feature. To investigate treatment outcomes, loss of lifetime and relapse risk in adult BL patients treated with intensive immunochemotherapy, retrospective clinic‐based and population‐based lymphoma registries from six countries were used to identify 264 real‐world patients. The median age was 47 years and the majority had advanced‐stage disease and elevated LDH. Treatment protocols were R‐CODOX‐M/IVAC (47%), R‐hyper‐CVAD (16%), DA‐EPOCH‐R (11%), R‐BFM/GMALL (25%) and other (2%) leading to an overall response rate of 89%. The two‐year overall survival and event‐free survival were 84% and 80% respectively. For patients in complete remission/unconfirmed, the two‐year relapse risk was 6% but diminished to 0·6% for patients reaching 12 months of post‐remission event‐free survival (pEFS12). The loss of lifetime for pEFS12 patients was 0·4 (95% CI: −0·7 to 2) months. In conclusion, real‐world outcomes of adult BL are excellent following intensive immunochemotherapy. For pEFS12 patients, the relapse risk was low and life expectancy similar to that of a general population, which is important information for developing meaningful follow‐up strategies with increased focus on survivorship and less focus on routine disease surveillance.

Introduction: Non-endemic Burkitt lymphoma (BL) is a rare and highly aggressive B-cell malignancy, of whom a substantial number are adolescents and young adults (AYAs). In this particular group of patients, the balance between efficacy and long-term toxicities is of major concern, due to the long expected remaining lifetime. In this study, we investigated the outcomes for AYA patients treated with intensive immunochemotherapy. Patients and methods: Patients were identified through queries to clinic based and population-based lymphoma registries from six countries (Australia, Canada, Denmark, Norway, Sweden, and USA). All diagnoses were confirmed by local investigators; patients with classical BL histology plus detectable MYC translocation, were included. Patients between 18 and 39 years of age at diagnosis treated with intensive immunochemotherapy (DA-EPOCH-R or more intensively) were evaluated in pre-specified age groups. All treatment protocols included rituximab. Overall survival (OS) was defined as the time from diagnosis until death from any cause or censoring, while event-free survival (EFS) was defined as the time from diagnosis until unplanned re-treatment, progression/relapse, death, or censoring, whichever came first. Response evaluation was assessed using established response criteria based on CT and/or PET/CT imaging. Survival curves were computed using the Kaplan-Meier estimator. The cumulative incidence of relapse in patients reaching complete remission (CR) or CR unconfirmed (CRu) was computed by Aalen-Johansen estimator. The 5-year restricted loss of lifetime (RLOL) was defined as the area between the patient and general population survival curves until 5-years. The general population survival was retrieved from publicly available lifetables stratified on age, sex, calendar year, and country. Results: In total, 108 AYA BL patients were included. The median age was 30 years, ranging between 18 and 39 and 82% were male. The majority had advanced stage disease (Ann Arbor stage III-IV, 76%), extranodal involvement (87%), and elevated LDH (67%). Seven patients (6%) had CNS involvement at the time of diagnosis. The chemotherapy regimens used were CODOX-M/IVAC (51%), BFM/GMALL (34%), hyper-CVAD (7%), DA-EPOCH (5%), and others (3%). Among 74 patients for whom data on tumor lysis were available, 10 (14%) developed clinical tumor lysis upon start of chemotherapy, all presenting with advanced stage and extranodal disease. The response rate was 91% (89 in CR/CRu and 2% in partial remission). At a median follow-up of 53 months, 15 had an event and 10 died. The 2-year OS and EFS for the total population was 92% (87-97%, Figure 1) and 88% (82-94%), respectively. For 13 patients aged 18-21 2-year OS and EFS were both 100%, while 2-year OS and EFS for 43 patients aged 22-30 were 98% (93-100%) and 93% (85-100%), respectively. The 2-year OS and EFS for patients aged 31-39 were 86% (76-96%) and 80% (69-91%), respectively. For patients in CR/CRu and available date of response evaluation, the 2-year post-remission OS was 99% (97-100%) and the 2-year relapse risk was 2% (0-5%), with no relapses after 6 months. Compared to the general population, the RLOL was 0.8 months (-0.5-2.2 months). Nine patients did not respond to primary treatment (SD or PD), all which belonged to the age group 31-40 years (P<0.001 versus age group 18-30 years). The oldest age group had an inferior OS compared to younger patients (P=0.008), largely due to non-responders having poor subsequent survival with a 1-year OS of 33%. Conclusion: The outcomes of AYA BL patients following intensive immunochemotherapy are excellent with high remission rates and low risk of relapse in general. However, even among young patients age remained prognostic, with patients 31 years or older having inferior OS and lower response rate to first-line treatment. In patients achieving CR, survival was similar to that of the general population over the median follow-up of 4.5 years, illustrating the need to focus on survivorship issues in these individuals. Figure 1: Overall survival for BL patients following intensive immunochemotherapy for all patients and for age groups (18-21, 22-30, and 31-39 years). Figure 1 Disclosures Jørgensen: Gilead: Membership on an entity's Board of Directors or advisory committees; Roche: Membership on an entity's Board of Directors or advisory committees. Holte:Novartis: Honoraria, Other: Advisory board. Molin:Roche Holding AG: Honoraria; Merck & Co., Inc.: Honoraria; Bristol-Myers Squibb: Honoraria; Takeda Pharmaceuticals: Honoraria. Ekstroem Smedby:Takeda: Honoraria, Other: Grant funding, Research Funding; Celgene: Honoraria, Other: Grant funding, Research Funding; Janssen Cilag: Honoraria, Other: Grant funding, Research Funding. Song:Takeda: Honoraria; Celgene: Honoraria, Research Funding; Janssen: Honoraria; Amgen: Honoraria. Gerrie:Lundbeck, Seattle Genetics: Consultancy, Honoraria. Cheah:Roche, Janssen, MSD, Gilead, Loxo Oncology, Acerta, BMS: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees; Roche: Other: Travel expenses; Celgene, Roche, Abbvie: Research Funding. El-Galaly:Roche: Employment, Other: Travel support; Takeda: Other: Travel support.

Abstract Background: Non-endemic Burkitt lymphoma (BL) is a rare B-cell malignancy characterized by extreme tumor proliferation, frequent extranodal involvement, and the genetic hallmark of a MYC gene rearrangement. Despite an often dramatic initial presentation featuring tumor compression of vital organs and/or spontaneous tumor lysis syndrome, most patients who survive intensive immunochemotherapy induction are cured. Despite limited evidence of benefit, the current NCCN guidelines recommend that BL patients in CR are reviewed every 3 months for 2 years and every 6 months thereafter. Aims: To investigate outcomes, including relative survival and relapse risks conditional on event-free survival (EFS) milestones, in an international study of real-world BL patients treated with intensive immunochemotherapy. Patients and methods: This is a retrospective study of newly diagnosed BL patients identified from relevant population or hospital-based registers in Australia (Perth), Denmark (the Danish Lymphoma Registry), Sweden (the Swedish Lymphoma Registry) and Norway (Health Region South East). Patients who met the following criteria were included irrespective of HIV status: 1) age ≥18 years at diagnosis, 2) diagnosed during the period 2005-2017, 3) histology and immunohistochemistry consistent with BL, 4) MYC translocation detected by fluorescence in situ hybridization (FISH), and 5) intensive first line immunochemotherapy including rituximab (R-CHOEP or more intensive). Patient data were collected from registers and chart reviews. Overall survival (OS) was defined as time until death and EFS was defined as time to death, relapse/progression, or unplanned treatment, whichever came first. Prognostic features at baseline were evaluated using univariate Cox models with EFS as outcome. Standardized mortality ratios (SMRs), conditional relative survival estimates, and relapse risks were computed for the subset of patients achieving complete remission (CR or CRu), with follow-up measured from response evaluation and from different EFS milestones. Results: In total, 159 patients fulfilled the inclusion criteria of the study. The median age was 48 years (range 18-81) and the male:female ratio was 2.9. The baseline characteristics included stage III-IV (75%), elevated serum LDH (75%), extranodal involvement (83% - bone or bone marrow in 42% and CNS in 8%), B symptoms (60%), and ECOG performance score >1 (30%). The chemotherapy protocols used were CHOEP (2%), DA-EPOCH (13%), HYPER-CVAD (26%), CODOX-M/IVAC (28%), BFM or GMALL (31%), and others (1%). Clinical tumor lysis syndrome defined by severe electrolyte derangement, renal impairment, and/or cardiac arrhythmia, was noted in 16% of the patients, but no fatal episodes occurred. The overall response rate to first-line treatment was 88% (87% in CR/CRu) with 67% assessed by PET technology. The five-year EFS and OS estimates for the total population were 75% (95% CI 68-82%) and 82% (95% CI 76-88%), respectively, and the EFS and OS of patients <50 years of age were 81% (95% CI 71-90%) and 89% (95% CI 82-96%), respectively. In univariate analyses, age, advanced stage, and elevated LDH were associated with worse EFS. Among patients in CR/CRu (n=137), the 5-year EFS and OS from the time of response evaluation were 86% (95% CI 79-93%) and 91% (95% CI 86-96%), respectively. The 5-year cumulative incidence of relapse from the time of response assessment was 5% (95% CI 1-9%) in CR/CRu patients. The corresponding estimate was 3% (95% CI 0-6%) for patients alive after 6 months without events (EFS6), whereas no patients relapsed after 12 (EFS12, Figure 1). For CR/CRu patients, the 5-year relative survival after EFS6 and EFS12 was 97% (95% CI 93-102%) and 100% (95% CI 97-103%), respectively. In most subgroups, the SMRs gradually decreased with increased remission duration (Table 1). Conclusions: Outcomes of adult BL patients treated with intensive immunochemotherapy are excellent with no relapses occurring for patients reaching EFS12 and with a normalized relative survival after EFS6. For patients reaching EFS12, follow-up in late effects clinics, or discharging to primary care providers with a focus on survivorship issues rather than detection of recurrent lymphoma, should be considered. Updated analyses including patients from British Columbia (Canada) and the University of Iowa/Mayo Clinic SPORE MER register (USA) will be presented at the meeting. Disclosures Molin: Takeda Pharmaceuticals: Research Funding; Bristol-Myers Squibb: Honoraria; Roche Holding AG: Honoraria; Merck & Co., Inc: Honoraria. Ekstroem Smedby:Janssen Pharmaceuticals: Other: The Department have recieved partial funding from Janssen Pharmaceuticals.