Remaining challenges in predicting patient outcomes for diffuse large B-cell lymphoma

Validation of prognostic models in elderly patients with diffuse large B-cell lymphoma in a real-world nationwide population-based study - development of a clinical nomogram

The International Prognostic Index (IPI) is the most frequently used tool for prognostication in patients with newly diagnosed diffuse large B-cell lymphoma (DLBCL) of all ages. This study validated and compared six models developed for patients above 60 with International Prognostic Indices (IPI, R-IPI, NCCN-IPI). Moreover, we created a clinical nomogram with an online tool for individualized predictions. A total of 2,835 patients aged over 60 with newly diagnosed DLBCL treated with potentially curative immunochemotherapy were identified in the Danish Lymphoma Registry. A nomogram was developed by combining NCCN-IPI variables (excluding extranodal localization), albumin, and platelet levels in 1,970 patients and verified the results in the remaining 956 patients. Compared to other models, the elderly IPI (E-IPI) and age-adjusted IPI (aaIPI) showed better accuracy and discriminatory ability. However, the models failed to identify a high-risk group with a 3-year overall survival rate below 40%. Our nomogram-based model demonstrated superior discriminatory ability and provided more precise individual predictions than all other models based on a risk stratification system. Most clinical prognostic models fail to accurately predict patient outcomes in patients over 60 years old. Therefore, nomogram-based models should be considered in this population to prevent information loss due to variable dichotomization.

Smart variant filtering - A blueprint solution for massively parallel sequencing-based variant analysis

Massively parallel sequencing helps create new knowledge on genes, variants and their association with disease phenotype. This important technological advancement simultaneously makes clinical decision making, using genomic information for cancer patients, more complex. Currently, identifying actionable pathogenic variants with diagnostic, prognostic, or predictive impact requires substantial manual effort. Objective: The purpose is to design a solution for clinical diagnostics of lymphoma, specifically for systematic variant filtering and interpretation. Methods: A scoping review and demonstrations from specialists serve as a basis for a blueprint of a solution for massively parallel sequencing-based genetic diagnostics. Results: The solution uses machine learning methods to facilitate decision making in the diagnostic process. A validation round of interviews with specialists consolidated the blueprint and anchored it across all relevant expert disciplines. The scoping review identified four components of variant filtering solutions: algorithms and Artificial Intelligence (AI) applications, software, bioinformatics pipelines and variant filtering strategies. The blueprint describes the input, the AI model and the interface for dynamic browsing. Conclusion: An AI-augmented system is designed for predicting pathogenic variants. While such a system can be used to classify identified variants, diagnosticians should still evaluate the classification's accuracy, make corrections when necessary, and ultimately decide which variants are truly pathogenic.

Revisiting beta-2 microglobulin as a prognostic marker in diffuse large B-cell lymphoma

BACKGROUND

Several clinical prognostic models for diffuse large B-cell lymphoma (DLBCL) have been proposed, including the most commonly used International Prognostic Index (IPI), the National Comprehensive Cancer Network IPI (NCCN-IPI), and models incorporating beta-2 microglobulin (β2M). However, the role of β2M in DLBCL patients is not fully understood.

METHODS

We identified 6075 patients with newly diagnosed DLBCL treated with immunochemotherapy registered in the Danish Lymphoma Registry.

RESULTS

A total of 3232 patients had data available to calculate risk scores from each of the nine considered risk models for DLBCL, including a model developed from our population. Three of four models with β2M and NCCN-IPI performed better than the International Prognostic Indexes (IPI, age-adjusted IPI, and revised IPI). Five-year overall survival for high- and low-risk patients were 43.6% and 86.4% for IPI and 34.9% and 96.2% for NCCN-IPI. In univariate analysis, higher levels of β2M were associated with inferior survival, higher tumor burden (advanced clinical stage and bulky disease), previous malignancy and increased age, and creatinine levels. Furthermore, we developed a model (β2M-NCCN-IPI) by adding β2M to NCCN-IPI (c-index 0.708) with improved discriminatory ability compared to NCCN-IPI (c-index 0.698, p < 0.05) and 5-year OS of 33.1%, 56.2%, 82.4%, and 96.4% in the high, high-intermediate, low-intermediate and low-risk group, respectively.

CONCLUSION

International Prognostic Indices, except for NCCN-IPI, fail to accurately discriminate risk groups in the rituximab era. β2M, a readily available marker, could improve the discriminatory performance of NCCN-IPI and should be re-evaluated in the development setting of future models for DLBCL.

Should we use nomograms for risk predictions in diffuse large B cell lymphoma patients? A systematic review

Models based on risk stratification are increasingly reported for Diffuse large B cell lymphoma (DLBCL). Due to a rising interest in nomograms for cancer patients, we aimed to review and critically appraise prognostic models based on nomograms in DLBCL patients. A literature search in PubMed/Embase identified 59 articles that proposed prognostic models for DLBCL by combining parameters of interest (e.g., clinical, laboratory, immunohistochemical, and genetic) between January 2000 and 2024. Of them, 40 studies proposed different gene expression signatures and incorporated them into nomogram-based prognostic models. Although most studies assessed discrimination and calibration when developing the model, many lacked external validation. Current nomogram-based models for DLBCL are mainly developed from publicly available databases, lack external validation, and have no applicability in clinical practice. However, they may be helpful in individual patient counseling, although careful considerations should be made regarding model development due to possible limitations when choosing nomograms for prognostication.

Challenges identifying DLBCL patients with poor outcomes to upfront chemoimmunotherapy and its impact on frontline clinical trials

Diffuse large B cell lymphoma (DLBCL) has a variable course of disease among patients as it consists of subgroups that are clinically, biologically and molecularly heterogeneous. In this review, we will discuss how this heterogeneity has likely hindered the ability of traditional prognostic models to identify DLBCL patients at high risk of having poor outcomes with conventional upfront chemoimmunotherapy. We will highlight the challenges and downsides of using these models for risk stratification in clinical trials. Also, we present some of the novel prognosticators that have shown a prognostic value independently or when incorporated into existing prognostic models. Additionally, since the failure of frontline clinical trials to improve outcomes beyond R-CHOP chemoimmunotherapy may be at least partially explained by the restrictive eligibility criteria, risk stratification methods and the selection bias encountered due to the complexed logistics of clinical trials; we will discuss strategies to refine and modernize clinical trial design.

Plasma long non-coding RNAs as biomarkers for bone marrow infiltration and stage in diffuse large B-cell lymphoma

We aimed to evaluate the expression profiles of five circulating lncRNAs (HOTAIR, MALAT-1, XIST, SNHG15, and H19) in DLBCL patients and explore potential associations between their expression and different clinicopathological features. Diffuse large B-cell lymphoma (DLBCL), the most common non-Hodgkin lymphoma (NHL), exhibits marked genetic and clinical heterogeneity, emphasizing the need for improved tools for risk stratification. Long non-coding RNAs (lncRNAs) emerged as regulators in different cellular processes and have been linked to cancer pathogenesis. Real-time quantitative PCR (qRT-PCR) was used to evaluate lncRNA expression in the plasma of 65 newly diagnosed adult DLBCL patients and 30 age-matched controls. HOTAIR expression was significantly elevated in DLBCL patients, while SNHG15 was significantly downregulated. Interestingly, both HOTAIR and SNHG15 demonstrated robust discriminatory power between DLBCL and healthy individuals, achieving area under the curve (AUC) values of 69% and 71%, respectively. H19 expression displayed a significant association with early-stage (stage I) DLBCL. While upregulated HOTAIR was a significant independent predictor of poor prognosis, high SNHG15 expression appeared to have a protective effect on mortality rates. Our findings suggest that circulating lncRNA expression patterns are promising tools as non-invasive biomarkers for diagnosis of DLBCL. Specific lncRNAs, such as HOTAIR, SNHG15, and H19, could offer potential for disease staging and patient prognosis. Long-term follow-up studies are recommended to further elucidate the interplay between these lncRNAs and survival rates, as well as their interactions with other genetic and pathological features of DLBCL.

Application of machine learning in the management of lymphoma: Current practice and future prospects

In the past decade, digitization of medical records and multiomics data analysis in lymphoma has led to the accessibility of high-dimensional records. The digitization of medical records, the visualization of extensive volume data extracted from medical images, and the integration of multiomics methods into clinical decision-making have produced many datasets. As a promising auxiliary tool, machine learning (ML) intends to extract homologous features in large-scale data sets and encode them into various patterns to complete complicated tasks. At present, artificial intelligence and digital mining have shown promising prospects in the field of lymphoma pathological image analysis. The paradigm shift from qualitative analysis to quantitative analysis makes the pathological diagnosis more intelligent and the results more accurate and objective. ML can promote accurate lymphoma diagnosis and provide patients with prognostic information and more individualized treatment options. Based on the above, this comprehensive review of the general workflow of ML highlights recent advances in ML techniques in the diagnosis, treatment, and prognosis of lymphoma, and clarifies the boundedness and future orientation of the ML technique in the clinical practice of lymphoma.

Prognostic indices in diffuse large B-cell lymphoma: a population-based comparison and validation study of multiple models

Currently, the International Prognostic Index (IPI) is the most used and reported model for prognostication in patients with newly diagnosed diffuse large B-cell lymphoma (DLBCL). IPI-like variations have been proposed, but only a few have been validated in different populations (e.g., revised IPI (R-IPI), National Comprehensive Cancer Network IPI (NCCN-IPI)). We aimed to validate and compare different IPI-like variations to identify the model with the highest predictive accuracy for survival in newly diagnosed DLBCL patients. We included 5126 DLBCL patients treated with immunochemotherapy with available data required by 13 different prognostic models. All models could predict survival, but NCCN-IPI consistently provided high levels of accuracy. Moreover, we found similar 5-year overall survivals in the high-risk group (33.4%) compared to the original validation study of NCCN-IPI. Additionally, only one model incorporating albumin performed similarly well but did not outperform NCCN-IPI regarding discrimination (c-index 0.693). Poor fit, discrimination, and calibration were observed in models with only three risk groups and without age as a risk factor. In this extensive retrospective registry-based study comparing 13 prognostic models, we suggest that NCCN-IPI should be reported as the reference model along with IPI in newly diagnosed DLBCL patients until more accurate validated prognostic models for DLBCL become available.

Iterated cross validation method for prediction of survival in diffuse large B-cell lymphoma for small size dataset

Efforts have been made to improve the risk stratification model for patients with diffuse large B-cell lymphoma (DLBCL). This study aimed to evaluate the disease prognosis using machine learning models with iterated cross validation (CV) method. A total of 122 patients with pathologically confirmed DLBCL and receiving rituximab-containing chemotherapy were enrolled. Contributions of clinical, laboratory, and metabolic imaging parameters from fluorine-18 fluorodeoxyglucose (FDG) positron emission tomography/computed tomography (PET/CT) scans to the prognosis were evaluated using five regression models, namely logistic regression, random forest, support vector classifier (SVC), deep neural network (DNN), and fuzzy neural network models. Binary classification predictions for 3-year progression free survival (PFS) and 3-year overall survival (OS) were conducted. The 10-iterated fivefold CV with shuffling process was conducted to predict the capability of learning machines. The median PFS and OS were 41.0 and 43.6 months, respectively. Two indicators were found to be independent predictors for prognosis: international prognostic index and total metabolic tumor volume (MTVsum) from FDG PET/CT. For PFS, SVC and DNN (both with accuracy 71%) have the best predictive results, of which outperformed other algorithms. For OS, the DNN has the best predictive result (accuracy 76%). Using clinical and metabolic parameters as input variables, the machine learning methods with iterated CV method add the predictive values for PFS and OS evaluation in DLBCL patients.

The application of machine learning to imaging in hematological oncology: A scoping review

Background

Here, we conducted a scoping review to (i) establish which machine learning (ML) methods have been applied to hematological malignancy imaging; (ii) establish how ML is being applied to hematological cancer radiology; and (iii) identify addressable research gaps.

Methods

The review was conducted according to the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews guidelines. The inclusion criteria were (i) pediatric and adult patients with suspected or confirmed hematological malignancy undergoing imaging (population); (ii) any study using ML techniques to derive models using radiological images to apply to the clinical management of these patients (concept); and (iii) original research articles conducted in any setting globally (context). Quality Assessment of Diagnostic Accuracy Studies 2 criteria were used to assess diagnostic and segmentation studies, while the Newcastle-Ottawa scale was used to assess the quality of observational studies.

Results

Of 53 eligible studies, 33 applied diverse ML techniques to diagnose hematological malignancies or to differentiate them from other diseases, especially discriminating gliomas from primary central nervous system lymphomas (n=18); 11 applied ML to segmentation tasks, while 9 applied ML to prognostication or predicting therapeutic responses, especially for diffuse large B-cell lymphoma. All studies reported discrimination statistics, but no study calculated calibration statistics. Every diagnostic/segmentation study had a high risk of bias due to their case-control design; many studies failed to provide adequate details of the reference standard; and only a few studies used independent validation.

Conclusion

To deliver validated ML-based models to radiologists managing hematological malignancies, future studies should (i) adhere to standardized, high-quality reporting guidelines such as the Checklist for Artificial Intelligence in Medical Imaging; (ii) validate models in independent cohorts; (ii) standardize volume segmentation methods for segmentation tasks; (iv) establish comprehensive prospective studies that include different tumor grades, comparisons with radiologists, optimal imaging modalities, sequences, and planes; (v) include side-by-side comparisons of different methods; and (vi) include low- and middle-income countries in multicentric studies to enhance generalizability and reduce inequity.

Sequencing therapy in relapsed DLBCL

Diffuse large B-cell lymphoma (DLBCL) is the most common lymphoid malignancy worldwide, comprising approximately 30% of all lymphomas. Currently, 50% to 60% of patients diagnosed with DLBCL are alive at 5 years and cured with modern therapy, but about 10% to 15% of patients are refractory to first-line therapy, and an additional 20% to 30% relapse following a complete response. Patients who have relapses beyond 2 years may experience more favorable outcomes and have forms of DLBCL that can be distinguished biologically. Patients who experience early relapse or who have primary refractory disease (less than a complete response or relapse within 3 to 6 months of initial therapy) have worse outcomes. For decades, the standard of care treatment strategy for fit patients with relapsed DLBCL has been salvage therapy with non-cross-resistant combination chemoimmunotherapy regimens followed by high-dose chemotherapy and autologous stem cell transplantation (ASCT) as stem cell rescue for patients with chemosensitive disease. Recent data suggest that certain patients may benefit from chimeric antigen receptor T-cell therapy (CAR T) in the second-line setting. Additional novel therapies exist for patients who are ineligible, who are unable to access these therapies, or who fail ASCT and/or CAR T. Despite the advent of new therapies for DLBCL and improved outcomes, DLBCL remains a life-threatening illness. Thus, it is essential for clinicians to engage in serious illness conversations with their patients. Goals-of-care communication can be improved through skills-based training and has been demonstrated to have an impact on patient experiences.

Data-driven support to decision-making in molecular tumour boards for lymphoma: A design science approach

Background

The increasing amount of molecular data and knowledge about genomic alterations from next-generation sequencing processes together allow for a greater understanding of individual patients, thereby advancing precision medicine. Molecular tumour boards feature multidisciplinary teams of clinical experts who meet to discuss complex individual cancer cases. Preparing the meetings is a manual and time-consuming process.

Purpose

To design a clinical decision support system to improve the multimodal data interpretation in molecular tumour board meetings for lymphoma patients at Karolinska University Hospital, Stockholm, Sweden. We investigated user needs and system requirements, explored the employment of artificial intelligence, and evaluated the proposed design with primary stakeholders.

Methods

Design science methodology was used to form and evaluate the proposed artefact. Requirements elicitation was done through a scoping review followed by five semi-structured interviews. We used UML Use Case diagrams to model user interaction and UML Activity diagrams to inform the proposed flow of control in the system. Additionally, we modelled the current and future workflow for MTB meetings and its proposed machine learning pipeline. Interactive sessions with end-users validated the initial requirements based on a fictive patient scenario which helped further refine the system.

Results

The analysis showed that an interactive secure Web-based information system supporting the preparation of the meeting, multidisciplinary discussions, and clinical decision-making could address the identified requirements. Integrating artificial intelligence via continual learning and multimodal data fusion were identified as crucial elements that could provide accurate diagnosis and treatment recommendations.

Impact

Our work is of methodological importance in that using artificial intelligence for molecular tumour boards is novel. We provide a consolidated proof-of-concept system that could support the end-to-end clinical decision-making process and positively and immediately impact patients.

Conclusion

Augmenting a digital decision support system for molecular tumour boards with retrospective patient material is promising. This generates realistic and constructive material for human learning, and also digital data for continual learning by data-driven artificial intelligence approaches. The latter makes the future system adaptable to human bias, improving adequacy and decision quality over time and over tasks, while building and maintaining a digital log.

Bcl-6-dependent risk stratification by nuclear expression of Peli1 in diffuse large B-cell lymphoma

Background/Aim: Peli1 is an E3 ubiquitin ligase involving lymphomagenesis by lysine 63 ubiquitination-mediated stabilization of Bcl-6 with in diffuse large B-cell lymphoma (DLBCL). Materials and Methods: We categorized nuclear expression of Peli1 according to Bcl-6 status by immunohistochemistry in DLBCL (n=100), and analyzed clinicopathologic association with prognosis. Results: We established Bcl-6/Peli1 risk model composed of high risk (Bcl-6+/Peli1+ or Bcl-6-/Peli1-; n=64) and low risk (Bcl-6+/Peli1- or Bcl-6-/Peli1+; n=36). High risk group had more frequent non-GCB subtype (83% vs 64%; p=0.033) and Bcl-6-negativity (69% vs 28%; p<0.001) than low risk group. Univariate survival analysis for progression-free survival (PFS) and overall survival (OS) revealed Bcl-6/Peli1 risk group (p=0.026 and p=0.021) and other conventional variables including international prognostic index (IPI), stage, ECOG performance status, number of extranodal sites were significant prognostic factors, along with B symptoms for OS. In multivariate analysis for PFS, Bcl-6/Peli1 risk group (p=0.032; HR=3.29), IPI (p=0.013; HR=3.39) and ECOG PS (p=0.035; HR=3.08) were independent prognostic factors. In multivariate analysis for OS, Bcl-6/Peli1 risk group (p=0.048; HR=7.87) and IPI (p=0.001; HR=12.15) were associated with prognosis. Conclusions: DLBCL had distinctive risk groups according to pairs of nuclear Peli1 and Bcl-6 expression. These results suggest the potential role of Peli1 and Bcl-6 in risk assessment in DLBCL.

Predictive models for clinical decision making: Deep dives in practical machine learning

The deployment of machine learning for tasks relevant to complementing standard of care and advancing tools for precision health has gained much attention in the clinical community, thus meriting further investigations into its broader use. In an introduction to predictive modelling using machine learning, we conducted a review of the recent literature that explains standard taxonomies, terminology and central concepts to a broad clinical readership. Articles aimed at readers with little or no prior experience of commonly used methods or typical workflows were summarised and key references are highlighted. Continual interdisciplinary developments in data science, biostatistics and epidemiology also motivated us to further discuss emerging topics in predictive and data-driven (hypothesis-less) analytics with machine learning. Through two methodological deep dives using examples from precision psychiatry and outcome prediction after lymphoma, we highlight how the use of, for example, natural language processing can outperform established clinical risk scores and aid dynamic prediction and adaptive care strategies. Such realistic and detailed examples allow for critical analysis of the importance of new technological advances in artificial intelligence for clinical decision-making. New clinical decision support systems can assist in prevention and care by leveraging precision medicine.

Baseline Total Metabolic Tumor Volume is Prognostic for Refractoriness to Immunochemotherapy in DLBCL: Results From GOYA

INTRODUCTION

A good response to initial therapy is key to maximizing survival in patients with diffuse large B-cell lymphoma (DLBCL), but patients with chemorefractory disease and early progression have poor outcomes.

PATIENTS AND METHODS

Data from the GOYA study in patients with DLBCL who received first-line rituximab or obinutuzumab plus cyclophosphamide, doxorubicin, vincristine, and prednisone (CHOP) were analyzed. Positron emission tomography/computed tomography (PET/CT)-derived characteristics associated with total metabolic tumor volume (TMTV) and clinical risk factors for primary chemorefractory disease and disease progression within 12 months (POD12) were explored.

RESULTS

Of those patients fulfilling the criteria for analysis, 108/1126 (10%) were primary chemorefractory and 147/1106 (13%) had POD12. Primary chemorefractory and POD12 status were strongly associated with reduced overall survival. After multivariable analysis of clinical and imaging-based risk factors by backward elimination, only very high TMTV (quartile [Q] 1 vs. Q4 odds ratio [OR]: 0.45; P = .006) and serum albumin levels (low vs. normal OR of 1.86; P = .004) were associated with primary chemorefractoriness. After additionally accounting for BCL2/MYC translocation in a subset of patients, TMTV and BCL2/MYC double-hit status remained as significant predictors of primary chemorefractoriness (Q1 vs. Q4 OR: 0.32, P = .01 and double-hit vs. no-hit OR of 4.47, P = .02, respectively). Risk factors including very high TMTV, high sum of the product of the longest diameters (SPD), geographic region (Asia), short time since diagnosis, extranodal involvement and low serum albumin were retained for POD12.

CONCLUSION

PET-derived TMTV has prognostic value in identifying patients at risk of early treatment failure.

A Review of Artificial Intelligence Applications in Hematology Management: Current Practices and Future Prospects

Background

Machine learning (ML) and deep learning (DL) methods have recently garnered a great deal of attention in the field of cancer research by making a noticeable contribution to the growth of predictive medicine and modern oncological practices. Considerable focus has been particularly directed toward hematologic malignancies because of the complexity in detecting early symptoms. Many patients with blood cancer do not get properly diagnosed until their cancer has reached an advanced stage with limited treatment prospects. Hence, the state-of-the-art revolves around the latest artificial intelligence (AI) applications in hematology management.

Objective

This comprehensive review provides an in-depth analysis of the current AI practices in the field of hematology. Our objective is to explore the ML and DL applications in blood cancer research, with a special focus on the type of hematologic malignancies and the patient’s cancer stage to determine future research directions in blood cancer.

Methods

We searched a set of recognized databases (Scopus, Springer, and Web of Science) using a selected number of keywords. We included studies written in English and published between 2015 and 2021. For each study, we identified the ML and DL techniques used and highlighted the performance of each model.

Results

Using the aforementioned inclusion criteria, the search resulted in 567 papers, of which 144 were selected for review.

Conclusions

The current literature suggests that the application of AI in the field of hematology has generated impressive results in the screening, diagnosis, and treatment stages. Nevertheless, optimizing the patient’s pathway to treatment requires a prior prediction of the malignancy based on the patient’s symptoms or blood records, which is an area that has still not been properly investigated.

Value of total lesion glycolysis and cell-of-origin subtypes for prognostic stratification of diffuse large B-cell lymphoma patients

Background

This study aimed to explore the added prognostic value of baseline metabolic volumetric parameters and cell of origin subtypes to the National Comprehensive Cancer Network International Prognostic Index (NCCN-IPI) in nodal diffuse large B-cell lymphoma (DLBCL) patients.

Methods

A total of 184 consecutive de novo nodal DLBCL patients who underwent baseline positron emission tomography/computed tomography (PET/CT) were included in this study. Kaplan-Meier estimates were generated to evaluate the clinical, biological, and PET/CT parameters' prognostic value. The Cox proportional hazards model was performed to examine the potential independent predictors for progression-free survival (PFS) and overall survival (OS).

Results

With a median follow-up of 35 months, the 3-year PFS and OS were 65.2% and 73.0%, respectively. In univariate analysis, total lesion glycolysis (TLG), cell-of-origin subtypes, and NCCN-IPI were both PFS and OS predictors. High TLG (≥1,852), non-germinal center B (non-GCB), as well as high NCCN-IPI (≥4), were shown to be independently significantly associated with inferior PFS and OS after multivariate analysis. Based on the number of risk factors (high TLG, non-GCB, and high NCCN-IPI), a revised risk model was designed, and the participants were divided into four risk groups with very different outcomes, in which the PFS rates were 89.7%, 66.2%, 51.7%, and 26.7% (χ²=30.179, P<0.001), and OS rates were 93.1%, 73.8%, 56.7%, and 43.3%, respectively (χ²=23.649, P<0.001), respectively. Compared with the NCCN-IPI alone, the revised risk model showed a stronger ability to reveal further discrimination among subgroups, especially for participants with very unfavorable survival outcomes (PFS: χ²=9.963, P=0.002; OS: χ²=4.166, P=0.041, respectively).

Conclusions

The TLG, cell-of-origin subtypes, and NCCN-IPI are independent prognostic survival factors in DLBCL patients. Moreover, the revised risk model composed of the number of risk factors (high TLG, non-GCB, and high NCCN-IPI) can stratify patients better than the NCCN-IPI, especially for patients at high risk, which suggests its potential integration into decision making for personalized medicine.

Precision medicine in follicular lymphoma: Focus on predictive biomarkers

Current care for patients with follicular lymphoma (FL) offers most of them long-term survival. Improving it further will require careful patient selection. This review focuses on predictive biomarkers (ie, those whose outcome correlations depend on the treatment strategy) in FL, because awareness of what patient subsets benefit most or least from each therapy will help in this task. The first part of this review aims to summarize what biomarkers are predictive in FL, the magnitude of the effect and the quality of the evidence. We find predictive biomarkers in the setting of (a) indication of active treatment, (b) front-line induction (use of anthracyline-based regimens, CHOP vs bendamustine, addition of rituximab), (c) post-(front-line)induction (rituximab maintenance, radioimmunotherapy), and (d) relapse (hematopoietic stem cell transplant) and targeted agents. The second part of this review discusses the challenges of precision medicine in FL, including (a) cost, (b) clinical relevance considerations, and (c) difficulties over the broad implementation of biomarkers. We then provide our view on what biomarkers may become used in the next few years. We conclude by underscoring the importance of assessing the potential predictiveness of available biomarkers to improve patient care but also that there is a long road ahead before reaching their broad implementation due to remaining scientific, technological, and economic hurdles.

Statistical Challenges in Development of Prognostic Models in Diffuse Large B-Cell Lymphoma: Comparison Between Existing Models - A Systematic Review

Background and Aim

Based on advances in the diagnosis, classification, and management of diffuse large B-cell lymphoma (DLBCL), a number of new prognostic models have been proposed. The aim of this study was to review and compare different prognostic models of DLBCL based on the statistical methods used to evaluate the performance of each model, as well as to analyze the possible limitations of the methods.

Methods and Results

A literature search identified 46 articles that proposed 55 different prognostic models for DLBCL by combining different clinical, laboratory, and other parameters of prognostic significance. In addition, six studies used nomograms, which avoid risk categorization, to create prognostic models. Only a minority of studies assessed discrimination and/or calibration to compare existing models built upon different statistical methods in the process of development of a new prognostic model. All models based on nomograms reported the c-index as a measure of discrimination. There was no uniform evaluation of the performance in other prognostic models. We compared these models of DLBCL by calculating differences and ratios of 3-year overall survival probabilities between the high- and the low-risk groups. We found that the highest and lowest ratio between low- and high-risk groups was 6 and 1.31, respectively, while the difference between these groups was 18.9% and 100%, respectively. However, these studies had limited duration of follow-up and the number of patients ranged from 71 to 335.

Conclusion

There is no universal statistical instrument that could facilitate a comparison of prognostic models in DLBCL. However, when developing a prognostic model, it is recommended to report its discrimination and calibration in order to facilitate comparisons between different models. Furthermore, prognostic models based on nomograms are becoming more appealing owing to individualized disease-related risk estimations. However, they have not been validated yet in other study populations.