Eloranta, Sandra

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.

PURPOSE CNS progression or relapse is an uncommon but devastating complication of aggressive B-cell lymphoma. There is no consensus regarding the optimal approach to CNS prophylaxis. This study was designed to determine whether high-dose methotrexate (HD-MTX) is effective at preventing CNS progression in patients at high risk of this complication. PATIENTS AND METHODS Patients age 18-80 years with aggressive B-cell lymphoma and high risk of CNS progression, treated with curative-intent anti–CD20-based chemoimmunotherapy, were included in this international, retrospective, observational study. Cause-specific hazard ratios (HRs) and cumulative risks of CNS progression were calculated according to use of HD-MTX, with time to CNS progression calculated from diagnosis for all patients (all-pts) and from completion of frontline systemic lymphoma induction therapy, for patients in complete response at completion of chemoimmunotherapy (CR-pts). RESULTS Two thousand four hundred eighteen all-pts (HD-MTX; n = 425) and 1,616 CR-pts (HD-MTX; n = 356) were included. CNS International Prognostic Index was 4-6 in 83.4% all-pts. Patients treated with HD-MTX had a lower risk of CNS progression (adjusted HR, 0.59 [95% CI, 0.38 to 0.90]; P = .014), but significance was not retained when confined to CR-pts (adjusted HR, 0.74 [95% CI, 0.42 to 1.30]; P = .29), with 5-year adjusted risk difference of 1.6% (95% CI, –1.5 to 4.4; all-pts) and 1.4% (95% CI, –1.5 to 4.1; CR-pts). Subgroups were underpowered to draw definitive conclusions regarding the efficacy of HD-MTX in individual high-risk clinical scenarios; however, there was no clear reduction in CNS progression risk with HD-MTX in any high-risk subgroup. CONCLUSION In this large study, high-risk patients receiving HD-MTX had a 7.2% 2-year risk of CNS progression, consistent with the progression risk in previously reported high-risk cohorts. Use of HD-MTX was not associated with a clinically meaningful reduction in risk of CNS progression.

Abstract Introduction Central nervous system relapse (secondary central nervous system lymphoma -SCNS) is an uncommon but devastating complication of aggressive B-cell lymphoma. Patients (Pts) with CNS-IPI 4-6 are at greatest risk (10.2% at 2 years). Intravenous high-dose methotrexate (HD-MTX) is widely used to mitigate SCNS risk but data supporting this practice are limited. Methods We performed a multicentre, retrospective study at 21 sites in Australia, Asia, North America and Europe. Chart or registry review was performed for consecutively diagnosed pts with diffuse large B-cell lymphoma (DLBCL) and CNS-IPI 4-6, high grade B-cell lymphoma (HGBL) with rearrangements of MYC+BCL2 and/or BCL6 and primary breast/testicular DLBCL irrespective of CNS-IPI. Pts were diagnosed between 2000-2020, 18-80 years at diagnosis, and treated with curative intent anti-CD20 based chemo-immunotherapy. Pts with CNS involvement at diagnosis were excluded. HD-MTX was defined as at least one cycle of intravenous MTX at any dose. Time to SCNS was calculated from date of diagnosis (all-pts), and from the end of frontline systemic lymphoma therapy, defined as 6x21 days from diagnosis (complete response (CR-pts)), until SCNS, systemic relapse, death, or censoring, whichever came first. Cumulative risk of SCNS was computed using the Aalen-Johansen estimator treating death and systemic relapses as competing events. Adjusted cumulative risks were obtained by using an inverse probability of treatment weighting approach. The average treatment effect was computed as the difference in adjusted 5-year risk of SCNS. Results - 2300 and 1455 pts were included in the all-pts and CR-pts analyses, respectively. Baseline demographics and details of therapy are summarised in Table 1. Except for a predominance of males, pts ≤60 years and pts with ECOG 0-1 in the HD-MTX vs no HD-MTX groups, the demographics and treatments were well balanced. At a median follow up of 5.9 years (range 0.0-19.1) and 5.5 years from diagnosis (range 0.0-18.7), 201/2300 and 84/1455 pts experienced CNS events in the all-pts and CR-pts analyses respectively. For all-pts(n=2300), CNS-IPI was 4-6 in 2052(89.2%), with R-CHOP-like therapy given to 93.8%. 410 pts (17.8%) received HD-MTX (265 HD-MTX alone, 145 in combination with intrathecal methotrexate (IT-MTX);435 received IT-MTX alone;1455 received neither. There were 32/410 and 169/1890 SCNS events, with median time from diagnosis to SCNS of 8.8 and 6.7 months in the HD-MTX and no HD-MTX groups respectively. 5-year OS was 70% (95% CI, 65-76%) and 55% (95% CI 53-57%) in HD-MTX and no HD-MTX groups respectively. There was no difference in the adjusted 5-year risk of SCNS between the HD-MTX and no HD-MTX groups (8.4% vs 9.1%, adjusted hazard ratio [HR] 0.71, p=0.100) (Figure 1). For CR-pts(n=1455), CNS-IPI was 4-6 in 1267(87.0%), with R-CHOP-like therapy given to 93.3%. 284 pts (19.5%) received HD-MTX (170 HD-MTX alone, 114 with IT-MTX);298 received IT-MTX alone;873 received neither. There were 16/284 and 68/1171 SCNS events, with median time from diagnosis to SCNS of 11.0 and 10.3 months in the HD-MTX and no HD-MTX groups respectively. 5-year OS was 74%(95% CI 67-81%) and 75%(95% CI 72-78%) in the HD-MTX groups and no HD-MTX groups respectively (adjusted HR 1.08, p=0.622). There was no difference in the 5-year risk of CNS relapse between the HD-MTX and no HD-MTX groups 5.0% vs 6.0% (adjusted HR 1.03, p=0.903) (Figure 2). Exploratory analysis of the impact of HD-MTX among the highest risk groups CNS IPI 5 (n=368), CNS-IPI 6 (n=59) and CNS-IPI 6 plus all pts with testicular, renal or adrenal involvement (n=349) did not reveal differences in SCNS rates in HD-MTX treated pts. Additional subgroup analyses will be presented at the meeting. Conclusions To our knowledge, this is the largest study of the efficacy of HD-MTX in reducing SCNS events focusing exclusively on high-risk pts. The overall incidence of CNS relapse observed was consistent with previous reports in similar patient cohorts at 9%. The use of HD-MTX did not lower SCNS rates overall or when analysis was confined to CR pts at completion of curative intent therapy to compensate for potential immortal bias associated with HD-MTX therapy. Despite the limitations of the non-randomized and retrospective design, it appears unlikely that HD-MTX is associated with a clinically meaningful reduction in SCNS rates in pts with high risk for SCNS. Figure 1 Figure 1. Disclosures Lewis: AstraZeneca: Consultancy, Honoraria; Novartis: Patents & Royalties: Conference attendance; Janssen: Honoraria, Patents & Royalties: Conference attendance; Roche: Consultancy, Honoraria. Villa: Janssen: Honoraria; Gilead: Honoraria; AstraZeneca: Honoraria; AbbVie: Honoraria; Seattle Genetics: Honoraria; Celgene: Honoraria; Lundbeck: Honoraria; Roche: Honoraria; NanoString Technologies: Honoraria. Bobillo: F. Hoffmann-La Roche Ltd: Consultancy, Speakers Bureau; Gilead: Speakers Bureau. Ekstroem Smedby: Takeda: Consultancy; Janssen Cilag: Research Funding. Savage: Merck: Consultancy, Honoraria, Other: Institutional clinical trial funding; BMS: Consultancy, Honoraria, Other: Institutional clinical trial funding; AbbVie: Consultancy, Honoraria; Roche: Research Funding; Takeda: Other: Institutional clinical trial funding; Servier: Consultancy, Honoraria; Seattle Genetics: Consultancy, Honoraria; Astra-Zeneca: Consultancy, Honoraria; Beigene: Other: Institutional clinical trial funding; Genentech: Research Funding. Eyre: Beigene: Honoraria, Research Funding; Incyte: Consultancy; Secura Bio: Consultancy, Honoraria; Janssen: Honoraria; Gilead/KITE: Honoraria, Other: Travel support for conferences, Research Funding, Speakers Bureau; Loxo Oncology: Consultancy, Honoraria, Membership on an entity's Board of Directors or advisory committees; Abbvie: Consultancy, Honoraria, Other: Travel to conferences; AstraZeneca: Honoraria, Research Funding; Roche: Consultancy, Honoraria. Cwynarski: Incyte: Consultancy, Speakers Bureau; Gilead: Consultancy, Speakers Bureau; Atara: Consultancy; Celgene: Consultancy; Takeda: Consultancy, Other: travel to scientific conferences, Speakers Bureau; Kite, a Gilead Company: Consultancy, Other: travel to scientific conferences, Speakers Bureau; Janssen: Consultancy, Other: travel to scientific conferences; Roche: Consultancy, Other: travel to scientific conferences, Speakers Bureau; BMS/Celgene: Other: travel to scientific conferences. Stewart: Teva: Honoraria; Sandoz: Honoraria; Amgen: Honoraria; AstraZeneca: Honoraria; Novartis: Honoraria; Celgene: Honoraria; Gilead: Honoraria; Abbvie: Honoraria; Janssen: Honoraria; Roche: Honoraria. Bishton: Gilead: Honoraria, Other: Travel grants; AbbVie: Honoraria, Other: Travel grants; Celgene/BMS: Honoraria, Other: travel grants; Celltrion: Honoraria, Other: Travel grants; Takeda.: Honoraria, Other: Travel grants . Fox: F. Hoffmann-La Roche Ltd: Consultancy, Membership on an entity's Board of Directors or advisory committees. Joffe: Epizyme: Consultancy; AstraZeneca: Consultancy. Eloranta: Janssen Pharmaceutical NV: Other: NV. Sehn: Genmab: Consultancy; Novartis: Consultancy; Debiopharm: Consultancy. Manos: Bristol-Myers Squibb: Other: Travel and meetings. Hawkes: Specialised Therapeutics: Consultancy; Gilead: Membership on an entity's Board of Directors or advisory committees; Merck Sharpe Dohme: Membership on an entity's Board of Directors or advisory committees; Novartis: Membership on an entity's Board of Directors or advisory committees; Antigene: Membership on an entity's Board of Directors or advisory committees; Regeneron: Speakers Bureau; Bristol Myers Squib/Celgene: Membership on an entity's Board of Directors or advisory committees, Research Funding; Merck KgA: Research Funding; Astra Zeneca: Membership on an entity's Board of Directors or advisory committees, Research Funding, Speakers Bureau; Roche: Membership on an entity's Board of Directors or advisory committees, Other: Travel and accommodation expenses, Research Funding, Speakers Bureau; Janssen: Speakers Bureau. Minson: Novartis: Research Funding; Hoffman La Roche: Research Funding. Dickinson: Celgene: Research Funding; Amgen: Honoraria; Takeda: Research Funding; Gilead Sciences: Consultancy, Honoraria, Speakers Bureau; MSD: Consultancy, Honoraria, Research Funding, Speakers Bureau; Janssen: Consultancy, Honoraria; Bristol-Myers Squibb: Consultancy, Honoraria; Roche: Consultancy, Honoraria, Other: travel, accommodation, expenses, Research Funding, Speakers Bureau; Novartis: Consultancy, Honoraria, Research Funding, Speakers Bureau. Øvlisen: Abbvie: Other: Travel expenses. Gregory: Roche: Honoraria, Membership on an entity's Board of Directors or advisory committees, Other: Travel fees, Speakers Bureau; Janssen: Consultancy; Novartis: Consultancy. Ku: Roche: Consultancy; Antegene: Consultancy; Genor Biopharma: Consultancy. Talaulikar: Roche: Honoraria, Research Funding; Jansenn: Honoraria, Research Funding; Amgen: Honoraria, Research Funding; Takeda: Honoraria, Research Funding; EUSA Pharma: Honoraria, Research Funding. Maurer: Pfizer: Consultancy, Membership on an entity's Board of Directors or advisory committees; Celgene: Research Funding; Genentech: Research Funding; Kite Pharma: Membership on an entity's Board of Directors or advisory committees; Morphosys: Membership on an entity's Board of Directors or advisory committees, Research Funding; Nanostring: Research Funding. El-Galaly: Abbvie: Other: Speakers fee; ROCHE Ltd: Ended employment in the past 24 months. Cheah: Roche: Consultancy, Honoraria, Other: advisory and travel expenses, Research Funding; Janssen: Consultancy, Honoraria, Other: advisory; MSD: Consultancy, Honoraria, Other: advisory, Research Funding; Gilead: Consultancy, Honoraria, Other: advisory; Ascentage pharma: Consultancy, Honoraria, Other: advisory; Beigene: Consultancy, Honoraria, Other: advisory; AbbVie: Research Funding; Celgene: Research Funding; AstraZeneca: Consultancy, Honoraria, Other: advisory; Loxo/Lilly: Consultancy, Honoraria, Other: advisory; TG Therapeutics: Consultancy, Honoraria, Other: advisory.