Huong Thi Thanh Ha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Huong Thi Thanh Ha has a total of 169 co-authors. Here are the top co-authors by number of shared publications:
Anh Le
(1) School of Biomedical Engineering, International University, Vietnam National University, Ho Chi Minh City, Ho Chi Minh City, Vietnam; (2) Vietnam National University, Ho Chi Minh City, Ho Chi Minh, Vietnam
4 shared publicationsAnh Phuc Hoang Le
School of Biomedical Engineering, International University, Ho Chi Minh City, Vietnam
3 shared publications- Binh Thanh Nguyen
University of Science, Vietnam National University Ho Chi Minh City, Ho Chi Minh City, Vietnam
3 shared publications - Lua Ngo
School of Biomedical Engineering, International University, Vietnam National University Ho Chi Minh City, Ho Chi Minh City, Vietnam
3 shared publications My Nguyen
University of Science
3 shared publicationsAnh An
School of Biomedical Engineering, International University, Ho Chi Minh City, Viet Nam
2 shared publications
Latest Publications
- 2 September 2026
- Published by Springer Nature
- p. 150-165
A Comparison of Machine Learning Methods for Alzheimer’s Disease Classification in Vietnamese Patients
- 2 September 2026
- Published by Springer Nature
- p. 150-165
A Comparison of Machine Learning Methods for Alzheimer’s Disease Classification in Vietnamese Patients
- 15 August 2026
- Published by Springer Nature
- p. 460-471
GAFB-MKL: Adaptive Filter Banks via Genetic Algorithm and Sparse Multiple Kernel Learning for EEG-Based Motor Imagery Classification
- 15 August 2026
- Published by Springer Nature
- p. 460-471
GAFB-MKL: Adaptive Filter Banks via Genetic Algorithm and Sparse Multiple Kernel Learning for EEG-Based Motor Imagery Classification
- 27 May 2026
- Published by SAGE Publications in The Neuroradiology Journal
Development of a serverless, interactive application for Alzheimer’s disease detection and visualization using MRI images
Background: Alzheimer’s disease requires early detection for effective intervention with disease-modifying treatments, yet significant implementation barriers persist in clinical practice, including limited computational infrastructure and the gap between research model performance and practical deployment in resource-constrained settings. Objectives: To develop and evaluate a computer-aided diagnosis system for classifying cognitive states (AD, MCI, and CN) from structural MRI, with automated preprocessing and cost-effective cloud deployment suitable for resource-constrained healthcare facilities. Design: Computer-aided diagnosis system integrating neural architecture search with serverless cloud infrastructure. Methods: A multi-view MRI analysis model was optimized through neural architecture search, incorporating Universal Inverted Bottleneck blocks and Kolmogorov–Arnold Networks. Automated MRI preprocessing using FSL was deployed through cloud-based serverless functions for scalable image processing. Evaluation used the ADNI dataset (1687 individuals: 368 AD, 625 MCI, and 694 CN). A web application was developed providing patient management, MRI visualization, and automated diagnostic prediction. Results: The model achieved 86.7% accuracy and 0.900 AUC in three-class classification with 1.7 million parameters. High specificity was observed across all classes (CN: 91.0%, MCI: 91.8%, AD: 97.3%), with 100% CN-AD specificity ensuring no AD cases were misclassified as cognitively normal. Operational costs were approximately 0.028 USD per diagnosis for typical hospital workloads. Conclusion: This system provides a cost-effective approach for early Alzheimer’s diagnosis accessible to resource-constrained environments. Despite challenges in MCI classification, the combination of neural architecture search with serverless deployment demonstrates progress toward clinically deployable automated AD detection. Future work should focus on prospective clinical validation and integration of interpretability features.
- 27 May 2026
- Published by SAGE Publications in The Neuroradiology Journal
Development of a serverless, interactive application for Alzheimer’s disease detection and visualization using MRI images
Background: Alzheimer’s disease requires early detection for effective intervention with disease-modifying treatments, yet significant implementation barriers persist in clinical practice, including limited computational infrastructure and the gap between research model performance and practical deployment in resource-constrained settings. Objectives: To develop and evaluate a computer-aided diagnosis system for classifying cognitive states (AD, MCI, and CN) from structural MRI, with automated preprocessing and cost-effective cloud deployment suitable for resource-constrained healthcare facilities. Design: Computer-aided diagnosis system integrating neural architecture search with serverless cloud infrastructure. Methods: A multi-view MRI analysis model was optimized through neural architecture search, incorporating Universal Inverted Bottleneck blocks and Kolmogorov–Arnold Networks. Automated MRI preprocessing using FSL was deployed through cloud-based serverless functions for scalable image processing. Evaluation used the ADNI dataset (1687 individuals: 368 AD, 625 MCI, and 694 CN). A web application was developed providing patient management, MRI visualization, and automated diagnostic prediction. Results: The model achieved 86.7% accuracy and 0.900 AUC in three-class classification with 1.7 million parameters. High specificity was observed across all classes (CN: 91.0%, MCI: 91.8%, AD: 97.3%), with 100% CN-AD specificity ensuring no AD cases were misclassified as cognitively normal. Operational costs were approximately 0.028 USD per diagnosis for typical hospital workloads. Conclusion: This system provides a cost-effective approach for early Alzheimer’s diagnosis accessible to resource-constrained environments. Despite challenges in MCI classification, the combination of neural architecture search with serverless deployment demonstrates progress toward clinically deployable automated AD detection. Future work should focus on prospective clinical validation and integration of interpretability features.
- 19 February 2026
- Published by Springer Nature in Microchimica Acta
- Vol. 193 (3) , 170
Development and human samples validation of a plasma pTau‑217 electrochemical sensor for Alzheimer’s detection in Vietnamese patients
- 19 February 2026
- Published by Springer Nature in Microchimica Acta
- Vol. 193 (3) , 170
Development and human samples validation of a plasma pTau‑217 electrochemical sensor for Alzheimer’s detection in Vietnamese patients
- 22 November 2025
- Published by Springer Nature
- p. 127-139
FA-GPNet: When Gaussian Process Meets Auto-Encoder and FBCSP - A Hybrid Model for Motor Imagery Classification
- 22 November 2025
- Published by Springer Nature
- p. 127-139
FA-GPNet: When Gaussian Process Meets Auto-Encoder and FBCSP - A Hybrid Model for Motor Imagery Classification
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11179-11188
REMEMBER: Retrieval-based Explainable Multimodal Evidence-guided Modeling for Brain Evaluation and Reasoning in Zero- and Few-shot Neurodegenerative Diagnosis
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 11179-11188
Open AccessREMEMBER: Retrieval-based Explainable Multimodal Evidence-guided Modeling for Brain Evaluation and Reasoning in Zero- and Few-shot Neurodegenerative Diagnosis
- Open Access
- 17 September 2025
- Published by Elsevier in IBRO Neuroscience Reports
- Vol. 19, 645
Asia-Pacific perspectives in neuroscience: Insights from the IBRO APRC mini-series
- 17 September 2025
- Published by Elsevier in IBRO Neuroscience Reports
- Vol. 19, 645
Open AccessAsia-Pacific perspectives in neuroscience: Insights from the IBRO APRC mini-series
- Open Access
- 30 June 2025
- Published by Biomedpress in Biomedical Research and Therapy
- Vol. 12 (6) , 7453-7463
A Pilot Study on Implementing Home Blood Pressure Telemonitoring for Older Adults with Mild Cognitive Impairment in Viet Nam
Introduction: This pilot study aimed to evaluate the feasibility of home blood pressure (BP) telemonitoring among older Vietnamese adults with mild cognitive impairment (MCI) and uncontrolled hypertension in a Geriatrics clinic in Viet Nam. The recruitment (83.8%) and retention (64.5%) rates demonstrate moderate feasibility; however, significant barriers — such as technical reliability and patient non-adherence — were identified. This study underscores the critical challenges of real-world implementation and offers insights for enhancing future telemonitoring interventions for this vulnerable population. Methods: The control group received standard care, which included adhering to medication prescriptions and attending routine monthly clinic visits for blood pressure monitoring. The locally developed BP telemonitoring device, previously validated at Viet Nam National University, showed an accuracy comparable to international standards. For participants with MCI, caregivers were involved in the consent process to ensure ethical safeguards and full comprehension of study procedures. We conducted a two-arm pilot study. Eligible older patients with MCI and uncontrolled hypertension were invited to participate. Patients were allocated to the intervention group if they were interested in BP telemonitoring; otherwise, they were placed in the control group. Patients were trained to measure their home BP and followed up for three months. Alerts were generated when there were insufficient BP readings. Results: We invited 74 eligible patients, but 12 declined participation. Overall, 62 participants were allocated to the telemonitoring group (n = 31) or the usual care group (n = 31). The recruitment rate was 83.8%, and the retention rate was 64.5%. The most common reason for withdrawing was “telemonitoring BP devices did not work properly” (45.4%). Alerts were triggered in 22 patients (70.9%), and over 80% of these alerts resulted from patient non-adherence and system problems. After three months, systolic BP was lower in both the intervention group and the control group compared to systolic BP at baseline (telemonitoring group, 137.1 [14.5] mm Hg vs. control group, 143.1 [18.8] mm Hg). No significant difference was observed between the two groups (adjusted mean difference −1.58 mm Hg [95% CI −19.25 to 16.08]). Conclusions: This pilot study demonstrated the feasibility of home BP telemonitoring in older Vietnamese adults with MCI and uncontrolled hypertension. However, technical reliability and patient adherence issues must be addressed before wider-scale implementation. Future research with a larger sample size and a longer follow-up period is necessary to confirm these findings.
- 30 June 2025
- Published by Biomedpress in Biomedical Research and Therapy
- Vol. 12 (6) , 7453-7463
Open AccessA Pilot Study on Implementing Home Blood Pressure Telemonitoring for Older Adults with Mild Cognitive Impairment in Viet Nam
Introduction: This pilot study aimed to evaluate the feasibility of home blood pressure (BP) telemonitoring among older Vietnamese adults with mild cognitive impairment (MCI) and uncontrolled hypertension in a Geriatrics clinic in Viet Nam. The recruitment (83.8%) and retention (64.5%) rates demonstrate moderate feasibility; however, significant barriers — such as technical reliability and patient non-adherence — were identified. This study underscores the critical challenges of real-world implementation and offers insights for enhancing future telemonitoring interventions for this vulnerable population. Methods: The control group received standard care, which included adhering to medication prescriptions and attending routine monthly clinic visits for blood pressure monitoring. The locally developed BP telemonitoring device, previously validated at Viet Nam National University, showed an accuracy comparable to international standards. For participants with MCI, caregivers were involved in the consent process to ensure ethical safeguards and full comprehension of study procedures. We conducted a two-arm pilot study. Eligible older patients with MCI and uncontrolled hypertension were invited to participate. Patients were allocated to the intervention group if they were interested in BP telemonitoring; otherwise, they were placed in the control group. Patients were trained to measure their home BP and followed up for three months. Alerts were generated when there were insufficient BP readings. Results: We invited 74 eligible patients, but 12 declined participation. Overall, 62 participants were allocated to the telemonitoring group (n = 31) or the usual care group (n = 31). The recruitment rate was 83.8%, and the retention rate was 64.5%. The most common reason for withdrawing was “telemonitoring BP devices did not work properly” (45.4%). Alerts were triggered in 22 patients (70.9%), and over 80% of these alerts resulted from patient non-adherence and system problems. After three months, systolic BP was lower in both the intervention group and the control group compared to systolic BP at baseline (telemonitoring group, 137.1 [14.5] mm Hg vs. control group, 143.1 [18.8] mm Hg). No significant difference was observed between the two groups (adjusted mean difference −1.58 mm Hg [95% CI −19.25 to 16.08]). Conclusions: This pilot study demonstrated the feasibility of home BP telemonitoring in older Vietnamese adults with MCI and uncontrolled hypertension. However, technical reliability and patient adherence issues must be addressed before wider-scale implementation. Future research with a larger sample size and a longer follow-up period is necessary to confirm these findings.
- Open Access
- 13 June 2025
- Published by Neurotak Publishing in Neuroscience Research Notes
- Vol. 8 (2) , 404.1-404.13
Electroencephalogram (EEG) based automated detection of mental disorders using artificial intelligence processing pipelines
Bipolar disorder, major depressive disorder, and schizophrenia often have overlapping symptoms that lead to frequent misdiagnoses. To address the need for an objective, quantitative and accurate tool for diagnosing mental disorders, we developed an AI-based approach using electroencephalography (EEG) signals. Our study analysed data from Seoul National University, including EEG assessments and medical records of 383 subjects: bipolar disorder (n=67), major depressive disorder (n=199), and schizophrenia (n=117). Our method involved three steps: (1) balancing the dataset with SMOTE up-sampling, (2) extracting key features, and (3) employing machine learning and deep learning models for classification. The combination of Independent Component Analysis, ANOVA F-value, and Gradient Boosting yielded the highest accuracy of 96.67% and minimal misclassifications. These results suggest this approach could significantly improve the correct diagnosis of mental disorders, and it is feasible to quantify the EEG signals to obtain an objective computer-aided diagnosis system.
- 13 June 2025
- Published by Neurotak Publishing in Neuroscience Research Notes
- Vol. 8 (2) , 404.1-404.13
Open AccessElectroencephalogram (EEG) based automated detection of mental disorders using artificial intelligence processing pipelines
Bipolar disorder, major depressive disorder, and schizophrenia often have overlapping symptoms that lead to frequent misdiagnoses. To address the need for an objective, quantitative and accurate tool for diagnosing mental disorders, we developed an AI-based approach using electroencephalography (EEG) signals. Our study analysed data from Seoul National University, including EEG assessments and medical records of 383 subjects: bipolar disorder (n=67), major depressive disorder (n=199), and schizophrenia (n=117). Our method involved three steps: (1) balancing the dataset with SMOTE up-sampling, (2) extracting key features, and (3) employing machine learning and deep learning models for classification. The combination of Independent Component Analysis, ANOVA F-value, and Gradient Boosting yielded the highest accuracy of 96.67% and minimal misclassifications. These results suggest this approach could significantly improve the correct diagnosis of mental disorders, and it is feasible to quantify the EEG signals to obtain an objective computer-aided diagnosis system.
- 5 June 2025
- Published by Springer Nature
- p. 363-375
Effect of Alpha Music on the Stress Level of Vietnamese Students
- 5 June 2025
- Published by Springer Nature
- p. 363-375
Effect of Alpha Music on the Stress Level of Vietnamese Students