Halima El Omri

Post cytotoxic myeloid neoplasms signify a heterogenous pool of poorly understood hematologic neoplasms with unfortunate survival and ineffective therapies. There is a lack of consensus on prognostic indicators, primarily due to the heterogenous disease spectrum encompassing different pathological, cytogenomic and original disease variables. This retrospective, single-center study over 10 years duration on MN-pCT cases diagnosed at NCCCR, a member of Hamad Medical Corporation. The study aimed to analyze clinicopathologic and cytogenomic characteristics, identify key prognostic predictors, and assess their impact on mortality through univariate and multivariate analyses. We identified 42 MN-pCT patients, noting a 31.7% prevalence of autoimmune diseases as primary condition, which is higher than previously reported. TP53 was the most frequently mutated gene, found in 28.6% of tested cases. Significant determinants of a shorter latency period included prior exposure to alkylating agents and TP53 positivity (by NGS or IHC) (P < 0.05). Younger patients (≤ 50 years) exhibited longer survival (P = 0.018). Poor prognostic markers included dyserythropoiesis (P = 0.045), MPO downregulation (P = 0.026), mutated TP53 (NGS/IHC) (P = 0.004), and failure to achieve CR (P = 0.002). Multivariate Cox regression identified both a latency period of ≥ 5 years and TP53 positivity (detected by either NGS or IHC) as statistically significant independent factors associated with reduced overall survival (P < 0.05). It is important to highlight that P53 mutation by NGS was a common parameter identified by the multivariate analysis that adversely impacted both MN-Pct survival and OS. This study stands as a significant contribution to our understanding of the clinicopathologic characteristics and prognostic predictors of MN-pCT in MENA region. It also underscores the existence of adverse prognostic factors, extending beyond the genetic influences and emphasizing the necessity of recognizing it as a distinct entity in the future classification systems.

Reliable and rapid medical diagnosis is the cornerstone for improving the survival rate and quality of life of cancer patients. The problem of clinical decision-making pertaining to the management of patients with hematologic cancer is multifaceted and intricate due to the risk of therapy-induced myelosuppression, multiple infections, and febrile neutropenia (FN). Myelosuppression due to treatment increases the risk of sepsis and mortality in hematological cancer patients with febrile neutropenia. A high prevalence of multidrug-resistant organisms is also noted in such patients, which implies that these patients are left with limited or no-treatment options amidst severe health complications. Hence, early screening of patients for such organisms in their bodies is vital to enable hospital preparedness, curtail the spread to other weak patients in hospitals, and limit community outbreaks. Even though predictive models for sepsis and mortality exist, no model has been suggested for the prediction of multidrug-resistant organisms in hematological cancer patients with febrile neutropenia. Hence, for predicting three critical clinical complications, such as sepsis, the presence of multidrug-resistant organisms, and mortality, from the data available from medical records, we used 1166 febrile neutropenia episodes reported in 513 patients. The XGboost algorithm is suggested from 10-fold cross-validation on 6 candidate models. Other highlights are (1) a novel set of easily available features for the prediction of the aforementioned clinical complications and (2) the use of data augmentation methods and model-scoring-based hyperparameter tuning to address the problem of class disproportionality, a common challenge in medical datasets and often the reason behind poor event prediction rate of various predictive models reported so far. The proposed model depicts improved recall and AUC (area under the curve) for sepsis (recall = 98%, AUC = 0.85), multidrug-resistant organism (recall = 96%, AUC = 0.91), and mortality (recall = 86%, AUC = 0.88) prediction. Our results encourage the need to popularize artificial intelligence-based devices to support clinical decision-making.

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.

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.

Multiple myeloma (MM) is a hematologic disorder of B lymphocytes characterized by the accumulation of malignant plasma cells (PCs) in the bone marrow. The altered plasma cells overproduce abnormal monoclonal immunoglobulins and also stimulate osteoclasts. The host’s immune system and microenvironment are of paramount importance in the growth of PCs and, thus, in the pathogenesis of the disease. The interaction of MM cells with the bone marrow (BM) microenvironment through soluble factors and cell adhesion molecules causes pathogenesis of the disease through activation of multiple signaling pathways, including NF-κβ, PI3K/AKT and JAK/STAT. These activated pathways play a critical role in the inhibition of apoptosis, sustained proliferation, survival and migration of MM cells. Besides, these pathways also participate in developing resistance against the chemotherapeutic drugs in MM. The imbalance between inflammatory and anti-inflammatory cytokines in MM leads to an increased level of pro-inflammatory cytokines, which in turn play a significant role in dysregulation of signaling pathways and proliferation of MM cells; however, the association appears to be inadequate and needs more research. In this review, we are highlighting the recent findings on the roles of various cytokines and growth factors in the pathogenesis of MM and the potential therapeutic utility of aberrantly activated signaling pathways to manage the MM disease.

The current study retrospectively evaluated cytogenetic profiles, various prognostic factors, and survival outcomes in 128 acute myeloid leukemia (AML) patients (14 ≤ age ≤ 70 years) admitted to the National Center for Cancer Care and Research (NCCCR), Hamad Medical Corporation, Doha, Qatar, between January 2010 and December 2016. The median age at diagnosis was 43 years, and 80% were less than 60 years old; 75% of patients were male. Cytogenetic analysis was integrated into the World Health Organization 2008 classification and showed that the percentages of normal and abnormal karyotypes were similar, accounting for 48.4% of each group of patients. The AML risk stratification based on cytogenetic analysis resulted in the following distribution: 18% in the favorable risk group, 57% in the intermediate-risk group, 24% in the unfavorable risk group, and 1% unknown. Only 88 patients received therapy with curative intent; 67% achieved complete remission, increasing to 81% after inductions 1 and 2. The median overall survival (OS) and disease-free survival (DFS) in AML patients were 26.6 and 19.5 months, respectively. The 3-year OS and DFS were 40 and 36%, respectively. Prognostic factors including age, gender, white blood cell count, and risk stratification were not significantly associated with treatment outcomes, whereas response to treatment vs. failure was significantly associated with the outcome (p = 0.01). The current study supports the importance of cytogenetics as a useful tool in diagnosis, prognosis, and risk assessment in AML treatment.