Oluwafisayo Babatope Ayoade
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
Oluwafisayo Babatope Ayoade has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Chun Ruan
School of Computer, Data and Mathematical Sciences, Western Sydney University, Sydney 2751, Australia
4 shared publications - Joseph Bamidele Awotunde
University of Ilorin
4 shared publications - Seyed Shahrestani
School of Computer, Data and Mathematical Sciences, Western Sydney University, Sydney 2751, Australia
4 shared publications Joseph Bamidele Awotunde
3 shared publicationsAgbotiname Lucky Imoize
University of Lagos
2 shared publicationsAyorinde Oladele Idowu
Bamidele Olumilua University of Education
2 shared publications
Latest Publications
- Open Access
- 2 September 2026
- Published by Elsevier in SSRN Electronic Journal
Earth-Human Digital Twin: A Physics-Informed Artificial Intelligence Framework for Predicting Climate-Induced Human Vulnerability and Migration Using WorldPop, Satellite Earth Observation, and CMIP6 Climate Projections
Climate induced migration is an imminent global challenge formed from the interplay of climate change, environmental degradation, exposure to populations, and vulnerability. An Earth-human digital twin framework was developed in this study using 51 variables sourced from CMIP6 climate projections, ERA5 reanalysis, WorldPop, Earth observation, socioeconomic and socio-political and other information on past migration and more recently to assess future human vulnerability and displacement scenario risk. Using machine learning, deep learning, and physics-informed artificial intelligence approaches, a global 1 km spatial resolution database covering 2020-2100 was constructed and analyzed. Through comparative modelling, we find that the proposed physics-informed CNN-LSTM-GNN architecture reaches the highest predictive performance with an R² of 0.96, RMSE of 5.89, accuracy of 96.5%, F1 of 0.96 and AUC-ROC of 0.98 against Random Forest, XGBoost, Support Vector Regression, and regular deep learning models. Analysis of the Explainable AI revealed that temperature anomaly (22.8%), intensity of the drought (19.6%), population density (15.4%), poverty (13.7%) and degradation of vegetation (10.8%) were the top drivers of migration risk. Predictions were accurate 89.7% to 94.2% of the time for major climate-driven displacement events. Results from the scenario simulations of the future CMIP6 indicate that populations at high risk of migration could increase from 180 million (SSP1-2.6) to 910 million (SSP5-8.5), and migration probability from 12.4% to 58.9%. The Earth-Human Digital Twin will provide a scalable and explainable predictive simulation for anticipating climate vulnerability and hotspot migration to support evidence-based adaptation.
- 2 September 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessEarth-Human Digital Twin: A Physics-Informed Artificial Intelligence Framework for Predicting Climate-Induced Human Vulnerability and Migration Using WorldPop, Satellite Earth Observation, and CMIP6 Climate Projections
Climate induced migration is an imminent global challenge formed from the interplay of climate change, environmental degradation, exposure to populations, and vulnerability. An Earth-human digital twin framework was developed in this study using 51 variables sourced from CMIP6 climate projections, ERA5 reanalysis, WorldPop, Earth observation, socioeconomic and socio-political and other information on past migration and more recently to assess future human vulnerability and displacement scenario risk. Using machine learning, deep learning, and physics-informed artificial intelligence approaches, a global 1 km spatial resolution database covering 2020-2100 was constructed and analyzed. Through comparative modelling, we find that the proposed physics-informed CNN-LSTM-GNN architecture reaches the highest predictive performance with an R² of 0.96, RMSE of 5.89, accuracy of 96.5%, F1 of 0.96 and AUC-ROC of 0.98 against Random Forest, XGBoost, Support Vector Regression, and regular deep learning models. Analysis of the Explainable AI revealed that temperature anomaly (22.8%), intensity of the drought (19.6%), population density (15.4%), poverty (13.7%) and degradation of vegetation (10.8%) were the top drivers of migration risk. Predictions were accurate 89.7% to 94.2% of the time for major climate-driven displacement events. Results from the scenario simulations of the future CMIP6 indicate that populations at high risk of migration could increase from 180 million (SSP1-2.6) to 910 million (SSP5-8.5), and migration probability from 12.4% to 58.9%. The Earth-Human Digital Twin will provide a scalable and explainable predictive simulation for anticipating climate vulnerability and hotspot migration to support evidence-based adaptation.
- Open Access
- 31 August 2026
- Published by Scifiniti Publishing in Computing&AI Connect
- Vol. 3 (1) , 1-10
Machine Learning-Driven Multimodal Forensic Data Fusion for Enhanced Disaster Victim Identification: Integrating DNA, Dental, and Facial Image Data
Using synthetic disaster simulations, a machine learning-based multimodal forensic data fusion framework was developed for disaster victim identification (DVI). By integrating DNA, dental, and facial picture data from 10,000 synthetic files, the framework comprised 5,000 ante-mortem and 5,000 postmortem profiles. DNA data were represented using 200 synthetic SNP markers, while each dental phenotype was represented using features such as tooth count, treatment history, and bone loss. Also, facial data were represented as 64D ResNet-50 embeddings. The dataset was divided into training, validation, and test sets in a 70:15:15 ratio. Three unimodal models and two fusion strategies were evaluated in 10 independent runs. The proposed feature-level fusion model performed best, with 94.8 ± 0.4% accuracy, 0.94 ± 0.01 precision, 0.94 ± 0.01 recall, 0.94 ± 0.02 F1, and 0.97 ± 0.01 macro-averaged OvR ROC-AUC. The accuracy of decision-level fusion was 93.5% ± 0.5, which is better than the DNA-only (88.4% ± 0.6), dental-only (82.7% ± 0.7), and facial image-only (84.9% ± 0.5) classifiers. When one of the three models was missing, accuracy declined to more than 90.5%. Under severely degraded multimodal conditions, the accuracy was 88.7% ± 0.7. ANOVA revealed significant differences between unimodal and fusion models (F = 18.45, p = 0.0002). Attention weights were assigned as follows: 40% to DNA, 34% to dental, and 26% to facial data, which helps explain the interpretability. The results show good performance on synthetic DVI simulations but require testing on actual forensic data.
- 31 August 2026
- Published by Scifiniti Publishing in Computing&AI Connect
- Vol. 3 (1) , 1-10
Open AccessMachine Learning-Driven Multimodal Forensic Data Fusion for Enhanced Disaster Victim Identification: Integrating DNA, Dental, and Facial Image Data
Using synthetic disaster simulations, a machine learning-based multimodal forensic data fusion framework was developed for disaster victim identification (DVI). By integrating DNA, dental, and facial picture data from 10,000 synthetic files, the framework comprised 5,000 ante-mortem and 5,000 postmortem profiles. DNA data were represented using 200 synthetic SNP markers, while each dental phenotype was represented using features such as tooth count, treatment history, and bone loss. Also, facial data were represented as 64D ResNet-50 embeddings. The dataset was divided into training, validation, and test sets in a 70:15:15 ratio. Three unimodal models and two fusion strategies were evaluated in 10 independent runs. The proposed feature-level fusion model performed best, with 94.8 ± 0.4% accuracy, 0.94 ± 0.01 precision, 0.94 ± 0.01 recall, 0.94 ± 0.02 F1, and 0.97 ± 0.01 macro-averaged OvR ROC-AUC. The accuracy of decision-level fusion was 93.5% ± 0.5, which is better than the DNA-only (88.4% ± 0.6), dental-only (82.7% ± 0.7), and facial image-only (84.9% ± 0.5) classifiers. When one of the three models was missing, accuracy declined to more than 90.5%. Under severely degraded multimodal conditions, the accuracy was 88.7% ± 0.7. ANOVA revealed significant differences between unimodal and fusion models (F = 18.45, p = 0.0002). Attention weights were assigned as follows: 40% to DNA, 34% to dental, and 26% to facial data, which helps explain the interpretability. The results show good performance on synthetic DVI simulations but require testing on actual forensic data.
- Open Access
- 16 January 2026
- Published by MDPI AG in Electronics
- Vol. 15 (2) , 394
Comparative Epidemiology of Machine and Deep Learning Diagnostics in Diabetes and Sickle Cell Disease: Africa’s Challenges, Global Non-Communicable Disease Opportunities
Non-communicable diseases (NCDs) such as Diabetes Mellitus (DM) and Sickle Cell Disease (SCD) pose an escalating health challenge in Africa, underscored by diagnostic deficiencies, inadequate surveillance, and limited health system capacity that contribute to late diagnoses and consequent preventable complications. This review adopts a comparative framework that considers DM and SCD as complementary indicator diseases, both metabolic and genetic, and highlights intersecting diagnostic, infrastructural, and governance hurdles relevant to AI-enabled screening in resource-constrained environments. The study synthesizes epidemiological data across both African and high-income regions and methodically catalogs machine learning (ML) and deep learning (DL) research by clinical application, including risk prediction, image-based diagnostics, remote patient monitoring, privacy-preserving learning, and governance frameworks. Our key observations reveal significant disparities in disease detection and health outcomes, driven by underdiagnosis, a lack of comprehensive newborn screening for SCD, and fragmented diabetes surveillance systems in Africa, despite the availability of effective diagnostic technologies in other regions. The reviewed literature on ML/DL shows high algorithmic accuracy, particularly in diabetic retinopathy screening and emerging applications in SCD microscopy. However, most studies are constrained by small, single-site datasets that lack robust external validation and do not align well with real-world clinical workflows. The review identifies persistent implementation challenges, including data scarcity, device variability, limited connectivity, and inadequate calibration and subgroup analysis. By integrating epidemiological insights into AI diagnostic capabilities and health system realities, this work extends beyond earlier surveys to offer a comprehensive, Africa-centric, implementation-focused synthesis. It proposes actionable operational and policy recommendations, including offline-first deployment strategies, federated learning approaches for low-bandwidth scenarios, integration with primary care and newborn screening initiatives, and enhanced governance structures, to promote equitable and scalable AI-enhanced diagnostics for NCDs.
- 16 January 2026
- Published by MDPI AG in Electronics
- Vol. 15 (2) , 394
Open AccessComparative Epidemiology of Machine and Deep Learning Diagnostics in Diabetes and Sickle Cell Disease: Africa’s Challenges, Global Non-Communicable Disease Opportunities
Non-communicable diseases (NCDs) such as Diabetes Mellitus (DM) and Sickle Cell Disease (SCD) pose an escalating health challenge in Africa, underscored by diagnostic deficiencies, inadequate surveillance, and limited health system capacity that contribute to late diagnoses and consequent preventable complications. This review adopts a comparative framework that considers DM and SCD as complementary indicator diseases, both metabolic and genetic, and highlights intersecting diagnostic, infrastructural, and governance hurdles relevant to AI-enabled screening in resource-constrained environments. The study synthesizes epidemiological data across both African and high-income regions and methodically catalogs machine learning (ML) and deep learning (DL) research by clinical application, including risk prediction, image-based diagnostics, remote patient monitoring, privacy-preserving learning, and governance frameworks. Our key observations reveal significant disparities in disease detection and health outcomes, driven by underdiagnosis, a lack of comprehensive newborn screening for SCD, and fragmented diabetes surveillance systems in Africa, despite the availability of effective diagnostic technologies in other regions. The reviewed literature on ML/DL shows high algorithmic accuracy, particularly in diabetic retinopathy screening and emerging applications in SCD microscopy. However, most studies are constrained by small, single-site datasets that lack robust external validation and do not align well with real-world clinical workflows. The review identifies persistent implementation challenges, including data scarcity, device variability, limited connectivity, and inadequate calibration and subgroup analysis. By integrating epidemiological insights into AI diagnostic capabilities and health system realities, this work extends beyond earlier surveys to offer a comprehensive, Africa-centric, implementation-focused synthesis. It proposes actionable operational and policy recommendations, including offline-first deployment strategies, federated learning approaches for low-bandwidth scenarios, integration with primary care and newborn screening initiatives, and enhanced governance structures, to promote equitable and scalable AI-enhanced diagnostics for NCDs.
- Open Access
- 2 December 2025
- Published by MDPI AG in Preprints.org
Comparative Epidemiology and Machine and Deep Learning Diagnostics in Diabetes and Sickle Cell Disease: Africa’s Challenges, Global Non-Communicable Diseases Opportunities
Non-communicable diseases (NCDs) such as Diabetes Mellitus (DM) and Sickle Cell Disease (SCD) pose significant challenges to global health systems, particularly in Africa, where the impact is specifically severe due to limited healthcare infrastructure and inadequate surveillance capacity. While both diseases differ in their pathologies, DM is primarily a metabolic condition, and SCD is a monogenic inherited disorder; however, both diseases intersect with socio-economic disparities and weak primary care systems, making them critical public health concerns. This study provides a comparative epidemiological analysis of DM and SCD, focusing on trends in prevalence, morbidity, comorbidities, management deficiencies, and mortality in African regions compared with high-income countries. It highlights the importance of early diagnosis, accessible screening programs, and effective patient management strategies to combat the threat of these NCDs. The research highlights how historical neglect, stigma, comorbidities, health risks, and chronic underfunding have worsened health outcomes in Africa. The study evaluates the potential of AI-driven diagnostics to enhance detection and management in healthcare, discussing how ML and DL models can utilize multimodal data to improve early risk stratification, newborn and antenatal screening, and detection of complications, and highlighting the role of these technologies in supporting triage and follow-up decision-making at the primary care level. It contrasts this with the more effective disease surveillance and management strategies observed in high-income nations. The study highlights the urgent need for customized health policies, public education initiatives, and community-based approaches to improve diagnosis and treatment. Ultimately, this research highlights the urgent need to address structural inequities such as limited healthcare funding and unequal access to medical resources in global responses to NCDs, while also recognizing Africa’s potential for intervention, prevention, and the establishment of sustainable disease management systems.
- 2 December 2025
- Published by MDPI AG in Preprints.org
Open AccessComparative Epidemiology and Machine and Deep Learning Diagnostics in Diabetes and Sickle Cell Disease: Africa’s Challenges, Global Non-Communicable Diseases Opportunities
Non-communicable diseases (NCDs) such as Diabetes Mellitus (DM) and Sickle Cell Disease (SCD) pose significant challenges to global health systems, particularly in Africa, where the impact is specifically severe due to limited healthcare infrastructure and inadequate surveillance capacity. While both diseases differ in their pathologies, DM is primarily a metabolic condition, and SCD is a monogenic inherited disorder; however, both diseases intersect with socio-economic disparities and weak primary care systems, making them critical public health concerns. This study provides a comparative epidemiological analysis of DM and SCD, focusing on trends in prevalence, morbidity, comorbidities, management deficiencies, and mortality in African regions compared with high-income countries. It highlights the importance of early diagnosis, accessible screening programs, and effective patient management strategies to combat the threat of these NCDs. The research highlights how historical neglect, stigma, comorbidities, health risks, and chronic underfunding have worsened health outcomes in Africa. The study evaluates the potential of AI-driven diagnostics to enhance detection and management in healthcare, discussing how ML and DL models can utilize multimodal data to improve early risk stratification, newborn and antenatal screening, and detection of complications, and highlighting the role of these technologies in supporting triage and follow-up decision-making at the primary care level. It contrasts this with the more effective disease surveillance and management strategies observed in high-income nations. The study highlights the urgent need for customized health policies, public education initiatives, and community-based approaches to improve diagnosis and treatment. Ultimately, this research highlights the urgent need to address structural inequities such as limited healthcare funding and unequal access to medical resources in global responses to NCDs, while also recognizing Africa’s potential for intervention, prevention, and the establishment of sustainable disease management systems.
- 30 August 2025
- Published by Springer Nature
- p. 114-142
Advancements in Machine Learning Techniques for Diabetes Mellitus: A Review of Progression, Challenges and Future Directions
- 30 August 2025
- Published by Springer Nature
- p. 114-142
Advancements in Machine Learning Techniques for Diabetes Mellitus: A Review of Progression, Challenges and Future Directions
- Open Access
- 26 June 2025
- Published by MDPI AG in Electronics
- Vol. 14 (13) , 2583
Machine Learning and Deep Learning Approaches for Predicting Diabetes Progression: A Comparative Analysis
The global burden of diabetes mellitus (DM) continues to escalate, posing significant challenges to healthcare systems worldwide. This study compares machine learning (ML) and deep learning (DL) methods, their hybrids, and ensemble strategies for predicting the health outcomes of diabetic patients. This work aims to find the best solutions that strike a balance between computational efficiency and accurate prediction. The study systematically assessed a range of predictive models, including sophisticated DL techniques and conventional ML algorithms, based on computational efficiency and performance indicators. The study assessed prediction accuracy, processing speed, scalability, resource consumption, and interpretability using publicly accessible diabetes datasets. It methodically evaluates the selected models using key performance indicators (KPIs), training times, and memory usage. AdaBoost had the highest F1-score (0.74) on PIMA-768, while RF excelled on PIMA-2000 (~0.73). An RNN led the 3-class BRFSS survey (0.44), and a feed-forward DNN excelled on the binary BRFSS subset (0.45), while RF also achieved perfect accuracy on the EMR dataset (1.00) confirming that model performance is tightly coupled to each dataset’s scale, feature mix and label structure. The results highlight how lightweight, interpretable ML and DL models work in resource-constrained environments and for real-time health analytics. The study also compares its results with existing prediction models, confirming the benefits of selected ML approaches in enhancing diabetes-related medical outcomes that are substantial for practical implementation, providing a reliable and efficient framework for automated diabetes prediction to support initiative-taking disease management techniques and tailored treatment. The study concludes the essentiality of conducting a thorough assessment and validation of the model using current institutional datasets as this enhances accuracy, security, and confidence in AI-assisted healthcare decision-making.
- 26 June 2025
- Published by MDPI AG in Electronics
- Vol. 14 (13) , 2583
Open AccessMachine Learning and Deep Learning Approaches for Predicting Diabetes Progression: A Comparative Analysis
The global burden of diabetes mellitus (DM) continues to escalate, posing significant challenges to healthcare systems worldwide. This study compares machine learning (ML) and deep learning (DL) methods, their hybrids, and ensemble strategies for predicting the health outcomes of diabetic patients. This work aims to find the best solutions that strike a balance between computational efficiency and accurate prediction. The study systematically assessed a range of predictive models, including sophisticated DL techniques and conventional ML algorithms, based on computational efficiency and performance indicators. The study assessed prediction accuracy, processing speed, scalability, resource consumption, and interpretability using publicly accessible diabetes datasets. It methodically evaluates the selected models using key performance indicators (KPIs), training times, and memory usage. AdaBoost had the highest F1-score (0.74) on PIMA-768, while RF excelled on PIMA-2000 (~0.73). An RNN led the 3-class BRFSS survey (0.44), and a feed-forward DNN excelled on the binary BRFSS subset (0.45), while RF also achieved perfect accuracy on the EMR dataset (1.00) confirming that model performance is tightly coupled to each dataset’s scale, feature mix and label structure. The results highlight how lightweight, interpretable ML and DL models work in resource-constrained environments and for real-time health analytics. The study also compares its results with existing prediction models, confirming the benefits of selected ML approaches in enhancing diabetes-related medical outcomes that are substantial for practical implementation, providing a reliable and efficient framework for automated diabetes prediction to support initiative-taking disease management techniques and tailored treatment. The study concludes the essentiality of conducting a thorough assessment and validation of the model using current institutional datasets as this enhances accuracy, security, and confidence in AI-assisted healthcare decision-making.
- Open Access
- 26 June 2025
- Published by MDPI AG in Preprints.org
Machine Learning and Deep Learning Approaches for Predicting Diabetes Progression: A Comparative Analysis
The global burden of diabetes mellitus (DM) continues to escalate, posing significant challenges to healthcare systems worldwide. This study compares machine learning (ML) and deep learning (DL) methods, their hybrids, and ensemble strategies for predicting the health outcomes of diabetic patients. This work aims to find the best solutions that balance computational efficiency and accurate prediction. The study systematically assessed a range of predictive models, including sophisticated DL techniques and conventional ML algorithms, based on computational efficiency and performance indicators. The study assessed prediction accuracy, processing speed, scalability, resource consumption, and interpretability using publicly accessible diabetes datasets. It methodically evaluates the selected models using key performance indicators (KPIs), training times, and memory usage. AdaBoost achieved the highest F1-score (0.74) on PIMA-768, while RF excelled on PIMA-2000 (~0.73). An RNN led the 3-class BRFSS survey (0.44), and a feed-forward DNN excelled in the binary BRFSS subset (0.45). RF also achieved perfect accuracy on the EMR dataset (1.00) showing that model performance depends on each dataset’s scale, feature mix and label structure. The results highlight how lightweight, interpretable ML and DL models work in resource-constrained environments and for real-time health analytics. The study also compares its results with existing prediction models, confirming the benefits of selected ML approaches in enhancing diabetes-related medical outcomes, substantial for practical implementation, providing a reliable and efficient framework for automated diabetes prediction to support initiative-taking disease management techniques and tailored treatment. The study concludes the essentiality of conducting a thorough assessment and validation of the model using current institutional datasets as this enhances accuracy, security, and confidence in AI-assisted healthcare decision-making.
- 26 June 2025
- Published by MDPI AG in Preprints.org
Open AccessMachine Learning and Deep Learning Approaches for Predicting Diabetes Progression: A Comparative Analysis
The global burden of diabetes mellitus (DM) continues to escalate, posing significant challenges to healthcare systems worldwide. This study compares machine learning (ML) and deep learning (DL) methods, their hybrids, and ensemble strategies for predicting the health outcomes of diabetic patients. This work aims to find the best solutions that balance computational efficiency and accurate prediction. The study systematically assessed a range of predictive models, including sophisticated DL techniques and conventional ML algorithms, based on computational efficiency and performance indicators. The study assessed prediction accuracy, processing speed, scalability, resource consumption, and interpretability using publicly accessible diabetes datasets. It methodically evaluates the selected models using key performance indicators (KPIs), training times, and memory usage. AdaBoost achieved the highest F1-score (0.74) on PIMA-768, while RF excelled on PIMA-2000 (~0.73). An RNN led the 3-class BRFSS survey (0.44), and a feed-forward DNN excelled in the binary BRFSS subset (0.45). RF also achieved perfect accuracy on the EMR dataset (1.00) showing that model performance depends on each dataset’s scale, feature mix and label structure. The results highlight how lightweight, interpretable ML and DL models work in resource-constrained environments and for real-time health analytics. The study also compares its results with existing prediction models, confirming the benefits of selected ML approaches in enhancing diabetes-related medical outcomes, substantial for practical implementation, providing a reliable and efficient framework for automated diabetes prediction to support initiative-taking disease management techniques and tailored treatment. The study concludes the essentiality of conducting a thorough assessment and validation of the model using current institutional datasets as this enhances accuracy, security, and confidence in AI-assisted healthcare decision-making.
- Open Access
- 19 September 2023
- Published by European Alliance for Innovation n.o. in EAI Endorsed Transactions on Pervasive Health and Technology
- Vol. 9
An Ensemble Models for the Prediction of Sickle Cell Disease from Erythrocytes Smears
INTRODUCTION: The human blood as a collection of tissues containing Red Blood Cells (RBCs), circular in shape and acting as an oxygen carrier, are frequently deformed by multiple blood diseases inherited from parents. These hereditary diseases of blood involve abnormal haemoglobin (Hb) or anemia which are major public health issues. Sickle Cell Disease (SCD) is one of the common non-communicable disease and genetic disorder due to changes in hematological conditions of the RBCs which often causes the inheritance of mutant Hb genes by the patient.. OBJECTIVES: The process of manual valuation, predictions and diagnosis of SCD necessitate for a passionate time spending and if not done properly can lead to wrong predictions and diagnosis. Machine Learning (ML), a branch of AI which emphases on building systems that improve performance based on the data they consume is appropriate. Despite previous research efforts in predicting with single ML algorithm, the existing systems still suffer from high false and wrong predictions. METHODS: Thus, this paper aimed at performing comparative analysis of individual ML algorithms and their ensemble models for effective predictions of SCD (elongated shapes) in erythrocytes blood cells. Three ML algorithms were selected, and ensemble models were developed to perform the predictions and metrics were used to evaluate the performance of the model using accuracy, sensitivity, Receiver Operating Characteristics-Area under Curve (ROC-AUC) and F1 score metrics. The results were compared with existing literature for model(s) with the best prediction metrics performance.. RESULTS: The analysis was carried out using Python programming language. Individual ML algorithms reveals that their accuracies show MLR=87%, XGBoost=90%, and RF=93%, while hybridized RF-MLR=92% and RF-XGBoost=99%. The accuracy of RF-XGBoost of 99% outperformed other individual ML algorithms and Hybrid models. CONCLUSION: Thus, the study concluded that involving hybridized ML algorithms in medical datasets increased predictions performance as it removed the challenges of high variance, low accuracy and feature noise and biases of medical datasets. The paper concluded that ensemble classifiers should be considered to improve sickle cell disease predictions.
- 19 September 2023
- Published by European Alliance for Innovation n.o. in EAI Endorsed Transactions on Pervasive Health and Technology
- Vol. 9
Open AccessAn Ensemble Models for the Prediction of Sickle Cell Disease from Erythrocytes Smears
INTRODUCTION: The human blood as a collection of tissues containing Red Blood Cells (RBCs), circular in shape and acting as an oxygen carrier, are frequently deformed by multiple blood diseases inherited from parents. These hereditary diseases of blood involve abnormal haemoglobin (Hb) or anemia which are major public health issues. Sickle Cell Disease (SCD) is one of the common non-communicable disease and genetic disorder due to changes in hematological conditions of the RBCs which often causes the inheritance of mutant Hb genes by the patient.. OBJECTIVES: The process of manual valuation, predictions and diagnosis of SCD necessitate for a passionate time spending and if not done properly can lead to wrong predictions and diagnosis. Machine Learning (ML), a branch of AI which emphases on building systems that improve performance based on the data they consume is appropriate. Despite previous research efforts in predicting with single ML algorithm, the existing systems still suffer from high false and wrong predictions. METHODS: Thus, this paper aimed at performing comparative analysis of individual ML algorithms and their ensemble models for effective predictions of SCD (elongated shapes) in erythrocytes blood cells. Three ML algorithms were selected, and ensemble models were developed to perform the predictions and metrics were used to evaluate the performance of the model using accuracy, sensitivity, Receiver Operating Characteristics-Area under Curve (ROC-AUC) and F1 score metrics. The results were compared with existing literature for model(s) with the best prediction metrics performance.. RESULTS: The analysis was carried out using Python programming language. Individual ML algorithms reveals that their accuracies show MLR=87%, XGBoost=90%, and RF=93%, while hybridized RF-MLR=92% and RF-XGBoost=99%. The accuracy of RF-XGBoost of 99% outperformed other individual ML algorithms and Hybrid models. CONCLUSION: Thus, the study concluded that involving hybridized ML algorithms in medical datasets increased predictions performance as it removed the challenges of high variance, low accuracy and feature noise and biases of medical datasets. The paper concluded that ensemble classifiers should be considered to improve sickle cell disease predictions.
- Open Access
An Enhanced Hyper-Parameter Optimization of a Convolutional Neural Network Model for Leukemia Cancer Diagnosis in a Smart Healthcare System
Healthcare systems in recent times have witnessed timely diagnoses with a high level of accuracy. Internet of Medical Things (IoMT)-enabled deep learning (DL) models have been used to support medical diagnostics in real time, thus resolving the issue of late-stage diagnosis of various diseases and increasing performance accuracy. The current approach for the diagnosis of leukemia uses traditional procedures, and in most cases, fails in the initial period. Hence, several patients suffering from cancer have died prematurely due to the late discovery of cancerous cells in blood tissue. Therefore, this study proposes an IoMT-enabled convolutional neural network (CNN) model to detect malignant and benign cancer cells in the patient’s blood tissue. In particular, the hyper-parameter optimization through radial basis function and dynamic coordinate search (HORD) optimization algorithm was used to search for optimal values of CNN hyper-parameters. Utilizing the HORD algorithm significantly increased the effectiveness of finding the best solution for the CNN model by searching multidimensional hyper-parameters. This implies that the HORD method successfully found the values of hyper-parameters for precise leukemia features. Additionally, the HORD method increased the performance of the model by optimizing and searching for the best set of hyper-parameters for the CNN model. Leukemia datasets were used to evaluate the performance of the proposed model using standard performance indicators. The proposed model revealed significant classification accuracy compared to other state-of-the-art models.
Open AccessAn Enhanced Hyper-Parameter Optimization of a Convolutional Neural Network Model for Leukemia Cancer Diagnosis in a Smart Healthcare System
Healthcare systems in recent times have witnessed timely diagnoses with a high level of accuracy. Internet of Medical Things (IoMT)-enabled deep learning (DL) models have been used to support medical diagnostics in real time, thus resolving the issue of late-stage diagnosis of various diseases and increasing performance accuracy. The current approach for the diagnosis of leukemia uses traditional procedures, and in most cases, fails in the initial period. Hence, several patients suffering from cancer have died prematurely due to the late discovery of cancerous cells in blood tissue. Therefore, this study proposes an IoMT-enabled convolutional neural network (CNN) model to detect malignant and benign cancer cells in the patient’s blood tissue. In particular, the hyper-parameter optimization through radial basis function and dynamic coordinate search (HORD) optimization algorithm was used to search for optimal values of CNN hyper-parameters. Utilizing the HORD algorithm significantly increased the effectiveness of finding the best solution for the CNN model by searching multidimensional hyper-parameters. This implies that the HORD method successfully found the values of hyper-parameters for precise leukemia features. Additionally, the HORD method increased the performance of the model by optimizing and searching for the best set of hyper-parameters for the CNN model. Leukemia datasets were used to evaluate the performance of the proposed model using standard performance indicators. The proposed model revealed significant classification accuracy compared to other state-of-the-art models.