Jillian Reeze T. Mbbs Medina
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Jillian Reeze T. Mbbs Medina has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Abhigan Babu Shrestha
Patan Academy of Health Sciences Hospital, Lalitpur, Nepal
1 shared publication - Bikram Prasad Gajurel
Department of Neurology, Tribhuvan University Teaching Hospital, Kathmandu, Nepal
1 shared publication - Chenwei Wu
University of Michigan, Ann Arbor, MI, USA
1 shared publication - Constanza Vásquez-Venegas
Scientific Image Analysis Lab, Faculty of Medicine, Universidad de Chile, Santiago, RM, Chile
1 shared publication - Daniel K. Ebner
Department of Radiation Oncology, Mayo Clinic, Rochester, MN 55905, USA
1 shared publication - Felipe Mirshawka
School of Biomedical Engineering, Faculdade Israelita de Ciências da Saúde Albert Einstein, Hospital Israelita Albert Einstein, São Paulo, Brazil
1 shared publication
Latest Publications
- 25 November 2024
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 38 (4) , 2563-2579
Detecting and Mitigating the Clever Hans Effect in Medical Imaging: A Scoping Review
The Clever Hans effect occurs when machine learning models rely on spurious correlations instead of clinically relevant features and poses significant challenges to the development of reliable artificial intelligence (AI) systems in medical imaging. This scoping review provides an overview of methods for identifying and addressing the Clever Hans effect in medical imaging AI algorithms. A total of 173 papers published between 2010 and 2024 were reviewed, and 37 articles were selected for detailed analysis, with classification into two categories: detection and mitigation approaches. Detection methods include model-centric, data-centric, and uncertainty and bias-based approaches, while mitigation strategies encompass data manipulation techniques, feature disentanglement and suppression, and domain knowledge-driven approaches. Despite the progress in detecting and mitigating the Clever Hans effect, the majority of current machine learning studies in medical imaging do not report or test for shortcut learning, highlighting the need for more rigorous validation and transparency in AI research. Future research should focus on creating standardized benchmarks, developing automated detection tools, and exploring the integration of detection and mitigation strategies to comprehensively address shortcut learning. Establishing community-driven best practices and leveraging interdisciplinary collaboration will be crucial for ensuring more reliable, generalizable, and equitable AI systems in healthcare.
- 25 November 2024
- Published by Springer Nature in Journal of Imaging Informatics in Medicine
- Vol. 38 (4) , 2563-2579
Detecting and Mitigating the Clever Hans Effect in Medical Imaging: A Scoping Review
The Clever Hans effect occurs when machine learning models rely on spurious correlations instead of clinically relevant features and poses significant challenges to the development of reliable artificial intelligence (AI) systems in medical imaging. This scoping review provides an overview of methods for identifying and addressing the Clever Hans effect in medical imaging AI algorithms. A total of 173 papers published between 2010 and 2024 were reviewed, and 37 articles were selected for detailed analysis, with classification into two categories: detection and mitigation approaches. Detection methods include model-centric, data-centric, and uncertainty and bias-based approaches, while mitigation strategies encompass data manipulation techniques, feature disentanglement and suppression, and domain knowledge-driven approaches. Despite the progress in detecting and mitigating the Clever Hans effect, the majority of current machine learning studies in medical imaging do not report or test for shortcut learning, highlighting the need for more rigorous validation and transparency in AI research. Future research should focus on creating standardized benchmarks, developing automated detection tools, and exploring the integration of detection and mitigation strategies to comprehensively address shortcut learning. Establishing community-driven best practices and leveraging interdisciplinary collaboration will be crucial for ensuring more reliable, generalizable, and equitable AI systems in healthcare.
- Open Access
- 20 October 2023
- Published by Wolters Kluwer Health in Medicine
- Vol. 102 (42) , e35560
Utilization rates of intravenous thrombolysis for acute ischemic stroke in Asian countries:: A systematic review and meta-analysis
Background: Despite intravenous thrombolysis (IVT) being used for the treatment of acute ischemic stroke (AIS) for over two decades, its accessibility remains limited in various regions of the world. The Asian region, which experiences the highest age-standardized incidence of AIS, currently lacks comprehensive data on the utilization of IVT. Aims: This study aimed to provide precise estimates of IVT usage for AIS in Asian countries. Methods: A literature search was conducted on PubMed and Google using appropriate search terms. English language, peer reviewed articles published after 2010 were included in the analysis. The pooled proportion was calculated utilizing the DerSimonian and Laird random-effects model. Additionally, a subgroup analysis was conducted, taking into account factors such as the study's country, the economic status of the country, specific Asian regions, publication year (before 2015 and from 2015 onwards), study location, study setting, hospital stroke protocol, and national stroke guidelines. Results: 67 observational studies with 778,046 patients with AIS were included in the meta-analysis. The overall utilization rate of IVT was found to be 9.1%. High-income countries had a higher rate (11.3%) compared to lower-middle-income (8.1%) and upper-middle-income countries (9%). Central and North Asia had the highest rate (17.5%) and Southeast Asia had the lowest rate (6.8%). Studies conducted after 2015 had a higher thrombolysis rate (11.3%) compared to those before 2015 (1.5%). Presence of hospital stroke protocols (10.7%) and national stroke guidelines (10.1%) were associated with higher thrombolysis rates. Conclusion: The overall utilization rate of IVT for AIS in Asia stood at 9.1%, showcasing noteworthy disparities across countries, regions, and income brackets. To improve thrombolysis rates in the region, addressing prehospital delays, increasing public awareness, and implementing stroke protocols and national guidelines are key strategies.
- 20 October 2023
- Published by Wolters Kluwer Health in Medicine
- Vol. 102 (42) , e35560
Open AccessUtilization rates of intravenous thrombolysis for acute ischemic stroke in Asian countries:: A systematic review and meta-analysis
Background: Despite intravenous thrombolysis (IVT) being used for the treatment of acute ischemic stroke (AIS) for over two decades, its accessibility remains limited in various regions of the world. The Asian region, which experiences the highest age-standardized incidence of AIS, currently lacks comprehensive data on the utilization of IVT. Aims: This study aimed to provide precise estimates of IVT usage for AIS in Asian countries. Methods: A literature search was conducted on PubMed and Google using appropriate search terms. English language, peer reviewed articles published after 2010 were included in the analysis. The pooled proportion was calculated utilizing the DerSimonian and Laird random-effects model. Additionally, a subgroup analysis was conducted, taking into account factors such as the study's country, the economic status of the country, specific Asian regions, publication year (before 2015 and from 2015 onwards), study location, study setting, hospital stroke protocol, and national stroke guidelines. Results: 67 observational studies with 778,046 patients with AIS were included in the meta-analysis. The overall utilization rate of IVT was found to be 9.1%. High-income countries had a higher rate (11.3%) compared to lower-middle-income (8.1%) and upper-middle-income countries (9%). Central and North Asia had the highest rate (17.5%) and Southeast Asia had the lowest rate (6.8%). Studies conducted after 2015 had a higher thrombolysis rate (11.3%) compared to those before 2015 (1.5%). Presence of hospital stroke protocols (10.7%) and national stroke guidelines (10.1%) were associated with higher thrombolysis rates. Conclusion: The overall utilization rate of IVT for AIS in Asia stood at 9.1%, showcasing noteworthy disparities across countries, regions, and income brackets. To improve thrombolysis rates in the region, addressing prehospital delays, increasing public awareness, and implementing stroke protocols and national guidelines are key strategies.