Jiamin Du
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiamin Du has a total of 80 co-authors. Here are the top co-authors by number of shared publications:
- Huibert Burger
Department of Primary and Long-term Care Medicine, University Medical Center Groningen, Groningen, The Netherlands
2 shared publications - Sarah Janus
Department of Primary and Long-term Care, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
2 shared publications - Subhashisa Swain
Nuffield Department of Primary Care Health Sciences, University of Oxford, Oxford, UK
2 shared publications Sytse Zuidema
Department of Primary and Long-Term Care, University Medical Center Groningen, University of Groningen , 9713GZ Groningen Hanzeplein 1, Groningen
2 shared publicationsTingting Zhu
Department of Engineering Science, University of Oxford , Oxford
2 shared publications- Ying Zou
Department of Primary and Long-Term Care, University Medical Center Groningen, University of Groningen , 9713GZ Groningen Hanzeplein 1, Groningen
2 shared publications
Latest Publications
- Open Access
- 31 October 2026
- Published by Oxford University Press (OUP) in Age and Ageing
- Vol. 55 (11)
Attitudes of people living with dementia and their carers towards the use of generative artificial intelligence to inform structured medication reviews
Background: Polypharmacy is common in people living with dementia (PLwD) and associated with adverse outcomes. Although Structured Medication Reviews (SMRs) are recommended to optimise medication regimens, their delivery is often constrained by limited resources. Artificial intelligence (AI) may support SMRs, yet little is known about how it is perceived by PLwD and their carers. This study explored their experiences of polypharmacy, views on SMRs and attitudes towards use of AI tools in SMRs. Methods: Semi-structured interviews with 12 PLwD experiencing polypharmacy and two focus groups with 14 carers were conducted via Microsoft Teams or telephone and analysed using Reflexive Thematic Analysis. Results: Two themes were constructed: participants’ perspectives on meaningful SMRs, and embracing AI while preserving patient safety and the human touch. Participants described challenges in managing polypharmacy, with carers playing a central role in supporting adherence and monitoring side effects. Experiences of SMRs varied. SMRs were most valued when clinicians were empathetic and able to offer personalised guidance. Participants viewed AI use in SMRs positively, provided that such tools were well validated and used to assist rather than replace healthcare professionals. AI was also seen as potentially reducing administrative burden and supporting more person-centred care. However, some had concerns regarding patient safety and data security, highlighting the need for appropriate regulation and human oversight. Conclusion: Participants were supportive of AI use in SMRs, despite concerns about safety, data security and disclosure of AI use, and emphasised the importance of patient-clinician interactions and lived experience involvement in AI tool development.
- 31 October 2026
- Published by Oxford University Press (OUP) in Age and Ageing
- Vol. 55 (11)
Open AccessAttitudes of people living with dementia and their carers towards the use of generative artificial intelligence to inform structured medication reviews
Background: Polypharmacy is common in people living with dementia (PLwD) and associated with adverse outcomes. Although Structured Medication Reviews (SMRs) are recommended to optimise medication regimens, their delivery is often constrained by limited resources. Artificial intelligence (AI) may support SMRs, yet little is known about how it is perceived by PLwD and their carers. This study explored their experiences of polypharmacy, views on SMRs and attitudes towards use of AI tools in SMRs. Methods: Semi-structured interviews with 12 PLwD experiencing polypharmacy and two focus groups with 14 carers were conducted via Microsoft Teams or telephone and analysed using Reflexive Thematic Analysis. Results: Two themes were constructed: participants’ perspectives on meaningful SMRs, and embracing AI while preserving patient safety and the human touch. Participants described challenges in managing polypharmacy, with carers playing a central role in supporting adherence and monitoring side effects. Experiences of SMRs varied. SMRs were most valued when clinicians were empathetic and able to offer personalised guidance. Participants viewed AI use in SMRs positively, provided that such tools were well validated and used to assist rather than replace healthcare professionals. AI was also seen as potentially reducing administrative burden and supporting more person-centred care. However, some had concerns regarding patient safety and data security, highlighting the need for appropriate regulation and human oversight. Conclusion: Participants were supportive of AI use in SMRs, despite concerns about safety, data security and disclosure of AI use, and emphasised the importance of patient-clinician interactions and lived experience involvement in AI tool development.
- Open Access
Attitudes of People Living with Dementia and their Carers towards the use of Generative Artificial Intelligence to inform Structured Medication Reviews
Background: Polypharmacy is common in people living with dementia (PLwD) and associated with adverse outcomes. Although Structured Medication Reviews (SMRs) are recommended to optimise medication regimens, their delivery is often constrained by limited healthcare resources. Artificial intelligence (AI) may support SMRs, yet little is known about how it is perceived by PLwD and their carers. This study explored their experiences of polypharmacy, views on SMRs, and attitudes towards use of AI tools in SMRs. Methods: Semi-structured interviews with 12 PLwD experiencing polypharmacy and two focus groups with 14 carers were conducted via Microsoft Teams or telephone and analysed using Reflexive Thematic Analysis. Results: Two themes were constructed: experiences of SMRs, and attitudes towards AI in SMRs. Participants described challenges in managing polypharmacy, with carers often playing a central role in supporting adherence and monitoring side effects. Experiences of SMRs varied widely. SMRs were most valued when clinicians were empathetic and able to offer personalised guidance. Participants viewed AI use in SMRs positively, provided that such tools were well validated and used to assist rather than replace healthcare professionals. AI was viewed as having the potential to reduce administrative burden and support more person-centred care. However, some had concerns regarding patient safety and data security, highlighting the need for appropriate regulation and human oversight. Conclusion: Participants were supportive of AI use in SMRs, despite concerns about safety, data security and disclosure of AI use, and emphasised the importance of patient–clinician interactions and lived experience involvement in AI tool development.
Open AccessAttitudes of People Living with Dementia and their Carers towards the use of Generative Artificial Intelligence to inform Structured Medication Reviews
Background: Polypharmacy is common in people living with dementia (PLwD) and associated with adverse outcomes. Although Structured Medication Reviews (SMRs) are recommended to optimise medication regimens, their delivery is often constrained by limited healthcare resources. Artificial intelligence (AI) may support SMRs, yet little is known about how it is perceived by PLwD and their carers. This study explored their experiences of polypharmacy, views on SMRs, and attitudes towards use of AI tools in SMRs. Methods: Semi-structured interviews with 12 PLwD experiencing polypharmacy and two focus groups with 14 carers were conducted via Microsoft Teams or telephone and analysed using Reflexive Thematic Analysis. Results: Two themes were constructed: experiences of SMRs, and attitudes towards AI in SMRs. Participants described challenges in managing polypharmacy, with carers often playing a central role in supporting adherence and monitoring side effects. Experiences of SMRs varied widely. SMRs were most valued when clinicians were empathetic and able to offer personalised guidance. Participants viewed AI use in SMRs positively, provided that such tools were well validated and used to assist rather than replace healthcare professionals. AI was viewed as having the potential to reduce administrative burden and support more person-centred care. However, some had concerns regarding patient safety and data security, highlighting the need for appropriate regulation and human oversight. Conclusion: Participants were supportive of AI use in SMRs, despite concerns about safety, data security and disclosure of AI use, and emphasised the importance of patient–clinician interactions and lived experience involvement in AI tool development.
- Open Access
- 30 March 2026
- Published by Center for Open Science in PsyArXiv
A Comprehensive Review in Unimodal and Multimodal Emotion Recognition
Emotion recognition is a fundamental component of human-centered intelligent systems, supporting applications in healthcare, education, marketing, and human–computer interaction. Despite rapid progress driven by deep learning across facial, speech, textual, and multi-modal settings, the literature remains difficult to compare due to inconsistent emotion models, heterogeneous datasets, and varying evaluation protocols. This survey addresses this gap by providing a unified synthesis of deep learning-based uni-modal and multi-modal emotion recognition within a coherent analytical framework covering emotion modeling, dataset curation, representation learning, fusion strategies, and evaluation. Rather than listing methods, we organize existing work around key structural choices and trade-offs that affect generalization. For uni-modal approaches, we analyze how facial, speech, and textual methods increasingly rely on self-supervised pretraining to mitigate annotation scarcity, while retaining modality-specific limitations. For multi-modal systems, we examine alignment, modality dominance, complementarity, robustness, and the emerging role of large language models in affective reasoning. We further highlight persistent challenges, including label ambiguity, cross-dataset generalization, fairness, and the gap between benchmark performance and real-world deployment. This survey provides a unified perspective and a roadmap for future research. Resources are available at https://github.com/jackchen69/Awesome-Emotion-Models.
- 30 March 2026
- Published by Center for Open Science in PsyArXiv
Open AccessA Comprehensive Review in Unimodal and Multimodal Emotion Recognition
Emotion recognition is a fundamental component of human-centered intelligent systems, supporting applications in healthcare, education, marketing, and human–computer interaction. Despite rapid progress driven by deep learning across facial, speech, textual, and multi-modal settings, the literature remains difficult to compare due to inconsistent emotion models, heterogeneous datasets, and varying evaluation protocols. This survey addresses this gap by providing a unified synthesis of deep learning-based uni-modal and multi-modal emotion recognition within a coherent analytical framework covering emotion modeling, dataset curation, representation learning, fusion strategies, and evaluation. Rather than listing methods, we organize existing work around key structural choices and trade-offs that affect generalization. For uni-modal approaches, we analyze how facial, speech, and textual methods increasingly rely on self-supervised pretraining to mitigate annotation scarcity, while retaining modality-specific limitations. For multi-modal systems, we examine alignment, modality dominance, complementarity, robustness, and the emerging role of large language models in affective reasoning. We further highlight persistent challenges, including label ambiguity, cross-dataset generalization, fairness, and the gap between benchmark performance and real-world deployment. This survey provides a unified perspective and a roadmap for future research. Resources are available at https://github.com/jackchen69/Awesome-Emotion-Models.
- Open Access
- 30 January 2026
- Published by Oxford University Press (OUP) in European Journal of Preventive Cardiology
- Vol. 33 (6) , 958-972
Economic evaluation of alternative cardiac rehabilitation programmes compared to centre-based cardiac rehabilitation programmes: a systematic review
Aims: Traditional centre-based cardiac rehabilitation (CBCR) has several drawbacks, including high costs, limited accessibility, and low utilisation rates. As a result, alternative cardiac rehabilitation programmes (ACRPs), such as home-based rehabilitation and telerehabilitation, have been developed. This systematic review aims to synthesise existing evidence on the economic evaluation of ACRPs compared to CBCR. Methods and results: We searched databases of MEDLINE, Embase, CINAHL, Cochrane CENTRAL, Web of Science, and EconLit, as well as trials registers of Clinicaltrials.gov, International Clinical Trials Registry Platform, and EU Clinical Trials Register. The last search date was 20 March 2025. We included randomised controlled trials that directly compared ACRP with CBCR in terms of cost and effectiveness. Study quality was assessed using the Cochrane Risk of Bias tool and the Drummond 10-item checklist. Both qualitative and quantitative syntheses were conducted, with random-effects models applied in the meta-analysis. Thirteen studies met the inclusion criteria, comprising 2040 participants. Meta-analysis showed a non-significant trend favouring CBCR over ACRP for EQ-5D (SMD = −0.32; 95% CI: −0.71 to 0.06; I2 = 79%). For QALY, there was no difference between ACRP and CBCR (SMD = −0.02; 95% CI: −0.19 to 0.15; I2 = 0). Ten of the thirteen studies reported lower costs for ACRP compared with traditional CBCR. Three of five economic evaluations found ACRP to be cost-effective. Conclusion: ACRPs demonstrate cost-effectiveness comparable to traditional CBCR. This review highlights the potential of ACRPs, such as home-based rehabilitation and telerehabilitation, as solutions for broader implementation in CR practice.
- 30 January 2026
- Published by Oxford University Press (OUP) in European Journal of Preventive Cardiology
- Vol. 33 (6) , 958-972
Open AccessEconomic evaluation of alternative cardiac rehabilitation programmes compared to centre-based cardiac rehabilitation programmes: a systematic review
Aims: Traditional centre-based cardiac rehabilitation (CBCR) has several drawbacks, including high costs, limited accessibility, and low utilisation rates. As a result, alternative cardiac rehabilitation programmes (ACRPs), such as home-based rehabilitation and telerehabilitation, have been developed. This systematic review aims to synthesise existing evidence on the economic evaluation of ACRPs compared to CBCR. Methods and results: We searched databases of MEDLINE, Embase, CINAHL, Cochrane CENTRAL, Web of Science, and EconLit, as well as trials registers of Clinicaltrials.gov, International Clinical Trials Registry Platform, and EU Clinical Trials Register. The last search date was 20 March 2025. We included randomised controlled trials that directly compared ACRP with CBCR in terms of cost and effectiveness. Study quality was assessed using the Cochrane Risk of Bias tool and the Drummond 10-item checklist. Both qualitative and quantitative syntheses were conducted, with random-effects models applied in the meta-analysis. Thirteen studies met the inclusion criteria, comprising 2040 participants. Meta-analysis showed a non-significant trend favouring CBCR over ACRP for EQ-5D (SMD = −0.32; 95% CI: −0.71 to 0.06; I2 = 79%). For QALY, there was no difference between ACRP and CBCR (SMD = −0.02; 95% CI: −0.19 to 0.15; I2 = 0). Ten of the thirteen studies reported lower costs for ACRP compared with traditional CBCR. Three of five economic evaluations found ACRP to be cost-effective. Conclusion: ACRPs demonstrate cost-effectiveness comparable to traditional CBCR. This review highlights the potential of ACRPs, such as home-based rehabilitation and telerehabilitation, as solutions for broader implementation in CR practice.
- Open Access
- 25 December 2025
- Published by Wiley in Alzheimer's & Dementia
- Vol. 21 (S4) , e100866
Evaluating the impact of the Oxford Brain Health Clinic pathway on psychiatrists' confidence in diagnosing memory disorders, and their perceived assessment usefulness
Background: The Oxford Brain Health Clinic (OBHC) was launched in August 2020 to provide enhanced assessments for memory clinic patients including MRI, advanced cognitive and lifestyle assessments, and optional research assessments. This study evaluates the impact of the OBHC pathway on psychiatrists' diagnostic confidence and the perceived usefulness of each assessment compared to a standard memory clinic (MC) pathway, to inform future refinement and NHS adoption. Method: We retrospectively selected 100 cases from the South Oxford memory clinic (50 OBHC, 50 MC) seen between August 2021 and August 2022. Anonymised records, including assessments, diagnoses, and management plans, were extracted and reviewed. Six psychiatrists rated their diagnostic confidence (0 = no confidence, 10 = no doubt) and the usefulness of each assessment using a five‐point Likert scale (range from 1 = not useful at all to 5 = extremely useful). Each case was randomly assigned to two raters. Descriptive analysis was conducted for confidence and usefulness scores. Mann‐Whitney U tests were used to compare diagnostic confidence between pathways, and multiple linear regression was applied to adjust for the influence of patients' cognitive status. Results: In the OBHC pathway, 48% of cases had dementia, 24% had mild cognitive impairment (MCI), and 28% had no memory disorder related diagnosis, compared to 74%, 16%, and 10% respectively in the MC pathway. Mean diagnostic confidence was high in both pathways (OBHC:8.58 ± 1.2; MC:8.38 ± 1.2). Regression analysis indicated that the OBHC pathway resulted in higher diagnostic confidence (β = ‐0.521, p = 0.067) compared to the MC pathway, although the result was not statistically significant. Assessments rated as useful (scores > 3) in the OBHC pathway included MRI, ACE‐III, observations, and informant interviews, while the MC pathway prioritised clinical interviews, relative discussions, CT, and MoCA. Conclusions: The OBHC pathway demonstrates diagnostic confidence equal to or greater than that of standard memory clinics and offers all patients research engagement opportunities. Some assessments within the OBHC pathway address dementia risk factors, potentially enhancing management and research initiatives despite their limited immediate diagnostic utility. These results support the further refinement of the OBHC pathway within the NHS.
- 25 December 2025
- Published by Wiley in Alzheimer's & Dementia
- Vol. 21 (S4) , e100866
Open AccessEvaluating the impact of the Oxford Brain Health Clinic pathway on psychiatrists' confidence in diagnosing memory disorders, and their perceived assessment usefulness
Background: The Oxford Brain Health Clinic (OBHC) was launched in August 2020 to provide enhanced assessments for memory clinic patients including MRI, advanced cognitive and lifestyle assessments, and optional research assessments. This study evaluates the impact of the OBHC pathway on psychiatrists' diagnostic confidence and the perceived usefulness of each assessment compared to a standard memory clinic (MC) pathway, to inform future refinement and NHS adoption. Method: We retrospectively selected 100 cases from the South Oxford memory clinic (50 OBHC, 50 MC) seen between August 2021 and August 2022. Anonymised records, including assessments, diagnoses, and management plans, were extracted and reviewed. Six psychiatrists rated their diagnostic confidence (0 = no confidence, 10 = no doubt) and the usefulness of each assessment using a five‐point Likert scale (range from 1 = not useful at all to 5 = extremely useful). Each case was randomly assigned to two raters. Descriptive analysis was conducted for confidence and usefulness scores. Mann‐Whitney U tests were used to compare diagnostic confidence between pathways, and multiple linear regression was applied to adjust for the influence of patients' cognitive status. Results: In the OBHC pathway, 48% of cases had dementia, 24% had mild cognitive impairment (MCI), and 28% had no memory disorder related diagnosis, compared to 74%, 16%, and 10% respectively in the MC pathway. Mean diagnostic confidence was high in both pathways (OBHC:8.58 ± 1.2; MC:8.38 ± 1.2). Regression analysis indicated that the OBHC pathway resulted in higher diagnostic confidence (β = ‐0.521, p = 0.067) compared to the MC pathway, although the result was not statistically significant. Assessments rated as useful (scores > 3) in the OBHC pathway included MRI, ACE‐III, observations, and informant interviews, while the MC pathway prioritised clinical interviews, relative discussions, CT, and MoCA. Conclusions: The OBHC pathway demonstrates diagnostic confidence equal to or greater than that of standard memory clinics and offers all patients research engagement opportunities. Some assessments within the OBHC pathway address dementia risk factors, potentially enhancing management and research initiatives despite their limited immediate diagnostic utility. These results support the further refinement of the OBHC pathway within the NHS.
- Open Access
- 6 April 2025
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 22 (4) , 574
Barriers and Facilitators of Cardiac Rehabilitation in a Middle-Income Country: A Qualitative Study from China
Background: Although effective and recommended by guidelines worldwide, Cardiac Rehabilitation (CR) remains scarce and underutilized. CR implementation has taken place in middle-income countries, but the progress is influenced by both positive and negative factors that remain underexplored. This study identified the barriers and facilitators of CR in a middle-income country, specifically China. Methods: An exploratory qualitative study was conducted using semi-structured interviews. Results: Fifteen CR stakeholders were interviewed. According to the interviewees, the delivery of CR is impeded due to a lack of resources, a lack of CR professionals, and a lack of coordination between health institutions. The participation of CR is hindered by a lack of awareness, a lack of reimbursement, and a lack of access to CR. However, the interviewees also mentioned facilitating factors, namely, a positive attitude of stakeholders, high motivation of some patients, and policy support. Conclusions: More awareness regarding the effectiveness of CR is needed. Implementing CR in secondary and primary health institutions could overcome the barriers regarding travel distance and transportation to faraway hospitals. The CR reimbursement methods are needed to ease the financial burden on patients. Our findings reveal factors that need to be considered by policymakers to deliver CR on a wider scale in China.
- 6 April 2025
- Published by MDPI AG in International Journal of Environmental Research and Public Health
- Vol. 22 (4) , 574
Open AccessBarriers and Facilitators of Cardiac Rehabilitation in a Middle-Income Country: A Qualitative Study from China
Background: Although effective and recommended by guidelines worldwide, Cardiac Rehabilitation (CR) remains scarce and underutilized. CR implementation has taken place in middle-income countries, but the progress is influenced by both positive and negative factors that remain underexplored. This study identified the barriers and facilitators of CR in a middle-income country, specifically China. Methods: An exploratory qualitative study was conducted using semi-structured interviews. Results: Fifteen CR stakeholders were interviewed. According to the interviewees, the delivery of CR is impeded due to a lack of resources, a lack of CR professionals, and a lack of coordination between health institutions. The participation of CR is hindered by a lack of awareness, a lack of reimbursement, and a lack of access to CR. However, the interviewees also mentioned facilitating factors, namely, a positive attitude of stakeholders, high motivation of some patients, and policy support. Conclusions: More awareness regarding the effectiveness of CR is needed. Implementing CR in secondary and primary health institutions could overcome the barriers regarding travel distance and transportation to faraway hospitals. The CR reimbursement methods are needed to ease the financial burden on patients. Our findings reveal factors that need to be considered by policymakers to deliver CR on a wider scale in China.
- 21 November 2023
- Published by University of Groningen Press
The patterns in psychotropic drug prescriptions among older people with dementia
- 21 November 2023
- Published by University of Groningen Press
The patterns in psychotropic drug prescriptions among older people with dementia
- Open Access
- 17 March 2022
- Published by Wiley in International Journal of Geriatric Psychiatry
- Vol. 37 (4)
Time trends in psychotropic drug prescriptions in Dutch nursing home residents with dementia between 2003 and 2018
Objective: Several European studies investigated the trends in psychotropic drug prescriptions (PDPs) among nursing home (NH) residents and reported a decline in antipsychotics prescriptions. Since the Dutch long‐term care system differs from other European systems (e.g. higher threshold for NH admission and trained elderly care physicians), this study explores the trends in PDPs in Dutch NH residents with dementia.Methods: The study used data from nine studies, comprising two cross‐sectional studies, one cohort study, and six cluster‐randomized controlled trials, collected in Dutch NHs between 2003 and 2018. With multilevel logistic regression analysis, NHs as a random effect, we estimated the trends in PDPs overall and for five specific psychotropic drug groups (antipsychotics, antidepressants, anxiolytics, hypnotics, and anti‐dementia drugs), adjusting for confounders: age, gender, severity of dementia, severity of neuropsychiatric symptoms, and length of stay in NHs.Results: The absolute prescription rate of antipsychotics was 37.5% in 2003 and decreased (OR = 0.947, 95% CI [0.926, 0.970]) every year. The absolute prescription rate of anti‐dementia drugs was 0.8% in 2003 and increased (OR = 1.162, 95% CI [1.105, 1.223]) per year. The absolute rate of overall PDPs declined from 62.7% in 2003 to 40.4% in 2018.Conclusions: Among Dutch NH residents with dementia, the odds of antipsychotics prescriptions decreased by 5.3% per year while the odds of anti‐dementia drug prescriptions increased by 16.2%. There were no distinct trends in antidepressants, anxiolytics, and hypnotics prescriptions. However, overall PDPs were still high. The PDPs in NH residents remain an issue of concern.
- 17 March 2022
- Published by Wiley in International Journal of Geriatric Psychiatry
- Vol. 37 (4)
Open AccessTime trends in psychotropic drug prescriptions in Dutch nursing home residents with dementia between 2003 and 2018
Objective: Several European studies investigated the trends in psychotropic drug prescriptions (PDPs) among nursing home (NH) residents and reported a decline in antipsychotics prescriptions. Since the Dutch long‐term care system differs from other European systems (e.g. higher threshold for NH admission and trained elderly care physicians), this study explores the trends in PDPs in Dutch NH residents with dementia.Methods: The study used data from nine studies, comprising two cross‐sectional studies, one cohort study, and six cluster‐randomized controlled trials, collected in Dutch NHs between 2003 and 2018. With multilevel logistic regression analysis, NHs as a random effect, we estimated the trends in PDPs overall and for five specific psychotropic drug groups (antipsychotics, antidepressants, anxiolytics, hypnotics, and anti‐dementia drugs), adjusting for confounders: age, gender, severity of dementia, severity of neuropsychiatric symptoms, and length of stay in NHs.Results: The absolute prescription rate of antipsychotics was 37.5% in 2003 and decreased (OR = 0.947, 95% CI [0.926, 0.970]) every year. The absolute prescription rate of anti‐dementia drugs was 0.8% in 2003 and increased (OR = 1.162, 95% CI [1.105, 1.223]) per year. The absolute rate of overall PDPs declined from 62.7% in 2003 to 40.4% in 2018.Conclusions: Among Dutch NH residents with dementia, the odds of antipsychotics prescriptions decreased by 5.3% per year while the odds of anti‐dementia drug prescriptions increased by 16.2%. There were no distinct trends in antidepressants, anxiolytics, and hypnotics prescriptions. However, overall PDPs were still high. The PDPs in NH residents remain an issue of concern.