Mohamed Kamal
Research Subjects
Mohamed Kamal has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Abdelrahman Enayet
Department of Neurosurgery, Children’s Cancer Hospital, Cairo, Egypt
6 shared publications - Amal Refaat
Department of Radiology, Children’s Cancer Hospital, Cairo, Egypt
6 shared publications - Eman Eldebawy
Department of Radiation Oncology, Children’s Cancer Hospital, Cairo, Egypt
6 shared publications - Eslam Maher
Experimental Cancer Medicine Centre (ECMC), Department of Surgery and Cancer, Imperial College London London UK
6 shared publications - Hala Taha
Department of Mathematical Sciences, College of Science, Princess Nourah Bint Abdulrahman University, P. O. Box 84428, Riyadh 11671, Saudi Arabia
6 shared publications - Madiha Awad
Department of Pediatric Oncology, Children’s Cancer Hospital, Cairo, Egypt
6 shared publications
Latest Publications
- Open Access
Automated Antibiogram Extraction from Unstructured Microbiology Reports: A Comparative Performance and Efficiency Analysis of Domain-Specific Named Entity Recognition (NER) Pipelines
Antibiograms are essential tools in antimicrobial stewardship programs (ASPs), guiding empirical antibiotic therapy and tracking antimicrobial resistance (AMR) trends. However, the manual compilation of antibiograms from unstructured microbiology reports is labor-intensive and prone to delays. Here, we present a comparative study of three Natural Language Processing (NLP) approaches for automating data extraction from free-text reports: a rule-based Named Entity Recognition (NER) system, a statistical NER model using the spaCy library, and a transformer-based question-answering (QA) model leveraging DistilBERT. We generated a synthetic dataset of 3,000 microbiology reports to evaluate these methods, focusing on extraction accuracy (precision, recall, F1-score) and computational efficiency. The rule-based NER achieved perfect accuracy (F1 = 1.00) with minimal computational resources, making it highly suitable for real-time deployment. The spaCy model, after domain-specific fine-tuning, demonstrated strong performance (F1 = 1.00), effectively handling linguistic variations. In contrast, the transformer QA model showed moderate accuracy, excelling at extracting organism names but underperforming in detecting contamination status due to contextual ambiguities (F1 = 0.68-0.8). Computational efficiency analysis revealed that the rule-based and spaCy NER models could process reports rapidly with limited resources, while the transformer QA model required substantial computational power, potentially limiting its clinical utility. Additionally, we developed a prototype Expert System using R Shiny employing the rule-based NER to integrate extracted data into a real-time antibiogram dashboard, demonstrating the feasibility of these approaches in practical settings. The STEWEX (Stewardship Expert System) prototype has the capabilities of real-time building of fully functional antibiogram from simulated unstructured reports and simulated antibiotic susceptibility results. In conclusion, our results suggest that while advanced NLP methods offer flexibility, rule-based NER systems provide unparalleled accuracy and efficiency for data extraction from unstructured reports in ASPs, which represents bottle neck in development of antibiogram. Future efforts will focus on validating these approaches using real-world clinical data with the ultimate goal of fully automating antibiogram generation to support data-driven antimicrobial stewardship.
Open AccessAutomated Antibiogram Extraction from Unstructured Microbiology Reports: A Comparative Performance and Efficiency Analysis of Domain-Specific Named Entity Recognition (NER) Pipelines
Antibiograms are essential tools in antimicrobial stewardship programs (ASPs), guiding empirical antibiotic therapy and tracking antimicrobial resistance (AMR) trends. However, the manual compilation of antibiograms from unstructured microbiology reports is labor-intensive and prone to delays. Here, we present a comparative study of three Natural Language Processing (NLP) approaches for automating data extraction from free-text reports: a rule-based Named Entity Recognition (NER) system, a statistical NER model using the spaCy library, and a transformer-based question-answering (QA) model leveraging DistilBERT. We generated a synthetic dataset of 3,000 microbiology reports to evaluate these methods, focusing on extraction accuracy (precision, recall, F1-score) and computational efficiency. The rule-based NER achieved perfect accuracy (F1 = 1.00) with minimal computational resources, making it highly suitable for real-time deployment. The spaCy model, after domain-specific fine-tuning, demonstrated strong performance (F1 = 1.00), effectively handling linguistic variations. In contrast, the transformer QA model showed moderate accuracy, excelling at extracting organism names but underperforming in detecting contamination status due to contextual ambiguities (F1 = 0.68-0.8). Computational efficiency analysis revealed that the rule-based and spaCy NER models could process reports rapidly with limited resources, while the transformer QA model required substantial computational power, potentially limiting its clinical utility. Additionally, we developed a prototype Expert System using R Shiny employing the rule-based NER to integrate extracted data into a real-time antibiogram dashboard, demonstrating the feasibility of these approaches in practical settings. The STEWEX (Stewardship Expert System) prototype has the capabilities of real-time building of fully functional antibiogram from simulated unstructured reports and simulated antibiotic susceptibility results. In conclusion, our results suggest that while advanced NLP methods offer flexibility, rule-based NER systems provide unparalleled accuracy and efficiency for data extraction from unstructured reports in ASPs, which represents bottle neck in development of antibiogram. Future efforts will focus on validating these approaches using real-world clinical data with the ultimate goal of fully automating antibiogram generation to support data-driven antimicrobial stewardship.
- Open Access
- 3 March 2025
- Published by American Association for Cancer Research (AACR)
Supplementary Table S2 from Epidemiology and Clinical Outcomes of Childhood Central Nervous System Cancers in a Large Low/Middle-Income Country Pediatric Oncology Center: A Report on 5,051 Kids
Diagnoses of children with CNS tumors according to the International Classification of Childhood Cancer (ICCC), third edition (ICCC-3). We annotated our cases according to ICCC-3 which is based on ICD-O-3 codes for both topographies and morphologies, to categorize childhood cancers.
- 3 March 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S2 from Epidemiology and Clinical Outcomes of Childhood Central Nervous System Cancers in a Large Low/Middle-Income Country Pediatric Oncology Center: A Report on 5,051 Kids
Diagnoses of children with CNS tumors according to the International Classification of Childhood Cancer (ICCC), third edition (ICCC-3). We annotated our cases according to ICCC-3 which is based on ICD-O-3 codes for both topographies and morphologies, to categorize childhood cancers.
- Open Access
- 3 March 2025
- Published by American Association for Cancer Research (AACR)
Data from Epidemiology and Clinical Outcomes of Childhood Central Nervous System Cancers in a Large Low/Middle-Income Country Pediatric Oncology Center: A Report on 5,051 Kids
Background:Central nervous system (CNS) tumors are the leading cause of cancer-related deaths in children. Although most cases come from low- and middle-income countries (LMIC) where their prognosis is worse, few epidemiologic studies are conducted in these regions.Methods:We conducted a registry-based cohort study for childhood CNS tumors at Children’s Cancer Hospital, Egypt, over 15 years. Unified treatment protocols were implemented. Survival analyses were conducted using the Kaplan–Meier function. Cases were additionally annotated using the International Classification of Childhood Cancer-3 classification.Results:In total, 5,051 children ≤18 years of age were identified, accounting for 20% of all childhood cancers treated at Children’s Cancer Hospital, Egypt. The most common tumor sites were the posterior fossa (36.8%) and brainstem (17.7%). Pathologies were predominantly astrocytic (n = 1,360; 26.9%) and embryonal (n = 1,003; 19.9%) in origin. The 5-year overall survival (OS) and event-free survival for all cases were 64.6% and 51.8%, respectively. More specifically, 1,421 low-grade gliomas were identified, with a 5-year OS of 91.1%. Medulloblastoma (n = 801) recorded a 5-year OS of 66%. The entity with the worst prognosis was diffuse intrinsic pontine glioma (n = 633), with a 5-year OS of 3.2%.Conclusions:We report on a large number of childhood CNS tumors from an LMIC. This study underscores the need to understand the burden of childhood brain tumors and its outcomes in resource-constrained settings.Impact:This study reports on the epidemiology and clinical outcomes of 5,000+ children with CNS tumors from a specialized LMIC center. Despite the lack of many sophisticated and advanced facilities, LMICs can improve the clinical end-results with experience and augmented efforts.
- 3 March 2025
- Published by American Association for Cancer Research (AACR)
Open AccessData from Epidemiology and Clinical Outcomes of Childhood Central Nervous System Cancers in a Large Low/Middle-Income Country Pediatric Oncology Center: A Report on 5,051 Kids
Background:Central nervous system (CNS) tumors are the leading cause of cancer-related deaths in children. Although most cases come from low- and middle-income countries (LMIC) where their prognosis is worse, few epidemiologic studies are conducted in these regions.Methods:We conducted a registry-based cohort study for childhood CNS tumors at Children’s Cancer Hospital, Egypt, over 15 years. Unified treatment protocols were implemented. Survival analyses were conducted using the Kaplan–Meier function. Cases were additionally annotated using the International Classification of Childhood Cancer-3 classification.Results:In total, 5,051 children ≤18 years of age were identified, accounting for 20% of all childhood cancers treated at Children’s Cancer Hospital, Egypt. The most common tumor sites were the posterior fossa (36.8%) and brainstem (17.7%). Pathologies were predominantly astrocytic (n = 1,360; 26.9%) and embryonal (n = 1,003; 19.9%) in origin. The 5-year overall survival (OS) and event-free survival for all cases were 64.6% and 51.8%, respectively. More specifically, 1,421 low-grade gliomas were identified, with a 5-year OS of 91.1%. Medulloblastoma (n = 801) recorded a 5-year OS of 66%. The entity with the worst prognosis was diffuse intrinsic pontine glioma (n = 633), with a 5-year OS of 3.2%.Conclusions:We report on a large number of childhood CNS tumors from an LMIC. This study underscores the need to understand the burden of childhood brain tumors and its outcomes in resource-constrained settings.Impact:This study reports on the epidemiology and clinical outcomes of 5,000+ children with CNS tumors from a specialized LMIC center. Despite the lack of many sophisticated and advanced facilities, LMICs can improve the clinical end-results with experience and augmented efforts.
- Open Access
- 3 March 2025
- Published by American Association for Cancer Research (AACR)
Supplementary Table S1 from Epidemiology and Clinical Outcomes of Childhood Central Nervous System Cancers in a Large Low/Middle-Income Country Pediatric Oncology Center: A Report on 5,051 Kids
Detailed diagnoses by pathology. The pathological subtypes discussed in the study are presented in more detail with all the histological diagnoses and their grade.
- 3 March 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S1 from Epidemiology and Clinical Outcomes of Childhood Central Nervous System Cancers in a Large Low/Middle-Income Country Pediatric Oncology Center: A Report on 5,051 Kids
Detailed diagnoses by pathology. The pathological subtypes discussed in the study are presented in more detail with all the histological diagnoses and their grade.
- Open Access
- 3 March 2025
- Published by American Association for Cancer Research (AACR)
Supplementary Figure S1 from Epidemiology and Clinical Outcomes of Childhood Central Nervous System Cancers in a Large Low/Middle-Income Country Pediatric Oncology Center: A Report on 5,051 Kids
Detailed pathological diagnosis for all childhood CNS tumors included in the cohort. Bars represent the count of each subtype. Pilocytic astrocytoma was the most common subtype.
- 3 March 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Figure S1 from Epidemiology and Clinical Outcomes of Childhood Central Nervous System Cancers in a Large Low/Middle-Income Country Pediatric Oncology Center: A Report on 5,051 Kids
Detailed pathological diagnosis for all childhood CNS tumors included in the cohort. Bars represent the count of each subtype. Pilocytic astrocytoma was the most common subtype.
- Open Access
- 3 March 2025
- Published by American Association for Cancer Research (AACR)
Supplementary Table S3 from Epidemiology and Clinical Outcomes of Childhood Central Nervous System Cancers in a Large Low/Middle-Income Country Pediatric Oncology Center: A Report on 5,051 Kids
Survival analysis by subgroups reclassified based on the International Classification of Childhood Cancer (ICCC), third edition (ICCC-3). Five-year overall and event-free survival alongside their 95% CIs.
- 3 March 2025
- Published by American Association for Cancer Research (AACR)
Open AccessSupplementary Table S3 from Epidemiology and Clinical Outcomes of Childhood Central Nervous System Cancers in a Large Low/Middle-Income Country Pediatric Oncology Center: A Report on 5,051 Kids
Survival analysis by subgroups reclassified based on the International Classification of Childhood Cancer (ICCC), third edition (ICCC-3). Five-year overall and event-free survival alongside their 95% CIs.
- 8 January 2025
- Published by American Association for Cancer Research (AACR) in Cancer Epidemiology, Biomarkers & Prevention
- p. OF1-OF8
Epidemiology and Clinical Outcomes of Childhood Central Nervous System Cancers in a Large Low/Middle-Income Country Pediatric Oncology Center: A Report on 5,051 Kids
Background: Central nervous system (CNS) tumors are the leading cause of cancer-related deaths in children. Although most cases come from low- and middle-income countries (LMIC) where their prognosis is worse, few epidemiologic studies are conducted in these regions. Methods: We conducted a registry-based cohort study for childhood CNS tumors at Children’s Cancer Hospital, Egypt, over 15 years. Unified treatment protocols were implemented. Survival analyses were conducted using the Kaplan–Meier function. Cases were additionally annotated using the International Classification of Childhood Cancer-3 classification. Results: In total, 5,051 children ≤18 years of age were identified, accounting for 20% of all childhood cancers treated at Children’s Cancer Hospital, Egypt. The most common tumor sites were the posterior fossa (36.8%) and brainstem (17.7%). Pathologies were predominantly astrocytic (n = 1,360; 26.9%) and embryonal (n = 1,003; 19.9%) in origin. The 5-year overall survival (OS) and event-free survival for all cases were 64.6% and 51.8%, respectively. More specifically, 1,421 low-grade gliomas were identified, with a 5-year OS of 91.1%. Medulloblastoma (n = 801) recorded a 5-year OS of 66%. The entity with the worst prognosis was diffuse intrinsic pontine glioma (n = 633), with a 5-year OS of 3.2%. Conclusions: We report on a large number of childhood CNS tumors from an LMIC. This study underscores the need to understand the burden of childhood brain tumors and its outcomes in resource-constrained settings. Impact: This study reports on the epidemiology and clinical outcomes of 5,000+ children with CNS tumors from a specialized LMIC center. Despite the lack of many sophisticated and advanced facilities, LMICs can improve the clinical end-results with experience and augmented efforts.
- 8 January 2025
- Published by American Association for Cancer Research (AACR) in Cancer Epidemiology, Biomarkers & Prevention
- p. OF1-OF8
Epidemiology and Clinical Outcomes of Childhood Central Nervous System Cancers in a Large Low/Middle-Income Country Pediatric Oncology Center: A Report on 5,051 Kids
Background: Central nervous system (CNS) tumors are the leading cause of cancer-related deaths in children. Although most cases come from low- and middle-income countries (LMIC) where their prognosis is worse, few epidemiologic studies are conducted in these regions. Methods: We conducted a registry-based cohort study for childhood CNS tumors at Children’s Cancer Hospital, Egypt, over 15 years. Unified treatment protocols were implemented. Survival analyses were conducted using the Kaplan–Meier function. Cases were additionally annotated using the International Classification of Childhood Cancer-3 classification. Results: In total, 5,051 children ≤18 years of age were identified, accounting for 20% of all childhood cancers treated at Children’s Cancer Hospital, Egypt. The most common tumor sites were the posterior fossa (36.8%) and brainstem (17.7%). Pathologies were predominantly astrocytic (n = 1,360; 26.9%) and embryonal (n = 1,003; 19.9%) in origin. The 5-year overall survival (OS) and event-free survival for all cases were 64.6% and 51.8%, respectively. More specifically, 1,421 low-grade gliomas were identified, with a 5-year OS of 91.1%. Medulloblastoma (n = 801) recorded a 5-year OS of 66%. The entity with the worst prognosis was diffuse intrinsic pontine glioma (n = 633), with a 5-year OS of 3.2%. Conclusions: We report on a large number of childhood CNS tumors from an LMIC. This study underscores the need to understand the burden of childhood brain tumors and its outcomes in resource-constrained settings. Impact: This study reports on the epidemiology and clinical outcomes of 5,000+ children with CNS tumors from a specialized LMIC center. Despite the lack of many sophisticated and advanced facilities, LMICs can improve the clinical end-results with experience and augmented efforts.
- 3 May 2024
- Published by Taylor & Francis in Personalized Medicine
- Vol. 21 (3) , 151-161
Improving resource allocation in the precision medicine Era: a simulation-based approach using R
The application of personalized medicine in developing countries is a major challenge, especially for those with poor economic status. A critical factor in improving the application of personalized medicine is the efficient allocation of resources. In healthcare systems, optimizing resource allocation without compromising patient care is paramount. This tutorial employs a simulation-based approach to evaluate the efficiency of bed allocation within a hospital setting. Utilizing a patient arrival model with an exponential distribution, we simulated patient trajectories to examine system bottlenecks, particularly focusing on waiting times. Initial simulations painted a scenario of an 'unstable' system, where waiting times and queue lengths surged due to the limited number of available beds. This research offers insights for hospital management on resource optimization leading to improved patient care.
- 3 May 2024
- Published by Taylor & Francis in Personalized Medicine
- Vol. 21 (3) , 151-161
Improving resource allocation in the precision medicine Era: a simulation-based approach using R
The application of personalized medicine in developing countries is a major challenge, especially for those with poor economic status. A critical factor in improving the application of personalized medicine is the efficient allocation of resources. In healthcare systems, optimizing resource allocation without compromising patient care is paramount. This tutorial employs a simulation-based approach to evaluate the efficiency of bed allocation within a hospital setting. Utilizing a patient arrival model with an exponential distribution, we simulated patient trajectories to examine system bottlenecks, particularly focusing on waiting times. Initial simulations painted a scenario of an 'unstable' system, where waiting times and queue lengths surged due to the limited number of available beds. This research offers insights for hospital management on resource optimization leading to improved patient care.
- Open Access
Unlocking Efficient Hospital Operations: Discrete Event Simulation in R
In healthcare systems, optimizing resource allocation without compromising patient care is paramount. This study employs a simulation-based approach to evaluate the efficiency of bed allocation within a hospital setting. Utilizing a patient arrival model with an exponential distribution, we simulated patient trajectories to examine system bottlenecks, particularly focusing on waiting times. Initial simulations painted a scenario of an “unstable” system, where waiting times and queue lengths surged due to the limited number of available beds. Through iterative simulations, we explored the operational research question: “What is the minimum number of beds required to stabilize the system?” Our results, visualized in a series of detailed metrics plots, suggest that the addition of a specific number of beds can significantly reduce patient waiting time and stabilize the system. This research offers insights for hospital management on resource optimization, potentially leading to improved patient care and reduced operational costs.
Open AccessUnlocking Efficient Hospital Operations: Discrete Event Simulation in R
In healthcare systems, optimizing resource allocation without compromising patient care is paramount. This study employs a simulation-based approach to evaluate the efficiency of bed allocation within a hospital setting. Utilizing a patient arrival model with an exponential distribution, we simulated patient trajectories to examine system bottlenecks, particularly focusing on waiting times. Initial simulations painted a scenario of an “unstable” system, where waiting times and queue lengths surged due to the limited number of available beds. Through iterative simulations, we explored the operational research question: “What is the minimum number of beds required to stabilize the system?” Our results, visualized in a series of detailed metrics plots, suggest that the addition of a specific number of beds can significantly reduce patient waiting time and stabilize the system. This research offers insights for hospital management on resource optimization, potentially leading to improved patient care and reduced operational costs.
- 1 May 1992
- Published by Oxford University Press (OUP) in Transactions of the Royal Society of Tropical Medicine and Hygiene
- Vol. 86 (3) , 300-301
Tropical spastic paraparesis associated with HTLV-1 in Egypt
Niel T. Constantine, Daniel A. Scott, Mohamed Kamal, Chester R. Roberts, Arndt Rolfs, H.C. Schumacher, Peter Marx; Tropical spastic paraparesis associated with
- 1 May 1992
- Published by Oxford University Press (OUP) in Transactions of the Royal Society of Tropical Medicine and Hygiene
- Vol. 86 (3) , 300-301
Tropical spastic paraparesis associated with HTLV-1 in Egypt
Niel T. Constantine, Daniel A. Scott, Mohamed Kamal, Chester R. Roberts, Arndt Rolfs, H.C. Schumacher, Peter Marx; Tropical spastic paraparesis associated with