Jian Huo
Research Subjects
Jian Huo has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Anmin Hu
Department of Anesthesia, Shenzhen Peoples Hospital, Shenzhen, China
8 shared publications - Wei Lin
Shenzhen United Scheme Technology Company Limited, Shenzhen, China
5 shared publications - Chaoran Wu
Department of Anesthesiology, Shenzhen People’s Hospital, The First Affiliated Hospital, Southern University of Science and Technology, Shenzhen, China, sustc.edu.cn
4 shared publications - Yan Yu
Department of Anesthesia, Shenzhen People's Hospital, The First Affiliated Hospital of Southern University of Science and Technology, Shenzhen Key Medical Discipline, Shenzhen, China
4 shared publications - Huijie Li
Macao Polytechnic University, Macao, China
3 shared publications - Wuman Luo
Macao Polytechnic University
2 shared publications
Latest Publications
- Open Access
- 23 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (7) , 5761-5774
Multi-Agent Learning for Precise and Collaborative Control of Anesthetics in TIVA
Precise and collaborative control of multiple anesthetics in Total Intravenous Anesthesia (TIVA) is essential for ensuring patient safety and maintaining the target depth of anesthesia (DoA). However, existing automated anesthesia control methods often fail to effectively capture the complex synergistic interactions between anesthetics and lack adaptability to patient-specific physiological variability, thereby limiting their clinical applicability. To address these issues, we propose AnesMADRL, a novel Multi-Agent Deep Reinforcement Learning (MADRL)-based framework that leverages the Counterfactual Multi-Agent algorithm for effective credit assignment between agents controlling propofol and remifentanil, and adopts a continuous action space to enable fine-grained dose adjustments. Furthermore, AnesMADRL integrates comprehensive patient-specific physiological indicators and employs a random forest-based simulator to generate dynamic and diverse training environments. Experimental results show that AnesMADRL significantly outperforms baseline methods and human expertise in terms of anesthetic efficiency and total drug consumption. Relative to human expertise, AnesMADRL achieves roughly twofold efficiency while reducing total dose to about one-half, highlighting its potential to enhance patient safety and optimize clinical outcomes.
- 23 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (7) , 5761-5774
Open AccessMulti-Agent Learning for Precise and Collaborative Control of Anesthetics in TIVA
Precise and collaborative control of multiple anesthetics in Total Intravenous Anesthesia (TIVA) is essential for ensuring patient safety and maintaining the target depth of anesthesia (DoA). However, existing automated anesthesia control methods often fail to effectively capture the complex synergistic interactions between anesthetics and lack adaptability to patient-specific physiological variability, thereby limiting their clinical applicability. To address these issues, we propose AnesMADRL, a novel Multi-Agent Deep Reinforcement Learning (MADRL)-based framework that leverages the Counterfactual Multi-Agent algorithm for effective credit assignment between agents controlling propofol and remifentanil, and adopts a continuous action space to enable fine-grained dose adjustments. Furthermore, AnesMADRL integrates comprehensive patient-specific physiological indicators and employs a random forest-based simulator to generate dynamic and diverse training environments. Experimental results show that AnesMADRL significantly outperforms baseline methods and human expertise in terms of anesthetic efficiency and total drug consumption. Relative to human expertise, AnesMADRL achieves roughly twofold efficiency while reducing total dose to about one-half, highlighting its potential to enhance patient safety and optimize clinical outcomes.
- 19 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (3) , 2167-2180
Value Decomposition-Based Multi-Agent Learning for Anesthetics Collaborative Control
Automated control of personalized multiple anesthetics in clinical Total Intravenous Anesthesia (TIVA) is crucial yet challenging. Current systems, including target-controlled infusion (TCI) and closedloop systems, either rely on relatively static pharmacokinetic/pharmacodynamic (PK/PD) models or focus on single anesthetic control. So they limit both personalization and collaborative control. To address these issues, we propose a novel Value Decomposition MultiAgent Deep Reinforcement Learning (VD-MADRL) framework based on Markov Game (MG) for Personalized Multiple Anesthetics Control in a Closed-Loop system (PMAC-CL). VD-MADRL optimizes the collaboration between two anesthetics propofol (Agent I) and remifentanil (Agent II) by leveraging a MG to identify optimal actions among heterogeneous agents. We employ various value function decomposition methods to resolve the credit allocation problem and enhance collaborative control. We also introduce a multivariate environment model based on random forest (RF) for anesthesia state simulation. To ensure data validity, we design a data resampling and alignment technique to synchronize trajectory data from different devices, avoiding gradient explosion and maintaining conformity to Markov property. Extensive experiments on general and thoracic surgery datasets demonstrate that VD-MADRL provides more refined dose adjustments and maintains multiple anesthesia state indicators more stably at target levels compared to human experience. Especially, the bestperforming algorithm, VDN in general surgery with online training, achieved a 16.4% increase in cumulative reward (CR) and a 58.0% reduction in mean MDPE compared to human experience. This demonstrates its great clinical value
- 19 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30 (3) , 2167-2180
Value Decomposition-Based Multi-Agent Learning for Anesthetics Collaborative Control
Automated control of personalized multiple anesthetics in clinical Total Intravenous Anesthesia (TIVA) is crucial yet challenging. Current systems, including target-controlled infusion (TCI) and closedloop systems, either rely on relatively static pharmacokinetic/pharmacodynamic (PK/PD) models or focus on single anesthetic control. So they limit both personalization and collaborative control. To address these issues, we propose a novel Value Decomposition MultiAgent Deep Reinforcement Learning (VD-MADRL) framework based on Markov Game (MG) for Personalized Multiple Anesthetics Control in a Closed-Loop system (PMAC-CL). VD-MADRL optimizes the collaboration between two anesthetics propofol (Agent I) and remifentanil (Agent II) by leveraging a MG to identify optimal actions among heterogeneous agents. We employ various value function decomposition methods to resolve the credit allocation problem and enhance collaborative control. We also introduce a multivariate environment model based on random forest (RF) for anesthesia state simulation. To ensure data validity, we design a data resampling and alignment technique to synchronize trajectory data from different devices, avoiding gradient explosion and maintaining conformity to Markov property. Extensive experiments on general and thoracic surgery datasets demonstrate that VD-MADRL provides more refined dose adjustments and maintains multiple anesthesia state indicators more stably at target levels compared to human experience. Especially, the bestperforming algorithm, VDN in general surgery with online training, achieved a 16.4% increase in cumulative reward (CR) and a 58.0% reduction in mean MDPE compared to human experience. This demonstrates its great clinical value
- Open Access
- 30 May 2025
- Published by Wolters Kluwer Health in Medicine
- Vol. 104 (22) , e42589
Dexmedetomidine increases the risk of delirium in critically ill patients: A propensity score analysis
Delirium frequently affects patients in intensive care units (ICUs). Dexmedetomidine (DEX), a sedative with limited respiratory depressant effects, may be advantageous for preventing sedation-related delirium. Current evidence on the potential association between DEX and delirium is mixed, and the specific relationship between DEX administration within 24 hours and delirium occurrence remains unclear. This study investigated the risk and outcomes of delirium in ICU patients who received DEX within 24 hours preceding a delirium assessment, compared to those who did not. A systematic analysis of data extracted from the MIMIC-III v1.4, MIMIC-IV v0.4, and eICU collaborative research databases was conducted. Two patient cohorts were formed to assess the relative risks of delirium, mortality, ICU and hospital lengths of stay, and the likelihood of home discharge within the preceding 24 hours following DEX administration. Propensity score matching (1:1) ensured balance within the matched cohort and aided in identifying potential prognostic factors. Multinomial regression modeling and propensity score calculations were employed for statistical analysis. Among 78,364 patients analyzed, 22,159 (28.28%) had positive delirium records. Propensity matching yielded 4666 patients (2333 per treatment group) with balanced covariates. DEX administration significantly increased the risk of delirium (P < .001). It was also associated with extended ICU stay (P < .001) but surprisingly showed lower mortality (P < .001). Patients treated with DEX had greater odds of home discharge (P < .01) with no significant difference in hospitalization duration (P = .06). DEX was independently associated with delirium in critically ill patients.
- 30 May 2025
- Published by Wolters Kluwer Health in Medicine
- Vol. 104 (22) , e42589
Open AccessDexmedetomidine increases the risk of delirium in critically ill patients: A propensity score analysis
Delirium frequently affects patients in intensive care units (ICUs). Dexmedetomidine (DEX), a sedative with limited respiratory depressant effects, may be advantageous for preventing sedation-related delirium. Current evidence on the potential association between DEX and delirium is mixed, and the specific relationship between DEX administration within 24 hours and delirium occurrence remains unclear. This study investigated the risk and outcomes of delirium in ICU patients who received DEX within 24 hours preceding a delirium assessment, compared to those who did not. A systematic analysis of data extracted from the MIMIC-III v1.4, MIMIC-IV v0.4, and eICU collaborative research databases was conducted. Two patient cohorts were formed to assess the relative risks of delirium, mortality, ICU and hospital lengths of stay, and the likelihood of home discharge within the preceding 24 hours following DEX administration. Propensity score matching (1:1) ensured balance within the matched cohort and aided in identifying potential prognostic factors. Multinomial regression modeling and propensity score calculations were employed for statistical analysis. Among 78,364 patients analyzed, 22,159 (28.28%) had positive delirium records. Propensity matching yielded 4666 patients (2333 per treatment group) with balanced covariates. DEX administration significantly increased the risk of delirium (P < .001). It was also associated with extended ICU stay (P < .001) but surprisingly showed lower mortality (P < .001). Patients treated with DEX had greater odds of home discharge (P < .01) with no significant difference in hospitalization duration (P = .06). DEX was independently associated with delirium in critically ill patients.
- Open Access
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 4098-4116
POMA-C: A Framework for Solving the Problem of Precise Anesthesia Control Under Incomplete Observation Environment in Low-Income Areas
This paper introduces the POMA-C (Partial Observable Model for Anesthesia Control) framework, developed to address the challenge of anesthesia management in environments with incomplete physiological monitoring, such as low-resource settings where critical indicators like the Bispectral Index (BIS) are often unavailable. Unlike traditional methods that rely on fully observable data, POMA-C frames the problem of anesthesia control under incomplete observability within a Partially Observable Markov Decision Process (POMDP), enabling the precise control of anesthesia despite missing data. By establishing a formal correspondence between the anesthesia control process and POMDP, this framework provides a theoretical foundation for modeling anesthesia control in uncertain environments. The framework employs the POMCPOW (Partially Observable Monte Carlo Planning with ObservationWeighting) algorithm, which integrates Monte Carlo Tree Search (MCTS) and particle filtering to estimate the patient’s true physiological state and guide optimal anesthetic decisions. Through comprehensive ablation experiments—where key observation dimensions are systematically reduced to simulate missing data—POMA-C demonstrates significantly higher decision accuracy and cumulative reward optimization compared to methods like Q-learning and human expertise, even in data-constrained environments. This work not only provides a robust solution for anesthesia control under incomplete observability but also bridges the gap between MDP and POMDP models, offering a foundation for future research in automated anesthesia management.
- 30 December 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 4098-4116
Open AccessPOMA-C: A Framework for Solving the Problem of Precise Anesthesia Control Under Incomplete Observation Environment in Low-Income Areas
This paper introduces the POMA-C (Partial Observable Model for Anesthesia Control) framework, developed to address the challenge of anesthesia management in environments with incomplete physiological monitoring, such as low-resource settings where critical indicators like the Bispectral Index (BIS) are often unavailable. Unlike traditional methods that rely on fully observable data, POMA-C frames the problem of anesthesia control under incomplete observability within a Partially Observable Markov Decision Process (POMDP), enabling the precise control of anesthesia despite missing data. By establishing a formal correspondence between the anesthesia control process and POMDP, this framework provides a theoretical foundation for modeling anesthesia control in uncertain environments. The framework employs the POMCPOW (Partially Observable Monte Carlo Planning with ObservationWeighting) algorithm, which integrates Monte Carlo Tree Search (MCTS) and particle filtering to estimate the patient’s true physiological state and guide optimal anesthetic decisions. Through comprehensive ablation experiments—where key observation dimensions are systematically reduced to simulate missing data—POMA-C demonstrates significantly higher decision accuracy and cumulative reward optimization compared to methods like Q-learning and human expertise, even in data-constrained environments. This work not only provides a robust solution for anesthesia control under incomplete observability but also bridges the gap between MDP and POMDP models, offering a foundation for future research in automated anesthesia management.
- Open Access
- 17 April 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Correction: Application of AI in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
- 17 April 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessCorrection: Application of AI in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis (Preprint)
Journal of Medical Internet Research - International Scientific Journal for Medical Research, Information and Communication on the Internet #Preprint #PeerReviewMe: Warning: This is a unreviewed preprint. Readers are warned that the document has not been peer-reviewed by expert/patient reviewers or an academic editor, may contain misleading claims, and is likely to undergo changes before final publication, if accepted, or may have been rejected/withdrawn. Readers with interest and expertise are encouraged to sign up as peer-reviewer, if the paper is within an open peer-review period. Please cite this preprint only for review purposes or for grant applications and CVs (if you are the author).
- Open Access
- 17 April 2024
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 26 (1) , e59628
Correction: Application of AI in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis
[This corrects the article DOI: 10.2196/51250.].
- 17 April 2024
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 26 (1) , e59628
Open AccessCorrection: Application of AI in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis
[This corrects the article DOI: 10.2196/51250.].
- Open Access
- 12 April 2024
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 26 (1) , e51250
Application of AI in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis
Background: The continuous monitoring and recording of patients’ pain status is a major problem in current research on postoperative pain management. In the large number of original or review articles focusing on different approaches for pain assessment, many researchers have investigated how computer vision (CV) can help by capturing facial expressions. However, there is a lack of proper comparison of results between studies to identify current research gaps. Objective: The purpose of this systematic review and meta-analysis was to investigate the diagnostic performance of artificial intelligence models for multilevel pain assessment from facial images. Methods: The PubMed, Embase, IEEE, Web of Science, and Cochrane Library databases were searched for related publications before September 30, 2023. Studies that used facial images alone to estimate multiple pain values were included in the systematic review. A study quality assessment was conducted using the Quality Assessment of Diagnostic Accuracy Studies, 2nd edition tool. The performance of these studies was assessed by metrics including sensitivity, specificity, log diagnostic odds ratio (LDOR), and area under the curve (AUC). The intermodal variability was assessed and presented by forest plots. Results: A total of 45 reports were included in the systematic review. The reported test accuracies ranged from 0.27-0.99, and the other metrics, including the mean standard error (MSE), mean absolute error (MAE), intraclass correlation coefficient (ICC), and Pearson correlation coefficient (PCC), ranged from 0.31-4.61, 0.24-2.8, 0.19-0.83, and 0.48-0.92, respectively. In total, 6 studies were included in the meta-analysis. Their combined sensitivity was 98% (95% CI 96%-99%), specificity was 98% (95% CI 97%-99%), LDOR was 7.99 (95% CI 6.73-9.31), and AUC was 0.99 (95% CI 0.99-1). The subgroup analysis showed that the diagnostic performance was acceptable, although imbalanced data were still emphasized as a major problem. All studies had at least one domain with a high risk of bias, and for 20% (9/45) of studies, there were no applicability concerns. Conclusions: This review summarizes recent evidence in automatic multilevel pain estimation from facial expressions and compared the test accuracy of results in a meta-analysis. Promising performance for pain estimation from facial images was established by current CV algorithms. Weaknesses in current studies were also identified, suggesting that larger databases and metrics evaluating multiclass classification performance could improve future studies. Trial Registration: PROSPERO CRD42023418181; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=418181
- 12 April 2024
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 26 (1) , e51250
Open AccessApplication of AI in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis
Background: The continuous monitoring and recording of patients’ pain status is a major problem in current research on postoperative pain management. In the large number of original or review articles focusing on different approaches for pain assessment, many researchers have investigated how computer vision (CV) can help by capturing facial expressions. However, there is a lack of proper comparison of results between studies to identify current research gaps. Objective: The purpose of this systematic review and meta-analysis was to investigate the diagnostic performance of artificial intelligence models for multilevel pain assessment from facial images. Methods: The PubMed, Embase, IEEE, Web of Science, and Cochrane Library databases were searched for related publications before September 30, 2023. Studies that used facial images alone to estimate multiple pain values were included in the systematic review. A study quality assessment was conducted using the Quality Assessment of Diagnostic Accuracy Studies, 2nd edition tool. The performance of these studies was assessed by metrics including sensitivity, specificity, log diagnostic odds ratio (LDOR), and area under the curve (AUC). The intermodal variability was assessed and presented by forest plots. Results: A total of 45 reports were included in the systematic review. The reported test accuracies ranged from 0.27-0.99, and the other metrics, including the mean standard error (MSE), mean absolute error (MAE), intraclass correlation coefficient (ICC), and Pearson correlation coefficient (PCC), ranged from 0.31-4.61, 0.24-2.8, 0.19-0.83, and 0.48-0.92, respectively. In total, 6 studies were included in the meta-analysis. Their combined sensitivity was 98% (95% CI 96%-99%), specificity was 98% (95% CI 97%-99%), LDOR was 7.99 (95% CI 6.73-9.31), and AUC was 0.99 (95% CI 0.99-1). The subgroup analysis showed that the diagnostic performance was acceptable, although imbalanced data were still emphasized as a major problem. All studies had at least one domain with a high risk of bias, and for 20% (9/45) of studies, there were no applicability concerns. Conclusions: This review summarizes recent evidence in automatic multilevel pain estimation from facial expressions and compared the test accuracy of results in a meta-analysis. Promising performance for pain estimation from facial images was established by current CV algorithms. Weaknesses in current studies were also identified, suggesting that larger databases and metrics evaluating multiclass classification performance could improve future studies. Trial Registration: PROSPERO CRD42023418181; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=418181
- Open Access
- 26 July 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Application of AI in in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis (Preprint)
BACKGROUND The continuous monitoring and recording of patients’ pain status is a major problem in current research on postoperative pain management. In the large number of original or review articles focusing on different approaches for pain assessment, many researchers have investigated how computer vision (CV) can help by capturing facial expressions. However, there is a lack of proper comparison of results between studies to identify current research gaps. OBJECTIVE The purpose of this systematic review and meta-analysis was to investigate the diagnostic performance of artificial intelligence models for multilevel pain assessment from facial images. METHODS The PubMed, Embase, IEEE, Web of Science, and Cochrane Library databases were searched for related publications before September 30, 2023. Studies that used facial images alone to estimate multiple pain values were included in the systematic review. A study quality assessment was conducted using the Quality Assessment of Diagnostic Accuracy Studies, 2nd edition tool. The performance of these studies was assessed by metrics including sensitivity, specificity, log diagnostic odds ratio (LDOR), and area under the curve (AUC). The intermodal variability was assessed and presented by forest plots. RESULTS A total of 45 reports were included in the systematic review. The reported test accuracies ranged from 0.27-0.99, and the other metrics, including the mean standard error (MSE), mean absolute error (MAE), intraclass correlation coefficient (ICC), and Pearson correlation coefficient (PCC), ranged from 0.31-4.61, 0.24-2.8, 0.19-0.83, and 0.48-0.92, respectively. In total, 6 studies were included in the meta-analysis. Their combined sensitivity was 98% (95% CI 96%-99%), specificity was 98% (95% CI 97%-99%), LDOR was 7.99 (95% CI 6.73-9.31), and AUC was 0.99 (95% CI 0.99-1). The subgroup analysis showed that the diagnostic performance was acceptable, although imbalanced data were still emphasized as a major problem. All studies had at least one domain with a high risk of bias, and for 20% (9/45) of studies, there were no applicability concerns. CONCLUSIONS This review summarizes recent evidence in automatic multilevel pain estimation from facial expressions and compared the test accuracy of results in a meta-analysis. Promising performance for pain estimation from facial images was established by current CV algorithms. Weaknesses in current studies were also identified, suggesting that larger databases and metrics evaluating multiclass classification performance could improve future studies. CLINICALTRIAL PROSPERO CRD42023418181; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=418181
- 26 July 2023
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessApplication of AI in in Multilevel Pain Assessment Using Facial Images: Systematic Review and Meta-Analysis (Preprint)
BACKGROUND The continuous monitoring and recording of patients’ pain status is a major problem in current research on postoperative pain management. In the large number of original or review articles focusing on different approaches for pain assessment, many researchers have investigated how computer vision (CV) can help by capturing facial expressions. However, there is a lack of proper comparison of results between studies to identify current research gaps. OBJECTIVE The purpose of this systematic review and meta-analysis was to investigate the diagnostic performance of artificial intelligence models for multilevel pain assessment from facial images. METHODS The PubMed, Embase, IEEE, Web of Science, and Cochrane Library databases were searched for related publications before September 30, 2023. Studies that used facial images alone to estimate multiple pain values were included in the systematic review. A study quality assessment was conducted using the Quality Assessment of Diagnostic Accuracy Studies, 2nd edition tool. The performance of these studies was assessed by metrics including sensitivity, specificity, log diagnostic odds ratio (LDOR), and area under the curve (AUC). The intermodal variability was assessed and presented by forest plots. RESULTS A total of 45 reports were included in the systematic review. The reported test accuracies ranged from 0.27-0.99, and the other metrics, including the mean standard error (MSE), mean absolute error (MAE), intraclass correlation coefficient (ICC), and Pearson correlation coefficient (PCC), ranged from 0.31-4.61, 0.24-2.8, 0.19-0.83, and 0.48-0.92, respectively. In total, 6 studies were included in the meta-analysis. Their combined sensitivity was 98% (95% CI 96%-99%), specificity was 98% (95% CI 97%-99%), LDOR was 7.99 (95% CI 6.73-9.31), and AUC was 0.99 (95% CI 0.99-1). The subgroup analysis showed that the diagnostic performance was acceptable, although imbalanced data were still emphasized as a major problem. All studies had at least one domain with a high risk of bias, and for 20% (9/45) of studies, there were no applicability concerns. CONCLUSIONS This review summarizes recent evidence in automatic multilevel pain estimation from facial expressions and compared the test accuracy of results in a meta-analysis. Promising performance for pain estimation from facial images was established by current CV algorithms. Weaknesses in current studies were also identified, suggesting that larger databases and metrics evaluating multiclass classification performance could improve future studies. CLINICALTRIAL PROSPERO CRD42023418181; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=418181