Kiffon Keigher
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Kiffon Keigher has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Demetrius Klee Lopes
Brain and Spine Institute, Advocate Lutheran General Hospital, Chicago, IL, USA
2 shared publications - João Victor Sanders
Brain and Spine Institute, Advocate Health, Chicago, Illinois, USA
2 shared publications - Krishna Chaitanya Joshi
Department of Neurological Surgery, Rush University Medical Center, Chicago, Illinois, USA
2 shared publications - Marion Oliver
Brain and Spine Institute, Advocate Lutheran General Hospital, Chicago, IL, USA
2 shared publications
Latest Publications
- 24 September 2025
- Published by SAGE Publications in Interventional Neuroradiology
- Vol. 32 (5) , 2930-2937
An evidence-based pulsatile tinnitus clinical workflow: A systematic review of literature
Introduction: Endovascular management options for pulsatile tinnitus (PT) patients have increased in recent years with promising results. However, standardized endovascular team referral criteria remain limited. We conducted a systematic review and suggested an evidence-based referral protocol for PT patients to the neuroendovascular team. Methods: A literature review was conducted in February 2025 using the PubMed/MEDLINE database. We included English-written studies published in the last 5 years, focusing on PT diagnosis and management. Exclusion criteria included: (1) in vitro or animal studies, (2) studies focused on open surgery approaches, (3) studies addressing only non-PT, and (4) case reports, case series (3–10 cases), commentaries, letters to the editor, editorials, and book chapters. Results: Our initial search retrieved 257 papers. Of these, 219 were excluded after reading the title and abstract, and an additional 12 were excluded after full-text review. A total of 26 papers were eligible for inclusion in this review and in developing our protocol. After PT diagnosis and imaging, our protocol consists of the following three questions: (1) Is non-invasive imaging suspicious for a dural arteriovenous fistula, high-risk vascular lesions, or idiopathic intracranial hypertension? (2) Despite normal neuroimaging, is there clinical suspicion of a high-risk vascular lesion? (3) Although a low-risk lesion is diagnosed, is PT debilitating? If there is a “yes” to any of these questions, referral to the endovascular team is recommended. Conclusion: We suggested an evidence-based referral protocol for PT patients to the neuroendovascular team.
- 24 September 2025
- Published by SAGE Publications in Interventional Neuroradiology
- Vol. 32 (5) , 2930-2937
An evidence-based pulsatile tinnitus clinical workflow: A systematic review of literature
Introduction: Endovascular management options for pulsatile tinnitus (PT) patients have increased in recent years with promising results. However, standardized endovascular team referral criteria remain limited. We conducted a systematic review and suggested an evidence-based referral protocol for PT patients to the neuroendovascular team. Methods: A literature review was conducted in February 2025 using the PubMed/MEDLINE database. We included English-written studies published in the last 5 years, focusing on PT diagnosis and management. Exclusion criteria included: (1) in vitro or animal studies, (2) studies focused on open surgery approaches, (3) studies addressing only non-PT, and (4) case reports, case series (3–10 cases), commentaries, letters to the editor, editorials, and book chapters. Results: Our initial search retrieved 257 papers. Of these, 219 were excluded after reading the title and abstract, and an additional 12 were excluded after full-text review. A total of 26 papers were eligible for inclusion in this review and in developing our protocol. After PT diagnosis and imaging, our protocol consists of the following three questions: (1) Is non-invasive imaging suspicious for a dural arteriovenous fistula, high-risk vascular lesions, or idiopathic intracranial hypertension? (2) Despite normal neuroimaging, is there clinical suspicion of a high-risk vascular lesion? (3) Although a low-risk lesion is diagnosed, is PT debilitating? If there is a “yes” to any of these questions, referral to the endovascular team is recommended. Conclusion: We suggested an evidence-based referral protocol for PT patients to the neuroendovascular team.
- 25 July 2025
- Published by SAGE Publications in Interventional Neuroradiology
Methinks AI software for identifying large vessel occlusion in non-contrast head CT: A pilot retrospective study in American population
Background: Non-contrast computed tomography (NCCT) is the first image for stroke assessment, but its sensitivity for detecting large vessel occlusion (LVO) is limited. Artificial intelligence (AI) algorithms may contribute to a faster LVO diagnosis using only NCCT. This study evaluates the performance and the potential diagnostic time saving of Methinks LVO AI algorithm in a U.S. multi-facility stroke network. Methods: This retrospective pilot study reviewed NCCT and computed tomography angiography (CTA) images between 2015 and 2023. The Methinks AI algorithm, designed to detect LVOs in the internal carotid artery and middle cerebral artery, was tested for sensitivity, specificity, and predictive values. A neuroradiologist reviewed cases to establish a gold standard. To evaluate potential time saving in workflow, time gaps between NCCT and CTA were analyzed and stratified into four groups in true positive cases: Group 1 (60 min). Results: From a total of 1155 stroke codes, 608 NCCT exams were analyzed. Methinks LVO demonstrated 75% sensitivity and 83% specificity, identifying 146 out of 194 confirmed LVO cases correctly. The PPV of the algorithm was 72%. The NPV was 83% (considering ‘other occlusion’, ‘stenosis’ and ‘posteriors’ as negatives), and 73% considered the same conditions as positives. Among the true positive cases, we found 112 patients Group 1, 32 patients in Group 2, 15 patients in Group 3, 3 patients in Group 4. Conclusion: The Methinks AI algorithm shows promise for improving LVO detection from NCCT, especially in resource limited settings. However, its sensitivity remains lower than CTA-based systems, suggesting the need for further refinement.
- 25 July 2025
- Published by SAGE Publications in Interventional Neuroradiology
Methinks AI software for identifying large vessel occlusion in non-contrast head CT: A pilot retrospective study in American population
Background: Non-contrast computed tomography (NCCT) is the first image for stroke assessment, but its sensitivity for detecting large vessel occlusion (LVO) is limited. Artificial intelligence (AI) algorithms may contribute to a faster LVO diagnosis using only NCCT. This study evaluates the performance and the potential diagnostic time saving of Methinks LVO AI algorithm in a U.S. multi-facility stroke network. Methods: This retrospective pilot study reviewed NCCT and computed tomography angiography (CTA) images between 2015 and 2023. The Methinks AI algorithm, designed to detect LVOs in the internal carotid artery and middle cerebral artery, was tested for sensitivity, specificity, and predictive values. A neuroradiologist reviewed cases to establish a gold standard. To evaluate potential time saving in workflow, time gaps between NCCT and CTA were analyzed and stratified into four groups in true positive cases: Group 1 (60 min). Results: From a total of 1155 stroke codes, 608 NCCT exams were analyzed. Methinks LVO demonstrated 75% sensitivity and 83% specificity, identifying 146 out of 194 confirmed LVO cases correctly. The PPV of the algorithm was 72%. The NPV was 83% (considering ‘other occlusion’, ‘stenosis’ and ‘posteriors’ as negatives), and 73% considered the same conditions as positives. Among the true positive cases, we found 112 patients Group 1, 32 patients in Group 2, 15 patients in Group 3, 3 patients in Group 4. Conclusion: The Methinks AI algorithm shows promise for improving LVO detection from NCCT, especially in resource limited settings. However, its sensitivity remains lower than CTA-based systems, suggesting the need for further refinement.