Dataset Information

Integrative Prognostic Machine Learning Models in Mantle Cell Lymphoma.

ABSTRACT: Patients with mantle cell lymphoma (MCL), an incurable B-cell malignancy, benefit from accurate pretreatment disease stratification. We curated an extensive database of 862 patients diagnosed between 2014 and 2022. A machine learning (ML) gradient-boosted model incorporated baseline features from clinicopathologic, cytogenetic, and genomic data with high predictive power discriminating between patients with indolent or responsive MCL and those with aggressive disease (AUC ROC = 0.83). In addition, we utilized the gradient-boosted framework as a robust feature selection method for multivariate logistic and survival modeling. The best ML models incorporated features from clinical and genomic data types highlighting the need for correlative molecular studies in precision oncology. As proof of concept, we launched our most accurate and practical models using an application interface, which has potential for clinical implementation. We designated the 20-feature ML model-based index the "integrative MIPI" or iMIPI and a similar 10-feature ML index the "integrative simplified MIPI" or iMIPI-s. The top 10 baseline prognostic features represented in the iMIPI-s are: lactase dehydrogenase (LDH), Ki-67%, platelet count, bone marrow involvement percentage, hemoglobin levels, the total number of observed somatic mutations, TP53 mutational status, Eastern Cooperative Oncology Group performance level, beta-2 microglobulin, and morphology. Our findings emphasize that prognostic applications and indices should include molecular features, especially TP53 mutational status. This work demonstrates the clinical utility of complex ML models and provides further evidence for existing prognostic markers in MCL.

Significance

Our model is the first to integrate a dynamic algorithm with multiple clinical and molecular features, allowing for accurate predictions of MCL disease outcomes in a large patient cohort.

SUBMITTER: Hill HA

PROVIDER: S-EPMC10395375 | biostudies-literature | 2023 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Integrative Prognostic Machine Learning Models in Mantle Cell Lymphoma.

Hill Holly A HA Jain Preetesh P Ok Chi Young CY Sasaki Koji K Chen Han H Wang Michael L ML Chen Ken K

Cancer research communications 20230802 8

Patients with mantle cell lymphoma (MCL), an incurable B-cell malignancy, benefit from accurate pretreatment disease stratification. We curated an extensive database of 862 patients diagnosed between 2014 and 2022. A machine learning (ML) gradient-boosted model incorporated baseline features from clinicopathologic, cytogenetic, and genomic data with high predictive power discriminating between patients with indolent or responsive MCL and those with aggressive disease (AUC ROC = 0.83). In additio ...[more]

PMID: 37538987

Similar Datasets

Project description:BackgroundPatients with mantle cell lymphoma (MCL) exhibit a wide variation in clinical presentation and outcome. However, the commonly used prognostic models are outdated and inadequate to address the needs of the current multidisciplinary management of this disease. This study aims to investigate the clinical and pathological features of MCL in the immunochemotherapy era and improve the prognostic models for a more accurate prediction of patient outcomes.MethodsThe North American Mantle Cell Lymphoma Project is a multi-institutional collaboration of 23 institutions across North America to evaluate and refine prognosticators for front-line therapy. A total of 586 MCL cases diagnosed between 2000 and 2012 are included in this study. A comprehensive retrospective analysis was performed on the clinicopathological features, treatment approaches, and outcomes of these cases. The establishment of novel prognostic models was based on in-depth examination of baseline parameters, and subsequent validation in an independent cohort of MCL cases.ResultsIn front-line strategies, the use of hematopoietic stem cell transplantation was the most significant parameter affecting outcomes, for both overall survival (OS, p < 0.0001) and progression-free survival (PFS, p < 0.0001). P53 positive expression was the most significant pathological parameter correlating with inferior outcomes (p < 0.0001 for OS and p = 0.0021 for PFS). Based on the baseline risk factor profile, we developed a set of prognostic models incorporating clinical, laboratory, and pathological parameters that are specifically tailored for various applications. These models, when tested in the validation cohort, exhibited strong predictive power for survival and showed a stratification resembling the training cohort.ConclusionsThe outcome of patients with MCL has markedly improved over the past two decades, and further enhancement is anticipated with the evolution of clinical management. The innovative prognostic models developed in this study would serve as a valuable tool to guide the selection of more suitable treatment strategies for patients with MCL.

Project description:BackgroundThe prognostic index of natural killer lymphoma (PINK) is recommended for use as a prognostic model for determining the best non-anthracycline-based treatment for extranodal natural killer T-cell lymphoma, nasal-type (ENKTL). However, this model does not provide an accurate individual risk estimation for patients; therefore, our retrospective study was conducted to determine this risk.MethodsClinical data from 250 patients with ENKTL treated with non-anthracycline-based regimens were analyzed. The statistically significant clinical characteristics were selected as the parameters for our models. The patient data from 250 patients were randomly divided into 5 groups for 5-fold cross validation before final models were established on all of the patients' data. A statistical model nomogram based on a Cox proportional hazards model, and a machine learning model based on the lightGBM algorithm, were constructed. Concordance index (C-index) and calibration curve, areas under the curve (AUC) values, and binary error were used to evaluate two models.ResultsFive variables [age, the Chinese Southwest Oncology Group and Asia Lymphoma Study Group ENKTL (CA) staging system, Eastern Cooperative Oncology Group (ECOG) score, B symptoms, and lactate dehydrogenase (LDH)] were significant and were selected as parameters for creating the statistical model nomogram, while lesion sites (anatomical regions, lymph nodes and primary lesion site) took place of CA staging system in machine learning model. During cross validation, the mean C-indices of training cohort and validation cohort for statistical model nomogram and PINK were 0.851±0.008, 0.843±0.029, 0.758±0.019 and 0.757±0.080, respectively, while the mean 3-year AUC for machine learning model were 0.920±0.010 and 0.865±0.035, respectively. The calibration curves and binary errors showed a good correlation between the predicted result and the reality.ConclusionsThese two models could provide ENKTL patients with an accurate individual risk estimation in the era of non-anthracycline-based treatment.

Dataset Information

Integrative Prognostic Machine Learning Models in Mantle Cell Lymphoma.

Significance

Publications

Integrative Prognostic Machine Learning Models in Mantle Cell Lymphoma.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets