Diagnosis Of Myelodysplastic Syndrome Research Articles

Precision diagnosis of myelodysplastic syndromes using integrated genomic and clinical data: A machine learning approach

Precision diagnosis of myelodysplastic syndromes using integrated genomic and clinical data: A machine learning approach

Unveiling the Variances: Myelodysplastic Syndrome (MDS) Patient Admissions in Teaching vs Nonteaching Hospitals

Background We have carried out an analysis to evaluate the influence of hospital teaching status on the outcomes of individuals hospitalized with MDS. Methods The National Inpatient Sample (NIS) dataset for the years 2019-2020 was employed to identify individuals who were hospitalized with a primary diagnosis of MDS. These patients were then categorized into two groups: those who were hospitalized in teaching hospitals and those who were hospitalized in non-teaching hospitals. Multivariate regression analysis was performed to calculate the primary and secondary outcomes. Results In the years 2019 and 2020, a total of 17,000 patients were hospitalized with myelodysplastic syndromes (MDS). Among these, 24.05% (4,080) were admitted to non-teaching hospitals, while 75.94% (12,920) were admitted to teaching hospitals. Patients admitted to teaching hospitals had a higher likelihood of mortality (OR 1.84, 95% CI 1.03-3.27, P=0.037), as well as increased lengths of stay (+3.58 Days, 95% CI 2.82-4.34, P<0.001)and total hospitalization costs (+USD 66818, 95% CI 50528-83108, P<0.001). Additionally, patients in teaching hospitals had a higher incidence of acute respiratory failure (6.81% vs 4.4%), acute kidney injury (23.89% vs 17.72%), hematopoietic stem cell transplantation (14.36% vs 0.61%), and febrile neutropenia (11.03% vs 5.86%). However, patients in teaching hospitals had a lower incidence of anemia (41.86% vs 48.53%) and blood transfusions (38.8% vs 55.37%). Conclusion Individuals who were admitted to teaching hospitals with Myelodysplastic Syndromes (MDS) exhibited a notably higher mortality rate, as well as an extended length of stay and a corresponding increase in the total cost of hospitalization. Patients in teaching hospitals were also at risk for acute kidney injury, acute respiratory failure and febrile neutropenia.

Potential Diagnostic Value of Abnormal Pyroptosis Genes Expression in Myelodysplastic Syndromes (MDS): A Primary Observational Cohort Study

Background: Myelodysplastic syndromes (MDS) are determined by ineffective hematopoiesis and bone marrow cytological dysplasia with somatic gene mutations and chromosomal abnormalities. Accumulating evidence has revealed the pivotal role of NLRP3 inflammasome activation and pyroptotic cell death in the pathogenesis of MDS. Although MDS can be diagnosed with a variety of morphologic and cytogenetic tests, most of these tests have limitations or problems in practice. Materials and Methods: In the present study, we evaluated the expression of genes that form the inflammasome (NLRP3, ASC, and CASP1) in bone marrow specimens of MDS patients and compared the results with those of other leukemias to evaluate their diagnostic value for MDS. Primary samples of this observational cohort study were collected from aspiration samples of patients with myelodysplastic syndromes (27 cases) and patients with non-myelodysplastic syndrome hematological cancers (45 cases). After RNA extraction and c.DNA synthesis, candidate transcripts and housekeeping transcripts were measured by real-time PCR method (SYBER Green assay). Using Kruskal-Wallis the relative gene expressions were compared and differences with p value less than 0.05 were considered as significant. Discrimination capability, cut-off, and area under curve (AUC) of all markers were analyzed with recessive operation curve (ROC) analysis. Results:  We found that Caspase-1 and ASC genes expressed at more levels in MDS specimens compared to non-MDS hematological malignancies. A relative average expression of 10.22 with a p-value of 0.001 and 1.86 with p=0.019 was detected for Caspase-1 and ASC, respectively. ROC curve analysis shows an AUC of 0.739 with p=0.0001 for Caspase-1 and an AUC of 0.665 with p=0.0139 for ASC to MDS discrimination. Conclusion: Our results show that Caspase-1 and ASC gene expression levels can be used as potential biomarkers for MDS diagnosis. Prospective studies with large sample numbers are suggested.  

Comparison of cytomorphology and histomorphology in myelodysplastic syndromes.

Gold standard for the establishment of the diagnosis of myelodysplastic syndromes (MDS) are cytomorphological features of hematopoietic cells in peripheral blood and bone marrow aspirates. There is increasing evidence that bone marrow histomorphology not only aids in the diagnosis of MDS but can provide additional prognostic information, particularly through assessment of fibrosis and cellularity. However, there is only sparse data on direct comparison between histological and cytomorphological findings within the same MDS patient cohort. Therefore, we performed such an analysis under exceptionally well-standardized conditions. We reexamined biopsy material of 128 patients from the Düsseldorf MDS registry who underwent bone marrow trephine biopsy (in addition to bone marrow aspiration) at the time of diagnosis, addressing the following items: a. Analysis of concordance of diagnoses made by histology and cytomorphology b. Analysis of additional information by histology with regard to the diagnosis and prognosis. The respective biomaterials were available at our institution and had been processed according to unchanged protocols between 1992 and 2010. Fresh histopathological sections were obtained from the tissue blocks, stained under identical conditions and re-assessed by a designated expert pathologist (C.B.) without knowledge of the previous histopathological report or the respective cytomorphological diagnosis. The latter, likewise, was uniformly made by the same expert cytomorphologist (U.G.). Histopathology of bone marrow trephine biopsies reliably captured the diagnosis of MDS. Assignment to the diagnostic WHO subgroup was not entirely concordant with cytomorphology, mainly due to incongruences between the proportion of CD34-positive cells on histopathology and the cytomorphological blast count. Histopathology provided additional diagnostic and prognostic information with high diagnostic and prognostic significance, such as fibrosis. Likewise, histopathology allowed more reliable estimation of bone marrow cellularity.

Construction and experimental validation of a novel ferroptosis-related gene signature for myelodysplastic syndromes.

Myelodysplastic syndromes (MDS) are clonal hematopoietic disorders characterized by morphological abnormalities and peripheral blood cytopenias, carrying a risk of progression to acute myeloid leukemia. Although ferroptosis is a promising target for MDS treatment, the specific roles of ferroptosis-related genes (FRGs) in MDS diagnosis have not been elucidated. MDS-related microarray data were obtained from the Gene Expression Omnibus database. A comprehensive analysis of FRG expression levels in patients with MDS and controls was conducted, followed by the use of multiple machine learning methods to establish prediction models. The predictive ability of the optimal model was evaluated using nomogram analysis and an external data set. Functional analysis was applied to explore the underlying mechanisms. The mRNA levels of the model genes were verified in MDS clinical samples by quantitative real-time polymerase chain reaction (qRT-PCR). The extreme gradient boosting model demonstrated the best performance, leading to the identification of a panel of six signature genes: SREBF1, PTPN6, PARP9, MAP3K11, MDM4, and EZH2. Receiver operating characteristic curves indicated that the model exhibited high accuracy in predicting MDS diagnosis, with area under the curve values of 0.989 and 0.962 for the training and validation cohorts, respectively. Functional analysis revealed significant associations between these genes and the infiltrating immune cells. The expression levels of these genes were successfully verified in MDS clinical samples. Our study is the first to identify a novel model using FRGs to predict the risk of developing MDS. FRGs may be implicated in MDS pathogenesis through immune-related pathways. These findings highlight the intricate correlation between ferroptosis and MDS, offering insights that may aid in identifying potential therapeutic targets for this debilitating disorder.

A Pre-Leukemic DNA Methylation Signature in Healthy Individuals at Higher Risk for Developing Myeloid Malignancy.

DNA methylation alterations are widespread in acute myeloid leukemia (AML) and myelodysplastic syndrome (MDS), some of which appear to have evolved independently of somatic mutations in epigenetic regulators. While the presence of somatic mutations in peripheral blood can predict the risk of development of AML and MDS, its accuracy remains unsatisfactory. We performed global DNA methylation profiling in a case-control study nested within Singapore Chinese Health Study to evaluate if DNA methylation alterations were associated with AML/MDS development. Targeted deep sequencing and methylated DNA immunoprecipitation sequencing (MeDIP-seq) were performed on peripheral blood collected a median of 9.9 years prior to diagnosis of AML or MDS, together with age-matched still healthy individuals as controls. Sixty-six individuals who developed AML or MDS displayed significant DNA methylation changes in the peripheral blood compared with 167 age- and gender-matched controls who did not develop AML/MDS during the follow up period. Alterations in methylation in the differentially methylation regions (DMRs) were associated with increased odds of developing AML/MDS. The epigenetic changes may be acquired independently and prior to somatic mutations that relevant for AML/MDS development. The association between methylation changes and the risk of pre-AML/MDS in these individuals was considerably stronger than somatic mutations, suggesting that methylation changes could be used as biomarkers for pre- AML/MDS screening.

Analyzing Blood Cells of High-Risk Myelodysplastic Syndrome Patients Using Interferometric Phase Microscopy and Fluorescent Flow Cytometry.

Myelodysplastic syndromes (MDSs) are a group of potentially deadly diseases that affect the morphology and function of neutrophils. Rapid diagnosis of MDS is crucial for the initiation of treatment that can vastly improve disease outcome. In this work, we present a new approach for detecting morphological differences between neutrophils isolated from blood samples of high-risk MDS patients and blood bank donors (BBDs). Using fluorescent flow cytometry, neutrophils were stained with 2',7'-dichlorofluorescin diacetate (DCF), which reacts with reactive oxygen species (ROS), and Hoechst, which binds to DNA. We observed that BBDs possessed two cell clusters (designated H and L), whereas MDS patients possessed a single cluster (L). Later, we used FACS to sort the H and the L cells and used interferometric phase microscopy (IPM) to image the cells without utilizing cell staining. IPM images showed that H cells are characterized by low optical path delay (OPD) in the nucleus relative to the cytoplasm, especially in cell vesicles containing ROS, whereas L cells are characterized by low OPD in the cytoplasm relative to the nucleus and no ROS-containing vesicles. Moreover, L cells present a higher average OPD and dry mass compared to H cells. When examining neutrophils from MDS patients and BBDs by IPM during flow, we identified ~20% of cells as H cells in BBDs in contrast to ~4% in MDS patients. These results indicate that IPM can be utilized for the diagnosis of complex hematological pathologies such as MDS.

The Lived Experience of Seeking Pregnancy in a Woman with a History of Cancer

Myelodysplastic syndromes (MDS) are a rare form of cancer that affects the bone marrow's ability to produce mature blood cells. Several treatments are available, including chemotherapy using anticancer or cytotoxic drugs, blood or platelet transfusions, and stem cell transplants. In this study, a 33-year-old woman shares her experience of attempting to conceive while undergoing treatment for myelodysplastic syndromes. The study aimed to explore the psychosocial difficulties women with a history of cancer treatment may encounter when trying to get pregnant. Semi-structured qualitative interviews were undertaken, recorded, and transcribed verbatim. The transcript was analyzed by narrative analysis. Four themes were identified: 1) Support from loved ones, 2) Challenges in conceiving, 3) Emotional ups and downs during pregnancy, and 4) The joy of motherhood. A cancer diagnosis can devastate young women, primarily if the treatment affects their fertility. These women must have the support of their husbands. Fortunately, many methods are available to assist women in successfully conceiving, although the journey can be difficult and emotional. The ups and downs of the process are inevitable, but the desire to become a mother makes it all worth it in the end. Cancer treatment for myelodysplastic syndromes and related conditions can profoundly impact childbearing women. Such women may face significant challenges if they plan to have a child after treatment. Hence, further research with more women with the diagnosis of MDS is imperative in this critical area.

Ischemic stroke as the initial presentation in acute myeloid leukemia vs. myelodysplastic syndrome: a case report and literature review with pathophysiological and clinical exploration.

Myelodysplastic syndromes (MDS) and acute myeloid leukemia (AML) present intricate challenges due to their diverse clinical manifestations and thrombotic complications. Thromboembolism (TE) incidence in newly diagnosed AML patients is noteworthy, with arterial TE linked to poorer overall survival. Ischemic strokes, although relatively low in prevalence, carry significant clinical implications. We report the case of an 84-year-old male with Type 2 Diabetes, Hypertension, and Chronic Kidney Disease, presenting with seizures, focal neurological deficits, and pancytopenia. An unexpected diagnosis of AML or MDS emerged during the investigation. Despite interventions, the patient's condition deteriorated, leading to a fatal outcome weeks later. This case underscores the intricate relationship between hematologic malignancies and ischemic stroke. The rarity of this complication emphasizes the importance of understanding the multifaceted mechanisms at play, including hyperleukocytosis, pro-inflammatory cytokine release, coagulation cascade activation, and direct interactions with endothelial cells. In our literature review, analysis of 15 cases, including ours, revealed a wide age range (3-87 years) and a gender bias towards females. AML diagnosis was predominant, with uniformly low platelet counts. Cortical infarctions, especially in the anterior circulation, were common. Hyperleukocytosis, disseminated intravascular coagulation (DIC), and fatal outcomes were observed in a subset of cases. Despite the grim statistics and often poor prognosis, the identification of specific risk factors, such as thrombocytopenia and cytogenetic abnormalities, offers avenues for targeted prevention and management.

February 2024 Medical Image of the Month: Pulmonary Alveolar Proteinosis in Myelodysplastic Syndrome

No abstract available. Manuscript truncated after 150 words. Lymphadenopathy decreased after initiation of coccidiomycosis treatment, but symptoms and crazy paving findings continued to worsen. Further workup revealed a new diagnosis of myelodysplastic syndrome (MDS) and subsequent bronchoalveolar lavage (BAL) and histology results were consistent with secondary PAP, likely due to patient’s underlying hematologic disease. Pulmonary alveolar proteinosis (PAP) is a rare disease characterized by the accumulation of lipoproteinaceous material in the lung alveoli. There are two types of PAP that occur in adults: Idiopathic/ autoimmune and Secondary PAP. Idiopathic/autoimmune PAP is more common and is thought to result from antibody production against granulocyte-macrophage-colony-stimulating factor (GM-CSF) that regulates surfactant homeostasis. Secondary PAP results from a precipitating condition, often inhalation exposure, underlying malignancy, or immunocompromise. The clinical manifestations of PAP are nonspecific and includes dyspnea, nonproductive cough, fatigue, and weight loss. CT may show nonspecific findings of smooth, bilateral interlobular septal thickening superimposed on a background of ground-glass opacification (crazy-paving). Diagnosis is confirmed with …

Cutaneous manifestations of myelodysplastic syndrome: A systematic review.

Myelodysplastic syndrome (MDS) may present with specific skin lesions, such as leukaemia cutis, which is a well known poor prognostic marker of leukaemia with a high risk of acute leukaemic transformation. However, less is known regarding non-specific cutaneous manifestations of MDS including the prevalence, types and their prognostic and therapeutic significance, which we aimed to determine through this systematic review. We searched electronic databases (PubMed, Medline and EMBASE) from inception up to 26 January 2023 for studies reporting cutaneous manifestations of MDS. Eighty eight articles (case reports n=67, case series n=21), consisting of 134 patients were identified. We identified 6 common cutaneous manifestations: neutrophilic dermatoses (n=64), vasculitis (n=21), granulomatous (n=8), connective tissue disease (CTD) (n=7; composed of dermatomyositis (n=5), cutaneous lupus erythematosus (n=1), and systemic sclerosis (n=1)), panniculitis (n=4), immunobullous (n=1), and other (n=29). Cutaneous features either occurred at time of MDS diagnosis in 25.3%, preceding the diagnosis in 34.7% (range 0.5-216months), or after diagnosis in 40.0% (range 1-132months). Prognosis was poor (40.2% death) with 34.1% progressing to acute myeloid leukaemia (AML). 50% of those with MDS who progressed to AML had neutrophilic dermatoses (p=0.21). Myelodysplastic syndrome was fatal in 39.2% of neutrophilic dermatoses (median time from onset of cutaneous manifestation: 12months), 50% of vasculitis (7.5months), 62.5% of granulomatous (15.5months) and 14.3% of CTD (7months). Recognition of patterns of cutaneous features in MDS will improve early diagnosis and risk stratification according to subtype and associated prognosis.

Validation of a novel algorithm with a high specificity in ruling out MDS.

A previously published web-based App using Gradient-boosted models (GBMs) of eight laboratory parameters was established by Oster et al. to facilitate diagnosis or exclusion of myelodysplastic syndromes (MDS) in patients. To validate their algorithm, we compared 175 anemic patients with MDS diagnosis from our German MDS Registry with 1378 non-MDS anemic patients who consulted various specialties in the Düsseldorf university hospital. Based on hemoglobin level, leukocyte and platelet count, mean corpuscular volume, absolute neutrophil count, absolute monocyte count, glucose and creatinine, plus the patients' gender and age, we could not reproduce a high negative predictive value (NPV), but confirmed a useful specificity of 90.9% and a positive predictive value (PPV) of 77.1%. 1192 of 1378 controls were correctly categorized as "probably not MDS (pnMDS)" patients. A total of 65 patients were wrongly classified as "probable MDS (pMDS)," of whom 48 had alternative explanations for their altered laboratory results. In a second analysis, we included 29 patients with chronic myelomonocytic leukemia (CMML) resulting in only one label as possible MDS, suggesting that highly proliferative bone marrow disorders are correctly excluded. The possibility of reliably excluding MDS from differential diagnosis based on peripheral blood lab work appears to be attractive for patients and physicians alike while the confirmation of MDS diagnosis still requires a bone marrow biopsy.

Clinical Relevance of Differential RARα and PPARβ/δ Expression in Myelodysplastic Syndromes.

Myelodysplastic syndromes (MDS) are clinically heterogeneous hematological malignancies with an increased risk of transformation to acute myeloid leukemia, emphasizing the importance of identifying new diagnostic and prognostic markers. This study sought to investigate the predictive ability of all-trans retinoic acid (ATRA)-dependent nuclear transcription factors RARα and PPARβ/δ gene expression in MDS patients. Peripheral blood specimens were collected from 49 MDS patients and 15 healthy volunteers. The specimens were further separated in Ficoll density gradient to obtain the mononuclear cells fractions. Gene expression analysis was carried out using quantitative real-time polymerase chain reaction (qRT-PCR) technique. In the mononuclear cell fractions of MDS patients, RARα expression was increased (p<0.05) and PPARβ/δ expression was decreased (p<0.01) compared to healthy volunteers. When RARα and PPARβ/δ expression was compared in groups of MDS patients with different risks of disease progression, no statistically significant difference was found for RARα expression, while PPARβ/δ expression was significantly lower in the high-risk group of patients compared to the low-risk group (p<0.05). The expression of RARα was significantly associated with overall survival (p<0.05). ROC analysis showed that the expression of PPARβ/δ, rather than RARα expression, could have potential diagnostic value for MDS patients (AUC=0.75, p=0.003 and AUC=0.65, p=0.081, respectively). RARα and PPARβ/δ genes are putative biomarkers that may be associated with the diagnosis and prognosis of MDS.

Integrating AI and ML in Myelodysplastic Syndrome Diagnosis: State-of-the-Art and Future Prospects.

Myelodysplastic syndrome (MDS) is composed of diverse hematological malignancies caused by dysfunctional stem cells, leading to abnormal hematopoiesis and cytopenia. Approximately 30% of MDS cases progress to acute myeloid leukemia (AML), a more aggressive disease. Early detection is crucial to intervene before MDS progresses to AML. The current diagnostic process for MDS involves analyzing peripheral blood smear (PBS), bone marrow sample (BMS), and flow cytometry (FC) data, along with clinical patient information, which is labor-intensive and time-consuming. Recent advancements in machine learning offer an opportunity for faster, automated, and accurate diagnosis of MDS. In this review, we aim to provide an overview of the current applications of AI in the diagnosis of MDS and highlight their advantages, disadvantages, and performance metrics.

How to classify risk based on clinical and molecular modeling: integrating molecular markers in the risk assessment of myelodysplastic syndrome.

Myelodysplastic syndrome (MDS), also known as "myelodysplastic neoplasm," is a heterogeneous group of clonal myeloid neoplasms that typically affects older adults. The clinical phenotype, symptoms, and complications relate to the depth of cytopenia and progression to acute myeloid leukemia (AML). The diagnosis of MDS relies on morphologic criteria, such as evidence of dysplasia, disordered maturation, and increasing blast counts, which separate the disease into histologic subtypes with different probabilities for progression to AML. The treatment of MDS is often risk-adapted depending on the prognostic profile of each patient's disease. There has been a coevolution of diagnostic and prognostic systems for MDS developed over the past 40 years, both of which have now incorporated molecular markers. The new International Prognostic Scoring System-Molecular (IPSS-M) improves partitioning of patients compared to prior versions with resultant upgrading of 34% of patients into higher-risk groups due to the presence of mutations. The new IPSS-M also more accurately distinguishes intermediate-risk patients separating them into two tiers. The two new diagnostic classifications include MDS defined by mutations in SF3B1 and TP53, though there are differences in diagnostic criteria. Future efforts to refine MDS prognostication could investigate the interface between MDS and clonal cytopenia of undetermined significance, expand access to genomic testing, obtain results in a less invasive manner, and develop treatment-response predictors and dynamic risk models.

Diagnostic Value of CD34 and CD117 Immunohistochemistry and Megakaryocyte Morphology in Myelodysplastic Syndromes: A Retrospective Case-control Study.

This study evaluated the diagnostic value of CD34 and CD117 immunohistochemistry(IHC) and megakaryocyte morphology in Myelodysplastic syndromes (MDS). In this study, CD34-positive individual cells (Type I) and small clusters (Type II) were observed in most cases (91.2%). Type II CD34-positive was seen in 24 (49%) MDS cases, and positive percentage was higher than in acute myelogenous leukemia (AML) or aplastic anemia (AA). Type II CD117-positive were observed in 44 (89.8%) MDS cases and Type I were observed in 5 (10.2%) MDS. Type II CD117-positive percentage was higher than in AML or AA. Megakaryocyte counts were normal or increased in most MDS cases except one. Although megakaryocyte counts of AML and AA were predominantly decreased, Most MDS patients (81.6%) had abnormal megakaryocyte, whereas almost none of megakaryocyte abnormality was found in AML and AA. In conclusion, combined detection of CD34 and CD117 and observation of megakaryocyte count and morphology are useful for the diagnosis of MDS.

Abstract C032: Patterns of care and patients’ outcomes for myelodysplastic syndromes in Puerto Rico: A real-world data analysis

Abstract Background: Myelodysplastic syndromes (MDS) are a group of rare blood cancers with a wide range of clinical outcomes and a highly variable prognosis. Usually, most population-based registries do not collect cancer-related biological and genetic markers, which limits the use of population-based registries to address critical research questions. We leveraged the Puerto Rico (PR) Central Cancer Registry (PRCCR) to collect this data and analyze clinical characteristics and outcomes of patients diagnosed with MDS in PR. Methods: The study population includes patients diagnosed with MDS in PR between 2015 and 2019. Descriptive statistics and frequency analysis were used to describe the variables of interest. Logistic regression models were used to examine factors associated with the use of genetic marker tests. Bivariate analyses were performed to evaluate association between treatment patterns and patients’ characteristics. Three-year survival curves were estimated using Kaplan-Meier (with log-rank test to assess differences between survival curves). Multivariable Cox regression models were used to estimate the magnitude of association between the risk of dying among patients with MDS and different genetic markers/clinical characteristics. Results: The study cohort consisted of 475 patients. Between 67.2% and 81.7% of cases reported information of laboratory tests and prognostic markers. The abnormal karyotype had the highest presence in patients with MDS among those that reported the test with 47.4%. After adjusting for variables of interest, the risk of dying in MDS patients who did not have a del(5q) or a mutation of TP53, EZH2, or NRAS was 53%-85% lower than the risk of dying in patients who had either one of the mutations (p&amp;lt;0.05). Almost half of the MDS patients (47.4%) received treatment and of those, almost a third (29.3%) received it within the first 30 days after the diagnosis of MDS. The most common first-course treatment was azacitidine (52.0%), followed by lenalidomide (20.0%). Patients with a very low IPSS-R had a 3-year survival of 72.8% and those with a very high IPSS-R had a 3-year survival of 7.8%. Conclusion: The data from the PRCCR confirm the prognostic value of the IPSS-R and the role of the cytogenetic and molecular abnormalities on the patient’s outcomes. Citation Format: Karen J. Ortiz-Ortiz, Tonatiuh Suárez Ramos, Maira A. Castañeda-Avila, Carlos R. Torres-Cintrón, Axel Gierbolini-Bermúdez, Guillermo Tortolero-Luna. Patterns of care and patients’ outcomes for myelodysplastic syndromes in Puerto Rico: A real-world data analysis [abstract]. In: Proceedings of the 16th AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2023 Sep 29-Oct 2;Orlando, FL. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2023;32(12 Suppl):Abstract nr C032.

Integrating AI and ML in Myelodysplastic Syndrome Diagnosis: State of the Art and Future Prospects

Introduction: Myelodysplastic syndrome (MDS) is a diverse group of hematological malignancies characterized by dysfunctional pluripotent stem cells, leading to abnormal hematopoiesis and cytopenia. Early diagnosis is crucial for improving patient outcomes. Artificial Intelligence (AI) and Machine Learning (ML) have emerged as powerful tools in healthcare for disease diagnosis and monitoring. This review aims to summarize the current state of AI application in the diagnosis of MDS, discussing various ML models, their advantages, disadvantages, and performance metrics. Methods: A comprehensive search strategy was developed using Medical Subject Headings (MeSH) terms and relevant keywords related to MDS and AI/ML. Pubmed, Embase, and scopus were searched, and duplicates were removed. Only original research articles studying ML algorithms in the diagnosis of MDS in human subjects were included. Studies on animals, reviews, non-original articles, and non-English papers were excluded. For each article, data on the area under the receiver operating curve, sensitivity, specificity, and accuracy for the best preforming model were collected. Results: The search yielded 313 articles, and after screening, 16 articles met the inclusion criteria. These articles were grouped based on the data utilized in the training of their models. Five articles utilized bone marrow smears for the training of their data. Their models aimed to detect dysplastic cells and blasts in bone marrow smears. The majority of these studies utilized convolutional neural network (CNN), a ML algorithm, for image recognition. One study utilized decision tree models. The AUC of these models ranged between 0.8 and 0.996. All the models were internally validated but were not externally validates. Three studies utilized peripheral blood smears for the training of their ML models. Two of these studies also utilized CNN for the detection of dysplasia and subsequent diagnosis of MDS. One study utilized CART to create a decision tree algorithm. The AUC for these models ranged between 0.982-0.99. Four studies utilized flowcytometry data from bone marrow samples for the training of their AI models. These models achieved AUC ranging between 0.935-0.97. Two of these models were both internally and externally validated, one of which was on a prospective cohort. Conclusion: The integration of AI and ML in MDS diagnosis holds promise for early detection and improved patient care. The reviewed studies showed encouraging results, indicating that AI-based approaches can complement traditional diagnostic methods and aid in making more informed clinical decisions especially when it comes to analysing blood/bone smears. However, many of these models need to be externally validated in large prospective cohorts to establish AI's role in routine clinical practice.

Metabolic Syndrome Among Patients with Myelodysplastic Syndrome: A Population Analysis

Introduction: Metabolic syndrome (MS) comprises a cluster of cardiovascular risk factors, including central obesity, dysglycemia, elevated blood pressure (BP), increased triglyceride levels (HyperTG), and low HDL cholesterol levels. Epidemiologic and clinical data suggest that MS may be an important etiologic factor in the progression of certain cancer types. These studies have excluded patients with myelodysplastic syndromes (MDS), but MS may be relevant in these patients owing to the link between cardiovascular disease and MDS derived from clonal hematopoiesis. We conducted a population-based analysis to define the prevalence of MS and its components among patients with MDS and explore the effect of MS on MDS outcomes. Methods: We identified patients aged 66 and older diagnosed with MDS between 2007 and 2017 using the SEER-Medicare database. Preexisting MS was identified using ICD-9/10 codes in claims from at least 12 months before MDS diagnosis. MS was defined as the presence of 3 or more of the 5 MS components. MDS histologic risk was defined based on ICD-O-3 morphology codes. Transfusion dependence, defined as 2 or more transfusions within 8 weeks of MDS diagnosis date, and therapy with hypomethylating agents (HMA), lenalidomide and erythropoietin stimulating agents (ESA) were defined from HCPCS codes and prescription records. Other variables defined included age, sex, race/ethnicity, rurality (using RUCC codes), marital status, and socioeconomic status [SES] (using the Yost index). Descriptive statistics were used to define the frequency of MS and its components. MDS outcomes of interest were transformation to acute myeloid leukemia (AML), defined from ICD-9/10 codes for AML, and overall survival (OS), defined as the time between MDS diagnosis and death from any cause. Cox proportional hazards regression was used to determine the association between MS and AML transformation and OS, through adjusted hazard ratios (HR). Results: A total of 15,227 cases diagnosed with MDS between 2007 and 2017 were analyzed, including 3,402 (22.3%) with baseline MS. High BP was present in 72.2%, HyperTG in 47.8%, dysglycemia in 35.5%, central obesity in 4.6% and 0.5% had low HDL cholesterol. The prevalence of MS and the distribution of its components did not significantly differ based on MDS histologic risk (Table 1). The prevalence of hyperTG was notably higher in patients with MDS, especially in the high histologic risk category (50.4%). Compared to other MDS patients, those with preexisting MS were predominantly male (55.5% vs 53.3%, p=0.03) of non-White race (6.7% vs 4.8% non-Hispanic Black, p&amp;lt;0.01, and 2.1% vs 1.5% Hispanic, p&amp;lt;0.01), from urban/metropolitan areas (87.7% vs 86%, p=0.01) and lower SES quintiles 1 and 2 (34.2% vs 31.5%, p&amp;lt;0.01). In a model adjusting for age, sex, race/ethnicity, rurality, marital status, SES, MDS risk, transfusion dependence and MDS therapies (HMA, lenalidomide and ESA), baseline MS at the time of MDS diagnosis was not associated with a significant effect on the risk of AML transformation (HR=1.0, 95%CI 0.9-1.2) or the risk of death from any cause (HR=1.0, 95%CI 0.9-1.1) (Table 2). In models assessing the effect of MS subcomponents on MDS outcomes, high BP (HR=1.0, 95CI% 1.0-1.1) and obesity (HR=1.1, 95CI% 1.0-1.2) were associated with an increased risk of mortality. Obesity was also associated with an increased risk of transformation to AML (HR=1.3, 95CI% 1.0-1.6). Conclusions: The overall prevalence of MS among patients with MDS appears similar to that reported in the general population and does not differ based on the histologic risk category. The observed prevalence of HyperTG was higher than expected, particularly in high-risk MDS patients. Older males of non-White race from urban/metropolitan areas of lower SES are more likely affected across all groups. Though preexisting MS is present in an important proportion of MDS patients, it was not significantly associated with an increased risk of mortality or AML transformation after adjusting for confounders. Obesity was associated with higher mortality and linked to increased transformation to AML. Given recent data suggesting that statins may improve survival and decrease AML transformation in MDS, future studies should investigate the potential association between other metabolic parameters and MDS outcomes.

Communication That Enables Shared Decision-Making in Myelodysplastic Syndrome Is Suboptimal: Early Results from the Cancer Experience Registry

Background: Myelodysplastic Syndromes (MDS) are a heterogeneous group of marrow failure diseases whose prognosis and treatments are guided by marrow morphology, degrees of cytopenias, and genetic changes. Due to the complexity of the disorder, combined with the advanced age and frailty of most patients, conveying crucial information for shared decision-making poses challenges. Despite efforts designed to enhance communication, there is limited understanding of these initiatives' effectiveness. Methods: The Cancer Experience Registry® is an ongoing online research study conducted by the Cancer Support Community that seeks to uncover the emotional, physical, practical, and financial impact of cancer from the patient's perspective. In association with the MDS Foundation, this observational, cross-sectional study enrolls patients with MDS who provide socio-economic and clinical history, supplemented with information related to their MDS diagnosis. Frequencies and descriptive statistics are presented. Results: Between December 2021 and February 2023, 140 MDS patients joined the registry. By self-report, the study population was 51% female and 91% non-Hispanic white with a median age 61 (range 34-93). Like other cancer disease cohorts in the online registry, the MDS population was highly educated (81% attending college and 31% obtaining advanced degrees). 18% reported gross annual incomes less than $40,000 but 29% reported incomes above $80,000 (with 25% not responding). 70% were retired, 15% were still employed and 11% considered themselves unemployed due to disability. 41% of the patients were newly diagnosed (disease duration less than 1 year) and an additional 19% had MDS for less than 2 years. Interestingly, 24% carried a diagnosis of MDS for more than 6 years (including 11% reporting &amp;gt;10 years duration). 51% were in active treatment, 18% were between therapies, and 26% had never received any MDS-directed therapy. 76% self-reported a primary MDS diagnosis and 7% secondary MDS, with the remainder unsure. 33% of the respondents did not know their WHO morphologic subtype with 13% stating that they were never informed and 16% unsure if they were told this information. Similarly, although the IPSS-R is a critical determinant of prognosis and informs treatment decisions, 23% could not recall this score with 11% stating that they were not told their IPSS-R and 9% not sure if they were informed. Among 118 respondents, only 18% could remember their genetic testing results. 120 participants answered questions regarding whether they received additional assistance with MDS-related information and when this was provided. By patient recall, general information about MDS was provided to 78% at the time of diagnosis and an additional 5% after starting treatment. Help in understanding the WHO subtype and IPSS-R was remembered by 41% and 52%, respectively, at the time of diagnosis, and 8% and 9% after starting treatment. A third could not recall being informed about genetic mutational testing. Information about the possibility of MDS transforming into AML was not recalled by 21%. Information about transfusion support was remembered by 46% at the time of diagnosis and 17% after starting treatment (with 29% stating that they had not received information about transfusions and 8% unable to recall). A discussion about transplant options was remembered by 67%. Although a quarter of patients have never received therapy, 32% stated that they had never had a discussion of treatment options and an additional 6% were unsure if a discussion had occurred. A discussion about specific MDS medications was remembered by 51% at the time of diagnosis and 19% only after the start of therapy, with 30% not recalling any assistance in understanding medication options. Conclusions: Based on the early results of the Cancer Experience Registry® derived from a cohort of highly educated and motivated MDS patients, it appears that effective communication about MDS and treatment options is suboptimal. A significant proportion of respondents were unable to recall information about their diagnosis critical to informed shared decision-making. Given the complexities of an MDS diagnosis, additional efforts to educate patients are necessary. Patient support organizations, such as the Cancer Support Community and the MDS Foundation, can serve as valuable educational resources.