Naveed Syed
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Naveed Syed has a total of 96 co-authors. Here are the top co-authors by number of shared publications:
Imrana Afrooz
Sheikh Shakhbout Medical City, Abu Dhabi, UAE
9 shared publicationsShahrukh Hashmi
Sheikh Shakhbout Medical City, Abu Dhabi, UAE
7 shared publicationsMoussab Damlaj
Sheikh Shakhbout Medical City, Abu Dhabi, UAE
5 shared publicationsAshok Uttamchandani
Sheikh Shakbout Medical City, Abu Dhabi, United Arab Emirates
4 shared publicationsAzmat Ali Khan
Sheikh Shakhbout Medical City, Abu Dhabi, UAE
4 shared publicationsFarooq Ahmed Mir
Sheikh Shakhbout Medical City, Abu Dhabi, UAE
4 shared publications
Latest Publications
- Open Access
- 14 July 2026
- Published by Springer Nature in BJC Reports
- Vol. 4  (1) , 36
Long-term outcomes and GVHD in allogeneic hematopoietic cell transplantation abroad: a 14-year UAE multi-center cohort
Background Hematopoietic cell transplant (HCT) data are well reported, but for cohorts transplanted abroad and returning to countries without transplant services, long-term outcomes such as chronic graft versus host disease (GVHD) and overall survival remain poorly captured, underscoring the need for longitudinal follow-up. Methods We conducted a 14-year retrospective multi-center study of allogeneic HCT recipients followed at three tertiary hospitals in the United Arab Emirates(UAE). Transplant characteristics, conditioning, GVHD prophylaxis, and outcomes were abstracted from medical records. Crude survival was reported for all indications, Kaplan–Meier (KM) overall survival for diseases with ≥20 cases. Results A total of 363 allogeneic HCTs were analyzed. Overall, cohort characteristics differed from those reported in the literature: adults undergoing HCT were relatively young, female predominance was observed in pediatric malignancies and immune deficiencies, and matched unrelated donor (MUD) utilization was limited, while peripheral blood stem cell use was higher than typically described. In contrast, haploidentical donor utilization, conditioning intensity, and GVHD prophylaxis patterns were broadly consistent with international practice. GVHD incidence was high:69.2% in adults; 45.7% in children. In adults with acute myeloid leukemia (AML), acute GVHD was associated with an inferior 5-year OS (p = 0.036). In pediatric AML, both acute-/chronic GVHD were linked to poor survival (<50%), while survival for acute lymphoblastic leukemia (B-/T-ALL) exceeded 85%. cGVHD worsened overall survival (OS) more in pediatrics than adults. Conclusions Although most findings aligned with established benchmarks, the high GVHD incidence and its association with adverse outcomes highlight the need for improved prevention strategies and the development of local transplant services.
- 14 July 2026
- Published by Springer Nature in BJC Reports
- Vol. 4  (1) , 36
Open AccessLong-term outcomes and GVHD in allogeneic hematopoietic cell transplantation abroad: a 14-year UAE multi-center cohort
Background Hematopoietic cell transplant (HCT) data are well reported, but for cohorts transplanted abroad and returning to countries without transplant services, long-term outcomes such as chronic graft versus host disease (GVHD) and overall survival remain poorly captured, underscoring the need for longitudinal follow-up. Methods We conducted a 14-year retrospective multi-center study of allogeneic HCT recipients followed at three tertiary hospitals in the United Arab Emirates(UAE). Transplant characteristics, conditioning, GVHD prophylaxis, and outcomes were abstracted from medical records. Crude survival was reported for all indications, Kaplan–Meier (KM) overall survival for diseases with ≥20 cases. Results A total of 363 allogeneic HCTs were analyzed. Overall, cohort characteristics differed from those reported in the literature: adults undergoing HCT were relatively young, female predominance was observed in pediatric malignancies and immune deficiencies, and matched unrelated donor (MUD) utilization was limited, while peripheral blood stem cell use was higher than typically described. In contrast, haploidentical donor utilization, conditioning intensity, and GVHD prophylaxis patterns were broadly consistent with international practice. GVHD incidence was high:69.2% in adults; 45.7% in children. In adults with acute myeloid leukemia (AML), acute GVHD was associated with an inferior 5-year OS (p = 0.036). In pediatric AML, both acute-/chronic GVHD were linked to poor survival (<50%), while survival for acute lymphoblastic leukemia (B-/T-ALL) exceeded 85%. cGVHD worsened overall survival (OS) more in pediatrics than adults. Conclusions Although most findings aligned with established benchmarks, the high GVHD incidence and its association with adverse outcomes highlight the need for improved prevention strategies and the development of local transplant services.
- Open Access
External Validation and Calibration Assessment of Explainable Machine Learning Models for GVHD Prediction After Allogeneic HSCT
Background: Graft-versus-host disease (GVHD) remains a major determinant of morbidity and mortality following allogeneic hematopoietic stem cell transplantation (allo-HSCT). Existing GVHD prediction models demonstrate modest discrimination and limited generalizability, and calibration drift across external populations is rarely characterized despite its essential role in the clinical interpretability of predicted probabilities. Objectives: To develop and externally validate an explainable machine learning framework for predicting acute and chronic GVHD and associated overall survival in patients with acute myeloid leukemia (AML), acute lymphoblastic leukemia (ALL), and myelodysplastic syndromes (MDS) undergoing allo-HSCT, and to systematically characterize calibration across heterogeneous external validation cohorts to inform deployment requirements. Study Design: The model was developed on three publicly available registry-derived datasets (N = 2,509) and externally validated across six independent cohorts (N = 14,788) comprising adult and pediatric allo-HSCT recipients, including a regional Middle Eastern cohort (UAE and Jordan). A standardized preprocessing pipeline harmonized heterogeneous datasets. Gradient boosting models (CatBoost) were used for binary GVHD prediction; exploratory overall survival analysis used a Cox proportional hazards model with predicted acute GVHD risk as a covariate. Discrimination (AUROC with bootstrap 95% CI), calibration (logistic recalibration intercept and slope with analytical 95% CI), and feature importance (SHapley Additive exPlanations, SHAP) were assessed in training out-of-fold and all external cohorts. Results: In internal validation, AUROC was 0.63 (95% CI 0.61–0.65) for acute GVHD and 0.72 (95% CI 0.70–0.74) for chronic GVHD. External validation demonstrated AUROC ranges of 0.51–0.57 (acute) and 0.54–0.64 (chronic), with consistent performance across disease subgroups despite substantial heterogeneity in transplant practices and feature availability. In exploratory survival analysis, the acute-GVHD-informed Cox model achieved a training-cohort C-index of 0.679 (95% CI 0.658–0.697); external C-indices ranged from 0.47–0.53. Calibration analysis identified systematic external risk overestimation (negative calibration intercept in 10 of 11 evaluable external cohort-target combinations) with heterogeneous slope drift requiring cohort-specific recalibration. Key predictors included recipient age, graft source, conditioning intensity, GVHD prophylaxis, and HLA match ratio. Conclusions: An explainable, externally validated GVHD prediction framework was developed using heterogeneous registry-derived datasets, with systematic characterization of calibration drift across multiple external cohorts, an analysis rarely reported in prior GVHD prediction literature. Predictive performance was modest for acute GVHD and moderate for chronic GVHD, constrained by missing immunobiological variables and incomplete HLA characterization. Per-cohort recalibration is required before clinical deployment, with prospective validation and benchmarking against established GVHD risk scores identified as priority next steps.
Open AccessExternal Validation and Calibration Assessment of Explainable Machine Learning Models for GVHD Prediction After Allogeneic HSCT
Background: Graft-versus-host disease (GVHD) remains a major determinant of morbidity and mortality following allogeneic hematopoietic stem cell transplantation (allo-HSCT). Existing GVHD prediction models demonstrate modest discrimination and limited generalizability, and calibration drift across external populations is rarely characterized despite its essential role in the clinical interpretability of predicted probabilities. Objectives: To develop and externally validate an explainable machine learning framework for predicting acute and chronic GVHD and associated overall survival in patients with acute myeloid leukemia (AML), acute lymphoblastic leukemia (ALL), and myelodysplastic syndromes (MDS) undergoing allo-HSCT, and to systematically characterize calibration across heterogeneous external validation cohorts to inform deployment requirements. Study Design: The model was developed on three publicly available registry-derived datasets (N = 2,509) and externally validated across six independent cohorts (N = 14,788) comprising adult and pediatric allo-HSCT recipients, including a regional Middle Eastern cohort (UAE and Jordan). A standardized preprocessing pipeline harmonized heterogeneous datasets. Gradient boosting models (CatBoost) were used for binary GVHD prediction; exploratory overall survival analysis used a Cox proportional hazards model with predicted acute GVHD risk as a covariate. Discrimination (AUROC with bootstrap 95% CI), calibration (logistic recalibration intercept and slope with analytical 95% CI), and feature importance (SHapley Additive exPlanations, SHAP) were assessed in training out-of-fold and all external cohorts. Results: In internal validation, AUROC was 0.63 (95% CI 0.61–0.65) for acute GVHD and 0.72 (95% CI 0.70–0.74) for chronic GVHD. External validation demonstrated AUROC ranges of 0.51–0.57 (acute) and 0.54–0.64 (chronic), with consistent performance across disease subgroups despite substantial heterogeneity in transplant practices and feature availability. In exploratory survival analysis, the acute-GVHD-informed Cox model achieved a training-cohort C-index of 0.679 (95% CI 0.658–0.697); external C-indices ranged from 0.47–0.53. Calibration analysis identified systematic external risk overestimation (negative calibration intercept in 10 of 11 evaluable external cohort-target combinations) with heterogeneous slope drift requiring cohort-specific recalibration. Key predictors included recipient age, graft source, conditioning intensity, GVHD prophylaxis, and HLA match ratio. Conclusions: An explainable, externally validated GVHD prediction framework was developed using heterogeneous registry-derived datasets, with systematic characterization of calibration drift across multiple external cohorts, an analysis rarely reported in prior GVHD prediction literature. Predictive performance was modest for acute GVHD and moderate for chronic GVHD, constrained by missing immunobiological variables and incomplete HLA characterization. Per-cohort recalibration is required before clinical deployment, with prospective validation and benchmarking against established GVHD risk scores identified as priority next steps.
- Open Access
Long-term outcomes and GVHD in patients receiving hematopoietic cell transplants abroad: A 14-year UAE multi-center cohort
Background: Hematopoietic cell transplant (HCT) outcomes are well characterized in clinical trials and international registries, but data remain scarce for patients who undergo transplantation abroad and return home for follow-up. While transplant centers typically report procedural details and early mortality for this cohort, long-term survival and chronic graft versus host disease (GVHD) outcomes are seldom captured, underscoring the need for comprehensive reporting. Methods: We conducted a retrospective, multi-center study of all HCT recipients followed at all the three tertiary hospitals in Abu Dhabi, UAE, between 2009 and 2023. Patient demographics, transplant characteristics, overall survival (OS), and GVHD incidence were extracted from medical records. Kaplan–Meier OS estimates were calculated for diseases with ≥20 cases; crude survival was reported for rarer indications. Results: A total of 454 HCTs were analyzed: 350 (77.1%) allogeneic and 104 (22.9%) autologous. Adults undergoing allogeneic HCT were relatively young (median age 35.3 years), reflecting referral practices and the UAE’s demographic profile. An unexpected female predominance was observed in pediatric malignancies and immune deficiencies. Matched unrelated donor (MUD) transplants were rare, and the trend remained low over time, underscoring reliance on matched related donor (MRD) and mismatched related donor (MMRD). The incidence of GVHD was high, approaching the upper range of international reports: 69.2% in adults and 45.7% in children. In adults with AML, acute GVHD was associated with an inferior 5-year OS (67.9% vs. 86.2%, p=0.036), whereas chronic GVHD did not significantly impact outcomes. In pediatric AML, both acute and chronic GVHD were linked to poorer survival (<50% at 5 years), while outcomes for B/T-ALL, thalassemia, and SCID exceeded 85–90% at 5 years regardless of GVHD status. Conclusions: HCT outcomes in this transplant tourism cohort were generally comparable to international benchmarks, yet notable for younger adult recipients, predominance of allogeneic over autologous procedures, limited use of MUDs, and a high incidence of GVHD. These observations highlight the urgent need to establish sustainable local transplant capacity, build donor registries, and implement aggressive GVHD prevention and treatment practices to improve outcomes in the UAE.
Open AccessLong-term outcomes and GVHD in patients receiving hematopoietic cell transplants abroad: A 14-year UAE multi-center cohort
Background: Hematopoietic cell transplant (HCT) outcomes are well characterized in clinical trials and international registries, but data remain scarce for patients who undergo transplantation abroad and return home for follow-up. While transplant centers typically report procedural details and early mortality for this cohort, long-term survival and chronic graft versus host disease (GVHD) outcomes are seldom captured, underscoring the need for comprehensive reporting. Methods: We conducted a retrospective, multi-center study of all HCT recipients followed at all the three tertiary hospitals in Abu Dhabi, UAE, between 2009 and 2023. Patient demographics, transplant characteristics, overall survival (OS), and GVHD incidence were extracted from medical records. Kaplan–Meier OS estimates were calculated for diseases with ≥20 cases; crude survival was reported for rarer indications. Results: A total of 454 HCTs were analyzed: 350 (77.1%) allogeneic and 104 (22.9%) autologous. Adults undergoing allogeneic HCT were relatively young (median age 35.3 years), reflecting referral practices and the UAE’s demographic profile. An unexpected female predominance was observed in pediatric malignancies and immune deficiencies. Matched unrelated donor (MUD) transplants were rare, and the trend remained low over time, underscoring reliance on matched related donor (MRD) and mismatched related donor (MMRD). The incidence of GVHD was high, approaching the upper range of international reports: 69.2% in adults and 45.7% in children. In adults with AML, acute GVHD was associated with an inferior 5-year OS (67.9% vs. 86.2%, p=0.036), whereas chronic GVHD did not significantly impact outcomes. In pediatric AML, both acute and chronic GVHD were linked to poorer survival (<50% at 5 years), while outcomes for B/T-ALL, thalassemia, and SCID exceeded 85–90% at 5 years regardless of GVHD status. Conclusions: HCT outcomes in this transplant tourism cohort were generally comparable to international benchmarks, yet notable for younger adult recipients, predominance of allogeneic over autologous procedures, limited use of MUDs, and a high incidence of GVHD. These observations highlight the urgent need to establish sustainable local transplant capacity, build donor registries, and implement aggressive GVHD prevention and treatment practices to improve outcomes in the UAE.
- Open Access
- 3 May 2025
- Published by Knowledge E DMCC in International Journal of Hematology-Oncology and Stem Cell Research
- Vol. 19  (2) , 138-150
High GVHD Prevalence in Travel-Based SCT despite Young Patients and HLA Matching
Background: Patients from regions without stem cell transplantation (SCT) facilities often seek treatment abroad and return home for post-transplant care. Although extensive data exist on graft-versus-host disease (GVHD) and its risk factors, information on international SCT patients returning to countries that lack transplant facilities and expertise is scarce and not well documented. Materials and Methods: We screened 149 transplant recipients and analyzed the data of 91 patients who received transplants abroad and were followed up at our center from January 2019 to December 2022. This observational study used data from electronic medical records and employed descriptive statistics, inferential tests, and relative risk calculations with forest plots to analyze the prevalence of GVDH and its key risk factors. Results: Of the recipients, 31.8% were residents of nine countries residing in the UAE, and 67.2% were UAE citizens. Adults comprised 48.3% of the recipients, whereas 51.7% were pediatric patients. Hematological malignancy was the most common indication (49%), primarily in adults. Siblings comprised the majority of donors (52.6%), followed by related (23.09%) and unrelated donors (8.9%). Most patients (69.2%) received HLA-identical transplants, followed by 21.9% who received haplo-identical transplants. Among adults, 62.2% developed GVHD compared to 26% of pediatric patients. Recipients from related HLA-identical donors had a 50% prevalence of GVDH, whereas those from unrelated identical donors had a 71% prevalence. The overall prevalence of GVDH was 50% in 87.9% of patients who received allogeneic SCTs. Conclusion: Despite favorable factors, such as young age and matched related donors, we found a high prevalence of GVDH. Ocular GVHD was less prevalent than expected, and lung GVHD was weakly correlated with established risk factors. Larger multicenter studies are needed to assess and confirm the effect of contributing factors.
- 3 May 2025
- Published by Knowledge E DMCC in International Journal of Hematology-Oncology and Stem Cell Research
- Vol. 19  (2) , 138-150
Open AccessHigh GVHD Prevalence in Travel-Based SCT despite Young Patients and HLA Matching
Background: Patients from regions without stem cell transplantation (SCT) facilities often seek treatment abroad and return home for post-transplant care. Although extensive data exist on graft-versus-host disease (GVHD) and its risk factors, information on international SCT patients returning to countries that lack transplant facilities and expertise is scarce and not well documented. Materials and Methods: We screened 149 transplant recipients and analyzed the data of 91 patients who received transplants abroad and were followed up at our center from January 2019 to December 2022. This observational study used data from electronic medical records and employed descriptive statistics, inferential tests, and relative risk calculations with forest plots to analyze the prevalence of GVDH and its key risk factors. Results: Of the recipients, 31.8% were residents of nine countries residing in the UAE, and 67.2% were UAE citizens. Adults comprised 48.3% of the recipients, whereas 51.7% were pediatric patients. Hematological malignancy was the most common indication (49%), primarily in adults. Siblings comprised the majority of donors (52.6%), followed by related (23.09%) and unrelated donors (8.9%). Most patients (69.2%) received HLA-identical transplants, followed by 21.9% who received haplo-identical transplants. Among adults, 62.2% developed GVHD compared to 26% of pediatric patients. Recipients from related HLA-identical donors had a 50% prevalence of GVDH, whereas those from unrelated identical donors had a 71% prevalence. The overall prevalence of GVDH was 50% in 87.9% of patients who received allogeneic SCTs. Conclusion: Despite favorable factors, such as young age and matched related donors, we found a high prevalence of GVDH. Ocular GVHD was less prevalent than expected, and lung GVHD was weakly correlated with established risk factors. Larger multicenter studies are needed to assess and confirm the effect of contributing factors.
- Open Access
- 1 March 2025
- Published by AME Publishing Company in Journal of Medical Artificial Intelligence
- Vol. 8, 5
Novel hierarchical deep learning models predict type of leukemia from whole slide microscopic images of peripheral blood
Background: Diagnosis of leukemia relies on microscopic examination of suspected peripheral blood smears (PBS) by pathologists. However, this challenging and potentially error-prone process is further limited by the availability of pathologists. Developing a clinically applicable predictive artificial intelligence (AI) model offers a potential solution to these limitations. This study aimed to develop an AI model that predicts leukemia from microscopic images of peripheral blood smear. Methods: We developed hierarchical deep learning (DL) pipelines that were trained and validated on 7,255 high-power field (HPF) microscopy images collected from pre-diagnosed cases at our centre between January 2021 to August 2023. The proposed pipelines employed a high performing binary DL model in step 1 and multiclass DL models in step 2 to predict the label of each image from a slide, and then aggregate the results to provide a patient-level diagnostic prediction. This approach mimics the examination of PBS by trained hematopathologists, who examine multiple HPF patches under a microscope to predict the type of leukemia. The pipelines’ performance was assessed using F1 score, sensitivity, specificity, and accuracy, then compared against the three pathologists using Cohen’s kappa score. Results: The 3-class pipeline categorizes the slide as acute leukemia, chronic leukemia, or no leukemia. The F1 score, sensitivity, specificity, and accuracy were 94%, 94%, 95%, and 92% respectively. This pipeline outperformed the pathologists in all metrics. The agreement between this pipeline and pathologists ranged between 74–77%, while the agreement amongst the pathologists ranged from 82–87%. The 5-class pipeline categorizes the slide into acute myeloid leukemia (AML), acute lymphoblastic leukemia (ALL), chronic myeloid leukemia (CML), chronic lymphoblastic leukemia (CLL), and no leukemia. It achieved an F1 score of 77%, sensitivity of 80%, specificity of 94%, and accuracy of 70%. The 5-class pipeline outperformed pathologists in the CML and CLL classes but was inferior in other classes. The agreement between this pipeline and pathologists ranged between 52–53%, while the agreement amongst the pathologists ranged from 72–79%. Conclusions: Acute and chronic leukemia can be predicted with high sensitivity and specificity from whole-slide microscopic images of PBS by utilizing three deep-learning models in a hierarchical pattern and aggregating the results. This approach can efficiently predict and differentiate CLL from CML, but not ALL from AML. Applying cell segmentation in this level of the pipeline could improve the prediction in these classes. These pipelines can be applied in limited infrastructure settings to potentially identify types of leukemia with greater reliability.
- 1 March 2025
- Published by AME Publishing Company in Journal of Medical Artificial Intelligence
- Vol. 8, 5
Open AccessNovel hierarchical deep learning models predict type of leukemia from whole slide microscopic images of peripheral blood
Background: Diagnosis of leukemia relies on microscopic examination of suspected peripheral blood smears (PBS) by pathologists. However, this challenging and potentially error-prone process is further limited by the availability of pathologists. Developing a clinically applicable predictive artificial intelligence (AI) model offers a potential solution to these limitations. This study aimed to develop an AI model that predicts leukemia from microscopic images of peripheral blood smear. Methods: We developed hierarchical deep learning (DL) pipelines that were trained and validated on 7,255 high-power field (HPF) microscopy images collected from pre-diagnosed cases at our centre between January 2021 to August 2023. The proposed pipelines employed a high performing binary DL model in step 1 and multiclass DL models in step 2 to predict the label of each image from a slide, and then aggregate the results to provide a patient-level diagnostic prediction. This approach mimics the examination of PBS by trained hematopathologists, who examine multiple HPF patches under a microscope to predict the type of leukemia. The pipelines’ performance was assessed using F1 score, sensitivity, specificity, and accuracy, then compared against the three pathologists using Cohen’s kappa score. Results: The 3-class pipeline categorizes the slide as acute leukemia, chronic leukemia, or no leukemia. The F1 score, sensitivity, specificity, and accuracy were 94%, 94%, 95%, and 92% respectively. This pipeline outperformed the pathologists in all metrics. The agreement between this pipeline and pathologists ranged between 74–77%, while the agreement amongst the pathologists ranged from 82–87%. The 5-class pipeline categorizes the slide into acute myeloid leukemia (AML), acute lymphoblastic leukemia (ALL), chronic myeloid leukemia (CML), chronic lymphoblastic leukemia (CLL), and no leukemia. It achieved an F1 score of 77%, sensitivity of 80%, specificity of 94%, and accuracy of 70%. The 5-class pipeline outperformed pathologists in the CML and CLL classes but was inferior in other classes. The agreement between this pipeline and pathologists ranged between 52–53%, while the agreement amongst the pathologists ranged from 72–79%. Conclusions: Acute and chronic leukemia can be predicted with high sensitivity and specificity from whole-slide microscopic images of PBS by utilizing three deep-learning models in a hierarchical pattern and aggregating the results. This approach can efficiently predict and differentiate CLL from CML, but not ALL from AML. Applying cell segmentation in this level of the pipeline could improve the prediction in these classes. These pipelines can be applied in limited infrastructure settings to potentially identify types of leukemia with greater reliability.
- Open Access
Breaking Down the Hierarchy: A New Approach to Leukemia Classification
The complexities inherent to leukemia, multifaceted cancer affecting white blood cells, pose considerable diagnostic and treatment challenges, primarily due to reliance on laborious morphological analyses and expert judgment that are susceptible to errors. Addressing these challenges, this study presents a refined, comprehensive strategy leveraging advanced deep-learning techniques for the classification of leukemia subtypes. We commence by developing a hierarchical label taxonomy, paving the way for differentiating between various subtypes of leukemia. The research further introduces a novel hierarchical approach inspired by clinical procedures capable of accurately classifying diverse types of leukemia alongside reactive and healthy cells. An integral part of this study involves a meticulous examination of the performance of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) as classifiers. The proposed method exhibits an impressive success rate, achieving approximately 90\% accuracy across all leukemia subtypes, as substantiated by our experimental results. A visual representation of the experimental findings is provided to enhance the model's explainability and aid in understanding the classification process.
Open AccessBreaking Down the Hierarchy: A New Approach to Leukemia Classification
The complexities inherent to leukemia, multifaceted cancer affecting white blood cells, pose considerable diagnostic and treatment challenges, primarily due to reliance on laborious morphological analyses and expert judgment that are susceptible to errors. Addressing these challenges, this study presents a refined, comprehensive strategy leveraging advanced deep-learning techniques for the classification of leukemia subtypes. We commence by developing a hierarchical label taxonomy, paving the way for differentiating between various subtypes of leukemia. The research further introduces a novel hierarchical approach inspired by clinical procedures capable of accurately classifying diverse types of leukemia alongside reactive and healthy cells. An integral part of this study involves a meticulous examination of the performance of Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs) as classifiers. The proposed method exhibits an impressive success rate, achieving approximately 90\% accuracy across all leukemia subtypes, as substantiated by our experimental results. A visual representation of the experimental findings is provided to enhance the model's explainability and aid in understanding the classification process.
- Open Access
- 31 July 2024
- Published by MDPI AG in Preprints.org
Elevated Graft-versus-Host Disease Risk Among International Stem Cell Transplant Recipients: A Pilot Study from the UAE
Patients from regions without stem cell transplant (SCT) facilities often seek treatment abroad and return home for post-transplant care. While extensive data exists on GVHD and its risk factors, the prevalence of GVHD in international SCT patients returning to countries without transplant facilities, where multiple factors compromise post-transplant care, is not well documented. We screened 149 transplant recipients and analyzed data from 91 who received transplants abroad and were followed at our center from January 2019 to December 2022. This observational study used data from electronic medical records (EMR) and employed descriptive statistics, inferential tests, and relative risk calculations with forest plots to analyze GVHD prevalence and key risk factors. Of the recipients, 31.8% were residents from nine countries living in the UAE, and 67.2% were UAE citizens. Adults comprised 48.3% of the recipients, and 51.7% were pediatric. Hematological malignancies were the most common indication (49%), primarily in adults. Siblings were the majority of donors (52.6%), followed by related donors (23.09%), and unrelated donors (8.9%). Most (69.2%) received HLA-identical transplants followed by 21.9% who received haploidentical. Among adults, 62.2% developed GVHD, compared to 26% of pediatric patients. Recipients with related HLA-identical donors had a 50% GVHD prevalence, while those with unrelated identical donors had 71%. The overall GVHD prevalence was 50% among the 87.9% who received allogeneic SCTs. Despite favorable factors, GVHD prevalence remains high. Larger multicenter studies are needed to identify and assess the impact of contributing factors.
- 31 July 2024
- Published by MDPI AG in Preprints.org
Open AccessElevated Graft-versus-Host Disease Risk Among International Stem Cell Transplant Recipients: A Pilot Study from the UAE
Patients from regions without stem cell transplant (SCT) facilities often seek treatment abroad and return home for post-transplant care. While extensive data exists on GVHD and its risk factors, the prevalence of GVHD in international SCT patients returning to countries without transplant facilities, where multiple factors compromise post-transplant care, is not well documented. We screened 149 transplant recipients and analyzed data from 91 who received transplants abroad and were followed at our center from January 2019 to December 2022. This observational study used data from electronic medical records (EMR) and employed descriptive statistics, inferential tests, and relative risk calculations with forest plots to analyze GVHD prevalence and key risk factors. Of the recipients, 31.8% were residents from nine countries living in the UAE, and 67.2% were UAE citizens. Adults comprised 48.3% of the recipients, and 51.7% were pediatric. Hematological malignancies were the most common indication (49%), primarily in adults. Siblings were the majority of donors (52.6%), followed by related donors (23.09%), and unrelated donors (8.9%). Most (69.2%) received HLA-identical transplants followed by 21.9% who received haploidentical. Among adults, 62.2% developed GVHD, compared to 26% of pediatric patients. Recipients with related HLA-identical donors had a 50% GVHD prevalence, while those with unrelated identical donors had 71%. The overall GVHD prevalence was 50% among the 87.9% who received allogeneic SCTs. Despite favorable factors, GVHD prevalence remains high. Larger multicenter studies are needed to identify and assess the impact of contributing factors.
- Open Access
- 24 July 2024
- Published by Baishideng Publishing Group Inc. in World Journal of Clinical Oncology
- Vol. 15  (7) , 848-858
Low testing rates and high BRCA prevalence: Poly (ADP-ribose) polymerase inhibitor use in Middle East BRCA/homologous recombination deficiency-positive cancer patients
BACKGROUND Poly (ADP-ribose) polymerase inhibitors (PARPis) are approved as first-line therapies for breast cancer gene (BRCA )-positive, human epidermal growth factor receptor 2-negative locally advanced or metastatic breast cancer. They are also effective for new and recurrent ovarian cancers that are BRCA - or homologous recombination deficiency (HRD)-positive. However, data on these mutations and PARPi use in the Middle East are limited. AIM To assess BRCA /HRD prevalence and PARPi use in patients in the Middle East with breast/ovarian cancer. METHODS This was a single-center retrospective study of 57 of 472 breast cancer patients tested for BRCA mutations, and 25 of 65 ovarian cancer patients tested for HRD. These adult patients participated in at least four visits to the oncology service at our center between August 2021 and May 2023. Data were summarized using descriptive statistics and compared using counts and percentages. Response to treatment was assessed using Response Evaluation Criteria in Solid Tumors criteria. RESULTS Among the 472 breast cancer patients, 12.1% underwent BRCA testing, and 38.5% of 65 ovarian cancer patients received HRD testing. Pathogenic mutations were found in 25.6% of the tested patients: 26.3% breast cancers had germline BRCA (gBRCA ) mutations and 24.0% ovarian cancers showed HRD. Notably, 40.0% of gBRCA -positive breast cancers and 66.0% of HRD-positive ovarian cancers were Middle Eastern and Asian patients, respectively. PARPi treatment was used in 5 (33.3%) gBRCA -positive breast cancer patients as first-line therapy (n = 1; 7-months progression-free), for maintenance (n = 2; > 15-months progression-free), or at later stages due to compliance issues (n = 2). Four patients (66.6%) with HRD-positive ovarian cancer received PARPi and all remained progression-free. CONCLUSION Lower testing rates but higher BRCA mutations in breast cancer were found. Ethnicity reflected United Arab Emirates demographics, with breast cancer in Middle Eastern and ovarian cancer in Asian patients.
- 24 July 2024
- Published by Baishideng Publishing Group Inc. in World Journal of Clinical Oncology
- Vol. 15  (7) , 848-858
Open AccessLow testing rates and high BRCA prevalence: Poly (ADP-ribose) polymerase inhibitor use in Middle East BRCA/homologous recombination deficiency-positive cancer patients
BACKGROUND Poly (ADP-ribose) polymerase inhibitors (PARPis) are approved as first-line therapies for breast cancer gene (BRCA )-positive, human epidermal growth factor receptor 2-negative locally advanced or metastatic breast cancer. They are also effective for new and recurrent ovarian cancers that are BRCA - or homologous recombination deficiency (HRD)-positive. However, data on these mutations and PARPi use in the Middle East are limited. AIM To assess BRCA /HRD prevalence and PARPi use in patients in the Middle East with breast/ovarian cancer. METHODS This was a single-center retrospective study of 57 of 472 breast cancer patients tested for BRCA mutations, and 25 of 65 ovarian cancer patients tested for HRD. These adult patients participated in at least four visits to the oncology service at our center between August 2021 and May 2023. Data were summarized using descriptive statistics and compared using counts and percentages. Response to treatment was assessed using Response Evaluation Criteria in Solid Tumors criteria. RESULTS Among the 472 breast cancer patients, 12.1% underwent BRCA testing, and 38.5% of 65 ovarian cancer patients received HRD testing. Pathogenic mutations were found in 25.6% of the tested patients: 26.3% breast cancers had germline BRCA (gBRCA ) mutations and 24.0% ovarian cancers showed HRD. Notably, 40.0% of gBRCA -positive breast cancers and 66.0% of HRD-positive ovarian cancers were Middle Eastern and Asian patients, respectively. PARPi treatment was used in 5 (33.3%) gBRCA -positive breast cancer patients as first-line therapy (n = 1; 7-months progression-free), for maintenance (n = 2; > 15-months progression-free), or at later stages due to compliance issues (n = 2). Four patients (66.6%) with HRD-positive ovarian cancer received PARPi and all remained progression-free. CONCLUSION Lower testing rates but higher BRCA mutations in breast cancer were found. Ethnicity reflected United Arab Emirates demographics, with breast cancer in Middle Eastern and ovarian cancer in Asian patients.