Citations

Clear

14 citation(s) found for "Schwartz, Kara".

INNV-21. Initial experience with generative AI for clinical summarization in glioma MR interpretation
Black, David , Kaufmann, Tim , Charlotte, Rydberg, Kara, Schwartz, Ted, Passe, John, Port, Steven, Messina, Blezek, Daniel J. , Black, David, Carr, Carrie M. , Kaufmann, Tim, Kara, Schwartz, John, Port, Mark, Ian T. , Steven, Messina

Mayo Clinic

Neuro-Oncology | November 11, 2025 | Volume: 27 | Issue: Supplement_5 | Pages: v229-v229

10.1093/neuonc/noaf201.0910 Get It

Abstract BACKGROUND Patients with primary brain tumors often have very complex histories, but an accurate understanding of their care timeline is critical to provide the best care possible. Extracting pertinent facts from the medical record can be time consuming and frustrating. We sought to apply generative AI large language models (LLM) to this problem in order to supply providers with concise, accurate, and focused data including graphs and tables. METHODS After evaluating multiple LLMs, GEMINI 2.5 Pro was selected. Prompt engineering was iteratively refined across a range of patients to generate concise outputs using tables, graphs, and prose to describe timing of chemoradiation, tumor markers, procedures, and trends in MRI results. The model inferred BT-RADS scores from the MRI report prose. Using a 5-point Likert scale, neuroradiologists assessed the AI-output both prospectively and retrospectively comparing it to the medical record. LLM’s compared AI summaries to source material. RESULTS Six neuroradiologists each ranked 25 prospective patient outputs as accurate (82%/16%/1%), useful (94%/6%/0%), trustworthy (86%/13%/1%), and satisfactory (86%/10%/1%) for Likert ratings of highly agree/agree/neutral, respectively. No responses were disagree or highly disagree. Interobserver agreement was high (Gwent AC2 > 0.95). The LLM evaluation of referenced portions of the record determined > 85% of summary statements were supported by source documents. While users estimated time savings of a 1-10 minutes per case, they felt the greater benefit was having more organized data presented efficiently. CONCLUSIONS AI summaries of the medical record of complex patients with primary brain tumors give providers an accurate, well-organized display of the pertinent facts necessary for high quality care and save time in chart review. These summaries, which are generated early each morning, have been found to be helpful and are now being incorporated into our clinical practice and multidisciplinary tumor board.
Neuroimaging and Clinical Features in Late Onset Alexander Disease (S31.005)
Graff‐Radford, Jonathan , Schwartz, Kara M., Gavrilova, Ralitza, Kumar, Neeraj , Lachance, Daniel Honore

Mayo Clinic

Neurology | December 7, 2023 | Volume: 82 | Issue: 10_supplement | Pages: No page available

10.1212/wnl.82.10_supplement.s31.005 Get It

Automated CT angiography collateral scoring in anterior large vessel occlusion stroke: A multireader study
Jabal, Mohamed Sobhi , Kallmes, David F. , Harston, George , Schwartz, Kara M., Benson, John C. , Little, Jason T. , Nagelschneider, Alex A. , Nasr, Deena M. , Braksick, Sherry A, Klaas, James P. , Bilgin, Cem , Brinjikji, Waleed , Campeau, Norbert, Schwartz, Kara, Messina, Steven, Carr, Carrie, Benson, John , Little, Jason, Nagelschneider, Alex, Madhavan, Ajay A , Nasr, Deena, Braksick, Sherry, Klaas, James, Bilgin, Cem , Campeau, Norbert G. , Messina, Steven A. , Carr, Carrie M. , Madhavan, Ajay A. , Scharf, Eugene

Mayo Clinic

Interventional Neuroradiology | January 18, 2023 | Volume: 31 | Issue: 1 | Pages: 95-100

10.1177/15910199221150470 | PMID 36650942 Get It

Background Computed tomography (CT) angiography collateral score (CTA-CS) is an important clinical outcome predictor following mechanical thrombectomy for ischemic stroke with large vessel occlusion (LVO). The present multireader study aimed to evaluate the performance of e-CTA software for automated assistance in CTA-CS scoring. Materials and Methods Brain CTA images of 56 patients with anterior LVO were retrospectively processed. Twelve readers of various clinical training, including junior neuroradiologists, senior neuroradiologists, and neurologists graded collateral flow using visual CTA-CS scale in two sessions separated by a washout period. Reference standard was the consensus of three expert readers. Duration of reading time, inter-rater reliability, and statistical comparison of readers’ performance metrics were analyzed between the e-CTA assisted and unassisted sessions. Results e-CTA assistance resulted in significant increase in mean accuracy (58.6% to 67.5%, p = 0.003), mean F1 score (0.574 to 0.676, p = 0.002), mean precision (58.8% to 68%, p = 0.007), and mean recall (58.7% to 69.9%, p = 0.002), especially with slight filling deficit (CTA-CS 2 and 3). Mean reading time was reduced across all readers (103.4 to 59.7 s, p = 0.001), and inter-rater agreement in CTA-CS assessment was increased (Krippendorff's alpha 0.366 to 0.676). Optimized occlusion laterality detection was also noted with mean accuracy (92.9% to 96.8%, p = 0.009). Conclusion Automated assistance for CTA-CS using e-CTA software provided helpful decision support for readers in terms of improving scoring accuracy and reading efficiency for physicians with a range of experience and training backgrounds and leading to significant improvements in inter-rater agreement.
Superficial siderosis associated with an iatrogenic posterior fossa dural leak identified on CT cisternography
Madhavan, Ajay A. , Wood, Christopher P. , Aksamit, Allen J. , Schwartz, Kara M., Atkinson, John L. D., Kumar, Neeraj , Atkinson, John L., Madhavan, Ajay A

Mayo Clinic

The Neuroradiology Journal | September 3, 2021 | Volume: 35 | Issue: 3 | Pages: 403-407

10.1177/19714009211042875 | PMID 34477007 Get It

Superficial siderosis refers to hemosiderin deposition along the pial surface of the brain and spinal cord. It results from chronic and repetitive low-grade bleeding into the subarachnoid space. Dural tears are a common cause of superficial siderosis. Although such tears typically occur in the spine, dural tears can also occur in the posterior fossa. In many cases, posterior fossa dural tears are iatrogenic, and patients may present with neuroimaging evidence of postoperative pseudomeningoceles. We present a case of superficial siderosis caused by a persistent posterior fossa dural leak. The patient presented with superficial siderosis 30 years after a Chiari I malformation repair. A pinhole-sized dural tear was identified preoperatively using computed tomography cisternography. The dural defect was successfully repaired. An additional small tear that was not seen on imaging was also identified at surgery and successfully repaired.
e-ASPECTS software improves interobserver agreement and accuracy of interpretation of aspects score
Brinjikji, Waleed , Abbasi, Mehdi , Arnold, Catherine , Benson, John C. , Braksick, Sherry A, Klaas, James P. , Little, Jason T. , Nagelschneider, Alex A. , Schwartz, Kara M., Wood, Christopher P. , Nasr, Deena M. , Kallmes, David F. , Campeau, Norbert, Liebo, Greta B. , Luetmer, Patrick H , Messina, Steven A. , Wood, Christopher P , Kallmes, David F , Benson, John , Arnold, Catherine, Campeau, Norbert G. , Carr, Carrie M. , Cogswell, Petrice M. , Luetmer, Patrick H.

Mayo Clinic

Interventional Neuroradiology | April 15, 2021 | Volume: 27 | Issue: 6 | Pages: 781-787

10.1177/15910199211011861 | PMID 33853441 Get It

Introduction There is increased interest in the use of artificial intelligence-based (AI) software packages in the evaluation of neuroimaging studies for acute ischemic stroke. We studied whether, compared to standard image interpretation without AI, Brainomix e-ASPECTS software improved interobserver agreement and accuracy in detecting ASPECTS regions affected in anterior circulation LVO. Methods We included 60 consecutive patients with anterior circulation LVO who had TICI 3 revascularization within 60 minutes of their baseline CT. A total of 16 readers, including senior neuroradiologists, junior neuroradiologists and vascular neurologists participated. Readers interpreted CT scans on independent workstations and assessed final ASPECTS and evaluated whether each individual ASPECTS region was affected. Two months later, readers again evaluated the CT scans, but with assistance of e-ASPECTS software. We assessed interclass correlation coefficient for total ASPECTS and interobserver agreement with Fleiss’ Kappa for each ASPECTS region with and without assistance of the e-ASPECTS. We also assessed accuracy for the readers with and without e-ASPECTS assistance. In our assessment of accuracy, ground truth was the 24 hour CT in this cohort of patients who had prompt and complete revascularization. Results Interclass correlation coefficient for total ASPECTS without e-ASPECTS assistance was 0.395, indicating fair agreement compared, to 0.574 with e-ASPECTS assistance, indicating good agreement (P < 0.01). There was significant improvement in inter-rater agreement with e-ASPECTS assistance for each individual region with the exception of M6 and caudate. The e-ASPECTS software had higher accuracy than the overall cohort of readers (with and without e-ASPECTS assistance) for every region except the caudate. Conclusions Use of Brainomix e-ASPECTS software resulted in significant improvements in inter-rater agreement and accuracy of ASPECTS score evaluation in a large group of neuroradiologists and neurologists. e-ASPECTS software was more predictive of final infarct/ASPECTS than the overall group interpreting the CT scans with and without e-ASPECTS assistance.
Morbidity and Mortality Differences Between Hematopoietic Cell Transplantation Survivors and Other Cancer Survivors
Chow, Eric J. , Cushing‐Haugen, Kara L. , Khera, Nandita , Lee, Stephanie J. , Leisenring, Wendy M. , Mueller, Beth A. , Cheng, Guang‐Shing , Boeckh, Michael, Martin, Paul J. , Schwartz, Stephen M, Baker, K. Scott, Boeckh, Michael , Schwartz, Stephen Mark , Baker, Kevin Scott , Leisenring, Wendy , Chow, Eric J , Lee, Stephanie J

Mayo Clinic

Journal of Clinical Oncology | February 24, 2017 | Volume: 35 | Issue: 3 | Pages: 306-313

10.1200/jco.2016.68.8457 | PMID 27870568 Get It

Purpose To compare the risks of serious health outcomes among hematopoietic cell transplantation (HCT) survivors versus a matched population of patients with cancer who did not undergo HCT, where the primary difference may be exposure to HCT. Methods Two-year HCT survivors treated at a comprehensive cancer center from 1992 through 2009 who were Washington State residents (n = 1,792; 52% allogeneic and 90% hematologic malignancies) were frequency matched by demographic characteristics and underlying cancer diagnosis (as applicable) to non-HCT 2-year cancer survivors, using the state cancer registry (n = 5,455) and the general population (n = 16,340) using driver’s license files. Late outcomes for all three cohorts were ascertained from the state hospital discharge and death registries; subsequent cancers were ascertained from the state cancer registry. Results After median follow-up of 7.1 years, HCT survivors experienced significantly greater rates of hospitalization compared with matched non-HCT cancer survivors (280 v 173 episodes per 1,000 person-years, P < .001) and greater all-cause mortality (hazard ratio [HR], 1.1; 95% CI, 1.01 to 1.3). HCT survivors had more hospitalizations or death with infections (10-year cumulative incidence, 31% v 22%; HR, 1.4; 95% CI, 1.3 to 1.6) and respiratory complications (cumulative incidence, 27% v 20%; HR, 1.4; 95% CI, 1.2 to 1.5). Risks of digestive, skin, and musculoskeletal complications also were greater among HCT versus non-HCT cancer survivors. The two groups had similar risks of circulatory complications and second cancers. Both HCT and non-HCT cancer survivors had significantly greater 10-year cumulative incidences of all major organ-system outcomes versus the general population. Conclusion History of HCT was associated with late morbidity and mortality among cancer survivors. In particular, clinicians who care for HCT survivors should be aware of their high rates of late respiratory and infectious complications.
Brain Herniation into Arachnoid Granulations: Clinical and Neuroimaging Features
Lane, John I. , Eckel, Laurence J. , Schwartz, Kara M., Liebo, Greta B. , Lane, John Jack I, Van Gompel, Jamie J, Lehman, Vance T. , Gompel, Jamie J. Van

Mayo Clinic

Journal of Neuroimaging | June 8, 2016 | Volume: 26 | Issue: 6 | Pages: 592-598

10.1111/jon.12366 | PMID 27273503 Get It

ABSTRACTBACKGROUND/PURPOSEBrain herniation into presumed arachnoid granulations (BHAG) is an increasingly recognized entity. Though it has previously been described as isointense to brain matter on magnetic resonance imaging (MRI), we have encountered 21 cases in our clinical practice, many of which have signal abnormality in the herniated or adjacent parenchyma. We performed a systematic analysis on these cases to further understand the clinical significance.METHODSThis is a retrospective analysis of cases collected from our clinical MRI practice. Each case was evaluated for location, size, lobe of origin, associated signal abnormality, symptoms, and the presence or absence of intracranial hypertension.RESULTSTwenty‐one cases of BHAG identified in 16 patients. Seven cases (7/21, 33%) demonstrated signal abnormality in the herniated or underlying parenchyma. On serial imaging, the size of herniation either fluctuated (2/10, 20%) or stayed the same (8/10, 80%). The associated signal abnormalities increased (1/5, 20%), decreased (1/5, 20%), or remained stable (3/5, 60%). Four patients (4/16, 25%) had signs/symptoms that could be associated with the BHAG. Ten patients (10/16, 63%) had either imaging findings or clinical signs that could be associated with intracranial hypertension.CONCLUSIONIn contrast to previously reported cases, our study demonstrates that BHAG can be associated with MRI signal abnormalities of the herniated and adjacent brain. Symptoms are typically absent, though may be present in a small subset of patients, regardless of the presence of signal change or encephalomalacia of the involved brain. Indirect evidence of intracranial hypertension is present in a majority of patients but completely lacking in others.
Traumatic anterior cervical pseudomeningocele causing intracranial hypotension successfully treated with blood patch: case report
Takahashi, Edwin A. , Eckel, Laurence J. , Schwartz, Kara M., Diehn, Felix E. , Hunt, Christopher H. , Daniels, David J. , Takahashi, Edwin A

Mayo Clinic

Journal of Neurosurgery: Spine | May 29, 2015 | Volume: 23 | Issue: 3 | Pages: 303-305

10.3171/2014.12.spine14735 | PMID 26023899 Get It

Cervical pseudomeningocele is a rare complication of trauma. It develops when an extradural collection of cerebrospinal fluid (CSF) develops after a dural breach. The authors present the unusual case of a 33-year-old man with progressive headache, neck pain, mental status changes, and cardiopulmonary instability after polytrauma sustained from a motorcycle-versus-deer collision, without improvement during a 5-day hospitalization. Magnetic resonance imaging revealed a collection of CSF anterior to the cervical thecal sac compatible with an anterior cervical pseudomeningocele. A nontargeted epidural blood patch was performed with subsequent resolution of the patient's symptoms. Anterior cervical pseudomeningoceles are usually asymptomatic; however, these lesions can cause orthostatic headaches, neck pain, and cardiopulmonary compromise, as it did in the featured patient. Pseudomeningoceles should be included in the differential diagnosis for posttrauma patients with progressive neurological decline or postural headache, and blood patch may be an effective minimally invasive treatment.
Neuroimaging and clinical features in type II (late-onset) Alexander disease
Graff‐Radford, Jonathan , Schwartz, Kara M., Gavrilova, Ralitza H. , Kumar, Neeraj , Lachance, Daniel Honore

Mayo Clinic

Neurology | December 5, 2013 | Volume: 82 | Issue: 1 | Pages: 49-56

10.1212/01.wnl.0000438230.33223.bc | PMID 24306001 Get It

Vertebral Body Infarct and Ventral Cauda Equina Enhancement: Two Confirmatory Findings of Acute Spinal Cord Infarct
Schwartz, Kara M., Eckel, Laurence J. , Black, David F. , Wood, Christopher P. , Kotsenas, Amy L. , Wald, John T. , Hocker, Sara E. , Diehn, Felix E. , Hunt, Christopher H. , Lehman, Vance T. , Halaweish, Ahmed F

Mayo Clinic

Journal of Neuroimaging | October 12, 2013 | Volume: 25 | Issue: 1 | Pages: 133-135

10.1111/jon.12058 | PMID 24118402 Get It

ABSTRACTTwo valuable confirmatory MRI findings of acute spinal cord infarct are highlighted and discussed: concomitant vertebral body infarct and ventral cauda equina nerve root enhancement.