Guang-Bin Huang
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
Guang-Bin Huang has a total of 182 co-authors. Here are the top co-authors by number of shared publications:
- Yijie Zeng
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore
7 shared publications - Benjamin Kye Jyn Tan
Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
6 shared publications - Esther Yanxin Gao
Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
6 shared publications - Nicole Kye Wen Tan
Yong Loo Lin School of Medicine, National University of Singapore, Singapore, Singapore
6 shared publications - Song Tar Toh
Singapore General Hospital
6 shared publications - Yue Li
School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore 639798, Singapore
6 shared publications
Latest Publications
- Open Access
- 25 September 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e78718
Accuracy of Artificial Intelligence in Diagnosing Obstructive Sleep Apnea Using Photoplethysmography: Systematic Review and Meta-Analysis
Background: The traditional method for diagnosing obstructive sleep apnea (OSA) through polysomnography may be expensive and inaccessible. Recent developments in AI propose the use of photoplethysmography (PPG) to aid OSA diagnosis. Objective: This study seeks to evaluate the diagnostic accuracy of an AI-based approach in diagnosing OSA using PPG. Methods: PubMed, Embase, Scopus, Web of Science, and IEEE Xplore were searched from inception to November 3, 2025. The inclusion criteria comprised observational studies that evaluated the accuracy of AI-based methods of OSA diagnosis using PPG compared with conventional sleep testing used in adults. We excluded case reports, case series, reviews, meta-analyses, letters, conference abstracts, pediatric studies, animal studies, foreign language studies, studies with incomplete data, and studies focusing on individual apneic events without patient-level classification. The outcome of interest was the diagnostic accuracy of PPG-based AI models for OSA, as assessed in primary studies using random split tests, cross-validation, or external validation. Independent reviewers extracted data and assessed risk of bias using the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies-2) tool. A Bayesian bivariate meta-analysis was used to pool estimates. Further subgroup, sensitivity, and meta-regression analyses were conducted. Overall quality of evidence was assessed using the GRADE (Grading of Recommendations, Assessment, Development and Evaluations) framework. Results: From 12,579 records, we included 13 studies, comprising 9983 participants. All studies were rated as either low or unclear for risk of bias. The overall evidence quality was moderate. AI trained on PPG achieved a pooled sensitivity of 79.6% (95% credible interval [CrI] 55.5%‐93.8%) and specificity of 76.5% (95% CrI 48.2%‐94.0%), compared to conventional diagnosis. The overall specificity increased (apnea-hypopnea index [AHI] ≥5: 63.6%; AHI ≥15: 81.8%; AHI ≥30: 85.1%), but overall sensitivity decreased (AHI ≥5: 87.2%; AHI ≥15: 79.7%; AHI ≥30: 76.7%) with greater categorical AHI severity cutoffs. Additionally, deep learning models achieved a higher specificity (82.9%) than traditional machine learning (63.6%). OSA prevalence and device type were not clearly associated with sensitivity or specificity. Conclusions: AI models trained on PPG have reasonable accuracy and may potentially serve as a low-cost screening tool. However, limitations such as small sample sizes, potential sources of bias, underrepresentation of certain geographic regions, and the influence of potential confounding factors highlight the necessity for further research. Future work should focus on deep learning to improve the feasibility and accessibility of this approach in primary care.
- 25 September 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e78718
Open AccessAccuracy of Artificial Intelligence in Diagnosing Obstructive Sleep Apnea Using Photoplethysmography: Systematic Review and Meta-Analysis
Background: The traditional method for diagnosing obstructive sleep apnea (OSA) through polysomnography may be expensive and inaccessible. Recent developments in AI propose the use of photoplethysmography (PPG) to aid OSA diagnosis. Objective: This study seeks to evaluate the diagnostic accuracy of an AI-based approach in diagnosing OSA using PPG. Methods: PubMed, Embase, Scopus, Web of Science, and IEEE Xplore were searched from inception to November 3, 2025. The inclusion criteria comprised observational studies that evaluated the accuracy of AI-based methods of OSA diagnosis using PPG compared with conventional sleep testing used in adults. We excluded case reports, case series, reviews, meta-analyses, letters, conference abstracts, pediatric studies, animal studies, foreign language studies, studies with incomplete data, and studies focusing on individual apneic events without patient-level classification. The outcome of interest was the diagnostic accuracy of PPG-based AI models for OSA, as assessed in primary studies using random split tests, cross-validation, or external validation. Independent reviewers extracted data and assessed risk of bias using the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies-2) tool. A Bayesian bivariate meta-analysis was used to pool estimates. Further subgroup, sensitivity, and meta-regression analyses were conducted. Overall quality of evidence was assessed using the GRADE (Grading of Recommendations, Assessment, Development and Evaluations) framework. Results: From 12,579 records, we included 13 studies, comprising 9983 participants. All studies were rated as either low or unclear for risk of bias. The overall evidence quality was moderate. AI trained on PPG achieved a pooled sensitivity of 79.6% (95% credible interval [CrI] 55.5%‐93.8%) and specificity of 76.5% (95% CrI 48.2%‐94.0%), compared to conventional diagnosis. The overall specificity increased (apnea-hypopnea index [AHI] ≥5: 63.6%; AHI ≥15: 81.8%; AHI ≥30: 85.1%), but overall sensitivity decreased (AHI ≥5: 87.2%; AHI ≥15: 79.7%; AHI ≥30: 76.7%) with greater categorical AHI severity cutoffs. Additionally, deep learning models achieved a higher specificity (82.9%) than traditional machine learning (63.6%). OSA prevalence and device type were not clearly associated with sensitivity or specificity. Conclusions: AI models trained on PPG have reasonable accuracy and may potentially serve as a low-cost screening tool. However, limitations such as small sample sizes, potential sources of bias, underrepresentation of certain geographic regions, and the influence of potential confounding factors highlight the necessity for further research. Future work should focus on deep learning to improve the feasibility and accessibility of this approach in primary care.
- Open Access
- 8 July 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e80349
Artificial Intelligence Diagnosis of Obstructive Sleep Apnea Using Overnight Pulse Oximetry: A Systematic Review and Bayesian Meta-Analysis
Background: Obstructive sleep apnea (OSA) affects 38% of the population, yet over 90% of cases remain undiagnosed. The gold standard for diagnosis, polysomnography, requires specialized equipment and trained personnel, making it inaccessible in primary care and acute settings. With artificial intelligence (AI) advancements, oximetry-based AI models have emerged as potential alternatives for OSA diagnosis. Objective: This meta-analysis aims to evaluate the diagnostic accuracy of AI models trained on pulse oximetry readings in diagnosing OSA. Methods: A systematic search was conducted across Medline/PubMed, Embase, Scopus, Web of Science, and IEEE Xplore databases from inception to January 3, 2026. Studies that evaluated the diagnostic accuracy of AI models trained on oxygen saturation recordings, compared to the apnea-hypopnea index (AHI) as the reference standard, were included and screened by 2 blinded independent reviewers. Models were evaluated using Bayesian bivariate meta-analysis and meta-regression. Publication bias was examined using a selection model approach, while risk of bias and evidence quality were assessed with Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) and Grading of Recommendations Assessment, Development, and Evaluation (GRADE). Results: From 13,986 screened articles, 25 studies met the inclusion criteria, encompassing 23,171 participants with a mean age of 40 (SD 10.6) to 63 (SD 13.3) years and a BMI of 25 to 37 kg/m 2 . AI-oximetry models demonstrated a pooled sensitivity of 91.1% (95% credible interval [CrI] 89.7%‐92.4%) and specificity of 88.4% (95% CrI 85.3%‐90.8%). Neural network classifiers achieved the highest sensitivity (92.7%) and specificity (91.3%). Deep learning feature extraction models were significantly higher in sensitivity (by 3.7%; 95% CrI 0.9%-6.9%) than domain expert-based approaches. Sensitivity decreased slightly with higher AHI cutoffs, while specificity increased by 16.6% from an AHI cutoff of ≥5 to ≥30. Sensitivity analyses showed that even with up to 40% probability of an unpublished study, changes in accuracy were modest (area under the curve: 0.902 to 0.877). QUADAS-2 and GRADE assessments found low-moderate risk of bias with high overall quality of evidence. Conclusions: AI-oximetry models showed high diagnostic accuracy for OSA across models and AHI cutoffs, performing better than or comparably to traditional overnight oximetry and home sleep apnea tests. This review provides the first pooled quantitative synthesis of AI models trained solely on oximetry data, with additional evaluations of publication bias and methodological limitations. Prior reviews were largely narrative or used alternative AI inputs other than oximetry. This study advances the field by offering a clearer and more reliable evidence base on pooled AI oximetry performance. These findings support the potential of oximetry-based AI as a convenient and scalable tool for OSA screening and diagnosis, with potential real-world applications in both primary care and inpatient settings for early identification of high-risk patients. Prospective external validation in diverse populations and low-prevalence settings is still needed before widespread real-world use.
- 8 July 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e80349
Open AccessArtificial Intelligence Diagnosis of Obstructive Sleep Apnea Using Overnight Pulse Oximetry: A Systematic Review and Bayesian Meta-Analysis
Background: Obstructive sleep apnea (OSA) affects 38% of the population, yet over 90% of cases remain undiagnosed. The gold standard for diagnosis, polysomnography, requires specialized equipment and trained personnel, making it inaccessible in primary care and acute settings. With artificial intelligence (AI) advancements, oximetry-based AI models have emerged as potential alternatives for OSA diagnosis. Objective: This meta-analysis aims to evaluate the diagnostic accuracy of AI models trained on pulse oximetry readings in diagnosing OSA. Methods: A systematic search was conducted across Medline/PubMed, Embase, Scopus, Web of Science, and IEEE Xplore databases from inception to January 3, 2026. Studies that evaluated the diagnostic accuracy of AI models trained on oxygen saturation recordings, compared to the apnea-hypopnea index (AHI) as the reference standard, were included and screened by 2 blinded independent reviewers. Models were evaluated using Bayesian bivariate meta-analysis and meta-regression. Publication bias was examined using a selection model approach, while risk of bias and evidence quality were assessed with Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) and Grading of Recommendations Assessment, Development, and Evaluation (GRADE). Results: From 13,986 screened articles, 25 studies met the inclusion criteria, encompassing 23,171 participants with a mean age of 40 (SD 10.6) to 63 (SD 13.3) years and a BMI of 25 to 37 kg/m 2 . AI-oximetry models demonstrated a pooled sensitivity of 91.1% (95% credible interval [CrI] 89.7%‐92.4%) and specificity of 88.4% (95% CrI 85.3%‐90.8%). Neural network classifiers achieved the highest sensitivity (92.7%) and specificity (91.3%). Deep learning feature extraction models were significantly higher in sensitivity (by 3.7%; 95% CrI 0.9%-6.9%) than domain expert-based approaches. Sensitivity decreased slightly with higher AHI cutoffs, while specificity increased by 16.6% from an AHI cutoff of ≥5 to ≥30. Sensitivity analyses showed that even with up to 40% probability of an unpublished study, changes in accuracy were modest (area under the curve: 0.902 to 0.877). QUADAS-2 and GRADE assessments found low-moderate risk of bias with high overall quality of evidence. Conclusions: AI-oximetry models showed high diagnostic accuracy for OSA across models and AHI cutoffs, performing better than or comparably to traditional overnight oximetry and home sleep apnea tests. This review provides the first pooled quantitative synthesis of AI models trained solely on oximetry data, with additional evaluations of publication bias and methodological limitations. Prior reviews were largely narrative or used alternative AI inputs other than oximetry. This study advances the field by offering a clearer and more reliable evidence base on pooled AI oximetry performance. These findings support the potential of oximetry-based AI as a convenient and scalable tool for OSA screening and diagnosis, with potential real-world applications in both primary care and inpatient settings for early identification of high-risk patients. Prospective external validation in diverse populations and low-prevalence settings is still needed before widespread real-world use.
- Open Access
- 14 March 2026
- Published by Springer Nature in Journal of Scientific Computing
- Vol. 107 (1) , 22
Use of ELMs in Physics-Informed Machine Learning: Estimates on the Generalization Error in Learning ODE Solutions
Physics-Informed Neural Networks have been introduced to learn the solutions to Differential Problems. Extreme Learning Machines (ELMs), which are shallow feedforward architectures based on random projection, have been utilized along with other types of Neural Networks. Recently, ELM-based Physics-Informed Neural Networks have been combined with a functional interpolation technique called the Theory of Functional Connections, leading to an efficient method named the Extreme Theory of Functional Connections. The Extreme Theory of Functional Connections allows us to analytically satisfy the constraints, e.g., initial and/or boundary conditions that complete the differential problem removing one of the limitations of the traditional Physics-Informed Neural Networks frameworks: the need to learn the constraints alongside learning the solution within the domain. In this work, we provide upper bounds on the generalization error, in terms of the training error and number and choice of training points, of The Extreme Theory of Functional Connections in learning the solutions for the class of univariate Differential Problems. We fully cover three kinds of problems: first-order initial value problems, higher-order IVPs, and second-order two-point boundary value problems. The theoretical results for these three cases are validated with numerical experiments on some benchmark linear and non-linear problems. Furthermore, the resolution using the proposed method is tested by comparing the results obtained with the ones computed by MATLAB’s routines, and the proposed method outperforms the other solvers in terms of accuracy and computational efficiency.
- 14 March 2026
- Published by Springer Nature in Journal of Scientific Computing
- Vol. 107 (1) , 22
Open AccessUse of ELMs in Physics-Informed Machine Learning: Estimates on the Generalization Error in Learning ODE Solutions
Physics-Informed Neural Networks have been introduced to learn the solutions to Differential Problems. Extreme Learning Machines (ELMs), which are shallow feedforward architectures based on random projection, have been utilized along with other types of Neural Networks. Recently, ELM-based Physics-Informed Neural Networks have been combined with a functional interpolation technique called the Theory of Functional Connections, leading to an efficient method named the Extreme Theory of Functional Connections. The Extreme Theory of Functional Connections allows us to analytically satisfy the constraints, e.g., initial and/or boundary conditions that complete the differential problem removing one of the limitations of the traditional Physics-Informed Neural Networks frameworks: the need to learn the constraints alongside learning the solution within the domain. In this work, we provide upper bounds on the generalization error, in terms of the training error and number and choice of training points, of The Extreme Theory of Functional Connections in learning the solutions for the class of univariate Differential Problems. We fully cover three kinds of problems: first-order initial value problems, higher-order IVPs, and second-order two-point boundary value problems. The theoretical results for these three cases are validated with numerical experiments on some benchmark linear and non-linear problems. Furthermore, the resolution using the proposed method is tested by comparing the results obtained with the ones computed by MATLAB’s routines, and the proposed method outperforms the other solvers in terms of accuracy and computational efficiency.
- Open Access
- 8 December 2025
- Published by Springer Nature in Journal of Clinical Sleep Medicine
- Vol. 22 (1) , 5
Awake speech recordings for machine learning diagnosis of obstructive sleep apnea: a Bayesian meta-analysis
Study objectives Obstructive sleep apnea (OSA) is a prevalent but underdiagnosed condition linked to serious health risks. Due to the limited accessibility of polysomnography (PSG), AI (Artificial Intelligence)-based speech analysis has gained attention as a non-invasive screening tool. This Bayesian meta-analysis evaluates the diagnostic accuracy of AI models trained on awake speech and examines factors affecting performance. Methods We systematically searched Medline/PubMed, Embase, Scopus, Web of Science, and IEEE Xplore databases. Eligible studies included adults with OSA diagnosis via in-lab polysomnography or home sleep apnea tests and evaluated AI models using speech recordings. Models evaluated using random-split test sets or k-fold cross-validation were included in a Bayesian bivariate meta-analysis and meta-regression. Publication bias was examined using a selection model approach, while risk of bias and evidence quality were assessed with QUADAS-2 and GRADE. Results From 6,254 screened articles, 8 studies comprising 24 AI models, trained and tested on 1,060 and 825 participants were included. All studies used professional microphone recordings in the controlled hospital settings. AI models analysing awake speech recordings demonstrated pooled sensitivity and specificity of 82.9% (95% CrI: 80.0–86.4%) and 83.3% (95% CrI: 80.7–86.1%), respectively. The diagnostic odds ratio was 24.3 (95% CrI: 18.2–35.0). Higher mean age improved sensitivity. No significant effects were seen for OSA severity, model type, OSA prevalence, or male percentage. Publication bias was not evident. Conclusion AI models trained on awake speech recordings demonstrate good diagnostic accuracy for OSA and hold potential as a practical, scalable screening tool in both clinical and community-based settings.
- 8 December 2025
- Published by Springer Nature in Journal of Clinical Sleep Medicine
- Vol. 22 (1) , 5
Open AccessAwake speech recordings for machine learning diagnosis of obstructive sleep apnea: a Bayesian meta-analysis
Study objectives Obstructive sleep apnea (OSA) is a prevalent but underdiagnosed condition linked to serious health risks. Due to the limited accessibility of polysomnography (PSG), AI (Artificial Intelligence)-based speech analysis has gained attention as a non-invasive screening tool. This Bayesian meta-analysis evaluates the diagnostic accuracy of AI models trained on awake speech and examines factors affecting performance. Methods We systematically searched Medline/PubMed, Embase, Scopus, Web of Science, and IEEE Xplore databases. Eligible studies included adults with OSA diagnosis via in-lab polysomnography or home sleep apnea tests and evaluated AI models using speech recordings. Models evaluated using random-split test sets or k-fold cross-validation were included in a Bayesian bivariate meta-analysis and meta-regression. Publication bias was examined using a selection model approach, while risk of bias and evidence quality were assessed with QUADAS-2 and GRADE. Results From 6,254 screened articles, 8 studies comprising 24 AI models, trained and tested on 1,060 and 825 participants were included. All studies used professional microphone recordings in the controlled hospital settings. AI models analysing awake speech recordings demonstrated pooled sensitivity and specificity of 82.9% (95% CrI: 80.0–86.4%) and 83.3% (95% CrI: 80.7–86.1%), respectively. The diagnostic odds ratio was 24.3 (95% CrI: 18.2–35.0). Higher mean age improved sensitivity. No significant effects were seen for OSA severity, model type, OSA prevalence, or male percentage. Publication bias was not evident. Conclusion AI models trained on awake speech recordings demonstrate good diagnostic accuracy for OSA and hold potential as a practical, scalable screening tool in both clinical and community-based settings.
- 16 November 2025
- Published by Springer Nature in European Archives of Oto-Rhino-Laryngology
- Vol. 283 (4) , 2107-2116
Multichannel machine learning for polysomnographic diagnosis of obstructive sleep apnea: a Bayesian meta-analysis
Background Obstructive sleep apnea (OSA) affects 1 billion people globally, yet over 80% remain undiagnosed. The gold standard for diagnosis, overnight polysomnography, is highly accurate but labor-intensive, leading to delays and increased healthcare burden. Artificial intelligence (AI) models offer a promising alternative. This study pools existing evidence to evaluate AI-based OSA diagnostics. Methods A systematic search of PubMed, Embase, Scopus, Web of Science, and IEEE Xplore identified studies comparing AI models against the apnea-hypopnea index (AHI) for OSA diagnosis. Studies evaluating models using random-split test sets or k-fold cross-validation were included in a Bayesian bivariate meta-analysis and meta-regression. Risk of bias and evidence quality were assessed using QUADAS-2 and GRADE. Results From 6,254 records, 7 studies with 19 AI models trained and tested on 7,547 and 7,471 participants were included. No study had a high risk of bias. AI achieved a pooled sensitivity of 89.2% (95% CrI: 81.5–94.3%) and specificity of 87.1% (95% CrI: 82.6–90.8%). Neural networks (NNs) were the best-performing AI model compared to the other subtypes, achieving a sensitivity of 92.8% (95% CrI: 84.8–96.6%) and specificity of 87.8% (95% CrI: 81.1–92.6%). Age and sex had no effect. No publication bias was detected, and the evidence was of high quality. Conclusion Neural Networks AI models trained on polysomnography demonstrated excellent diagnostic accuracy in diagnosing OSA as compared to traditional machine learning. There is a need for further exploration and external validation of AI models to support their integration into routine sleep medicine practice, hence improving access to efficient and accurate OSA diagnosis. PROSPERO registration: CRD42024534235.
- 16 November 2025
- Published by Springer Nature in European Archives of Oto-Rhino-Laryngology
- Vol. 283 (4) , 2107-2116
Multichannel machine learning for polysomnographic diagnosis of obstructive sleep apnea: a Bayesian meta-analysis
Background Obstructive sleep apnea (OSA) affects 1 billion people globally, yet over 80% remain undiagnosed. The gold standard for diagnosis, overnight polysomnography, is highly accurate but labor-intensive, leading to delays and increased healthcare burden. Artificial intelligence (AI) models offer a promising alternative. This study pools existing evidence to evaluate AI-based OSA diagnostics. Methods A systematic search of PubMed, Embase, Scopus, Web of Science, and IEEE Xplore identified studies comparing AI models against the apnea-hypopnea index (AHI) for OSA diagnosis. Studies evaluating models using random-split test sets or k-fold cross-validation were included in a Bayesian bivariate meta-analysis and meta-regression. Risk of bias and evidence quality were assessed using QUADAS-2 and GRADE. Results From 6,254 records, 7 studies with 19 AI models trained and tested on 7,547 and 7,471 participants were included. No study had a high risk of bias. AI achieved a pooled sensitivity of 89.2% (95% CrI: 81.5–94.3%) and specificity of 87.1% (95% CrI: 82.6–90.8%). Neural networks (NNs) were the best-performing AI model compared to the other subtypes, achieving a sensitivity of 92.8% (95% CrI: 84.8–96.6%) and specificity of 87.8% (95% CrI: 81.1–92.6%). Age and sex had no effect. No publication bias was detected, and the evidence was of high quality. Conclusion Neural Networks AI models trained on polysomnography demonstrated excellent diagnostic accuracy in diagnosing OSA as compared to traditional machine learning. There is a need for further exploration and external validation of AI models to support their integration into routine sleep medicine practice, hence improving access to efficient and accurate OSA diagnosis. PROSPERO registration: CRD42024534235.
- 30 September 2025
- Published by Springer Nature in Sleep and Breathing
- Vol. 29 (5) , 303
Electrocardiogram heart rate variability for machine learning diagnosis of obstructive sleep apnoea: A Bayesian meta-analysis
Obstructive sleep apnoea syndrome (OSA) is a common yet underdiagnosed condition associated with significant health risks. Although polysomnography is the diagnostic gold standard, it is resource-intensive and unsuitable for widespread screening. Heart rate variability (HRV) derived from electrocardiogram (ECG) recordings has emerged as a promising, accessible alternative for OSA detection. Recent developments in machine learning have enabled automated HRV analysis, potentially offering a scalable screening tool for OSA. This study aimed to evaluate the diagnostic accuracy of machine learning-based models trained on HRV for detecting OSA in adults. We searched PubMed, Embase, Scopus, Web of Science, and IEEE Xplore (up to 20 October 2024) for eligible studies that assessed the accuracy of OSA diagnosis using AI models trained on HRV, compared to the apnoea-hypopnea index (AHI). Bayesian bivariate random-effects meta-analysis estimated pooled sensitivity and specificity. Risk of bias was assessed using QUADAS-2, and GRADE was used to rate evidence certainty. Nine studies with 2,019 participants met inclusion criteria. Pooled sensitivity was 79.0% (95% CrI: 74.9%-82.7%) and specificity was 75.0% (95% CrI: 67.9%-82.3%). The diagnostic odds ratio was 11.3 (95% CrI: 7.21-19.0%). Meta-regression showed specificity varied with demographic factors, while model architecture and validation methods had no significant impact. No publication bias was detected. Machine learning models trained on HRV show good diagnostic accuracy for OSA, with higher specificity than STOP-BANG and comparable performance to home sleep tests. Their scalability and potential integration into wearable devices offer a practical, cost-effective screening option. Further real-world validation is warranted.
- 30 September 2025
- Published by Springer Nature in Sleep and Breathing
- Vol. 29 (5) , 303
Electrocardiogram heart rate variability for machine learning diagnosis of obstructive sleep apnoea: A Bayesian meta-analysis
Obstructive sleep apnoea syndrome (OSA) is a common yet underdiagnosed condition associated with significant health risks. Although polysomnography is the diagnostic gold standard, it is resource-intensive and unsuitable for widespread screening. Heart rate variability (HRV) derived from electrocardiogram (ECG) recordings has emerged as a promising, accessible alternative for OSA detection. Recent developments in machine learning have enabled automated HRV analysis, potentially offering a scalable screening tool for OSA. This study aimed to evaluate the diagnostic accuracy of machine learning-based models trained on HRV for detecting OSA in adults. We searched PubMed, Embase, Scopus, Web of Science, and IEEE Xplore (up to 20 October 2024) for eligible studies that assessed the accuracy of OSA diagnosis using AI models trained on HRV, compared to the apnoea-hypopnea index (AHI). Bayesian bivariate random-effects meta-analysis estimated pooled sensitivity and specificity. Risk of bias was assessed using QUADAS-2, and GRADE was used to rate evidence certainty. Nine studies with 2,019 participants met inclusion criteria. Pooled sensitivity was 79.0% (95% CrI: 74.9%-82.7%) and specificity was 75.0% (95% CrI: 67.9%-82.3%). The diagnostic odds ratio was 11.3 (95% CrI: 7.21-19.0%). Meta-regression showed specificity varied with demographic factors, while model architecture and validation methods had no significant impact. No publication bias was detected. Machine learning models trained on HRV show good diagnostic accuracy for OSA, with higher specificity than STOP-BANG and comparable performance to home sleep tests. Their scalability and potential integration into wearable devices offer a practical, cost-effective screening option. Further real-world validation is warranted.
- Open Access
- 1 July 2025
- Published by SPIE-Intl Soc Optical Eng in Advanced Photonics Nexus
- Vol. 4 (04) , 046010-10
Achieving superior accuracy in photonic neural networks with physical multi-synapses
Artificial intelligence (AI) has seen extensive applications in recent decades, spanning from facial recognition to autonomous driving and natural language processing.1 However, the exponential surge in data poses challenges for traditional digital computing, leading to issues such as the “memory wall” and high energy consumption in AI tasks. The waning effect of Moore’s Law further highlights the limitations of traditional digital computing.2 Leveraging light as an information carrier presents a promising alternative, sparking strong interest in integrating photonics into AI applications.3
- 1 July 2025
- Published by SPIE-Intl Soc Optical Eng in Advanced Photonics Nexus
- Vol. 4 (04) , 046010-10
Open AccessAchieving superior accuracy in photonic neural networks with physical multi-synapses
Artificial intelligence (AI) has seen extensive applications in recent decades, spanning from facial recognition to autonomous driving and natural language processing.1 However, the exponential surge in data poses challenges for traditional digital computing, leading to issues such as the “memory wall” and high energy consumption in AI tasks. The waning effect of Moore’s Law further highlights the limitations of traditional digital computing.2 Leveraging light as an information carrier presents a promising alternative, sparking strong interest in integrating photonics into AI applications.3
- 30 November 2024
- Published by Springer Nature in Sleep and Breathing
- Vol. 29 (1) , 1-11
Artificial intelligence facial recognition of obstructive sleep apnea: a Bayesian meta-analysis
Purpose Conventional obstructive sleep apnea (OSA) diagnosis via polysomnography can be costly and inaccessible. Recent advances in artificial intelligence (AI) have enabled the use of craniofacial photographs to diagnose OSA. This meta-analysis aims to clarify the diagnostic accuracy of this innovative approach. Methods Two blinded reviewers searched PubMed, Embase, Scopus, Web of Science, and IEEE Xplore databases, then selected and graded the risk of bias of observational studies of adults (≥ 18 years) comparing the diagnostic performance of AI algorithms using craniofacial photographs, versus conventional OSA diagnostic criteria (i.e. apnea-hypopnea index [AHI]). Studies were excluded if they detected apneic events without diagnosing OSA. AI models evaluated with a random split test set or k-fold cross-validation were included in a Bayesian bivariate meta-analysis. Results From 5,147 records, 6 studies were included, containing 10 AI models trained/tested on 1,417/983 participants. The risk of bias was low. AI trained on craniofacial photographs achieved a pooled 84.9% sensitivity (95% credible interval [95% CrI]: 77.1–90.7%) and 71.2% specificity (95% CrI: 60.7–81.4%). Bayesian meta-regression identified deep learning (convolutional neural networks) as the most accurate AI algorithm (91.1% sensitivity, 79.2% specificity) comparable to home sleep apnea tests. AHI cutoffs, OSA prevalence, feature engineering, input data, camera type and informativeness of Bayesian prior did not alter diagnostic accuracy. There was no substantial publication bias. Conclusion AI trained on craniofacial photographs have high diagnostic accuracy and should be considered as a low-cost OSA screening tool. Future work focused on deep learning using smartphone images could improve the feasibility of this approach in primary care.
- 30 November 2024
- Published by Springer Nature in Sleep and Breathing
- Vol. 29 (1) , 1-11
Artificial intelligence facial recognition of obstructive sleep apnea: a Bayesian meta-analysis
Purpose Conventional obstructive sleep apnea (OSA) diagnosis via polysomnography can be costly and inaccessible. Recent advances in artificial intelligence (AI) have enabled the use of craniofacial photographs to diagnose OSA. This meta-analysis aims to clarify the diagnostic accuracy of this innovative approach. Methods Two blinded reviewers searched PubMed, Embase, Scopus, Web of Science, and IEEE Xplore databases, then selected and graded the risk of bias of observational studies of adults (≥ 18 years) comparing the diagnostic performance of AI algorithms using craniofacial photographs, versus conventional OSA diagnostic criteria (i.e. apnea-hypopnea index [AHI]). Studies were excluded if they detected apneic events without diagnosing OSA. AI models evaluated with a random split test set or k-fold cross-validation were included in a Bayesian bivariate meta-analysis. Results From 5,147 records, 6 studies were included, containing 10 AI models trained/tested on 1,417/983 participants. The risk of bias was low. AI trained on craniofacial photographs achieved a pooled 84.9% sensitivity (95% credible interval [95% CrI]: 77.1–90.7%) and 71.2% specificity (95% CrI: 60.7–81.4%). Bayesian meta-regression identified deep learning (convolutional neural networks) as the most accurate AI algorithm (91.1% sensitivity, 79.2% specificity) comparable to home sleep apnea tests. AHI cutoffs, OSA prevalence, feature engineering, input data, camera type and informativeness of Bayesian prior did not alter diagnostic accuracy. There was no substantial publication bias. Conclusion AI trained on craniofacial photographs have high diagnostic accuracy and should be considered as a low-cost OSA screening tool. Future work focused on deep learning using smartphone images could improve the feasibility of this approach in primary care.
- 11 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-10
Object Detection in Adverse Weather for Autonomous Vehicles Based on Sensor Fusion and Incremental Learning
Object detection is critical for autonomous vehicles. It enables safe and efficient autonomous driving. However, variations in weather conditions, such as night, fog, rain, and snow, introduce domain shifts that can lead to catastrophic forgetting in detection models, significantly degrading their performance in object detection tasks. This work introduces D-FusionNet, a model that combines data-level sensor fusion with domain incremental learning (Domain-IL) to improve detection performance under such conditions. By combining the complementary strengths of radar and camera sensors, and using Domain-IL to selectively retain features from different weather domains, D-FusionNet demonstrates improved accuracy in object detection, as validated on the RADIATE dataset. This approach effectively addresses catastrophic forgetting and increases object detection accuracy in adverse weather conditions, marking a significant advancement in autonomous vehicle technology.
- 11 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 73 (00189456) , 1-10
Object Detection in Adverse Weather for Autonomous Vehicles Based on Sensor Fusion and Incremental Learning
Object detection is critical for autonomous vehicles. It enables safe and efficient autonomous driving. However, variations in weather conditions, such as night, fog, rain, and snow, introduce domain shifts that can lead to catastrophic forgetting in detection models, significantly degrading their performance in object detection tasks. This work introduces D-FusionNet, a model that combines data-level sensor fusion with domain incremental learning (Domain-IL) to improve detection performance under such conditions. By combining the complementary strengths of radar and camera sensors, and using Domain-IL to selectively retain features from different weather domains, D-FusionNet demonstrates improved accuracy in object detection, as validated on the RADIATE dataset. This approach effectively addresses catastrophic forgetting and increases object detection accuracy in adverse weather conditions, marking a significant advancement in autonomous vehicle technology.