AI-supported modified risk staging for multiple myeloma cancer useful in real-world scenario

The role of staging in multiple myeloma

INTRODUCTION

The importance of cancer staging is determined by how accurately it can predict prognosis, and how useful it is for treatment decisions. Compared to other malignancies, multiple myeloma (MM) staging proved more challenging because of unreliable prognostic factors and wide-ranging life expectancy. As traditional MM staging continues to evolve, it requires reassessment of its prognostic and predictive value.

AREAS COVERED

The studies that included prognostic and predictive value of MM stages from 1975 through 2023 were selected for this review using PubMed, MEDLINE platforms. The history and evolution of MM staging are revisited, including its role in predicting survival, treatment planning and potential practical implications for the future. The role of MM staging for oncological practice and patient counseling is discussed.

EXPERT OPINION

The utility of the traditional MM staging remains unsatisfactory because it lacks a strong connection with the disease biology, prognosis or treatment planning. Additionally, it demonstrates a modest value for patient counseling because individual prognosis is subject to under- or overestimation, and the median survival or survival rates are difficult concepts to grasp. Although the role of MM stages may change in the future, the current research upholds the notion that MM staging benefits more medical research and clinical trials than oncological practice.

Chromothripsis detection with multiple myeloma patients based on deep graph learning

MOTIVATION

Chromothripsis, associated with poor clinical outcomes, is prognostically vital in multiple myeloma. The catastrophic event is reported to be detectable prior to the progression of multiple myeloma. As a result, chromothripsis detection can contribute to risk estimation and early treatment guidelines for multiple myeloma patients. However, manual diagnosis remains the gold standard approach to detect chromothripsis events with the whole-genome sequencing technology to retrieve both copy number variation (CNV) and structural variation data. Meanwhile, CNV data are much easier to obtain than structural variation data. Hence, in order to reduce the reliance on human experts' efforts and structural variation data extraction, it is necessary to establish a reliable and accurate chromothripsis detection method based on CNV data.

RESULTS

To address those issues, we propose a method to detect chromothripsis solely based on CNV data. With the help of structure learning, the intrinsic relationship-directed acyclic graph of CNV features is inferred to derive a CNV embedding graph (i.e. CNV-DAG). Subsequently, a neural network based on Graph Transformer, local feature extraction, and non-linear feature interaction, is proposed with the embedding graph as the input to distinguish whether the chromothripsis event occurs. Ablation experiments, clustering, and feature importance analysis are also conducted to enable the proposed model to be explained by capturing mechanistic insights.

AVAILABILITY AND IMPLEMENTATION

The source code and data are freely available at https://github.com/luvyfdawnYu/CNV_chromothripsis.

Graded Depth of Response and Neoplastic Plasma Cell Index as Indicators of Survival Outcomes in Patients With Multiple Myeloma Following Autologous Stem Cell Transplant

OBJECTIVES

With a substantial number of patients with multiple myeloma (MM) experiencing disease relapse, the quest for more sensitive methods to assess deeper responses indicative of cure continues.

METHODS

In this prospective analysis of 170 patients with MM at day 100 after autologous stem cell transplant, we evaluated the predictive value of conventional response, measurable residual disease (MRDTOTAL: the aberrant percentage of plasma cells [PC%] among total bone marrow cells), and neoplastic plasma cell index scores (NPCI: the aberrant PC% of total PCs).

RESULTS

Significantly better progression-free survival (PFS) and overall survival (OS) were observed with deepening conventional response. Conventional response-based stratification within the MRD-positive and MRD-negative subgroups showed a significantly higher PFS (hazard ratio [HR], 3.11; P < .005) and OS (HR, 3.08; P = .01) in the conventional response-positive/MRD-positive group compared with the conventional response-negative/MRD-positive group. Using K-adaptive partitioning to find the optimum threshold for MRD, patients achieving less than 0.001% MRDTOTAL had superior PFS (MRDTOTAL 0.001% to <0.1%: HR, 6.66, P < .005; MRDTOTAL ≥0.1%: HR, 11.52, P < .005) and OS (MRDTOTAL 0.001% to <0.1%: HR, 5.3, P < .05; MRDTOTAL ≥0.1%: HR = 9.21, P < .005). The C index and Akaike information criterion metrics demonstrated the superior performance of the NPCI compared with MRDTOTAL in predicting treatment outcome.

CONCLUSIONS

Progressive deepening of response, conventional as well as MRD, correlates with superior survival outcomes. The NPCI proved to be a superior determinant of survival and can be explored as a better statistic than MRD.

C-NMC: B-lineage acute lymphoblastic leukaemia: A blood cancer dataset

Development of computer-aided cancer diagnostic tools is an active research area owing to the advancements in deep-learning domain. Such technological solutions provide affordable and easily deployable diagnostic tools. Leukaemia, or blood cancer, is one of the leading cancers causing more than 0.3 million deaths every year. In order to aid the development of such an AI-enabled tool, we collected and curated a microscopic image dataset, namely C-NMC, of more than 15000 cancer cell images at a very high resolution of B-Lineage Acute Lymphoblastic Leukaemia (B-ALL). The dataset is prepared at the subject-level and contains images of both healthy and cancer patients. So far, this is the largest (as well as curated) dataset on B-ALL cancer in the public domain. C-NMC is available at The Cancer Imaging Archive (TCIA), USA and can be helpful for the research community worldwide for the development of B-ALL cancer diagnostic tools. This dataset was utilized in an international medical imaging challenge held at ISBI 2019 conference in Venice, Italy. In this paper, we present a detailed description and challenges of this dataset. We also present benchmarking results of all the methods applied so far on this dataset.

Machine Learning and Deep Learning Applications in Multiple Myeloma Diagnosis, Prognosis, and Treatment Selection

Simple Summary

Multiple myeloma is a malignant neoplasm of plasma cells with complex pathogenesis. With major progresses in multiple myeloma research, it is essential that we reconsider our methods for diagnosing and monitoring multiple myeloma disease. This fact needs the integration of serology, histology, radiology, and genetic data; therefore, multiple myeloma study has generated massive quantities of granular high-dimensional data exceeding human understanding. With improved computational techniques, artificial intelligence tools for data processing and analysis are becoming more and more relevant. Artificial intelligence represents a wide set of algorithms for which machine learning and deep learning are presently among the most impactful. This review focuses on artificial intelligence applications in multiple myeloma research, first illustrating machine learning and deep learning procedures and workflow, followed by how these algorithms are used for multiple myeloma diagnosis, prognosis, bone lesions identification, and evaluation of response to the treatment.

Abstract

Artificial intelligence has recently modified the panorama of oncology investigation thanks to the use of machine learning algorithms and deep learning strategies. Machine learning is a branch of artificial intelligence that involves algorithms that analyse information, learn from that information, and then employ their discoveries to make abreast choice, while deep learning is a field of machine learning basically represented by algorithms inspired by the organization and function of the brain, named artificial neural networks. In this review, we examine the possibility of the artificial intelligence applications in multiple myeloma evaluation, and we report the most significant experimentations with respect to the machine and deep learning procedures in the relevant field. Multiple myeloma is one of the most common haematological malignancies in the world, and among them, it is one of the most difficult ones to cure due to the high occurrence of relapse and chemoresistance. Machine learning- and deep learning-based studies are expected to be among the future strategies to challenge this negative-prognosis tumour via the detection of new markers for their prompt discovery and therapy selection and by a better evaluation of its relapse and survival.

A Clinical Prognostic Model Based on Machine Learning from the Fondazione Italiana Linfomi (FIL) MCL0208 Phase III Trial

Simple Summary

The interest in using Machine-Learning (ML) techniques in clinical research is growing. We applied ML to build up a novel prognostic model from patients affected with Mantle Cell Lymphoma (MCL) enrolled in a phase III open-labeled, randomized clinical trial from the Fondazione Italiana Linfomi (FIL)—MCL0208. This is the first application of ML in a prospective clinical trial on MCL lymphoma. We applied a novel ML pipeline to a large cohort of patients for which several clinical variables have been collected at baseline, and assessed their prognostic value based on overall survival. We validated it on two independent data series provided by European MCL Network. Due to its flexibility, we believe that ML would be of tremendous help in the development of a novel MCL prognostic score aimed at re-defining risk stratification.

Abstract

Background: Multicenter clinical trials are producing growing amounts of clinical data. Machine Learning (ML) might facilitate the discovery of novel tools for prognostication and disease-stratification. Taking advantage of a systematic collection of multiple variables, we developed a model derived from data collected on 300 patients with mantle cell lymphoma (MCL) from the Fondazione Italiana Linfomi-MCL0208 phase III trial (NCT02354313). Methods: We developed a score with a clustering algorithm applied to clinical variables. The candidate score was correlated to overall survival (OS) and validated in two independent data series from the European MCL Network (NCT00209222, NCT00209209); Results: Three groups of patients were significantly discriminated: Low, Intermediate (Int), and High risk (High). Seven discriminants were identified by a feature reduction approach: albumin, Ki-67, lactate dehydrogenase, lymphocytes, platelets, bone marrow infiltration, and B-symptoms. Accordingly, patients in the Int and High groups had shorter OS rates than those in the Low and Int groups, respectively (Int→Low, HR: 3.1, 95% CI: 1.0–9.6; High→Int, HR: 2.3, 95% CI: 1.5–4.7). Based on the 7 markers, we defined the engineered MCL international prognostic index (eMIPI), which was validated and confirmed in two independent cohorts; Conclusions: We developed and validated a ML-based prognostic model for MCL. Even when currently limited to baseline predictors, our approach has high scalability potential.

Does Ethnicity Matter in Multiple Myeloma Risk Prediction in the Era of Genomics and Novel Agents? Evidence From Real-World Data

Introduction

Current risk predictors of multiple myeloma do not integrate ethnicity-specific information. However, the impact of ethnicity on disease biology cannot be overlooked. In this study, we have investigated the impact of ethnicity in multiple myeloma risk prediction. In addition, an efficient and robust artificial intelligence (AI)-enabled risk-stratification system is developed for newly diagnosed multiple myeloma (NDMM) patients that utilizes ethnicity-specific cutoffs of key prognostic parameters.

Methods

K-adaptive partitioning is used to propose new cutoffs of parameters for two different datasets—the MMIn (MM Indian dataset) dataset and the MMRF (Multiple Myeloma Research Foundation) dataset belonging to two different ethnicities. The Consensus-based Risk-Stratification System (CRSS) is designed using the Gaussian mixture model (GMM) and agglomerative clustering. CRSS is validated via Cox hazard proportional methods, Kaplan–Meier analysis, and log-rank tests on progression-free survival (PFS) and overall survival (OS). SHAP (SHapley Additive exPlanations) is utilized to establish the biological relevance of the risk prediction by CRSS.

Results

There is a significant variation in the key prognostic parameters of the two datasets belonging to two different ethnicities. CRSS demonstrates superior performance as compared with the R-ISS in terms of C-index and hazard ratios on both the MMIn and MMRF datasets. An online calculator has been built that can predict the risk stage of a multiple myeloma (MM) patient based on the values of parameters and ethnicity.

Conclusion

Our methodology discovers changes in the cutoffs with ethnicities from the established cutoffs of prognostic features. The best predictor model for both cohorts was obtained with the new ethnicity-specific cutoffs of clinical parameters. Our study also revealed the efficacy of AI in building a deployable risk prediction system for MM. In the future, it is suggested to use the CRSS risk calculator on a large dataset as the cohort size of the present study is 25% of the cohort used in the R-ISS reported in 2015.

Branching clonal evolution patterns predominate mutational landscape in multiple myeloma

Multiple Myeloma (MM) arises from malignant transformation and deregulated proliferation of clonal plasma cells (PCs) harbouring heterogeneous molecular anomalies. The effect of evolving mutations on clone fitness and their cellular prevalence shapes the progressing myeloma genome and impacts clinical outcomes. Although clonal heterogeneity in MM is well established, which subclonal mutations emerge/persist/perish with progression in MM and which of these can be targeted therapeutically remains an open question. In line with this, we have sequenced pairwise whole exomes of 62 MM patients collected at two time points, i.e., at diagnosis and on progression. Somatic variants were called using a novel ensemble approach where a consensus was deduced from four variant callers (Illumina's Dragen, Strelka2, SomaticSniper and SpeedSeq) and actionable/druggable gene targets were identified. A marked intraclonal heterogeneity was observed. Branching evolution was observed among 72.58% patients, of whom 64.51% had low TMBs (<10) and 61.29% had 2 or more founder clones. The hypermutator patients (with high TMB levels ≥10 to ≤100) showed a significant decrease in their TMBs from diagnosis (median TMB 77.11) to progression (median TMB 31.22). A distinct temporal fall in subclonal driver mutations was identified recurrently across diagnosis to progression e.g., in PABPC1, BRAF, KRAS, CR1, DIS3 and ATM genes in 3 or more patients suggesting such patients could be treated early with target specific drugs like Vemurafenib/Cobimetinib. An analogous rise in driver mutations was observed in KMT2C, FOXD4L1, SP140, NRAS and other genes. A few drivers such as FAT4, IGLL5 and CDKN1A retained consistent distribution patterns at two time points. These findings are clinically relevant and point at consideration of evaluating multi time point subclonal mutational landscapes for designing better risk stratification strategies and tailoring time to time risk adapted combination therapies in future.