Xiaosong Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xiaosong Yu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Huixiang Shang
Department of Nursing, Affiliated Hospital of Zunyi Medical College, Zunyi, Guizhou, China
4 shared publications - Mingtao Quan
Nursing School of Zunyi Medical University Zunyi China
4 shared publications - Shengting Li
Nursing School of Zunyi Medical University Zunyi China
4 shared publications - Siqi Chen
Department of Nursing, Affiliated Hospital of Zunyi Medical College, Zunyi, Guizhou, China
4 shared publications - Tingting Tu
Department of Nursing, Affiliated Hospital of Zunyi Medical College, Zunyi, Guizhou, China
4 shared publications - Lin Zhang
Department of Nursing Affiliated Hospital of Zunyi Medical University Zunyi Guizhou China
1 shared publication
Latest Publications
- 20 May 2026
- Published by Wiley in Journal of Clinical Nursing
- Vol. 35 (9) , 3692-3707
Diagnostic Prediction Models for Depression in Patients With Breast Cancer: A Systematic Review
Aim: To systematically review the evidence on diagnostic prediction models for depression in patients with breast cancer. Design: Systematic review. Data Sources: Ten databases were searched from inception to 22 August 2025, with an updated search on 17 December 2025, to identify original studies developing and/or validating diagnostic prediction models for depression in patients with breast cancer. Methods: Data were extracted using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) framework. Two reviewers independently assessed risk of bias and applicability of included studies using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Results: Eleven studies were included. Reported area under the curve (AUC) values ranged from 0.784 to 0.890. All included studies were judged to be at high risk of bias, and seven raised high concerns regarding applicability. There was substantial heterogeneity in predictor selection across studies, with age, income level and family support being the most frequently reported predictors. Conclusion: Although preliminary research on diagnostic prediction models for depression in patients with breast cancer has been undertaken, their methodological quality remains weak. Reporting of external validation and calibration assessment was limited. Current evidence is therefore insufficient to support their routine use in nursing practice. Future research should standardise model development and validation and strengthen the evaluation of model performance. Implications for the Profession and/or Patient Care: This review suggests that existing diagnostic prediction models for depression in patients with breast cancer are not yet sufficiently robust for routine nursing use, but may provide a reference for future nursing screening research and the optimisation of related tools. Impact: This review synthesises the available evidence on diagnostic prediction models for depression in patients with breast cancer and provides a basis for future model development, validation and optimisation. Reporting Method: This review was reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses (PRISMA) statement and the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis: Systematic Reviews and Meta‐Analyses (TRIPOD‐SRMA) checklist. Patient or Public Contribution: No patient or public contribution.
- 20 May 2026
- Published by Wiley in Journal of Clinical Nursing
- Vol. 35 (9) , 3692-3707
Diagnostic Prediction Models for Depression in Patients With Breast Cancer: A Systematic Review
Aim: To systematically review the evidence on diagnostic prediction models for depression in patients with breast cancer. Design: Systematic review. Data Sources: Ten databases were searched from inception to 22 August 2025, with an updated search on 17 December 2025, to identify original studies developing and/or validating diagnostic prediction models for depression in patients with breast cancer. Methods: Data were extracted using the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS) framework. Two reviewers independently assessed risk of bias and applicability of included studies using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Results: Eleven studies were included. Reported area under the curve (AUC) values ranged from 0.784 to 0.890. All included studies were judged to be at high risk of bias, and seven raised high concerns regarding applicability. There was substantial heterogeneity in predictor selection across studies, with age, income level and family support being the most frequently reported predictors. Conclusion: Although preliminary research on diagnostic prediction models for depression in patients with breast cancer has been undertaken, their methodological quality remains weak. Reporting of external validation and calibration assessment was limited. Current evidence is therefore insufficient to support their routine use in nursing practice. Future research should standardise model development and validation and strengthen the evaluation of model performance. Implications for the Profession and/or Patient Care: This review suggests that existing diagnostic prediction models for depression in patients with breast cancer are not yet sufficiently robust for routine nursing use, but may provide a reference for future nursing screening research and the optimisation of related tools. Impact: This review synthesises the available evidence on diagnostic prediction models for depression in patients with breast cancer and provides a basis for future model development, validation and optimisation. Reporting Method: This review was reported in accordance with the Preferred Reporting Items for Systematic Reviews and Meta‐Analyses (PRISMA) statement and the Transparent Reporting of a Multivariable Prediction Model for Individual Prognosis or Diagnosis: Systematic Reviews and Meta‐Analyses (TRIPOD‐SRMA) checklist. Patient or Public Contribution: No patient or public contribution.
- Open Access
- 21 April 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e97418
Correction: AI-Enabled Wearables for Motor Function Assessment and Rehabilitation in Parkinson Disease: Scoping Review
[This corrects the article DOI: 10.2196/85596.].
- 21 April 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e97418
Open AccessCorrection: AI-Enabled Wearables for Motor Function Assessment and Rehabilitation in Parkinson Disease: Scoping Review
[This corrects the article DOI: 10.2196/85596.].
- Open Access
- 7 April 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Correction: AI-Enabled Wearables for Motor Function Assessment and Rehabilitation in Parkinson Disease: Scoping Review (Preprint)
UNSTRUCTURED 112445243wtszfazvs
- 7 April 2026
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessCorrection: AI-Enabled Wearables for Motor Function Assessment and Rehabilitation in Parkinson Disease: Scoping Review (Preprint)
UNSTRUCTURED 112445243wtszfazvs
- Open Access
- 26 February 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e85596
AI-Enabled Wearables for Motor Function Assessment and Rehabilitation in Parkinson Disease: Scoping Review
Background: Artificial intelligence (AI)–enabled wearable devices are rapidly emerging in rehabilitation and motor function assessment for patients with Parkinson disease (PD). However, evidence remains fragmented, integration into nursing practice is limited, and comprehensive synthesis is lacking. Objective: This study aimed to summarize studies on AI-enabled wearable devices for PD rehabilitation and motor function assessment, describing device types, monitored indicators, algorithms, and application characteristics, and identifying research gaps and barriers to clinical translation. Methods: Guided by the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) framework, 9 databases (China National Knowledge Infrastructure, Wanfang Data, SinoMed, Cochrane Library, PubMed, Web of Science, CINAHL, Scopus, and Embase) were searched from inception to December 2025. Eligible studies were published in English or Chinese from January 1, 2020, onward and enrolled people with PD using noninvasive, body-worn AI-enabled wearable devices for rehabilitation, assessment, or monitoring. Dissertations and full conference papers were included, whereas preprints and conference abstracts were excluded. Methodological quality was appraised using the Mixed Methods Appraisal Tool, 2018 tool. Results were synthesized narratively and mapped to characterize devices, sensing modalities, algorithms, and evaluation methods. Results: A total of 66 studies involving approximately 3579 participants were included. Wearable devices mainly comprised multisensor modules, smart insoles, and wrist-worn devices, with accelerometers being the most frequently used sensors. Data collection was predominantly passive, and most studies were conducted in laboratory or clinical settings using single- or short-term sessions. Internal validation approaches, particularly leave-one-out and k-fold cross-validation, were common, whereas external validation was rare, and reporting of calibration and clinical decision thresholds was limited. Sensitivity and accuracy were the most frequently reported performance metrics, highlighting substantial heterogeneity in analytical methods and outcome reporting. Conclusions: This scoping review systematically synthesized evidence on AI-enabled wearable devices for motor function assessment and rehabilitation in PD, complemented by an evidence map and guided by a rehabilitation- and nursing-oriented perspective, and identified key translational gaps between proof-of-concept studies and real-world rehabilitation workflows. Compared with previous reviews that primarily focused on monitoring functions or device performance, this review places greater emphasis on rehabilitation applications and nurse-led translation into practice, and proposes a conceptual “challenges and opportunities” framework to inform the design, evaluation, and reporting of devices and algorithms, while further highlighting key considerations for workflow integration and the implementation of decision-support systems. These findings have practical relevance for advancing continuity of rehabilitation across clinical, home, and community settings, and may help guide nurses in delivering continuous monitoring, personalized follow-up, and timely intervention, thereby improving the efficiency and accessibility of rehabilitation management.
- 26 February 2026
- Published by JMIR Publications Inc. in Journal of Medical Internet Research
- Vol. 28, e85596
Open AccessAI-Enabled Wearables for Motor Function Assessment and Rehabilitation in Parkinson Disease: Scoping Review
Background: Artificial intelligence (AI)–enabled wearable devices are rapidly emerging in rehabilitation and motor function assessment for patients with Parkinson disease (PD). However, evidence remains fragmented, integration into nursing practice is limited, and comprehensive synthesis is lacking. Objective: This study aimed to summarize studies on AI-enabled wearable devices for PD rehabilitation and motor function assessment, describing device types, monitored indicators, algorithms, and application characteristics, and identifying research gaps and barriers to clinical translation. Methods: Guided by the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) framework, 9 databases (China National Knowledge Infrastructure, Wanfang Data, SinoMed, Cochrane Library, PubMed, Web of Science, CINAHL, Scopus, and Embase) were searched from inception to December 2025. Eligible studies were published in English or Chinese from January 1, 2020, onward and enrolled people with PD using noninvasive, body-worn AI-enabled wearable devices for rehabilitation, assessment, or monitoring. Dissertations and full conference papers were included, whereas preprints and conference abstracts were excluded. Methodological quality was appraised using the Mixed Methods Appraisal Tool, 2018 tool. Results were synthesized narratively and mapped to characterize devices, sensing modalities, algorithms, and evaluation methods. Results: A total of 66 studies involving approximately 3579 participants were included. Wearable devices mainly comprised multisensor modules, smart insoles, and wrist-worn devices, with accelerometers being the most frequently used sensors. Data collection was predominantly passive, and most studies were conducted in laboratory or clinical settings using single- or short-term sessions. Internal validation approaches, particularly leave-one-out and k-fold cross-validation, were common, whereas external validation was rare, and reporting of calibration and clinical decision thresholds was limited. Sensitivity and accuracy were the most frequently reported performance metrics, highlighting substantial heterogeneity in analytical methods and outcome reporting. Conclusions: This scoping review systematically synthesized evidence on AI-enabled wearable devices for motor function assessment and rehabilitation in PD, complemented by an evidence map and guided by a rehabilitation- and nursing-oriented perspective, and identified key translational gaps between proof-of-concept studies and real-world rehabilitation workflows. Compared with previous reviews that primarily focused on monitoring functions or device performance, this review places greater emphasis on rehabilitation applications and nurse-led translation into practice, and proposes a conceptual “challenges and opportunities” framework to inform the design, evaluation, and reporting of devices and algorithms, while further highlighting key considerations for workflow integration and the implementation of decision-support systems. These findings have practical relevance for advancing continuity of rehabilitation across clinical, home, and community settings, and may help guide nurses in delivering continuous monitoring, personalized follow-up, and timely intervention, thereby improving the efficiency and accessibility of rehabilitation management.
- Open Access
- 10 October 2025
- Published by JMIR Publications Inc. in JMIR Preprints
AI-Enabled Wearables for Motor Function Assessment and Rehabilitation in Parkinson Disease: Scoping Review (Preprint)
BACKGROUND Artificial intelligence (AI)–enabled wearable devices are rapidly emerging in rehabilitation and motor function assessment for patients with Parkinson disease (PD). However, evidence remains fragmented, integration into nursing practice is limited, and comprehensive synthesis is lacking. OBJECTIVE This study aimed to summarize studies on AI-enabled wearable devices for PD rehabilitation and motor function assessment, describing device types, monitored indicators, algorithms, and application characteristics, and identifying research gaps and barriers to clinical translation. METHODS Guided by the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) framework, 9 databases (China National Knowledge Infrastructure, Wanfang Data, SinoMed, Cochrane Library, PubMed, Web of Science, CINAHL, Scopus, and Embase) were searched from inception to December 2025. Eligible studies were published in English or Chinese from January 1, 2020, onward and enrolled people with PD using noninvasive, body-worn AI-enabled wearable devices for rehabilitation, assessment, or monitoring. Dissertations and full conference papers were included, whereas preprints and conference abstracts were excluded. Methodological quality was appraised using the Mixed Methods Appraisal Tool, 2018 tool. Results were synthesized narratively and mapped to characterize devices, sensing modalities, algorithms, and evaluation methods. RESULTS A total of 66 studies involving approximately 3579 participants were included. Wearable devices mainly comprised multisensor modules, smart insoles, and wrist-worn devices, with accelerometers being the most frequently used sensors. Data collection was predominantly passive, and most studies were conducted in laboratory or clinical settings using single- or short-term sessions. Internal validation approaches, particularly leave-one-out and k-fold cross-validation, were common, whereas external validation was rare, and reporting of calibration and clinical decision thresholds was limited. Sensitivity and accuracy were the most frequently reported performance metrics, highlighting substantial heterogeneity in analytical methods and outcome reporting. CONCLUSIONS This scoping review systematically synthesized evidence on AI-enabled wearable devices for motor function assessment and rehabilitation in PD, complemented by an evidence map and guided by a rehabilitation- and nursing-oriented perspective, and identified key translational gaps between proof-of-concept studies and real-world rehabilitation workflows. Compared with previous reviews that primarily focused on monitoring functions or device performance, this review places greater emphasis on rehabilitation applications and nurse-led translation into practice, and proposes a conceptual “challenges and opportunities” framework to inform the design, evaluation, and reporting of devices and algorithms, while further highlighting key considerations for workflow integration and the implementation of decision-support systems. These findings have practical relevance for advancing continuity of rehabilitation across clinical, home, and community settings, and may help guide nurses in delivering continuous monitoring, personalized follow-up, and timely intervention, thereby improving the efficiency and accessibility of rehabilitation management.
- 10 October 2025
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessAI-Enabled Wearables for Motor Function Assessment and Rehabilitation in Parkinson Disease: Scoping Review (Preprint)
BACKGROUND Artificial intelligence (AI)–enabled wearable devices are rapidly emerging in rehabilitation and motor function assessment for patients with Parkinson disease (PD). However, evidence remains fragmented, integration into nursing practice is limited, and comprehensive synthesis is lacking. OBJECTIVE This study aimed to summarize studies on AI-enabled wearable devices for PD rehabilitation and motor function assessment, describing device types, monitored indicators, algorithms, and application characteristics, and identifying research gaps and barriers to clinical translation. METHODS Guided by the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) framework, 9 databases (China National Knowledge Infrastructure, Wanfang Data, SinoMed, Cochrane Library, PubMed, Web of Science, CINAHL, Scopus, and Embase) were searched from inception to December 2025. Eligible studies were published in English or Chinese from January 1, 2020, onward and enrolled people with PD using noninvasive, body-worn AI-enabled wearable devices for rehabilitation, assessment, or monitoring. Dissertations and full conference papers were included, whereas preprints and conference abstracts were excluded. Methodological quality was appraised using the Mixed Methods Appraisal Tool, 2018 tool. Results were synthesized narratively and mapped to characterize devices, sensing modalities, algorithms, and evaluation methods. RESULTS A total of 66 studies involving approximately 3579 participants were included. Wearable devices mainly comprised multisensor modules, smart insoles, and wrist-worn devices, with accelerometers being the most frequently used sensors. Data collection was predominantly passive, and most studies were conducted in laboratory or clinical settings using single- or short-term sessions. Internal validation approaches, particularly leave-one-out and k-fold cross-validation, were common, whereas external validation was rare, and reporting of calibration and clinical decision thresholds was limited. Sensitivity and accuracy were the most frequently reported performance metrics, highlighting substantial heterogeneity in analytical methods and outcome reporting. CONCLUSIONS This scoping review systematically synthesized evidence on AI-enabled wearable devices for motor function assessment and rehabilitation in PD, complemented by an evidence map and guided by a rehabilitation- and nursing-oriented perspective, and identified key translational gaps between proof-of-concept studies and real-world rehabilitation workflows. Compared with previous reviews that primarily focused on monitoring functions or device performance, this review places greater emphasis on rehabilitation applications and nurse-led translation into practice, and proposes a conceptual “challenges and opportunities” framework to inform the design, evaluation, and reporting of devices and algorithms, while further highlighting key considerations for workflow integration and the implementation of decision-support systems. These findings have practical relevance for advancing continuity of rehabilitation across clinical, home, and community settings, and may help guide nurses in delivering continuous monitoring, personalized follow-up, and timely intervention, thereby improving the efficiency and accessibility of rehabilitation management.