Staging System to Predict the Risk of Relapse in Multiple Myeloma Patients Undergoing Autologous Stem Cell Transplantation

A machine learning tool for the diagnosis of SARS-CoV-2 infection from hemogram parameters

Monocytes and neutrophils play key roles in the cytokine storm triggered by SARS-CoV-2 infection, which changes their conformation and function. These changes are detectable at the cellular and molecular level and may be different to what is observed in other respiratory infections. Here, we applied machine learning (ML) to develop and validate an algorithm to diagnose COVID-19 using blood parameters. In this retrospective single-center study, 49 hemogram parameters from 12,321 patients with clinical suspicion of COVID-19 and tested by RT-PCR (4239 positive and 8082 negative) were analysed. The dataset was randomly divided into training and validation sets. Blood cell parameters and patient age were used to construct the predictive model with the support vector machine (SVM) tool. The model constructed from the training set (5936 patients) achieved an accuracy for diagnosis of SARS-CoV-2 infection of 0.952 (95% CI: 0.875-0.892). Test sensitivity and specificity was 0.868 and 0.899, respectively, with a positive (PPV) and negative (NPV) predictive value of 0.896 and 0.872, respectively (prevalence 0.50). The validation set model (4964 patients) achieved an accuracy of 0.894 (95% CI: 0.883-0.903). Test sensitivity and specificity was 0.8922 and 0.8951, respectively, with a positive (PPV) and negative (NPV) predictive value of 0.817 and 0.94, respectively (prevalence 0.34). The area under the receiver operating characteristic curve was 0.952 for the algorithm performance. This algorithm may allow to rule out COVID-19 diagnosis with 94% of probability. This represents a great advance for early diagnostic orientation and guiding clinical decisions.

Transient Daratumumab-Induced Refractive Shift in Multidrug-Resistant Multiple Myeloma: Case Report and Literature Review

Daratumumab, an anti-CD38 monoclonal antibody, is worldwide approved for treatment of newly diagnosed and relapsed/refractory multiple myeloma (MM) patients and is available as intravenous or subcutaneous formulations. Intravenous daratumumab is associated with frequent infusion-related reactions, while eye complications, especially refractive shifts, are very rare, with only previously reported cases. Here, we described a rare case of multi-refractory MM who developed transient myopic shift during intravenous daratumumab infusion successfully treated only with cycloplegic collyrium not requiring infusion rate lowering or drug discontinuation. This conservative therapeutic approach allowed termination of induction therapy and autologous hematopoietic stem-cell transplantation resulting in durable complete remission.

Dry eye syndrome: comprehensive etiologies and recent clinical trials

Dry eye syndrome (DES) is multifactorial and likely to be a cause of concern more so than ever given the rapid pace of modernization, which is directly associated with many of the extrinsic causative factors. Additionally, recent studies have also postulated novel etiologies that may provide the basis for alternative treatment methods clinically. Such insights are especially important given that current approaches to tackle DES remains suboptimal. This review will primarily cover a comprehensive list of causes that lead to DES, summarize all the upcoming and ongoing clinical trials that focuses on treating this disease as well as discuss future potential treatments that can improve inclusivity.

A systematic review of the predicted outcomes related to hematopoietic stem cell transplantation: focus on applied machine learning methods' performance

INTRODUCTION

: Hematopoietic stem cell transplantation (HSCT) is a critical therapeutic procedure in blood diseases, and the investigation of HSCT data can provide valuable information. Machine learning (ML) techniques are novel and useful data analysis tools that have been applied in many studies to predict HSCT survival and estimate the risk of transplantation.

AREAS COVERED

: A systematic review was performed with a search of PubMed, Science Direct, Embase, Scopus, and the European Society for Blood and Marrow Transplantation, the Center for International Blood and Marrow Transplant Research, and the American Society for Transplantation and Cellular Therapy publications for articles published by September 2020.

EXPERT OPINION

: After investigating the results, 24 papers that met eligibility criteria were included in this study. The applied ML algorithms with the highest performance were Random Survival Forests (AUC=0.72) for survival-related, Random Survival Forests and Logistic Regression (AUC=0.77) for mortality-related, Deep Learning (AUC=0.8) for relapse, L2-Regularized Logistic Regression (AUC=0.66) for Acute-Graft Versus Host Disease, Random Survival Forests (AUC=0.88) for sepsis, Elastic-Net Regression (AUC=0.89) for cognitive impairment, and Bayesian Network (AUC=0.997) for oral mucositis outcome. This review reveals the potential of ML techniques to predict HSCT outcomes and apply them to developing clinical decision support systems.

Clinical evaluation of a phantom-based deep convolutional neural network for whole-body-low-dose and ultra-low-dose CT skeletal surveys

OBJECTIVE

This study evaluated the clinical utility of a phantom-based convolutional neural network noise reduction framework for whole-body-low-dose CT skeletal surveys.

MATERIALS AND METHODS

The CT exams of ten patients with multiple myeloma were retrospectively analyzed. Exams were acquired with routine whole-body-low-dose CT protocol and projection noise insertion was used to simulate 25% dose exams. Images were reconstructed with either iterative reconstruction or filtered back projection with convolutional neural network post-processing. Diagnostic quality and structure visualization were blindly rated (subjective scale ranging from 0 [poor] to 100 [excellent]) by three musculoskeletal radiologists for iterative reconstruction and convolutional neural network images at routine whole-body-low-dose and 25% dose CT.

RESULTS

For the diagnostic quality rating, the convolutional neural network outscored iterative reconstruction at routine whole-body-low-dose CT (convolutional neural network: 95 ± 5, iterative reconstruction: 85 ± 8) and at the 25% dose level (convolutional neural network: 79 ± 10, iterative reconstruction: 22 ± 13). Convolutional neural network applied to 25% dose was rated inferior to iterative reconstruction applied to routine dose. Similar trends were observed in rating experiments focusing on structure visualization.

CONCLUSION

Results indicate that the phantom-based convolutional neural network noise reduction framework can improve visualization of critical structures within CT skeletal surveys. At matched dose level, the convolutional neural network outscored iterative reconstruction for all conditions studied. The image quality improvement of convolutional neural network applied to 25% dose indicates a potential for dose reduction; however, the 75% dose reduction condition studied is not currently recommended for clinical implementation.

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

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.

MRI-Based Bone Marrow Radiomics Nomogram for Prediction of Overall Survival in Patients With Multiple Myeloma

Purpose

To develop and validate a radiomics nomogram for predicting overall survival (OS) in multiple myeloma (MM) patients.

Material and Methods

A total of 121 MM patients was enrolled and divided into training (n=84) and validation (n=37) sets. The radiomics signature was established by the selected radiomics features from lumbar MRI. The radiomics signature and clinical risk factors were integrated in multivariate Cox regression model for constructing radiomics nomogram to predict MM OS. The predictive ability and accuracy of the nomogram were evaluated by the index of concordance (C-index) and calibration curves, and compared with other four models including the clinical model, radiomics signature model, the Durie-Salmon staging system (D-S) and the International Staging System (ISS). The potential association between the radiomics signature and progression-free survival (PFS) was also explored.

Results

The radiomics signature, 1q21 gain, del (17p), and β2-MG≥5.5 mg/L showed significant association with MM OS. The predictive ability of radiomics nomogram was better than the clinical model, radiomics signature model, the D-S and the ISS (C-index: 0.793 vs. 0.733 vs. 0.742 vs. 0.554 vs. 0.671 in training set, and 0.812 vs. 0.799 vs.0.717 vs. 0.512 vs. 0.761 in validation set). The radiomics signature lacked the predictive ability for PFS (log-rank P=0.001 in training set and log-rank P=0.103 in validation set), whereas the 1-, 2- and 3-year PFS rates all showed significant difference between the high and low risk groups (P ≤ 0.05).

Conclusion

The MRI-based bone marrow radiomics may be an additional useful tool for MM OS prediction.

Accurate classification of plasma cell dyscrasias is achieved by combining artificial intelligence and flow cytometry

Monoclonal gammopathy of unknown significance (MGUS), smouldering multiple myeloma (SMM), and multiple myeloma (MM) are very common neoplasms. However, it is often difficult to distinguish between these entities. In the present study, we aimed to classify the most powerful markers that could improve diagnosis by multiparametric flow cytometry (MFC). The present study included 348 patients based on two independent cohorts. We first assessed how representative the data were in the discovery cohort (123 MM, 97 MGUS) and then analysed their respective plasma cell (PC) phenotype in order to obtain a set of correlations with a hypersphere visualisation. Cluster of differentiation (CD)27 and CD38 were differentially expressed in MGUS and MM (P < 0·001). We found by a gradient boosting machine method that the percentage of abnormal PCs and the ratio PC/CD117 positive precursors were the most influential parameters at diagnosis to distinguish MGUS and MM. Finally, we designed a decisional algorithm allowing a predictive classification ≥95% when PC dyscrasias were suspected, without any misclassification between MGUS and SMM. We validated this algorithm in an independent cohort of PC dyscrasias (n = 87 MM, n = 41 MGUS). This artificial intelligence model is freely available online as a diagnostic tool application website for all MFC centers worldwide (https://aihematology.shinyapps.io/PCdyscrasiasToolDg/).

Survival Outcomes of Newly Diagnosed Multiple Myeloma at a Tertiary Care Center in North India (IMAGe: 001A Study)

PURPOSE

The outcomes of patients with myeloma from developing countries are often lacking because of poor record maintenance. Publications from such settings are also limited because of the retrospective nature of the data collection. Information technology can bridge these gaps in developing countries with real-time data maintenance. We present the real-time survival data of the patients with myeloma from a tertiary care center in North India using one such indigenously built software.

PATIENTS AND METHODS

These are real-time data of all patients with myeloma presenting to a tertiary care center from North India. The patient characteristics (demographics, baseline disease characteristics, risk stratification, and outcomes) were recorded contemporaneously. The survival of the study population was analyzed and grouped based on various disease characteristics at diagnosis.

RESULTS

The median age of the study population (N = 696) was 65.9 (34.9-94.9) years with male predominance (65%). The median follow-up was 3.7 years (0-18.6 years) with the median overall survival (OS) not achieved. The OS of the study population at 1, 3, and 5 years was 94% (n = 558), 87.5% (n = 394), and 83.1% (n = 267), respectively. Most of the patients presented in advanced stages based on International Staging System (III:70%). On Kaplan-Meier analysis, the presence of weight loss (P = .01), renal dysfunction (P = .047), and anemia at diagnosis (P = .004) had a significant impact on survival. On Cox proportional model univariate analysis, the presence of renal dysfunction, anemia, and weight loss had the significant hazard ratio of 1.68 (1-2.82, P = .049), 3.18 (1.39-7.29, P = .0063), and 2.81 (1.22-6.42, P = .014), respectively, whereas on multivariate analysis of hypercalcemia, renal disease, anemia, and bone disease (CRAB) features, only anemia was found to have a significant hazard ratio of 2.56 (1.01-6.47, P = .046).

CONCLUSION

The real-world data show OS comparable with the published western literature. Only anemia was found to have significant impact on survival. The use of such software can aid in better data-keeping in resource-constrained settings.

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

•

An AI-enabled risk staging method, MRS, is developed using easy-to-acquire parameters.

•

Genomic tests cannot be performed owing to economical or geographical constraints.

•

MRS does not use cytogenetic abnormalities for risk stage prediction unlike RISS.

•

K-adaptive partitioning (KAP) used to find new thresholds for the parameters.

Introduction

: An efficient readily employable risk prognostication method is desirable for MM in settings where genomics tests cannot be performed owing to geographical/economical constraints. In this work, a new Modified Risk Staging (MRS) has been proposed for newly diagnosed Multiple Myeloma (NDMM) that exploits six easy-to-acquire clinical parameters i.e. age, albumin, β2-microglobulin (β2M), calcium, estimated glomerular filtration rate (eGFR) and hemoglobin.

Materials and Methods

: MRS was designed using a training cohort of 716 NDMM patients of our inhouse MM Indian (MMIn) cohort and validated on MMIn (n=354) cohort and MMRF (n=900) cohort. K-adaptive partitioning (KAP) was used to find new thresholds for the parameters. Risk staging rules, obtained via training a J48 classifier, were used to build MRS.

Results

: New thresholds were identified for albumin (3.6 g/dL), β2M (4.8 mg/L), calcium (11.13 mg/dL), eGFR (48.1 mL/min), and hemoglobin (12.3 g/dL) using KAP on the MMIn dataset. On the MMIn dataset, MRS outperformed ISS for OS prediction in terms of C-index, hazard ratios, and its corresponding p-values, but performs comparable in prediction of PFS. On both MMIn and MMRF datasets, MRS performed better than RISS in terms of C-index and p-values. A simple online tool was also designed to allow automated calculation of MRS based on the values of the parameters.

Discussion

: Our proposed ML-derived yet simple staging system, MRS, although does not employ genetic features, outperforms RISS as confirmed by better separability in KM survival curves and higher values of C-index on both MMIn and MMRF datasets.

Funding

: Grant: BT/MED/30/SP11006/2015 (Department of Biotechnology, Govt. of India), Grant: DST/ICPS/CPS-Individual/2018/279(G) (Department of Science and Technology, Govt. of India), UGC-Senior Research Fellowship.

Evaluation of Prognostic Significance of the International Staging System According to Glomerular Filtration Rate in Newly Diagnosed Multiple Myeloma Patients Eligible for Autologous Stem Cell Transplantation

Objective

The prognosis of multiple myeloma (MM) patients is highly heterogeneous. The aim of this study is to determine the impact of patients’ renal functions on the prognostic performance of the International Staging System (ISS). In addition, we aimed to evaluate the results of survival of patients with ISS stages and normal renal functions and those with ISS stages and abnormal renal functions with this study.

Materials and Methods

Two hundred and four patients with newly diagnosed MM who received an autologous stem cell transplantation after induction chemotherapy in our tertiary care center between the years of 2001 and 2018 were evaluated.

Results

There were 153 (75%) MM patients who had a glomerular filtration rate (GFR) of ≥60 mL/min and 51 (25%) MM patients who had GFR of <60 mL/min at the time of diagnosis in this study. There was a strong correlation between ISS stage and GFR. The ISS stages were higher in patients who had GFR of <60 mL/min than patients who had GFR of ≥60 mL/min (p<0.001). Patients with GFR of <60 mL/min were significantly more prevalent in the ISS III group than ISS I and II (p<0.001).

Conclusion

This study showed that the ISS provides significant prognostic information in MM patients with GFR of ≥60 mL/min at diagnosis. However, in patients with impaired renal function at the time of diagnosis, B2-microglobulin may not be a good prognostic indicator since it may be affected by renal dysfunction as well as tumor burden.

Artificial Intelligence in Hematology: Current Challenges and Opportunities

PURPOSE OF REVIEW

Artificial intelligence (AI), and in particular its subcategory machine learning, is finding an increasing number of applications in medicine, driven in large part by an abundance of data and powerful, accessible tools that have made AI accessible to a larger circle of investigators.

RECENT FINDINGS

AI has been employed in the analysis of hematopathological, radiographic, laboratory, genomic, pharmacological, and chemical data to better inform diagnosis, prognosis, treatment planning, and foundational knowledge related to benign and malignant hematology. As more widespread implementation of clinical AI nears, attention has also turned to the effects this will have on other areas in medicine. AI offers many promising tools to clinicians broadly, and specifically in the practice of hematology. Ongoing research into its various applications will likely result in an increasing utilization of AI by a broader swath of clinicians.

A Systematic Review of Machine Learning Techniques in Hematopoietic Stem Cell Transplantation (HSCT)

Machine learning techniques are widely used nowadays in the healthcare domain for the diagnosis, prognosis, and treatment of diseases. These techniques have applications in the field of hematopoietic cell transplantation (HCT), which is a potentially curative therapy for hematological malignancies. Herein, a systematic review of the application of machine learning (ML) techniques in the HCT setting was conducted. We examined the type of data streams included, specific ML techniques used, and type of clinical outcomes measured. A systematic review of English articles using PubMed, Scopus, Web of Science, and IEEE Xplore databases was performed. Search terms included "hematopoietic cell transplantation (HCT)," "autologous HCT," "allogeneic HCT," "machine learning," and "artificial intelligence." Only full-text studies reported between January 2015 and July 2020 were included. Data were extracted by two authors using predefined data fields. Following PRISMA guidelines, a total of 242 studies were identified, of which 27 studies met the inclusion criteria. These studies were sub-categorized into three broad topics and the type of ML techniques used included ensemble learning (63%), regression (44%), Bayesian learning (30%), and support vector machine (30%). The majority of studies examined models to predict HCT outcomes (e.g., survival, relapse, graft-versus-host disease). Clinical and genetic data were the most commonly used predictors in the modeling process. Overall, this review provided a systematic review of ML techniques applied in the context of HCT. The evidence is not sufficiently robust to determine the optimal ML technique to use in the HCT setting and/or what minimal data variables are required.

Machine learning in haematological malignancies

Machine learning is a branch of computer science and statistics that generates predictive or descriptive models by learning from training data rather than by being rigidly programmed. It has attracted substantial attention for its many applications in medicine, both as a catalyst for research and as a means of improving clinical care across the cycle of diagnosis, prognosis, and treatment of disease. These applications include the management of haematological malignancy, in which machine learning has created inroads in pathology, radiology, genomics, and the analysis of electronic health record data. As computational power becomes cheaper and the tools for implementing machine learning become increasingly democratised, it is likely to become increasingly integrated into the research and practice landscape of haematology. As such, machine learning merits understanding and attention from researchers and clinicians alike. This narrative Review describes important concepts in machine learning for unfamiliar readers, details machine learning's current applications in haematological malignancy, and summarises important concepts for clinicians to be aware of when appraising research that uses machine learning.