Search Results (23)

Ovarian cancer’s high mortality is primarily due to late-stage diagnosis, underscoring the critical need for improved early detection tools. This study develops and validates explainable artificial intelligence (XAI) models to discriminate malignant from benign ovarian masses using readily available demographic and laboratory data. A dataset of 309 patients (140 malignant, 169 benign) with 47 clinical parameters was analyzed. The Boruta algorithm selected 19 significant features, including tumor markers (CA125, HE4, CEA, CA19-9, AFP), hematological indices, liver function tests, and electrolytes. Five ensemble machine learning algorithms were optimized and evaluated using repeated stratified 5-fold cross-validation. The Gradient Boosting model achieved the highest performance with 88.99% (±3.2%) accuracy, 0.934 AUC-ROC, and 0.782 Matthews correlation coefficient. SHAP analysis identified HE4, CEA, globulin, CA125, and age as the most globally important features. Unlike black-box approaches, our XAI framework provides clinically interpretable decision pathways through LIME and SHAP visualizations, revealing how feature values push predictions toward malignancy or benignity. Partial dependence plots illustrated non-linear risk relationships, such as a sharp increase in malignancy probability with CA125 > 35 U/mL. This explainable approach demonstrates that ensemble models can achieve high diagnostic accuracy using routine lab data alone, performing comparably to established clinical indices while ensuring transparency and clinical plausibility. The integration of state-of-the-art XAI techniques highlights established biomarkers and reveals potential novel contributors like inflammatory and hepatic indices, offering a pragmatic, scalable triage tool to augment existing diagnostic pathways, particularly in resource-constrained settings. Full article

Artificial intelligence applications in histopathological diagnostics are rapidly expanding, with particular promise in complex hematological malignancies where diagnostic accuracy remains challenging and subjective. This study undertakes a scoping review to systematically map the extent of research on artificial intelligence applications in histopathological diagnostics of leukemias, examine geographic distribution and methodological approaches, and assess the current state of AI model performance and clinical readiness. A comprehensive search was conducted in the Scopus database covering publications from 2018 to 2025 (as of 12 July 2025), using five targeted search strategies combining AI, histopathology, and leukemia-related terms. Following a three-stage screening protocol, 418 publications were selected from an initial pool of over 75,000 records across multiple countries and research domains. The analysis revealed a marked increase in research output, peaking in 2024 with substantial contributions from India (26.3%), China (17.9%), USA (13.8%), and Saudi Arabia (11.1%). Among 43 documented datasets ranging from 80 to 42,386 images, studies predominantly utilized convolutional neural networks and deep learning approaches. AI models demonstrated high diagnostic accuracy, with 25 end-to-end models achieving an average accuracy of 97.72% compared to 96.34% for 20 classical machine learning approaches. Most studies focused on acute lymphoblastic leukemia detection and subtype classification using blood smear and bone marrow specimens. Despite promising diagnostic performance, significant gaps remain in clinical translation, standardization, and regulatory approval, with none of the reviewed AI systems currently FDA-approved for routine leukemia diagnostics. Future research should prioritize clinical validation studies, standardized datasets, and integration with existing diagnostic workflows to realize the potential of AI in hematopathological practice. Full article

Insights into the state of individual cells within a living organism are essential for identifying diseases and abnormalities. The internal state of a cell is reflected in its morphological features and changes in the localization of intracellular molecules. Using this information, it is possible to infer the state of the cells with high precision. In recent years, technological advancements and improvements in instrument specifications have made large-scale analyses, such as single-cell analysis, more widely accessible. Among these technologies, imaging flow cytometry (IFC) is a high-throughput imaging platform that can simultaneously acquire information from flow cytometry (FCM) and cellular images. While conventional FCM can only obtain fluorescence intensity information corresponding to each detector, IFC can acquire multidimensional information, including cellular morphology and the spatial arrangement of proteins, nucleic acids, and organelles for each imaging channel. This enables the discrimination of cell types and states based on the localization of proteins and organelles, which is difficult to assess accurately using conventional FCM. Because IFC can acquire a large number of single-cell morphological images in a short time, it is well suited for automated classification using machine learning. Furthermore, commercial instruments that combine integrated imaging and cell sorting capabilities have recently become available, enabling the sorting of cells based on their image information. In this review, we specifically highlight practical applications of IFC in four representative areas: cell cycle analysis, protein localization analysis, immunological synapse formation, and the detection of leukemic cells. In addition, particular emphasis is placed on applications that directly contribute to elucidating molecular mechanisms, thereby distinguishing this review from previous general overviews of IFC. IFC enables the estimation of cell cycle phases from large numbers of acquired cellular images using machine learning, thereby allowing more precise cell cycle analysis. Moreover, IFC has been applied to investigate intracellular survival and differentiation signals triggered by external stimuli, to monitor DNA damage responses such as γH2AX foci formation, and more recently, to detect immune synapse formation among interacting cells within large populations and to analyze these interactions at the molecular level. In hematological malignancies, IFC combined with fluorescence in situ hybridization (FISH) enables high-throughput detection of chromosomal abnormalities, such as BCR-ABL1 translocations. These advances demonstrate that IFC provides not only morphological and functional insights but also clinically relevant genomic information at the single-cell level. By summarizing these unique applications, this review aims to complement existing publications and provide researchers with practical insights into how IFC can be implemented in both basic and translational research. Full article

Adoptive cell therapies (ACTs) have revolutionized cancer treatment by harnessing the specificity and potency of T lymphocytes. Chimeric antigen receptor (CAR)-T cells have achieved landmark successes in B-cell malignancies and multiple myeloma. Tumor-infiltrating lymphocytes (TILs) and T-cell receptor (TCR)-engineered T cells offer complementary strategies to target solid tumors and intracellular antigens. Despite these advances, ACTs face challenges including cytokine release syndrome, neurotoxicity, on-target/off-tumor effects, manufacturing scalability, and immunosuppressive tumor microenvironments. Innovative strategies, such as dual-antigen targeting, localized delivery, checkpoint blockade combinations, gene-editing, and machine-learning-guided antigen discovery, are being used to mitigate toxicity, enhance efficacy, and streamline production. As CAR-T, TIL, and TCR modalities converge with advances in manufacturing and computational biology, the next generation of “living drugs” promises broader applicability across hematologic and solid tumors, improved safety profiles, and better treatment outcomes for patients. This review details the evolution of ACTs from first-generation CAR constructs to next-generation “armored” designs. It also focuses on the development and clinical deployment of TIL and TCR therapies. Furthermore, it synthesizes mechanisms, pivotal clinical trial outcomes, and ongoing challenges of ACTs. It also highlights strategies that will drive broader, safer, and more durable applications of these therapies across hematologic and solid tumors. Full article

Artificial Intelligence and machine learning are increasingly used to interrogate complex biological data. This systematic review evaluates their application to multi-omics for the molecular characterization of hematological malignancies, an area with unmet clinical need. We searched PubMed, Embase, Institute of Electrical and Electronics Engineers Xplore, and Web of Science from January 2015 to December 2024. Two reviewers screened records, extracted data, and used a modified appraisal emphasizing explainability, performance, reproducibility, and ethics. From 2847 records, 89 studies met inclusion criteria. Studies focused on acute myeloid leukemia (34), acute lymphoblastic leukemia (23), and multiple myeloma (18). Other hematological diseases were less frequently studied. Methods included Support Vector Machines, Random Forests, and deep learning (28, 25, and 24 studies). Multi-omics integration was reported in 23 studies. External validation occurred in 31 studies, and explainability in 19. The median diagnostic area under the curve was 0.87 (interquartile range 0.81 to 0.94); deep learning reached 0.91 but offered the least explainability. Artificial Intelligence and machine learning show promise for molecular characterization, yet gaps in validation, interpretability, and standardization remain. Priorities include external validation, interpretable modeling, harmonized evaluation, and standardized reporting with shared benchmarks to enable safe, reproducible clinical translation. Full article

Septic shock is a life-threatening complication of sepsis, particularly in patients with hematologic diseases who are highly susceptible to it due to profound immune dysregulation. Recent advances in artificial intelligence offer promising tools for improving septic shock diagnosis, prognosis, and treatment in this vulnerable population. In detail, these innovative models analyzing electronic health records, immune function, and real-time physiological data have demonstrated superior performance compared to traditional scoring systems such as Sequential Organ Failure Assessment. In patients with hematologic malignancies, machine learning approaches have shown strong accuracy in predicting the sepsis risk using biomarkers like lactate and red cell distribution width, the latter emerging as a powerful, cost-effective predictor of mortality. Deep reinforcement learning has enabled the dynamic modelling of immune responses, facilitating the design of personalized treatment regimens helpful in reducing simulated mortality. Additionally, algorithms driven by artificial intelligence can optimize fluid and vasopressor management, corticosteroid use, and infection risk. However, challenges related to data quality, transparency, and ethical concerns must be addressed to ensure their safe integration into clinical practice. Clinically, AI could enable earlier detection of septic shock, better patient triage, and tailored therapies, potentially lowering mortality and the number of ICU admissions. However, risks like misclassification and bias demand rigorous validation and oversight. A multidisciplinary approach is crucial to ensure that AI tools are implemented responsibly, with patient-centered outcomes and safety as primary goals. Overall, artificial intelligence holds transformative potential in managing septic shock among hematologic patients by enabling timely, individualized interventions, reducing overtreatment, and improving survival in this high-risk group of patients. Full article

Monoclonal Gammopathy of Undetermined Significance (MGUS) is a precursor to hematologic malignancies such as Multiple Myeloma (MM) and Waldenström Macroglobulinemia (WM). Accurate risk stratification of MGUS patients remains a clinical and computational challenge, with existing models often misclassifying both high-risk and low-risk individuals, leading to inefficient healthcare resource allocation. This study presents a machine learning (ML)-based approach for early prediction of MM/WM progression, using routinely collected hematological data, which are selected based on clinical relevance. A retrospective cohort of 292 MGUS patients, including 7 who progressed to malignancy, was analyzed. For each patient, a feature descriptor was constructed incorporating the latest biomarker values, their temporal trends over the previous year, age, and immunoglobulin subtype. To address the inherent class imbalance, data augmentation techniques were applied. Multiple ML classifiers were evaluated, with the Support Vector Machine (SVM) achieving the highest performance (94.3% accuracy and F1-score). The model demonstrates that a compact set of clinically relevant features can yield robust predictive performance. These findings highlight the potential of ML-driven decision-support systems in electronic health applications, offering a scalable solution for improving MGUS risk stratification, optimizing clinical workflows, and enabling earlier interventions. Full article

Multispecific antibodies have redefined the immunotherapeutic landscape in hematologic malignancies. Bispecific antibodies (BsAbs), which redirect cytotoxic T cells toward malignant targets via dual antigen engagement, are now established components of treatment for diseases such as acute lymphoblastic leukemia (ALL), diffuse large B-cell lymphoma (DLBCL), follicular lymphoma (FL), and multiple myeloma (MM). Clinical trials of agents like blinatumomab, glofitamab, mosunetuzumab, and teclistamab have demonstrated deep and durable responses in heavily pretreated populations. Trispecific antibodies (TsAbs), although still investigational, represent the next generation of immune redirection therapies, incorporating additional tumor antigens or co-stimulatory domains (e.g., CD28, 4-1BB) to mitigate antigen escape and enhance T-cell persistence. This review provides a comprehensive evaluation of BsAbs and TsAbs across hematologic malignancies, detailing molecular designs, mechanisms of action, therapeutic indications, resistance pathways, and toxicity profiles including cytokine release syndrome (CRS), immune effector cell-associated neurotoxicity syndrome (ICANS), cytopenias, and infections. We further discuss strategies to mitigate adverse effects and resistance, such as antigen switching, checkpoint blockade combinations, CELMoDs, and construct optimization. Notably, emerging platforms such as tetrafunctional constructs, checkpoint-integrated multispecifics, and protease-cleavable masking designs are expanding the therapeutic index of these agents. Early clinical evidence also supports the feasibility of applying multispecific antibodies to solid tumors. Finally, we highlight the transformative role of artificial intelligence (AI) and machine learning (ML) in multispecific antibody development, including antigen discovery, biomarker-driven treatment selection, toxicity prediction, and therapeutic optimization. Together, BsAbs and TsAbs illustrate the convergence of molecular precision, clinical innovation, and AI-driven personalization, establishing a new paradigm for immune-based therapy across hematologic and potentially solid tumor malignancies. Full article

Background. Acute promyelocytic leukemia (APL) is a subtype of acute myeloid leukemia defined by the presence of a genetic abnormality, namely the PML::RARA gene fusion, as the result of a reciprocal balanced translocation between chromosome 17 and chromosome 15. APL is a veritable emergency in hematology due to the risk of early death and coagulopathy if left untreated; thus, a rapid diagnosis is needed in this hematological malignancy. Needless to say, cytogenetic and molecular biology techniques, i.e., fluorescent in situ hybridization (FISH) and polymerase chain reaction (PCR), are essential in the diagnosis and management of patients diagnosed with APL. In recent years, the use of artificial intelligence (AI) and its brances, machine learning (ML), and deep learning (DL) in the field of medicine, including hematology, has brought to light new avenues for research in the fields of blood cancers. However, to our knowledge, there is no comprehensive evaluation of the potential applications of AI, ML, and DL in APL. Thus, the aim of the current publication was to evaluate the prospective uses of these novel technologies in APL. Methods. We conducted a comprehensive literature search in PubMed/MEDLINE, SCOPUS, and Web of Science and identified 20 manuscripts eligible for the qualitative analysis. Results. The included publications highlight the potential applications of ML, DL, and other AI branches in the diagnosis, evaluation, and management of APL. The examined AI models were based on the use of routine biological parameters, cytomorphology, flow-cytometry and/or OMICS, and demonstrated excellent performance metrics: sensitivity, specificity, accuracy, AUROC, and others. Conclusions. AI can emerge as a relevant tool in the evaluation of APL cases and potentially contribute to more rapid screening and identification of this hematological emergency. Full article

Hematopoietic stem cell transplantation (HSCT) is a life-saving therapy for hematologic malignancies, such as leukemia and lymphoma and other severe conditions but is associated with significant risks, including graft versus host disease (GVHD), relapse, and treatment-related mortality. The increasing complexity of clinical, genomic, and biomarker data has spurred interest in machine learning (ML), which has emerged as a transformative tool to enhance decision-making and optimize outcomes in HSCT. This review examines the applications of ML in HSCT, focusing on donor selection, conditioning regimen, and prediction of post-transplant outcomes. Machine learning approaches, including decision trees, random forests, and neural networks, have demonstrated potential in improving donor compatibility algorithms, mortality and relapse prediction, and GVHD risk stratification. Integrating “omics” data with ML models has enabled the identification of novel biomarkers and the development of highly accurate predictive tools, supporting personalized treatment strategies. Despite promising advancements, challenges persist, including data standardization, algorithm interpretability, and ethical considerations regarding patient privacy. While ML holds promise for revolutionizing HSCT management, addressing these barriers through multicenter collaborations and regulatory frameworks remains essential for broader clinical adoption. In addition, the potential of ML can cope with some challenges such as data harmonization, patients’ data protection, and availability of adequate infrastructure. Future research should prioritize larger datasets, multimodal data integration, and robust validation methods to fully realize ML’s transformative potential in HSCT. Full article

Background/Objectives: The rise of multidrug-resistant (MDR) infections demands personalized antibiotic strategies for febrile neutropenia (FN) in hematological malignancies. This study investigates machine learning (ML) for identifying patient profiles with increased susceptibility to bloodstream infections (BSI) during FN onset, aiming to tailor treatment approaches. Methods: From January 2020 to June 2022, we used the unsupervised ML algorithm KAMILA to analyze data from hospitalized hematological malignancy patients. Eleven features categorized clinical phenotypes and determined BSI and multidrug-resistant Gram-negative bacilli (MDR-GNB) prevalences at FN onset. Model performance was evaluated with a validation cohort from July 2022 to March 2023. Results: Among 462 FN episodes analyzed in the development cohort, 116 (25.1%) had BSIs. KAMILA’s stratification identified three risk clusters: Cluster 1 (low risk), Cluster 2 (intermediate risk), and Cluster 3 (high risk). Cluster 2 (28.4% of episodes) and Cluster 3 (43.7%) exhibited higher BSI rates of 26.7% and 37.6% and GNB BSI rates of 13.4% and 19.3%, respectively. Cluster 3 had a higher incidence of MDR-GNB BSIs, accounting for 75% of all MDR-GNB BSIs. Cluster 1 (27.9% of episodes) showed a lower BSI risk (<1%) with no GNB infections. Validation cohort results were similar: Cluster 3 had a BSI rate of 38.1%, including 78% of all MDR-GNB BSIs, while Cluster 1 had no GNB-related BSIs. Conclusions: Unsupervised ML-based risk stratification enhances evidence-driven decision-making for empiric antibiotic therapies at FN onset, crucial in an era of rising multi-drug resistance. Full article

Objectives: The aim of this study was to investigate the preoperative clinical and hematologic variables, including the neutrophil-to-lymphocyte ratio (NLR), that can be used to predict malignancy in patients with atypia of undetermined significance (AUS) thyroid nodules; we further aimed to develop a machine learning-based prediction model. Methods: We enrolled 280 patients who underwent surgery for AUS nodules at the Wonju Severance Christian Hospital between 2018 and 2022. A logistic regression-based model was trained and tested using cross-validation, with the performance evaluated using metrics such as the area under the receiver operating characteristic curve (AUROC). Results: Among the 280 patients, 116 (41.4%) were confirmed to have thyroid malignancies. Independent predictors of malignancy included age, tumor size, and the Korean Thyroid Imaging Reporting and Data System (K-TIRADS) classification, particularly in patients under 55 years of age. The addition of NLR to these predictors significantly improved the malignancy prediction accuracy in this subgroup. Conclusions: Incorporating NLR into preoperative assessments provides a cost-effective, accessible tool for refining surgical decision making in younger patients with AUS nodules. Full article

Myelodysplastic syndromes (MDSs) are a group of hematologic neoplasms accompanied by dysplasia of bone marrow (BM) hematopoietic cells with cytopenia. Recently, digitalized pathology and pathomics using computerized feature analysis have been actively researched for classifying and predicting prognosis in various tumors of hematopoietic tissues. This study analyzed the pathomic features of hematopoietic cells in BM aspiration smears of patients with MDS according to each hematopoietic cell lineage and dysplasia. We included 24 patients with an MDS and 21 with normal BM. The 12,360 hematopoietic cells utilized were to be classified into seven types: normal erythrocytes, normal granulocytes, normal megakaryocytes, dysplastic erythrocytes, dysplastic granulocytes, dysplastic megakaryocytes, and others. Four hundred seventy-six pathomic features quantifying cell intensity, shape, and texture were extracted from each segmented cell. After comparing the combination of feature selection and machine learning classifier methods using 5-fold cross-validation area under the receiver operating characteristic curve (AUROC), the quadratic discriminant analysis (QDA) with gradient boosting decision tree (AUROC = 0.63) and QDA with eXtreme gradient boosting (XGB) (AUROC = 0.64) showed a high AUROC combination. Through a feature selection process, 30 characteristics were further analyzed. Dysplastic erythrocytes and granulocytes showed lower median values on heatmap analysis compared to that of normal erythrocytes and granulocytes. The data suggest that pathomic features could be applied to cell differentiation in hematologic malignancies. It could be used as a new biomarker with an auxiliary role for more accurate diagnosis. Further studies including prediction survival and prognosis with larger cohort of patients are needed. Full article

Background: Hematologic malignancies are a group of heterogeneous neoplasms which originate from hematopoietic cells. The most common among them are leukemia, lymphoma, and multiple myeloma. Machine learning (ML) is a subfield of artificial intelligence that enables the analysis of large amounts of data, possibly finding hidden patterns. Methods: We performed a narrative review about recent applications of ML in the most common hematological malignancies. We focused on the most recent scientific literature about this topic. Results: ML tools have proved useful in the most common hematological malignancies, in particular to enhance diagnostic work-up and guide treatment. Conclusions: Although ML has multiple possible applications in this field, there are some issue that have to be fixed before they can be used in daily clinical practice. Full article

Colorectal cancer (CRC) currently ranks as the third most common cancer and the second leading cause of cancer-related deaths worldwide, posing a significant global health burden to the population. Recent studies have reported the emergence of a new clinical picture of the disease, with a notable increase in CRC rates in younger populations of <50 years of age. The American Cancer Society (ACS) now recommends CRC screening starting at age 45 for average-risk individuals. Dr. Aasma Shaukat’s Keynote Conference highlights the critical need for updated screening strategies, with an emphasis on addressing the suboptimal adherence rates and the effective management of the growing burden of CRC. Lowering the adenoma detection screening age can facilitate early identification of adenomas in younger asymptomatic patients, altering the epidemiologic landscape. However, its implications may not be as profound unless a drastic shift in the age distribution of CRC is observed. Currently, various screening options are available in practice, including stool-based tests like multitarget stool DNA (mtDNA) tests, fecal immunochemical testing (FIT), and imaging-based tests. In addition to existing screening methods, blood-based tests are now emerging as promising tools for early CRC detection. These tests leverage innovative techniques along with AI and machine learning algorithms, aiding in tumor detection at a significantly earlier stage, which was not possible before. Medicare mandates specific criteria for national coverage of blood-based tests, including sensitivity ≥ 74%, specificity ≥ 90%, FDA approval, and inclusion in professional society guidelines. Ongoing clinical trials, such as Freenome, Guardant, and CancerSEEK, offer hope for further advancements in blood-based CRC screening. The development of multicancer early detection tests like GRAIL demonstrates a tremendous potential for detecting various solid tumors and hematologic malignancies. Despite these breakthroughs, the question of accessibility and affordability still stands. The ever-evolving landscape of CRC screening reflects the strength of the scientific field in light of an altered disease epidemiology. Lowering screening age along with the integration of blood-based tests with existing screening methods holds great potential in reducing the CRC-related burden. At the same time, it is increasingly important to address the challenges of adaptation of the healthcare system to this change in the epidemiologic paradigm. Full article