Ali Ganjizadeh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ali Ganjizadeh has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Bradley J. Erickson
Mayo Clinic, Rochester, USA
7 shared publications - Bart M. Demaerschalk
Department of Neurology, Mayo Clinic College of Medicine and Science, Phoenix, Arizona, USA
5 shared publications - Stephanie J. Zawada
Robert D. and Patricia E. Kern Center for the Science of Health Care Delivery, Mayo Clinic
5 shared publications - Gian Marco Conte
Department of Radiology, Mayo Clinic, Rochester, USA
2 shared publications - Sanaz Vahdati
Artificial Intelligence Laboratory, Department of Radiology, Mayo Clinic , Rochester, MN 55905
2 shared publications Caden Collins
Division of Cerebrovascular Disease, Mayo Clinic, Scottsdale, AZ
1 shared publication
Latest Publications
- Open Access
- 3 July 2025
- Published by Oxford University Press (OUP) in Radiology Advances
- Vol. 2 (4) , umaf024
Decoding large language models for radiology: strategies for fine-tuning and prompt engineering
The advances in large language models (LLMs) have demonstrated sophisticated potential for automating complex tasks within the radiology workflow. From radiology report generation and report summarization to data collection for research trials, these models have proven to be powerful tools. However, optimal implementation of these models requires careful adaptation to the specialized medical domain. In addition, these models tend to generate information that is not truthful or factual, which can adversely affect patient care and clinical decisions. Strategies such as fine-tuning and prompt optimization have been shown to be impactful in eliminating these errors. Although these models undergo rapid updates and improvements, understanding the principles of prompt engineering and fine-tuning provides a foundation for evaluating and maintaining the performance of any LLM deployment. The current article aims to review the recent advancements in radiology using fine-tuning and prompt optimization to leverage LLMs’ capabilities. It delves into various techniques within each strategy, their advantages and limitations, and presents a framework to facilitate the practical integration of LLMs into radiology settings.
- 3 July 2025
- Published by Oxford University Press (OUP) in Radiology Advances
- Vol. 2 (4) , umaf024
Open AccessDecoding large language models for radiology: strategies for fine-tuning and prompt engineering
The advances in large language models (LLMs) have demonstrated sophisticated potential for automating complex tasks within the radiology workflow. From radiology report generation and report summarization to data collection for research trials, these models have proven to be powerful tools. However, optimal implementation of these models requires careful adaptation to the specialized medical domain. In addition, these models tend to generate information that is not truthful or factual, which can adversely affect patient care and clinical decisions. Strategies such as fine-tuning and prompt optimization have been shown to be impactful in eliminating these errors. Although these models undergo rapid updates and improvements, understanding the principles of prompt engineering and fine-tuning provides a foundation for evaluating and maintaining the performance of any LLM deployment. The current article aims to review the recent advancements in radiology using fine-tuning and prompt optimization to leverage LLMs’ capabilities. It delves into various techniques within each strategy, their advantages and limitations, and presents a framework to facilitate the practical integration of LLMs into radiology settings.
- Open Access
- 9 June 2025
- Published by Elsevier in Mayo Clinic Proceedings: Digital Health
- Vol. 3 (3) , 100240
Real-World Smartphone Data Predicts Mood After Ischemic Stroke and Transient Ischemic Attack Symptoms and May Constitute Digital Endpoints: A Proof-of-Concept Study
- 9 June 2025
- Published by Elsevier in Mayo Clinic Proceedings: Digital Health
- Vol. 3 (3) , 100240
Open AccessReal-World Smartphone Data Predicts Mood After Ischemic Stroke and Transient Ischemic Attack Symptoms and May Constitute Digital Endpoints: A Proof-of-Concept Study
- 1 June 2025
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 315 (3) , e241904
Recent Advances in Compact Portable Platforms and Gradient Hardware for Brain MRI
Recent advancements in compact MRI scanners, portable low-field-strength MRI systems, and high-performance gradient inserts address the challenges of conventional MRI for brain imaging, providing more accessible and versatile technology.
- 1 June 2025
- Published by Radiological Society of North America (RSNA) in Radiology
- Vol. 315 (3) , e241904
Recent Advances in Compact Portable Platforms and Gradient Hardware for Brain MRI
Recent advancements in compact MRI scanners, portable low-field-strength MRI systems, and high-performance gradient inserts address the challenges of conventional MRI for brain imaging, providing more accessible and versatile technology.
- Open Access
Behavioral Monitoring in Transient Ischemic Attack and Stroke Patients: Exploratory Micro- and Macrostructural Imaging Insights for Identifying Post-Stroke Depression with Accelerometers in UK Biobank
To examine the association between post-stroke depression (PSD) and macrostructural and microstructural brain measures, and to explore whether changes in accelerometer-measured physical activity (PA) are associated with PSD, we conducted an exploratory study in UK Biobank with dementia-free participants diagnosed with at least one prior stroke. Eligible participants (n = 1186) completed an MRI scan. Depression was classified based on positive depression screening scores (PHQ-2 ≥ 3). Multivariate linear regression models assessed the relationships between depression and structural and diffusion measures generated from brain MRI scans. Logistic regression models were used to examine the relationship between accelerometer-measured daily PA and future depression (n = 367). Depression was positively associated with total white matter hyperintensities (WMHs) volume (standardized β [95% CI]—0.1339 [0.012, 0.256]; FDR-adjusted p-value—0.039), periventricular WMHs volume (standardized β [95% CI]—0.1351 [0.020, 0.250]; FDR-adjusted p-value—0.027), and reduced MD for commissural fibers (standardized β [95% CI]—−0.139 [−0.255, −0.024]; adjusted p-value—0.045). The odds of depression decreased by 0.3% for each daily minute spent in objectively measured light PA, while each minute spent in sleep from midnight to 6:00 AM was associated with a 0.9% decrease in the odds of depression. This early-stage analysis using a population cohort offers a scientific rationale for researchers using multimodal data sources to investigate the heterogenous nature of PSD and, potentially, identify stroke patients at risk of poor outcomes.
Open AccessBehavioral Monitoring in Transient Ischemic Attack and Stroke Patients: Exploratory Micro- and Macrostructural Imaging Insights for Identifying Post-Stroke Depression with Accelerometers in UK Biobank
To examine the association between post-stroke depression (PSD) and macrostructural and microstructural brain measures, and to explore whether changes in accelerometer-measured physical activity (PA) are associated with PSD, we conducted an exploratory study in UK Biobank with dementia-free participants diagnosed with at least one prior stroke. Eligible participants (n = 1186) completed an MRI scan. Depression was classified based on positive depression screening scores (PHQ-2 ≥ 3). Multivariate linear regression models assessed the relationships between depression and structural and diffusion measures generated from brain MRI scans. Logistic regression models were used to examine the relationship between accelerometer-measured daily PA and future depression (n = 367). Depression was positively associated with total white matter hyperintensities (WMHs) volume (standardized β [95% CI]—0.1339 [0.012, 0.256]; FDR-adjusted p-value—0.039), periventricular WMHs volume (standardized β [95% CI]—0.1351 [0.020, 0.250]; FDR-adjusted p-value—0.027), and reduced MD for commissural fibers (standardized β [95% CI]—−0.139 [−0.255, −0.024]; adjusted p-value—0.045). The odds of depression decreased by 0.3% for each daily minute spent in objectively measured light PA, while each minute spent in sleep from midnight to 6:00 AM was associated with a 0.9% decrease in the odds of depression. This early-stage analysis using a population cohort offers a scientific rationale for researchers using multimodal data sources to investigate the heterogenous nature of PSD and, potentially, identify stroke patients at risk of poor outcomes.
- Open Access
- 10 January 2025
- Published by JMIR Publications Inc. in JMIR Neurotechnology
- Vol. 4, e56679
Exploring Remote Monitoring of Poststroke Mood With Digital Sensors by Assessment of Depression Phenotypes and Accelerometer Data in UK Biobank: Cross-Sectional Analysis
Background: Interest in using digital sensors to monitor patients with prior stroke for depression, a risk factor for poor outcomes, has grown rapidly; however, little is known about behavioral phenotypes related to future mood symptoms and if patients with and without previously diagnosed depression experience similar phenotypes. Objective: This study aimed to assess the feasibility of using digital sensors to monitor mood in patients with prior stroke with a prestroke depression diagnosis (DD) and controls. We examined relationships between physical activity behaviors and self-reported depression frequency. Methods: In the UK Biobank wearable accelerometer cohort, we retrospectively identified patients who had previously suffered a stroke (N=1603) and conducted cross-sectional analyses with those who completed a subsequent depression survey follow-up. Sensitivity analyses assessed a general population cohort excluding previous stroke participants and 2 incident cohorts: incident stroke (IS) and incident cerebrovascular disease (IC). Results: In controls, the odds of being in a higher depressed mood frequency category decreased by 23% for each minute spent in moderate‐to‐vigorous physical activity (odds ratio 0.77, 95% CI 0.69‐0.87; P<.001). This association persisted in both general cohorts and in the IC control cohort. Conclusions: Although moderate‐to‐vigorous physical activity was linked with less frequent depressed mood in patients with prior stroke without DD, this finding did not persist in DDs. Thus, accelerometer-mood monitoring may provide clinically useful insights about future mood in patients with prior stroke without DDs. Considering the finding in the IC cohort and the lack of findings in the IS cohorts, accelerometer-mood monitoring may also be appropriately applied to observing broader cerebrovascular disease pathogenesis.
- 10 January 2025
- Published by JMIR Publications Inc. in JMIR Neurotechnology
- Vol. 4, e56679
Open AccessExploring Remote Monitoring of Poststroke Mood With Digital Sensors by Assessment of Depression Phenotypes and Accelerometer Data in UK Biobank: Cross-Sectional Analysis
Background: Interest in using digital sensors to monitor patients with prior stroke for depression, a risk factor for poor outcomes, has grown rapidly; however, little is known about behavioral phenotypes related to future mood symptoms and if patients with and without previously diagnosed depression experience similar phenotypes. Objective: This study aimed to assess the feasibility of using digital sensors to monitor mood in patients with prior stroke with a prestroke depression diagnosis (DD) and controls. We examined relationships between physical activity behaviors and self-reported depression frequency. Methods: In the UK Biobank wearable accelerometer cohort, we retrospectively identified patients who had previously suffered a stroke (N=1603) and conducted cross-sectional analyses with those who completed a subsequent depression survey follow-up. Sensitivity analyses assessed a general population cohort excluding previous stroke participants and 2 incident cohorts: incident stroke (IS) and incident cerebrovascular disease (IC). Results: In controls, the odds of being in a higher depressed mood frequency category decreased by 23% for each minute spent in moderate‐to‐vigorous physical activity (odds ratio 0.77, 95% CI 0.69‐0.87; P<.001). This association persisted in both general cohorts and in the IC control cohort. Conclusions: Although moderate‐to‐vigorous physical activity was linked with less frequent depressed mood in patients with prior stroke without DD, this finding did not persist in DDs. Thus, accelerometer-mood monitoring may provide clinically useful insights about future mood in patients with prior stroke without DDs. Considering the finding in the IC cohort and the lack of findings in the IS cohorts, accelerometer-mood monitoring may also be appropriately applied to observing broader cerebrovascular disease pathogenesis.
- Open Access
- 4 June 2024
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 13 (11) , e032965
Accelerometer‐Measured Behavior Patterns in Incident Cerebrovascular Disease: Insights for Preventative Monitoring From the UK Biobank
Background: The goal was to compare patterns of physical activity (PA) behaviors (sedentary behavior [SB], light PA, moderate‐to‐vigorous PA [MVPA], and sleep) measured via accelerometers for 7 days between patients with incident cerebrovascular disease (CeVD) (n=2141) and controls (n=73 938). Methods and Results: In multivariate models, cases spent 3.7% less time in MVPA (incidence rate ratio [IRR], 0.963 [95% CI, 0.929–0.998]) and 1.0% more time in SB (IRR, 1.010 [95% CI, 1.001–1.018]). Between 12 and 24 months before diagnosis, cases spent more time in SB (IRR, 1.028 [95% CI, 1.001–1.057]). Within the year before diagnosis, cases spent less time in MVPA (IRR, 0.861 [95% CI, 0.771–0.964]). Although SB time was not associated with CeVD risk, MVPA time, both total min/d (hazard ratio [HR], 0.998 [95% CI, 0.997–0.999]) and guideline threshold adherence (≥150 min/wk) (HR, 0.909 [95% CI, 0.827–0.998]), was associated with decreased CeVD risk. Comorbid burden had a significant partial mediation effect on the relationship between MVPA and CeVD. Cases slept more during 12:00 to 17:59 hours (IRR, 1.091 [95% CI, 1.002–1.191]) but less during 0:00 to 5:59 hours (IRR, 0.984 [95% CI, 0.977–0.992]). No between‐group differences were significant at subgroup analysis. Conclusions: Daily behavior patterns were significantly different in patients before CeVD. Although SB was not associated with CeVD risk, the association between MVPA and CeVD risk is partially mediated by comorbid burden. This study has implications for understanding observable behavior patterns in cerebrovascular dysfunction and may help in developing remote monitoring strategies to prevent or reduce cerebrovascular decline.
- 4 June 2024
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 13 (11) , e032965
Open AccessAccelerometer‐Measured Behavior Patterns in Incident Cerebrovascular Disease: Insights for Preventative Monitoring From the UK Biobank
Background: The goal was to compare patterns of physical activity (PA) behaviors (sedentary behavior [SB], light PA, moderate‐to‐vigorous PA [MVPA], and sleep) measured via accelerometers for 7 days between patients with incident cerebrovascular disease (CeVD) (n=2141) and controls (n=73 938). Methods and Results: In multivariate models, cases spent 3.7% less time in MVPA (incidence rate ratio [IRR], 0.963 [95% CI, 0.929–0.998]) and 1.0% more time in SB (IRR, 1.010 [95% CI, 1.001–1.018]). Between 12 and 24 months before diagnosis, cases spent more time in SB (IRR, 1.028 [95% CI, 1.001–1.057]). Within the year before diagnosis, cases spent less time in MVPA (IRR, 0.861 [95% CI, 0.771–0.964]). Although SB time was not associated with CeVD risk, MVPA time, both total min/d (hazard ratio [HR], 0.998 [95% CI, 0.997–0.999]) and guideline threshold adherence (≥150 min/wk) (HR, 0.909 [95% CI, 0.827–0.998]), was associated with decreased CeVD risk. Comorbid burden had a significant partial mediation effect on the relationship between MVPA and CeVD. Cases slept more during 12:00 to 17:59 hours (IRR, 1.091 [95% CI, 1.002–1.191]) but less during 0:00 to 5:59 hours (IRR, 0.984 [95% CI, 0.977–0.992]). No between‐group differences were significant at subgroup analysis. Conclusions: Daily behavior patterns were significantly different in patients before CeVD. Although SB was not associated with CeVD risk, the association between MVPA and CeVD risk is partially mediated by comorbid burden. This study has implications for understanding observable behavior patterns in cerebrovascular dysfunction and may help in developing remote monitoring strategies to prevent or reduce cerebrovascular decline.
- Open Access
Feasibility of Observing Cerebrovascular Disease Phenotypes with Smartphone Monitoring: Study Design Considerations for Real-World Studies
Accelerated by the adoption of remote monitoring during the COVID-19 pandemic, interest in using digitally captured behavioral data to predict patient outcomes has grown; however, it is unclear how feasible digital phenotyping studies may be in patients with recent ischemic stroke or transient ischemic attack. In this perspective, we present participant feedback and relevant smartphone data metrics suggesting that digital phenotyping of post-stroke depression is feasible. Additionally, we proffer thoughtful considerations for designing feasible real-world study protocols tracking cerebrovascular dysfunction with smartphone sensors.
Open AccessFeasibility of Observing Cerebrovascular Disease Phenotypes with Smartphone Monitoring: Study Design Considerations for Real-World Studies
Accelerated by the adoption of remote monitoring during the COVID-19 pandemic, interest in using digitally captured behavioral data to predict patient outcomes has grown; however, it is unclear how feasible digital phenotyping studies may be in patients with recent ischemic stroke or transient ischemic attack. In this perspective, we present participant feedback and relevant smartphone data metrics suggesting that digital phenotyping of post-stroke depression is feasible. Additionally, we proffer thoughtful considerations for designing feasible real-world study protocols tracking cerebrovascular dysfunction with smartphone sensors.