Xixi Yan
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
Xixi Yan has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Jianbin Liu
Department of Radiology and
2 shared publications - Jinrong Wu
Research Centre for Data Analytics and Cognition, La Trobe University, Bundoora, VIC 3086, Australia
2 shared publications - Lei Zhang
Northwestern Polytechnical University, Xi'an, China
2 shared publications - Mingguang He
School of Optometry, The Hong Kong Polytechnic University, Hong Kong SAR, China
2 shared publications - Stuart Keel
Department of Noncommunicable Diseases, World Health Organization, Geneva, Switzerland
2 shared publications - Subhashaan Sreedharan
Department of Radiology, The Royal Melbourne Hospital, Parkville, Australia
2 shared publications
Latest Publications
- Open Access
- 17 April 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (4) , e0347527
The clinical characteristics and risk factors of steroid-induced ocular hypertension following pars plana vitrectomy
Objective: This study aimed to assess the incidence and risk factors for the development of steroid-induced ocular hypertension (SIOH) following 23-gauge (23G) pars plana vitrectomy. Methods: The clinical data of patients treated with 23G vitrectomy from January 2019 to March 2022 were reviewed retrospectively. The incidence and characteristics of SIOH post-operatively and treatment provided were recorded. The clinical risk factors for developing SIOH were analyzed using logistic regression analysis. Results: Among the 540 eligible patients, 111 (20.56%) cases developed SIOH. The majority (83.78%) of the SIOH cases developed between the third and seventh day postoperatively. Among these cases, 65 (58.56%) patients had an intraoperative pressure (IOP) of 30 mmHg or higher, and 31 (27.9%) had an IOP of 40 mmHg or higher. The IOP of all SIOH patients returned to normal within 1 month following the discontinuation of steroid and IOP-lowering medicine treatment. The independent risk factors for SIOH (IOP ≥ 23 mmHg) were myopia (odds ratio (OR) 5.22) and silicone oil filling (OR 8.20). For severe SIOH (IOP ≥ 30 mmHg) myopia and silicone oil filling were also identified as risk factors with an OR of 3.23 and 12.86, respectively. After adjusting the steroid administration pattern, the incidence of all SIOH and severe SIOH decreased to 17.11% and 9.14%, respectively. Conclusions: Myopia and silicone oil filling were identified as potential independent risk factors for the development of SIOH after vitrectomy. A shorter topical steroid therapy was associated with a lower incidence of SIOH particularly in high-risk patients.
- 17 April 2026
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 21 (4) , e0347527
Open AccessThe clinical characteristics and risk factors of steroid-induced ocular hypertension following pars plana vitrectomy
Objective: This study aimed to assess the incidence and risk factors for the development of steroid-induced ocular hypertension (SIOH) following 23-gauge (23G) pars plana vitrectomy. Methods: The clinical data of patients treated with 23G vitrectomy from January 2019 to March 2022 were reviewed retrospectively. The incidence and characteristics of SIOH post-operatively and treatment provided were recorded. The clinical risk factors for developing SIOH were analyzed using logistic regression analysis. Results: Among the 540 eligible patients, 111 (20.56%) cases developed SIOH. The majority (83.78%) of the SIOH cases developed between the third and seventh day postoperatively. Among these cases, 65 (58.56%) patients had an intraoperative pressure (IOP) of 30 mmHg or higher, and 31 (27.9%) had an IOP of 40 mmHg or higher. The IOP of all SIOH patients returned to normal within 1 month following the discontinuation of steroid and IOP-lowering medicine treatment. The independent risk factors for SIOH (IOP ≥ 23 mmHg) were myopia (odds ratio (OR) 5.22) and silicone oil filling (OR 8.20). For severe SIOH (IOP ≥ 30 mmHg) myopia and silicone oil filling were also identified as risk factors with an OR of 3.23 and 12.86, respectively. After adjusting the steroid administration pattern, the incidence of all SIOH and severe SIOH decreased to 17.11% and 9.14%, respectively. Conclusions: Myopia and silicone oil filling were identified as potential independent risk factors for the development of SIOH after vitrectomy. A shorter topical steroid therapy was associated with a lower incidence of SIOH particularly in high-risk patients.
- Open Access
- 28 July 2020
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 8 (7) , e16850
Predicting the Development of Type 2 Diabetes in a Large Australian Cohort Using Machine-Learning Techniques: Longitudinal Survey Study
Background: Previous conventional models for the prediction of diabetes could be updated by incorporating the increasing amount of health data available and new risk prediction methodology. Objective: We aimed to develop a substantially improved diabetes risk prediction model using sophisticated machine-learning algorithms based on a large retrospective population cohort of over 230,000 people who were enrolled in the study during 2006-2017. Methods: We collected demographic, medical, behavioral, and incidence data for type 2 diabetes mellitus (T2DM) in over 236,684 diabetes-free participants recruited from the 45 and Up Study. We predicted and compared the risk of diabetes onset in these participants at 3, 5, 7, and 10 years based on three machine-learning approaches and the conventional regression model. Results: Overall, 6.05% (14,313/236,684) of the participants developed T2DM during an average 8.8-year follow-up period. The 10-year diabetes incidence in men was 8.30% (8.08%-8.49%), which was significantly higher (odds ratio 1.37, 95% CI 1.32-1.41) than that in women at 6.20% (6.00%-6.40%). The incidence of T2DM was doubled in individuals with obesity (men: 17.78% [17.05%-18.43%]; women: 14.59% [13.99%-15.17%]) compared with that of nonobese individuals. The gradient boosting machine model showed the best performance among the four models (area under the curve of 79% in 3-year prediction and 75% in 10-year prediction). All machine-learning models predicted BMI as the most significant factor contributing to diabetes onset, which explained 12%-50% of the variance in the prediction of diabetes. The model predicted that if BMI in obese and overweight participants could be hypothetically reduced to a healthy range, the 10-year probability of diabetes onset would be significantly reduced from 8.3% to 2.8% (P<.001). Conclusions: A one-time self-reported survey can accurately predict the risk of diabetes using a machine-learning approach. Achieving a healthy BMI can significantly reduce the risk of developing T2DM.
- 28 July 2020
- Published by JMIR Publications Inc. in JMIR Medical Informatics
- Vol. 8 (7) , e16850
Open AccessPredicting the Development of Type 2 Diabetes in a Large Australian Cohort Using Machine-Learning Techniques: Longitudinal Survey Study
Background: Previous conventional models for the prediction of diabetes could be updated by incorporating the increasing amount of health data available and new risk prediction methodology. Objective: We aimed to develop a substantially improved diabetes risk prediction model using sophisticated machine-learning algorithms based on a large retrospective population cohort of over 230,000 people who were enrolled in the study during 2006-2017. Methods: We collected demographic, medical, behavioral, and incidence data for type 2 diabetes mellitus (T2DM) in over 236,684 diabetes-free participants recruited from the 45 and Up Study. We predicted and compared the risk of diabetes onset in these participants at 3, 5, 7, and 10 years based on three machine-learning approaches and the conventional regression model. Results: Overall, 6.05% (14,313/236,684) of the participants developed T2DM during an average 8.8-year follow-up period. The 10-year diabetes incidence in men was 8.30% (8.08%-8.49%), which was significantly higher (odds ratio 1.37, 95% CI 1.32-1.41) than that in women at 6.20% (6.00%-6.40%). The incidence of T2DM was doubled in individuals with obesity (men: 17.78% [17.05%-18.43%]; women: 14.59% [13.99%-15.17%]) compared with that of nonobese individuals. The gradient boosting machine model showed the best performance among the four models (area under the curve of 79% in 3-year prediction and 75% in 10-year prediction). All machine-learning models predicted BMI as the most significant factor contributing to diabetes onset, which explained 12%-50% of the variance in the prediction of diabetes. The model predicted that if BMI in obese and overweight participants could be hypothetically reduced to a healthy range, the 10-year probability of diabetes onset would be significantly reduced from 8.3% to 2.8% (P<.001). Conclusions: A one-time self-reported survey can accurately predict the risk of diabetes using a machine-learning approach. Achieving a healthy BMI can significantly reduce the risk of developing T2DM.
- 20 March 2020
- Published by Springer Nature in Neurosurgical Review
- Vol. 44 (2) , 1017-1022
Endoscopic-assisted surgery versus microsurgery for pineal region tumors: a single-center retrospective study
Pineal region tumors are extremely deep-seated and surgically challenging. The exposure and visualization obtained by microscopic surgery are relatively limiting. The application of high-definition endoscopes has recently provided neurosurgeons with a much more magnified and clearer view of the anatomy in the pineal region. The present study was performed to compare endoscopic-assisted surgery (ES) with microsurgery (MS) for pineal region tumors. We retrospectively analyzed patients admitted to our hospital for treatment of pineal region tumors from January 2016 to June 2019. All patients consented to undergo tumor resection with ES or MS. We compared the extent of resection, postoperative rate of hydrocephalus, complications, and outcomes between the two groups to estimate the safety and efficacy of ES. In total, 41 patients with pineal region tumors were divided into 2 groups: the ES group (n = 20) and MS group (n = 21). The rate of gross total resection was significantly higher in the ES than MS group (90.0% vs. 57.1%, p = 0.04). The rate of postoperative hydrocephalus was significantly lower in the ES than MS group (11.8% vs. 52.9%, p = 0.03). No significant differences were found in complications or the Karnofsky Performance Score between the two groups. ES can be used to safely and effectively achieve complete resection of pineal region tumors. In patients with obstructive hydrocephalus, ES provides a new way to directly open the aqueduct for cerebrospinal fluid recovery following tumor resection.
- 20 March 2020
- Published by Springer Nature in Neurosurgical Review
- Vol. 44 (2) , 1017-1022
Endoscopic-assisted surgery versus microsurgery for pineal region tumors: a single-center retrospective study
Pineal region tumors are extremely deep-seated and surgically challenging. The exposure and visualization obtained by microscopic surgery are relatively limiting. The application of high-definition endoscopes has recently provided neurosurgeons with a much more magnified and clearer view of the anatomy in the pineal region. The present study was performed to compare endoscopic-assisted surgery (ES) with microsurgery (MS) for pineal region tumors. We retrospectively analyzed patients admitted to our hospital for treatment of pineal region tumors from January 2016 to June 2019. All patients consented to undergo tumor resection with ES or MS. We compared the extent of resection, postoperative rate of hydrocephalus, complications, and outcomes between the two groups to estimate the safety and efficacy of ES. In total, 41 patients with pineal region tumors were divided into 2 groups: the ES group (n = 20) and MS group (n = 21). The rate of gross total resection was significantly higher in the ES than MS group (90.0% vs. 57.1%, p = 0.04). The rate of postoperative hydrocephalus was significantly lower in the ES than MS group (11.8% vs. 52.9%, p = 0.03). No significant differences were found in complications or the Karnofsky Performance Score between the two groups. ES can be used to safely and effectively achieve complete resection of pineal region tumors. In patients with obstructive hydrocephalus, ES provides a new way to directly open the aqueduct for cerebrospinal fluid recovery following tumor resection.
- 1 January 2020
- Published by Inderscience Publishers in International Journal of Embedded Systems
- Vol. 13 (4) , 414
Revocable ciphertext-policy attribute-based encryption in data outsourcing systems from lattices
Attribute-based encryption mechanism is widely used in outsourcing systems because of its characteristics of 'one-to-many' communication. However, users' attributes often change dynamically. In order to solve the problem of attribute revocation in the attribute-based encryption scheme in the outsourcing systems, a revocable ciphertext policy attribute-based encryption in data outsourcing systems from lattices is proposed. The scheme uses the LWE problem to construct the encryption and decryption algorithm, which can resist the quantum attack. Tree-access structure is adopted to realise flexible fine-grained access strategy. In addition, with the help of the data outsourcing management server, the attribute key and ciphertext are updated to achieve immediate attribute revocation. The scheme is proved to be secure under the selective attribute and selective plaintext attacks. The comparative analysis shows that the scheme has a significant improvement in performance, and it supports immediate attribute revocation, which is more suitable for the dynamic change of users in the outsourcing systems, such as social network platforms.
- 1 January 2020
- Published by Inderscience Publishers in International Journal of Embedded Systems
- Vol. 13 (4) , 414
Revocable ciphertext-policy attribute-based encryption in data outsourcing systems from lattices
Attribute-based encryption mechanism is widely used in outsourcing systems because of its characteristics of 'one-to-many' communication. However, users' attributes often change dynamically. In order to solve the problem of attribute revocation in the attribute-based encryption scheme in the outsourcing systems, a revocable ciphertext policy attribute-based encryption in data outsourcing systems from lattices is proposed. The scheme uses the LWE problem to construct the encryption and decryption algorithm, which can resist the quantum attack. Tree-access structure is adopted to realise flexible fine-grained access strategy. In addition, with the help of the data outsourcing management server, the attribute key and ciphertext are updated to achieve immediate attribute revocation. The scheme is proved to be secure under the selective attribute and selective plaintext attacks. The comparative analysis shows that the scheme has a significant improvement in performance, and it supports immediate attribute revocation, which is more suitable for the dynamic change of users in the outsourcing systems, such as social network platforms.
- Open Access
- 30 October 2019
- Published by JMIR Publications Inc. in JMIR Preprints
Predicting the Development of Type 2 Diabetes in a Large Australian Cohort Using Machine-Learning Techniques: Longitudinal Survey Study (Preprint)
BACKGROUND Previous conventional models for the prediction of diabetes could be updated by incorporating the increasing amount of health data available and new risk prediction methodology. OBJECTIVE We aimed to develop a substantially improved diabetes risk prediction model using sophisticated machine-learning algorithms based on a large retrospective population cohort of over 230,000 people who were enrolled in the study during 2006-2017. METHODS We collected demographic, medical, behavioral, and incidence data for type 2 diabetes mellitus (T2DM) in over 236,684 diabetes-free participants recruited from the 45 and Up Study. We predicted and compared the risk of diabetes onset in these participants at 3, 5, 7, and 10 years based on three machine-learning approaches and the conventional regression model. RESULTS Overall, 6.05% (14,313/236,684) of the participants developed T2DM during an average 8.8-year follow-up period. The 10-year diabetes incidence in men was 8.30% (8.08%-8.49%), which was significantly higher (odds ratio 1.37, 95% CI 1.32-1.41) than that in women at 6.20% (6.00%-6.40%). The incidence of T2DM was doubled in individuals with obesity (men: 17.78% [17.05%-18.43%]; women: 14.59% [13.99%-15.17%]) compared with that of nonobese individuals. The gradient boosting machine model showed the best performance among the four models (area under the curve of 79% in 3-year prediction and 75% in 10-year prediction). All machine-learning models predicted BMI as the most significant factor contributing to diabetes onset, which explained 12%-50% of the variance in the prediction of diabetes. The model predicted that if BMI in obese and overweight participants could be hypothetically reduced to a healthy range, the 10-year probability of diabetes onset would be significantly reduced from 8.3% to 2.8% (P<.001). CONCLUSIONS A one-time self-reported survey can accurately predict the risk of diabetes using a machine-learning approach. Achieving a healthy BMI can significantly reduce the risk of developing T2DM.
- 30 October 2019
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessPredicting the Development of Type 2 Diabetes in a Large Australian Cohort Using Machine-Learning Techniques: Longitudinal Survey Study (Preprint)
BACKGROUND Previous conventional models for the prediction of diabetes could be updated by incorporating the increasing amount of health data available and new risk prediction methodology. OBJECTIVE We aimed to develop a substantially improved diabetes risk prediction model using sophisticated machine-learning algorithms based on a large retrospective population cohort of over 230,000 people who were enrolled in the study during 2006-2017. METHODS We collected demographic, medical, behavioral, and incidence data for type 2 diabetes mellitus (T2DM) in over 236,684 diabetes-free participants recruited from the 45 and Up Study. We predicted and compared the risk of diabetes onset in these participants at 3, 5, 7, and 10 years based on three machine-learning approaches and the conventional regression model. RESULTS Overall, 6.05% (14,313/236,684) of the participants developed T2DM during an average 8.8-year follow-up period. The 10-year diabetes incidence in men was 8.30% (8.08%-8.49%), which was significantly higher (odds ratio 1.37, 95% CI 1.32-1.41) than that in women at 6.20% (6.00%-6.40%). The incidence of T2DM was doubled in individuals with obesity (men: 17.78% [17.05%-18.43%]; women: 14.59% [13.99%-15.17%]) compared with that of nonobese individuals. The gradient boosting machine model showed the best performance among the four models (area under the curve of 79% in 3-year prediction and 75% in 10-year prediction). All machine-learning models predicted BMI as the most significant factor contributing to diabetes onset, which explained 12%-50% of the variance in the prediction of diabetes. The model predicted that if BMI in obese and overweight participants could be hypothetically reduced to a healthy range, the 10-year probability of diabetes onset would be significantly reduced from 8.3% to 2.8% (P<.001). CONCLUSIONS A one-time self-reported survey can accurately predict the risk of diabetes using a machine-learning approach. Achieving a healthy BMI can significantly reduce the risk of developing T2DM.