Swarm Learning for decentralized and confidential clinical machine learning.

Fast and reliable detection of patients with severe and heterogeneous illnesses is a major goal of precision medicine1,2. Patients with leukaemia can be identified using machine learning on the basis of their blood transcriptomes3. However, there is an increasing divide between what is technically possible and what is allowed, because of privacy legislation4,5. Here, to facilitate the integration of any medical data from any data owner worldwide without violating privacy laws, we introduce Swarm Learning-a decentralized machine-learning approach that unites edge computing, blockchain-based peer-to-peer networking and coordination while maintaining confidentiality without the need for a central coordinator, thereby going beyond federated learning. To illustrate the feasibility of using Swarm Learning to develop disease classifiers using distributed data, we chose four use cases of heterogeneous diseases (COVID-19, tuberculosis, leukaemia and lung pathologies). With more than 16,400 blood transcriptomes derived from 127 clinical studies with non-uniform distributions of cases and controls and substantial study biases, as well as more than 95,000 chest X-ray images, we show that Swarm Learning classifiers outperform those developed at individual sites. In addition, Swarm Learning completely fulfils local confidentiality regulations by design. We believe that this approach will notably accelerate the introduction of precision medicine.

International Consensus Classification of Myeloid Neoplasms and Acute Leukemias: integrating morphologic, clinical, and genomic data.

The classification of myeloid neoplasms and acute leukemias was last updated in 2016 within a collaboration between the World Health Organization (WHO), the Society for Hematopathology, and the European Association for Haematopathology. This collaboration was primarily based on input from a clinical advisory committees (CACs) composed of pathologists, hematologists, oncologists, geneticists, and bioinformaticians from around the world. The recent advances in our understanding of the biology of hematologic malignancies, the experience with the use of the 2016 WHO classification in clinical practice, and the results of clinical trials have indicated the need for further revising and updating the classification. As a continuation of this CAC-based process, the authors, a group with expertise in the clinical, pathologic, and genetic aspects of these disorders, developed the International Consensus Classification (ICC) of myeloid neoplasms and acute leukemias. Using a multiparameter approach, the main objective of the consensus process was the definition of real disease entities, including the introduction of new entities and refined criteria for existing diagnostic categories, based on accumulated data. The ICC is aimed at facilitating diagnosis and prognostication of these neoplasms, improving treatment of affected patients, and allowing the design of innovative clinical trials.

Use, variability, and justification of eligibility criteria for phase II and III clinical trials in acute leukemia.

Clinical trial eligibility criteria can unfairly exclude patients or unnecessarily expose them to known risks if criteria are not concordant with drug safety. There are few data evaluating the extent to which acute leukemia eligibility criteria are justified. We analyzed criteria and drug safety data for front-line phase II and/or III acute leukemia trials with start dates 1/1/2010-12/31/2019 registered on clinicaltrials.gov. Multivariable analyses assessed concordance between criteria use and safety data (presence of criteria with a safety signal, or absence of criteria without a signal), and differences between criteria and safety-based limits. Of 250 eligible trials, concordant use of ejection fraction criteria was seen in 34.8%, corrected QT level (QTc) in 22.4%, bilirubin in 68.4%, aspartate transaminase/alanine aminotransferase (AST/ALT) in 58.8%, renal function in 68.4%, human immunodeficiency virus (HIV) in 54.8%, and hepatitis B and C in 42.0% and 41.2%. HIV and hepatitis B and C criteria use was concordant with safety data (adjusted Odds Ratios 2.04 [95%CI: 1.13, 3.66], 2.64 [95%CI: 1.38, 5.04], 2.27 [95%CI: 1.20, 4.32]) but organ function criteria were not (all P>0.05); phase III trials were not more concordant. Bilirubin criteria limits were the same as safety-based limits in 16.0% of trials, AST/ALT in 18.1%, and renal function in 13.9%; in 75.7%, 51.4%, and 56.5% of trials, criteria were more restrictive, respectively, by median differences of 0.2, 0.5, and 0.5 times the upper limits of normal. We found limited drug safety justifications for acute leukemia eligibility criteria. These data define criteria use and limits that can be rationally modified to increase patient inclusion and welfare.

Leukemia cancer cells and immune cells derived-exosomes: Possible roles in leukemia progression and therapy.

Exosomes have a significant impact on tumor survival, proliferation, metastasis, and recurrence. They also open up new therapeutic options and aid in the pathological identification and diagnosis of cancers. Exosomes have been shown in numerous studies to be essential for facilitating cell-to-cell communication. In B-cell hematological malignancies, the proteins and RNAs that are encased by circulating exosomes are thought to represent prospective sources for therapeutic drugs as well as biomarkers for diagnosis and prognosis. Additionally, exosomes can offer a "snapshot" of the tumor and the metastatic environment at any given point in time. In this review study, we concluded that leukemia-derived exosomes could be utilized as prognostic, diagnostic, and therapeutic biomarkers for individuals suffering from leukemia. Moreover, clinical studies have demonstrated that immune cells like dendritic cells create exosomes, which have the ability to activate the immune system against leukemia.

Clinical Characteristics and Diagnosis of Ph-Positive Mixed Phenotype Acute Leukemia.

BACKGROUND: The goal was to improve the clinical cognition of Ph-positive mixed phenotype acute leukemia and avoid misdiagnosis or delayed diagnosis. METHODS: The clinical manifestations and laboratory results (bone marrow cell morphology, multiparameter flow cytometry, and cytogenetics) of a case of Ph-positive mixed phenotype acute leukemia were analyzed, and related literature was reviewed. RESULTS: Blood routine: WBC 386.35 x 109/L, HGB 117.00 g/L, PLT 31 x 109/L; 80% of the original cells can be seen by artificial classification. Morphological examination of bone marrow cells showed that the proliferation of nucleated cells was obviously active, and the original cells accounted for 76%. The size of the original cells was somewhat uniform, most of the cells had less mass, were stained light grayish blue, the cytoplasm particles were not obvious, the nuclei were mostly round or quasi-round, some of them showed distortion and nuclear notch, and the chromatin was coarse. Some of the cells were rich in mass, small azurin granules were seen, the nuclei were regular, most of them were round, the chromatin was fine, the myeloperoxidase and esterase staining were negative, the eosinophils accounted for 2.5%, and the basophils accounted for 0.5%. Flow cytometry immunotyping: Two groups of abnormal cells were seen in the bone marrow. 1. A group included 12.32% of nuclear cells and showed abnormal myeloid primitive cell phenotype. Main expression: CD117, CD34, CD38, HLA-DR, CD33, CD64, CD123, weak expression: CD13, CD19. 2. The other group included 45.61% of the nuclear cells and had a B-lymphoblastic phenotype. Main expression: CD34, CD38, HLA-DR, CD123, CD19, CD10, CD9, cCD79a, TDT, weak expression of CD13, CD22. Mixed phenotype acute leukemia (M/B) immunophenotype was considered. Chromosome: 46,XY,t(9; 22)(q34;q11.2) [20]. BCR-ABL (P210) fusion gene was positive. CONCLUSIONS: Mixed phenotype acute leukemia (MPAL) is a rare type of malignant hematologic disease. Its diagnosis is based on the comprehensive evaluation of bone marrow cell morphology, immunophenotype, molecular and cytogenetic features.

Exploring core symptoms and interrelationships among symptoms in children with acute leukemia during chemotherapy: A network analysis.

PURPOSE: Children with acute leukemia have suffered from a considerable symptom burden during chemotherapy. However, few studies have focused on exploring the mechanisms among symptoms in children with acute leukemia. Our study aims to explore core symptoms and describe the interrelationships among symptoms in children with acute leukemia during chemotherapy. METHODS: From January 2021 to March 2023, 469 children with acute leukemia were recruited from 20 Chinese cities. The Memorial Symptom Assessment Scale 10-18 (MSAS 10-18) was used to evaluate the prevalence and severity of symptoms during chemotherapy. A network analysis was performed by the R software based on 31 symptoms. Centrality indices and density were used to explore core symptoms and describe interrelationships among symptoms in the network during chemotherapy. RESULTS: Worrying and feeling irritable were the central symptoms across the three centrality indices, including strength, closeness, and betweenness. Lack of energy was the most prevalent symptom; however, it was less central than other symptoms. The density of the "induction and remission" network significantly differed from other cycles' counterparts (p < 0.001). Global strength was greater in the " ≥ 8 years group " network than the " < 8 years group " network (p = 0.023). CONCLUSION: Network analysis provides a novel approach to identifying the core symptoms and understanding the interrelationships among symptoms. Our study indicates the need to assess emotional symptoms in children with acute leukemia during chemotherapy, especially during the induction and remission phases, as well as in older children. Future research is imperative to construct trajectories of dynamic symptom networks and centrality indices in longitudinal data to investigate the causal relationships among symptoms.

Leukemia Cutis in Skin of Color.

The various presentations of many dermatologic conditions among various skin types are slowly being elucidated throughout the recent years. These differences present as an issue as it leads to delayed diagnosis, treatment, and poorer quality of life. Herein, we present the characteristics of leukemia cutis in a skin of color patient with diagnosed chronic myelomonocytic leukemia. Adjei S, Temiz LA, Miller AC, et al. Leukemia cutis in skin of color. J Drugs Dermatol. 2023;22(7):687-689. doi:10.36849/JDD.7020.

Electrochemical and Optical Sensors for the Detection of Chemical Carcinogens Causing Leukemia.

The incidence and mortality due to neoplastic diseases have shown an increasing tendency over the years. Based on GLOBOCAN 2020 published by the International Agency for Research on Cancer (IARC), leukemias are the thirteenth most commonly diagnosed cancer in the world, with 78.6% of leukemia cases diagnosed in countries with a very high or high Human Development Index (HDI). Carcinogenesis is a complex process initiated by a mutation in DNA that may be caused by chemical carcinogens present in polluted environments and human diet. The IARC has identified 122 human carcinogens, e.g., benzene, formaldehyde, pentachlorophenol, and 93 probable human carcinogens, e.g., styrene, diazinone. The aim of the following review is to present the chemical carcinogens involved or likely to be involved in the pathogenesis of leukemia and to summarize the latest reports on the possibility of detecting these compounds in the environment or food with the use of electrochemical sensors.

Childhood leukemia: Brazilian reality in children under fifteen years.

Leukemia is among the most prevalent cancers in children and adolescents in Brazil, affecting about 75% of children's public, especially males. Therefore, the southeast region of Brazil has a higher prevalence of cases, in which from 2019 to 2022 there were 1710 leukemia cases. In addition, the average of general notifications had higher frequency in 2021 with 1761 diagnoses, with higher emphasis on the southeast region, presenting 495 cases this year. One of the goals of public entities for 2023 is to offer better quality in diagnostic services and rapid treatment of these children, since early diagnosis increases chances of cure by 90% and favorable outcomes in treatment.

Acute leukemia and lymphoma in pregnancy, a retrospective study from a tertiary center in Malaysia.

INTRODUCTION: Most evidence about the management of cancer and hematological malignancy in pregnancy are derived from retrospective observational studies with a small sample size. Availability of sufficiently large data has enabled evidence-based decision-making in this clinical dilemma. MATERIALS AND METHODS: Retrospective study looking into patients diagnosed with acute leukemia or lymphoma in pregnancy from 1st January 2014 to 1st January 2020 in Ampang General Hospital including newly or previously diagnosed and relapsed disease RESULTS: 37 cases of acute leukemia or lymphoma in pregnancy occurred in 34 patients. Majority of acute leukemia or lymphoma in pregnancy diagnosed in 1st trimester or in the setting of previously established or relapsed disease was therapeutically terminated. Thirteen pregnancies treated with antenatal chemotherapy resulted in livebirths except one stillbirth. More adverse obstetric outcomes are observed in pregnancies that did not receive antenatal chemotherapy, but association did not reach statistical significance. There was no significant difference in fetal outcome between cohort with and without antenatal chemotherapy. No treatment related mortality was observed in pregnancies with antenatal chemotherapy. Overall survival for newly diagnosed acute leukemia in pregnancy is significantly better with antenatal chemotherapy versus no antenatal chemotherapy. CONCLUSION: Treatment with chemotherapy in 2nd trimester of pregnancy onwards appears to have tolerable risks with favorable obstetric and fetal outcome. Deferment of treatment for acute leukemia in pregnancy to after delivery may cause increased risk of maternal and fetal adverse outcome.

Biomarker interaction selection and disease detection based on multivariate gain ratio.

BACKGROUND: Disease detection is an important aspect of biotherapy. With the development of biotechnology and computer technology, there are many methods to detect disease based on single biomarker. However, biomarker does not influence disease alone in some cases. It's the interaction between biomarkers that determines disease status. The existing influence measure I-score is used to evaluate the importance of interaction in determining disease status, but there is a deviation about the number of variables in interaction when applying I-score. To solve the problem, we propose a new influence measure Multivariate Gain Ratio (MGR) based on Gain Ratio (GR) of single-variate, which provides us with multivariate combination called interaction. RESULTS: We propose a preprocessing verification algorithm based on partial predictor variables to select an appropriate preprocessing method. In this paper, an algorithm for selecting key interactions of biomarkers and applying key interactions to construct a disease detection model is provided. MGR is more credible than I-score in the case of interaction containing small number of variables. Our method behaves better with average accuracy [Formula: see text] than I-score of [Formula: see text] in Breast Cancer Wisconsin (Diagnostic) Dataset. Compared to the classification results [Formula: see text] based on all predictor variables, MGR identifies the true main biomarkers and realizes the dimension reduction. In Leukemia Dataset, the experiment results show the effectiveness of MGR with the accuracy of [Formula: see text] compared to I-score with accuracy [Formula: see text]. The results can be explained by the nature of MGR and I-score mentioned above because every key interaction contains a small number of variables in Leukemia Dataset. CONCLUSIONS: MGR is effective for selecting important biomarkers and biomarker interactions even in high-dimension feature space in which the interaction could contain more than two biomarkers. The prediction ability of interactions selected by MGR is better than I-score in the case of interaction containing small number of variables. MGR is generally applicable to various types of biomarker datasets including cell nuclei, gene, SNPs and protein datasets.

Multiplex technologies for the assessment of minimal residual disease and low-level mutation detection in leukaemia: mass spectrometry versus next-generation sequencing.

With the focus of leukaemia management shifting to the implications of low-level disease burden, increasing attention is being paid on the development of highly sensitive methodologies required for detection. There are various techniques capable of identification of measurable residual disease (MRD) either evidencing as relevant mutation detection [e.g. nucleophosmin 1 (NPM1) mutation] or trace levels of leukaemic clonal populations. The vast majority of these methods only permit detection of a single clone or mutation. However, mass spectrometry and next-generation sequencing enable the interrogation of multiple genes simultaneously, facilitating a more complete genomic profile. In the present review, we explore the methodologies of both techniques in conjunction with the important advantages and limitations associated with each assay. We also highlight the evidence and the various instances where either technique has been used and propose future strategies for MRD detection.

OMIP - 081: A new 21-monoclonal antibody 10-color panel for diagnostic polychromatic immunophenotyping.

The 10-color panel consisting of 21 monoclonal antibodies (mAbs) is developed as a one-tube panel to detect leukemia and lymphoma cells in all hematopoietic cell lineages. In particular, this tube is mentioned for a fast screening to identify aberrant cells in samples suspected for malignant cell localization and to enable comprehensive immunophenotyping of samples with low cell counts. The panel contains mAbs for selection of the populations and mAbs against target antigens on the various hematopoietic maturation stages. Due to the limited number of PMTs in most used flow cytometers for clinical purposes, stacking of conjugates in one color is needed to include all relevant markers for simultaneous analysis of the aberrant cells. The 21-mAb panel is tested on peripheral blood (PB), and bone marrow (BM) samples and enables an efficient and correct identification of hematological malignancies. This panel improves the diagnostic potential.

Factors that contribute to disparities in time to acute leukemia diagnosis in young people: an in depth qualitative interview study.

BACKGROUND: Racial and ethnic disparities in outcomes for Black and Hispanic children with acute leukemia have been well documented, however little is known about the determinants of diagnostic delays in pediatric leukemia in the United States. The primary objective of this study is to identify factors contributing to delays preceding a pediatric leukemia diagnosis. METHODS: This qualitative study utilized in-depth semi-structured interviews. Parents and/or patients within two years of receiving a new acute leukemia diagnosis were asked to reflect upon their family's experiences preceding the patient's diagnosis. Subjects were purposively sampled for maximum variation in race, ethnicity, income, and language. Interviews were analyzed using inductive theory-building and the constant comparative method to understand the process of diagnosis. Chart review was conducted to complement qualitative data. RESULTS: Thirty-two interviews were conducted with a diverse population of English and Spanish speaking participants from two tertiary care pediatric cancer centers. Parents reported feeling frustrated when their intuition conflicted with providers' management decisions. Many felt laboratory testing was not performed soon enough. Additional contributors to delays included misattribution of vague symptoms to more common diagnoses, difficulties in obtaining appointments, and financial disincentives to seek urgent or emergent care. Reports of difficulty obtaining timely appointments and financial concerns were disproportionately raised among low-income Black and Hispanic participants. Comparatively, parents with prior healthcare experiences felt better able to navigate the system and advocate for additional testing at symptom onset. CONCLUSIONS: While there are disease-related factors contributing to delays in diagnosis, it is important to recognize there are multiple non-disease-related factors that also contribute to delays. Evidence-based approaches to reduce outcome disparities in pediatric cancer likely need to start in the primary care setting where timeliness of diagnosis can be addressed.

Primary cutaneous gamma-delta T-cell lymphoma masquerading as leukemia cutis in a patient recently diagnosed with small lymphocytic lymphoma: Clues to the diagnosis.

A 54-year-old man recently diagnosed with small lymphocytic lymphoma (SLL) had waxing and waning, indurated, erythematous plaques on his legs, with leukopenia and anemia disproportionate to the SLL burden in his marrow and pelvic lymph nodes. Punch biopsy of a plaque performed to evaluate for leukemia cutis revealed a lymphocytic lobular-panniculitis-like infiltrate resembling lupus panniculitis, but a preponderance of CD8+/Ki-67+ T-cells surrounding adipocytes raised concern for subcutaneous panniculitis-like T-cell lymphoma (SPTCL). Additional immunohistochemistry (IHC) studies showed that the adipotropic T-cells expressed TCR-gamma, supporting the rare, unexpected diagnosis of Primary cutaneous gamma-delta T-cell lymphoma (PCGDTCL). The patient subsequently met diagnostic criteria for hemophagocytic lymphohistiocytosis (HLH). PCGDTCL is an aggressive, HLH-associated lymphoma requiring different management than SPTCL and SLL. This case illustrates how PCGDTCL can co-exist with B-cell lymphoma and resemble panniculitis on biopsies. PCGDTCL and SPTCL should enter the differential diagnosis whenever patients present with the constellation of lobular panniculitis and unexplained cytopenias. In the present case, close clinicopathologic correlation and judicious use of IHC on a small sample allowed for a prompt diagnosis.

Hidden in plain sight: urinary Cryptococcus neoformans missed by routine diagnostics in a patient with acute leukemia.

Cryptococcuria is a rare manifestation of localized cryptococcal disease. We present a case of Cryptococcus neoformans urinary tract infection in an immunocompromised host missed by routine laboratory workup. The patient had negative blood cultures, a negative serum cryptococcal antigen (CrAg), and "non-Candida yeast" growing in urine culture that was initially dismissed as non-pathogenic. The diagnosis was ultimately made by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) from a repeat urine culture after transfer to a tertiary care center. Cryptococcus should be considered in the differential of refractory urinary tract infections growing non-Candida yeast.

How fine needle aspiration cytology and flow cytometry helped in diagnosing a high-grade B-cell lymphoma masquerading as leukaemia.

High-grade B-cell lymphoma (HGBL) has recently been introduced into the category of aggressive, mature B-cell lymphomas. It is biologically different from diffuse large B-cell lymphoma and Burkitt lymphoma and exhibits an aggressive course. Leukaemic presentation, though known in various types of mature B-cell and mature T-cell lymphomas, is rare in high-grade B-cell lymphoma. We report one such case of a high-grade B-cell lymphoma which was masquerading as acute leukaemia with a soft tissue infiltration, with added emphasis on the role of fine needle aspiration cytology and flow cytometry in the diagnosis, and their therapeutic significance.

Utility of emergent plain X-ray for childhood acute leukemia with bone pain.

BACKGROUND: We aimed to evaluate the utility of plain X-ray radiograph (PXR) findings in suggesting a diagnosis of acute leukemia in children presenting with bone pain in the emergency department (ED) of a children's hospital. METHODS: Using our radiology reporting system and registered data for childhood acute leukemia, we collected data regarding patients who underwent musculoskeletal PXR examinations in the ED due to bone pain in their extremities, from March 1, 2002 to June 30, 2015. We retrospectively reviewed their PXR findings and clinical information from the electronic medical records. RESULTS: A total of 1,331 patients underwent PXR examinations and in 12 PXR findings showed suspected acute leukemia. From the registered data we found 12 acute leukemia patients who underwent emergency extremity PXR. Ten patients were finally confirmed to have acute leukemia by bone marrow examinations. The most common finding was lucent metaphyseal bands, demonstrated in seven cases, whereas six patients did not show any abnormalities in their peripheral blood cell counts. Sensitivity and specificity values of PXR for acute leukemia diagnosis were 90.0% and 99.8%, respectively. Positive predictive value and negative predictive values were 75.0% and 99.9%, respectively. CONCLUSIONS: Plain X-ray radiograph is a useful diagnostic tool to detect possible acute leukemia in patients presenting with bone pain, earlier than abnormalities of their peripheral blood cell counts. Our results implied the possibility of re-examining PXRs in acute leukemia more carefully, even when there are no abnormalities in blood cell counts.

Discrimination of leukemias and non-leukemic cancers in blood serum samples of children and adolescents using a Raman spectral model.

This study aimed to identify the differences presented in the Raman spectrum of blood serum from normal subjects compared to leukemic and non-leukemic subjects and the differences between the leukemics and non-leukemics, correlating the spectral differences with the biomolecules. Serum samples from children and adolescents were subjected to Raman spectroscopy (830 nm, laser power 350 mW; n = 566 spectra, being 72 controls, 269 leukemics, and 225 non-leukemics). Exploratory analysis based on principal component analysis (PCA) of the serum sample's spectra was performed. Classification models based on partial least squares discriminant analysis (PLS-DA) were developed to classify the spectra into normal, leukemic, and non-leukemic, as well as to discriminate spectra of leukemic from non-leukemic. The exploratory analysis showed principal components with peaks related to amino acids, proteins, lipids, and carotenoids. The spectral differences between normal, leukemic, and non-leukemic showed features assigned to proteins (serum features), amino acids, and carotenoids. The PLS-DA model classified the spectra of the normal group versus leukemic and non-leukemic groups with accuracy of 66%, sensitivity of 99%, and specificity of 57%. The PLS-DA discriminated the spectra of the leukemic and non-leukemic groups with accuracy of 67%, sensitivity of 72%, and specificity of 60%. The study showed that Raman spectroscopy is a technique that may be used for the biochemical differentiation of leukemias and other types of cancer in serum samples of children and adolescents. Nevertheless, building an extensive data library of Raman spectra from serum samples of controls, leukemics, and non-leukemics of different age groups is necessary to understand the findings better.

An Enhanced Hyper-Parameter Optimization of a Convolutional Neural Network Model for Leukemia Cancer Diagnosis in a Smart Healthcare System.

Healthcare systems in recent times have witnessed timely diagnoses with a high level of accuracy. Internet of Medical Things (IoMT)-enabled deep learning (DL) models have been used to support medical diagnostics in real time, thus resolving the issue of late-stage diagnosis of various diseases and increasing performance accuracy. The current approach for the diagnosis of leukemia uses traditional procedures, and in most cases, fails in the initial period. Hence, several patients suffering from cancer have died prematurely due to the late discovery of cancerous cells in blood tissue. Therefore, this study proposes an IoMT-enabled convolutional neural network (CNN) model to detect malignant and benign cancer cells in the patient's blood tissue. In particular, the hyper-parameter optimization through radial basis function and dynamic coordinate search (HORD) optimization algorithm was used to search for optimal values of CNN hyper-parameters. Utilizing the HORD algorithm significantly increased the effectiveness of finding the best solution for the CNN model by searching multidimensional hyper-parameters. This implies that the HORD method successfully found the values of hyper-parameters for precise leukemia features. Additionally, the HORD method increased the performance of the model by optimizing and searching for the best set of hyper-parameters for the CNN model. Leukemia datasets were used to evaluate the performance of the proposed model using standard performance indicators. The proposed model revealed significant classification accuracy compared to other state-of-the-art models.