Pub Date : 2024-02-29DOI: 10.1101/2024.02.29.24303535
Roberto Mancebo-Martin, Lin Lin, Elena Dacal, Miguel Luengo-Oroz, David Bermejo-Pelaez
Bloodborne parasitic diseases such as malaria, filariasis or chagas pose significant challenges in clinical diagnosis, with microscopy as the primary tool for diagnosis. However, limitations such as time-consuming processes and the dependence on trained microscopists is critical, particularly in resource-constrained settings. Deep learning techniques have shown value to interpret microscopy images using large annotated databases for training. In this work, we propose a methodology leveraging self-supervised learning as a foundational model for blood parasite classification. Using a large unannotated database of blood microscopy images, the model is able to learn important image representations that are subsequently transferred to perform parasite classification of 11 different species of parasites requiring a smaller amount of labeled data. Our results show enhanced performance over fully supervised approaches, with ~100 labels per class sufficient to attain an F1 score of ~0.8. This approach is promising for advancing in-vitro diagnostic systems in primary healthcare settings.
疟疾、丝虫病或南美锥虫病等血源性寄生虫病给临床诊断带来了巨大挑战，显微镜检查是诊断的主要工具。然而，显微镜检查过程耗时且依赖训练有素的显微镜医师等局限性至关重要，尤其是在资源有限的情况下。深度学习技术已显示出利用大型注释数据库进行训练来解释显微镜图像的价值。在这项工作中，我们提出了一种利用自我监督学习作为血液寄生虫分类基础模型的方法。该模型利用一个大型未加注释的血液显微镜图像数据库，能够学习到重要的图像表征，随后将这些表征用于对 11 种不同种类的寄生虫进行寄生虫分类，而这只需要较少的标注数据。我们的结果表明，与完全有监督的方法相比，该方法的性能有所提高，每类约 100 个标签就足以达到约 0.8 的 F1 分数。这种方法有望推动基层医疗机构体外诊断系统的发展。
{"title":"How many labels do I need? Self-supervised learning strategies for multiple blood parasites classification in microscopy images","authors":"Roberto Mancebo-Martin, Lin Lin, Elena Dacal, Miguel Luengo-Oroz, David Bermejo-Pelaez","doi":"10.1101/2024.02.29.24303535","DOIUrl":"https://doi.org/10.1101/2024.02.29.24303535","url":null,"abstract":"Bloodborne parasitic diseases such as malaria, filariasis or chagas pose significant challenges in clinical diagnosis, with microscopy as the primary tool for diagnosis. However, limitations such as time-consuming processes and the dependence on trained microscopists is critical, particularly in resource-constrained settings. Deep learning techniques have shown value to interpret microscopy images using large annotated databases for training. In this work, we propose a methodology leveraging self-supervised learning as a foundational model for blood parasite classification. Using a large unannotated database of blood microscopy images, the model is able to learn important image representations that are subsequently transferred to perform parasite classification of 11 different species of parasites requiring a smaller amount of labeled data. Our results show enhanced performance over fully supervised approaches, with ~100 labels per class sufficient to attain an F1 score of ~0.8. This approach is promising for advancing in-vitro diagnostic systems in primary healthcare settings.","PeriodicalId":501203,"journal":{"name":"medRxiv - Hematology","volume":"35 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140009017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-08DOI: 10.1101/2024.02.06.24302401
Devdeep Mukherjee, Rialnat A. Lawal, Courtney D. Fitzhugh, Christopher S. Hourigan, Laura W. Dillon
There is increasing recognition of the risk of developing therapy-related myeloid malignancy, including after cellular therapy. While retrospective studies have implicated pre-existing TP53 mutated hematopoietic clones as a common causative mechanism, no prospective screening to identify those patients at greatest risk is currently possible. We demonstrate that ultradeep DNA-sequencing prior to therapy may be used for discovery of TP53 mutations that are subsequently associated with malignancy.
{"title":"TP53 mutation screening for patients at risk of myeloid malignancy","authors":"Devdeep Mukherjee, Rialnat A. Lawal, Courtney D. Fitzhugh, Christopher S. Hourigan, Laura W. Dillon","doi":"10.1101/2024.02.06.24302401","DOIUrl":"https://doi.org/10.1101/2024.02.06.24302401","url":null,"abstract":"There is increasing recognition of the risk of developing therapy-related myeloid malignancy, including after cellular therapy. While retrospective studies have implicated pre-existing <em>TP53</em> mutated hematopoietic clones as a common causative mechanism, no prospective screening to identify those patients at greatest risk is currently possible. We demonstrate that ultradeep DNA-sequencing prior to therapy may be used for discovery of <em>TP53</em> mutations that are subsequently associated with malignancy.","PeriodicalId":501203,"journal":{"name":"medRxiv - Hematology","volume":"109 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139759448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Allogeneic hematopoietic stem cell transplantation (allo-HSCT) is a cornerstone treatment for a broad spectrum of malignant and nonmalignant hematological disorders. However, the success of allo-HSCT is often overshadowed by acute graft-versus-host disease (aGVHD), a life-threatening complication with limited preventive options. Here, we found that the incidence and severity of aGVHD after allo-HSCT are highly dependent on the circadian timing of stem cell infusion. The incidence rate of aGVHD in patients decreased by approximately 50% for early infusion (before 2:00 pm) compared to later infusion (after 2:00 pm). Early-infused patients also experienced significantly lower three-year transplant-related mortality and improved GVHD-free, relapse-free survival. Animal studies using an aGVHD mouse model show that this improvement is mainly due to the recipient’s rhythm rather than the donor’s. Mechanistically, compared with late infusions, early infusions significantly reduced the levels of the pro-inflammatory cytokine IL-1α following the conditioning regimen and subsequently suppressed T-cell activation and differentiation after transplantation. Our study suggests that scheduling stem cell infusions early in the day could be a simple yet transformative intervention for the prevention of aGVHD.
异基因造血干细胞移植（allo-HSCT）是治疗各种恶性和非恶性血液病的基础疗法。然而，急性移植物抗宿主疾病（acute graft-versus-host disease，acGVHD）往往给异基因造血干细胞移植的成功蒙上了阴影。在这里，我们发现，allo-HSCT后急性移植物抗宿主疾病的发生率和严重程度与干细胞输注的昼夜节律时间有很大关系。早期输注（下午2:00之前）与晚期输注（下午2:00之后）相比，患者AGVHD的发生率降低了约50%。早期输注的患者三年移植相关死亡率也明显降低，无GVHD、无复发的存活率也有所提高。使用急性肾脏坏死小鼠模型进行的动物研究表明，这种改善主要是受体的节律而非供体的节律所致。从机理上讲，与晚期输注相比，早期输注可显著降低调理方案后促炎细胞因子 IL-1α 的水平，并随后抑制移植后 T 细胞的活化和分化。我们的研究表明，将干细胞输注安排在一天中的较早时间，可成为预防AGVHD的一种简单但具有变革性的干预措施。
{"title":"Optimizing Stem Cell Infusion Timing in the Prevention of Acute Graft versus Host Disease","authors":"Yiwen Hou, Yue Wu, Zhonglin Zhang, Liang Wang, Zhiwei Liu, Baolin Tang, Kaidi Song, Guangyu Sun, Xiaoyu Zhu, Cheng Zhan","doi":"10.1101/2024.02.06.24302168","DOIUrl":"https://doi.org/10.1101/2024.02.06.24302168","url":null,"abstract":"Allogeneic hematopoietic stem cell transplantation (allo-HSCT) is a cornerstone treatment for a broad spectrum of malignant and nonmalignant hematological disorders. However, the success of allo-HSCT is often overshadowed by acute graft-versus-host disease (aGVHD), a life-threatening complication with limited preventive options. Here, we found that the incidence and severity of aGVHD after allo-HSCT are highly dependent on the circadian timing of stem cell infusion. The incidence rate of aGVHD in patients decreased by approximately 50% for early infusion (before 2:00 pm) compared to later infusion (after 2:00 pm). Early-infused patients also experienced significantly lower three-year transplant-related mortality and improved GVHD-free, relapse-free survival. Animal studies using an aGVHD mouse model show that this improvement is mainly due to the recipient’s rhythm rather than the donor’s. Mechanistically, compared with late infusions, early infusions significantly reduced the levels of the pro-inflammatory cytokine IL-1α following the conditioning regimen and subsequently suppressed T-cell activation and differentiation after transplantation. Our study suggests that scheduling stem cell infusions early in the day could be a simple yet transformative intervention for the prevention of aGVHD.","PeriodicalId":501203,"journal":{"name":"medRxiv - Hematology","volume":"18 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139759589","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-06DOI: 10.1101/2024.02.02.24302163
Isabella Lin, Angela Wei, Tsumugi A Gebo, PC Boutros, Maeve Flanagan, Nicole Kucine, C Cunniff, VA Arboleda, VY Chang
Background Bloom Syndrome (BSyn) is an autosomal recessive disorder caused by biallelic germline variants in BLM, which functions to maintain genomic stability. BSyn patients have poor growth, immune defects, insulin resistance, and a significantly increased risk of malignancies, most commonly hematologic. The malignancy risk in carriers of pathogenic variants in BLM (BLM variant carriers) remains understudied. Clonal hematopoiesis of indeterminate potential (CHIP) is defined by presence of somatic mutations in leukemia-related genes in blood of individuals without leukemia and is associated with increased risk of leukemia. We hypothesize that somatic mutations driving clonal expansion may be an underlying mechanism leading to increased cancer risk in BSyn patients and BLM variant carriers.
{"title":"Increased Frequency of Clonal Hematopoiesis of Indeterminate Potential in Bloom Syndrome Probands and Carriers","authors":"Isabella Lin, Angela Wei, Tsumugi A Gebo, PC Boutros, Maeve Flanagan, Nicole Kucine, C Cunniff, VA Arboleda, VY Chang","doi":"10.1101/2024.02.02.24302163","DOIUrl":"https://doi.org/10.1101/2024.02.02.24302163","url":null,"abstract":"<strong>Background</strong> Bloom Syndrome (BSyn) is an autosomal recessive disorder caused by biallelic germline variants in <em>BLM,</em> which functions to maintain genomic stability. BSyn patients have poor growth, immune defects, insulin resistance, and a significantly increased risk of malignancies, most commonly hematologic. The malignancy risk in carriers of pathogenic variants in <em>BLM</em> (<em>BLM</em> variant carriers) remains understudied. Clonal hematopoiesis of indeterminate potential (CHIP) is defined by presence of somatic mutations in leukemia-related genes in blood of individuals without leukemia and is associated with increased risk of leukemia. We hypothesize that somatic mutations driving clonal expansion may be an underlying mechanism leading to increased cancer risk in BSyn patients and <em>BLM</em> variant carriers.","PeriodicalId":501203,"journal":{"name":"medRxiv - Hematology","volume":"14 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139761258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-17DOI: 10.1101/2024.01.16.24301320
Helen Parker, Amatta Mirandari, Carolina Jaramillo Oquendo, Martí Duran-Ferrer, Benjamin Stevens, Lara Buermann, Harindra E. Amarasinghe, Jaya Thomas, Latha Kadalayil, Louise Carr, Shama Syeda, Methusha Sakthipakan, Marina Parry, Zadie Davis, Neil McIver-Brown, Aliki Xochelli, Sarah Ennis, Lydia Scarfo, Paolo Ghia, Christina Kalpadakis, Gerassimos Pangalis, Davide Rossi, Simon Wagner, Matthew Ahearne, Marc Seifert, Christoph Plass, Dieter Weichenhan, Eva Kimby, Lesley-Ann Sutton, Richard Rosenquist, Francesco Forconi, Kostas Stamatopoulos, Marta Salido, Ana Ferrer, Catherine Thieblemont, Viktor Ljungström, Rose-Marie Amini, David Oscier, Renata Walewska, Matthew J.J. Rose-Zerilli, Jane Gibson, José Ignacio Martín-Subero, Christopher Oakes, Dean Bryant, Jonathan C Strefford
The epiCMIT (epigenetically-determined Cumulative MIToses) mitotic clock traces B-cell mitotic history via DNA methylation changes in heterochromatin and H3K27me3-containing chromatin. While high scores correlated with poor outcomes in CLL and MCL, its prognostic significance in SMZL remains unknown. Derived from 142 SMZL cases using DNA methylation microarrays, epiCMIT values were correlated with genomic, transcriptomic, and clinical data. EpiCMIT as a continuous variable was significantly higher in females (p=0.02), patients with IGHV1-2*04 allele usage (p<0001), intermediate IGHV somatic hypermutation load (97-99.9% identity, p=0.04), elevated mutational burden (25 vs. 17 mut/Mb, p=0.001), driver gene mutations [KLF2 (p<0.001), NOTCH2 (p<0.01), TP53 (p=0.01), KMT2D (p<0.001)], and del(7q) (p=0.01). Negative correlation between epiCMIT and telomere length (r=-0.29 p<0.001) supported the association between cumulated proliferation and telomere attrition. While univariate analysis highlighted epiCMIT as robust predictor of shorter treatment-free survival (TFS), multivariate analysis confirmed epiCMIT as an independent marker for shorter TFS. In summary, our matched multi-omic datasets facilitate the clinico-biological characterization of SMZL and introduces epiCMIT as a strong prognostic marker, identifying high-risk patients and predicting reduced treatment-free survival, hence providing a new tool for risk-adapted patient management.
epiCMIT（表观遗传学决定的累积有丝分裂）有丝分裂钟通过异染色质和含 H3K27me3 染色质的 DNA 甲基化变化追踪 B 细胞有丝分裂的历史。虽然高分与CLL和MCL的不良预后相关，但其在SMZL中的预后意义尚不清楚。利用 DNA 甲基化芯片从 142 个 SMZL 病例中得出 epiCMIT 值，并将其与基因组、转录组和临床数据相关联。作为连续变量的 EpiCMIT 在女性（p=0.02）、IGHV1-2*04 等位基因使用率（p<0001）、中间 IGHV 体细胞高突变负荷（97-99.9%，p=0.04）、突变负荷增加（25 vs. 17 mut/Mb，p=0.001）、驱动基因突变[KLF2（p<0.001）、NOTCH2（p<0.01）、TP53（p=0.01）、KMT2D（p<0.001）]和del（7q）（p=0.01）。epiCMIT 与端粒长度之间的负相关（r=-0.29 p<0.001）支持累积增殖与端粒损耗之间的关联。单变量分析强调 epiCMIT 是较短无治疗生存期（TFS）的可靠预测指标，而多变量分析则证实 epiCMIT 是较短 TFS 的独立标志物。总之，我们的匹配多组学数据集促进了 SMZL 的临床生物学特征描述，并将 epiCMIT 作为一个强有力的预后标志物，可识别高风险患者并预测缩短的无治疗生存期，从而为风险适应型患者管理提供了一种新工具。
{"title":"Proliferative History Is a Novel Driver of Clinical Outcome in Splenic Marginal Zone Lymphoma","authors":"Helen Parker, Amatta Mirandari, Carolina Jaramillo Oquendo, Martí Duran-Ferrer, Benjamin Stevens, Lara Buermann, Harindra E. Amarasinghe, Jaya Thomas, Latha Kadalayil, Louise Carr, Shama Syeda, Methusha Sakthipakan, Marina Parry, Zadie Davis, Neil McIver-Brown, Aliki Xochelli, Sarah Ennis, Lydia Scarfo, Paolo Ghia, Christina Kalpadakis, Gerassimos Pangalis, Davide Rossi, Simon Wagner, Matthew Ahearne, Marc Seifert, Christoph Plass, Dieter Weichenhan, Eva Kimby, Lesley-Ann Sutton, Richard Rosenquist, Francesco Forconi, Kostas Stamatopoulos, Marta Salido, Ana Ferrer, Catherine Thieblemont, Viktor Ljungström, Rose-Marie Amini, David Oscier, Renata Walewska, Matthew J.J. Rose-Zerilli, Jane Gibson, José Ignacio Martín-Subero, Christopher Oakes, Dean Bryant, Jonathan C Strefford","doi":"10.1101/2024.01.16.24301320","DOIUrl":"https://doi.org/10.1101/2024.01.16.24301320","url":null,"abstract":"The epiCMIT (epigenetically-determined Cumulative MIToses) mitotic clock traces B-cell mitotic history via DNA methylation changes in heterochromatin and H3K27me3-containing chromatin. While high scores correlated with poor outcomes in CLL and MCL, its prognostic significance in SMZL remains unknown. Derived from 142 SMZL cases using DNA methylation microarrays, epiCMIT values were correlated with genomic, transcriptomic, and clinical data. EpiCMIT as a continuous variable was significantly higher in females (<em>p</em>=0.02), patients with IGHV1-2*04 allele usage (<em>p</em><0001), intermediate IGHV somatic hypermutation load (97-99.9% identity, <em>p</em>=0.04), elevated mutational burden (25 vs. 17 mut/Mb, <em>p</em>=0.001), driver gene mutations [<em>KLF2</em> (<em>p</em><0.001), <em>NOTCH2</em> (<em>p</em><0.01), <em>TP53</em> (<em>p</em>=0.01), <em>KMT2D</em> (<em>p</em><0.001)], and del(7q) (<em>p</em>=0.01). Negative correlation between epiCMIT and telomere length (r=-0.29 <em>p</em><0.001) supported the association between cumulated proliferation and telomere attrition. While univariate analysis highlighted epiCMIT as robust predictor of shorter treatment-free survival (TFS), multivariate analysis confirmed epiCMIT as an independent marker for shorter TFS. In summary, our matched multi-omic datasets facilitate the clinico-biological characterization of SMZL and introduces epiCMIT as a strong prognostic marker, identifying high-risk patients and predicting reduced treatment-free survival, hence providing a new tool for risk-adapted patient management.","PeriodicalId":501203,"journal":{"name":"medRxiv - Hematology","volume":"4 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139510463","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-01-15DOI: 10.1101/2024.01.13.24301121
Aileen Liang, Cathy Wang, Alla E Iansavichene, Alejandro Lazo-Langner
Objective To analyze the safety and efficacy of different direct oral anticoagulant agents (DOACs) compared to warfarin in patients with concomitant atrial fibrillation (AF) and valvular disease or concomitant AF and chronic kidney disease (CKD).
{"title":"Comparing DOACs with warfarin in AF patients with chronic kidney disease or valvular disease: A systematic review and meta-analysis","authors":"Aileen Liang, Cathy Wang, Alla E Iansavichene, Alejandro Lazo-Langner","doi":"10.1101/2024.01.13.24301121","DOIUrl":"https://doi.org/10.1101/2024.01.13.24301121","url":null,"abstract":"<strong>Objective</strong> To analyze the safety and efficacy of different direct oral anticoagulant agents (DOACs) compared to warfarin in patients with concomitant atrial fibrillation (AF) and valvular disease or concomitant AF and chronic kidney disease (CKD).","PeriodicalId":501203,"journal":{"name":"medRxiv - Hematology","volume":"34 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139484253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Acute Myeloid Leukemia (AML) is a complex disease requiring accurate risk stratification for effective treatment planning. This study introduces an innovative ensemble machine learning model integrated with the European LeukemiaNet (ELN) 2022 recommendations to enhance AML risk stratification. The model demonstrated superior performance by utilizing a comprehensive dataset of 1,213 patients from National Taiwan University Hospital (NTUH) and an external cohort of 2,113 patients from UK-NCRI trials. On the external cohort, it improved a concordance index (c-index) from 0.61 to 0.64 and effectively distinguished three different risk levels with median hazard ratios ranging from 18% to 50% improved. Key insights were gained from the discovered significant features influencing risk prediction, including age, genetic mutations, and hematological parameters. Notably, the model identified specific cytogenetic and molecular alterations like TP53, IDH2, SRSF2, STAG2, KIT, TET2, and karyotype (-5, -7, -15, inv(16)), alongside age and platelet counts. Additionally, the study explored variations in the effectiveness of hematopoietic stem cell transplantation (HSCT) across different risk levels, offering new perspectives on treatment effects. In summary, this study develops an ensemble model based on the NTUH cohort to deliver improved performance in AML risk stratification, showcasing the potential of integrating machine learning techniques with medical guidelines to enhance patient care and personalized medicine.
{"title":"An Ensemble Model for Acute Myeloid Leukemia Risk Stratification Recommendations by Combining Machine Learning with Clinical Guidelines","authors":"Ming-Siang Chang, Cheng-Hong Tsai, Wen-Chien Chou, Hwei-Fang Tien, Hsin-An Hou, Chien-Yu Chen","doi":"10.1101/2024.01.08.24301018","DOIUrl":"https://doi.org/10.1101/2024.01.08.24301018","url":null,"abstract":"Acute Myeloid Leukemia (AML) is a complex disease requiring accurate risk stratification for effective treatment planning. This study introduces an innovative ensemble machine learning model integrated with the European LeukemiaNet (ELN) 2022 recommendations to enhance AML risk stratification. The model demonstrated superior performance by utilizing a comprehensive dataset of 1,213 patients from National Taiwan University Hospital (NTUH) and an external cohort of 2,113 patients from UK-NCRI trials. On the external cohort, it improved a concordance index (c-index) from 0.61 to 0.64 and effectively distinguished three different risk levels with median hazard ratios ranging from 18% to 50% improved. Key insights were gained from the discovered significant features influencing risk prediction, including age, genetic mutations, and hematological parameters. Notably, the model identified specific cytogenetic and molecular alterations like <em>TP53</em>, <em>IDH2</em>, <em>SRSF2</em>, <em>STAG2</em>, <em>KIT</em>, <em>TET2</em>, and karyotype (-5, -7, -15, inv(16)), alongside age and platelet counts. Additionally, the study explored variations in the effectiveness of hematopoietic stem cell transplantation (HSCT) across different risk levels, offering new perspectives on treatment effects. In summary, this study develops an ensemble model based on the NTUH cohort to deliver improved performance in AML risk stratification, showcasing the potential of integrating machine learning techniques with medical guidelines to enhance patient care and personalized medicine.","PeriodicalId":501203,"journal":{"name":"medRxiv - Hematology","volume":"25 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-01-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139412036","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-18DOI: 10.1101/2023.12.15.23299980
Michael Wittig, Tim Alexander Steiert, Hesham ElAbd, Frauke Degenhardt, Luca Valenti, Daniele Prati, Luisa Ronzoni, Luis Bujanda, Jesus M. Banales, Natalia Blay, Pietro Invernizzi, Maria Buti, Agustin Albillos, Javier Fernandez, Nicoletta Sacchi, Antonio Julia, Anna Latiano, Rafael de Cid, Mauro D'Amato, Rosanna Asselta, Matthias Laudes, Wolfgang Lieb, David Juhl, Christoph Gassner, Andre Franke
Blood transfusions, conducted between donors compatible in their red blood cell (RBC) antigens, play a life-saving role in transfusion medicine. Genetic differences at blood group loci between ethnicities result in diversity and altered frequency of RBC antigens that need to be considered in blood transfusion. Consequently, comprehensive, and accurate blood group antigen typing is especially relevant for inter-ethnicity blood transfusions and for minorities underrepresented in the donor population. Blood group microarray genotyping is a cost-efficient and scalable method for comprehensive blood group typing. Previously, however, microarray typing has been challenging for the clinically important blood group systems Rh and MNS, as these feature highly paralogous genomic loci leading to mixed signals. We here present an approach for accurately typing blood group systems, including Rh and MNS variations, that we benchmarked in an ethnically diverse cohort. We tested its performance using gold-standard, diagnostic-grade MALDI-TOF data from 1,052-samples, including 334 HGDP-CEPH diversity panel samples and applied the approach to 4,999 samples of a COVID-19 genetics study. Overall, we obtained a 99.95% benchmarking concordance and 99.43% call rate. In summary, we provide a highly accurate and cost-efficient high-throughput genotyping method for comprehensive blood group analysis that is also suitable for ethnically diverse sample sets.
{"title":"Calling for diversity: improving transfusion safety through high-throughput blood group microarray genotyping","authors":"Michael Wittig, Tim Alexander Steiert, Hesham ElAbd, Frauke Degenhardt, Luca Valenti, Daniele Prati, Luisa Ronzoni, Luis Bujanda, Jesus M. Banales, Natalia Blay, Pietro Invernizzi, Maria Buti, Agustin Albillos, Javier Fernandez, Nicoletta Sacchi, Antonio Julia, Anna Latiano, Rafael de Cid, Mauro D'Amato, Rosanna Asselta, Matthias Laudes, Wolfgang Lieb, David Juhl, Christoph Gassner, Andre Franke","doi":"10.1101/2023.12.15.23299980","DOIUrl":"https://doi.org/10.1101/2023.12.15.23299980","url":null,"abstract":"Blood transfusions, conducted between donors compatible in their red blood cell (RBC) antigens, play a life-saving role in transfusion medicine. Genetic differences at blood group loci between ethnicities result in diversity and altered frequency of RBC antigens that need to be considered in blood transfusion. Consequently, comprehensive, and accurate blood group antigen typing is especially relevant for inter-ethnicity blood transfusions and for minorities underrepresented in the donor population. Blood group microarray genotyping is a cost-efficient and scalable method for comprehensive blood group typing. Previously, however, microarray typing has been challenging for the clinically important blood group systems Rh and MNS, as these feature highly paralogous genomic loci leading to mixed signals. We here present an approach for accurately typing blood group systems, including Rh and MNS variations, that we benchmarked in an ethnically diverse cohort. We tested its performance using gold-standard, diagnostic-grade MALDI-TOF data from 1,052-samples, including 334 HGDP-CEPH diversity panel samples and applied the approach to 4,999 samples of a COVID-19 genetics study. Overall, we obtained a 99.95% benchmarking concordance and 99.43% call rate. In summary, we provide a highly accurate and cost-efficient high-throughput genotyping method for comprehensive blood group analysis that is also suitable for ethnically diverse sample sets.","PeriodicalId":501203,"journal":{"name":"medRxiv - Hematology","volume":"8 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138744946","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-17DOI: 10.1101/2023.12.15.23299936
Ryuichi Taketomi, Ko Sakatsume, Shintaro Katahira, Kota Goto, Misako Suzuki, Zuo Yunan, Konosuke Sasaki, Midori Miyatake, Katsuhiro Hosoyama, Koki Ito, Yusuke Suzuki, Goro Takahashi, Kiichiro Kumagai, Hisanori Horiuchi, Yoshikatsu Saiki
Background Recent advances in left ventricular assist device (LVAD) therapy have significantly contributed to the improved management of severe heart failure. The unignorable risk of bleeding events associated with the device therapy, however, remains to be addressed. Predictive factors for bleeding events are not fully defined.
{"title":"von Willebrand factor-related values can predict bleeding events in patients with left ventricular assist devices","authors":"Ryuichi Taketomi, Ko Sakatsume, Shintaro Katahira, Kota Goto, Misako Suzuki, Zuo Yunan, Konosuke Sasaki, Midori Miyatake, Katsuhiro Hosoyama, Koki Ito, Yusuke Suzuki, Goro Takahashi, Kiichiro Kumagai, Hisanori Horiuchi, Yoshikatsu Saiki","doi":"10.1101/2023.12.15.23299936","DOIUrl":"https://doi.org/10.1101/2023.12.15.23299936","url":null,"abstract":"<strong>Background</strong> Recent advances in left ventricular assist device (LVAD) therapy have significantly contributed to the improved management of severe heart failure. The unignorable risk of bleeding events associated with the device therapy, however, remains to be addressed. Predictive factors for bleeding events are not fully defined.","PeriodicalId":501203,"journal":{"name":"medRxiv - Hematology","volume":"56 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138819994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-12-13DOI: 10.1101/2023.12.09.23298879
Yangyang Li, Demin Kong, Yicheng Ding, Jinhuan Wang
Introduction Immune thrombocytopenic purpura (ITP) is characterized by a decrease in platelet counts and can be triggered by various factors, such as viral infections and vaccinations. Concerns have emerged regarding potential links between the vaccines for COVID-19 and the worsening of ITP. This systematic review aims to comprehensively assess the impact of COVID-19 vaccines on patients with ITP, including associated risks and outcomes.
{"title":"The impact of COVID-19 vaccines on patients with immune thrombocytopenic purpura: A protocol for a systematic review and meta-analysis","authors":"Yangyang Li, Demin Kong, Yicheng Ding, Jinhuan Wang","doi":"10.1101/2023.12.09.23298879","DOIUrl":"https://doi.org/10.1101/2023.12.09.23298879","url":null,"abstract":"<strong>Introduction</strong> Immune thrombocytopenic purpura (ITP) is characterized by a decrease in platelet counts and can be triggered by various factors, such as viral infections and vaccinations. Concerns have emerged regarding potential links between the vaccines for COVID-19 and the worsening of ITP. This systematic review aims to comprehensively assess the impact of COVID-19 vaccines on patients with ITP, including associated risks and outcomes.","PeriodicalId":501203,"journal":{"name":"medRxiv - Hematology","volume":"105 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138716075","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：