Evaluation of responses to cardiac imaging questions by the artificial intelligence large language model ChatGPT.

PURPOSE: To assess ChatGPT's ability as a resource for educating patients on various aspects of cardiac imaging, including diagnosis, imaging modalities, indications, interpretation of radiology reports, and management. METHODS: 30 questions were posed to ChatGPT-3.5 and ChatGPT-4 three times in three separate chat sessions. Responses were scored as correct, incorrect, or clinically misleading categories by three observers-two board certified cardiologists and one board certified radiologist with cardiac imaging subspecialization. Consistency of responses across the three sessions was also evaluated. Final categorization was based on majority vote between at least two of the three observers. RESULTS: ChatGPT-3.5 answered seventeen of twenty eight questions correctly (61 %) by majority vote. Twenty one of twenty eight questions were answered correctly (75 %) by ChatGPT-4 by majority vote. Majority vote for correctness was not achieved for two questions. Twenty six of thirty questions were answered consistently by ChatGPT-3.5 (87 %). Twenty nine of thirty questions were answered consistently by ChatGPT-4 (97 %). ChatGPT-3.5 had both consistent and correct responses to seventeen of twenty eight questions (61 %). ChatGPT-4 had both consistent and correct responses to twenty of twenty eight questions (71 %). CONCLUSION: ChatGPT-4 had overall better performance than ChatGTP-3.5 when answering cardiac imaging questions with regard to correctness and consistency of responses. While both ChatGPT-3.5 and ChatGPT-4 answers over half of cardiac imaging questions correctly, inaccurate, clinically misleading and inconsistent responses suggest the need for further refinement before its application for educating patients about cardiac imaging.

Advancing the Management of Long COVID by Integrating into Health Informatics Domain: Current and Future Perspectives.

The ongoing COVID-19 pandemic has profoundly affected millions of lives globally, with some individuals experiencing persistent symptoms even after recovering. Understanding and managing the long-term sequelae of COVID-19 is crucial for research, prevention, and control. To effectively monitor the health of those affected, maintaining up-to-date health records is essential, and digital health informatics apps for surveillance play a pivotal role. In this review, we overview the existing literature on identifying and characterizing long COVID manifestations through hierarchical classification based on Human Phenotype Ontology (HPO). We outline the aspects of the National COVID Cohort Collaborative (N3C) and Researching COVID to Enhance Recovery (RECOVER) initiative in artificial intelligence (AI) to identify long COVID. Through knowledge exploration, we present a concept map of clinical pathways for long COVID, which offers insights into the data required and explores innovative frameworks for health informatics apps for tackling the long-term effects of COVID-19. This study achieves two main objectives by comprehensively reviewing long COVID identification and characterization techniques, making it the first paper to explore incorporating long COVID as a variable risk factor within a digital health informatics application. By achieving these objectives, it provides valuable insights on long COVID's challenges and impact on public health.

A 49-Year-Old Woman With Exertional Dyspnea and Dizziness.

CASE PRESENTATION: A 49-year-old woman with a history of right breast cancer status post radiation therapy presented to our ED with increasing chest pain, exertional dyspnea, fatigue, and dizziness for several weeks. She denied syncope or near-syncope, and she had no personal or family history of cardiac disease. Her outpatient medications included tamoxifen and venlafaxine.

Iatrogenic Atrial Septal Defect Closure Through the Steerable Guide Catheter: Description of Technique and Single-Center Experience.

OBJECTIVES: To introduce a novel method of direct iatrogenic atrial septal defect (iASD) closure through the MitraClip steerable guide catheter (SGC). BACKGROUND: MitraClip implantation requires transseptal puncture and the creation of an iASD. There are relatively rare instances, such as hemodynamically significant shunting or concerns for embolus, where iASD must be closed during index procedure. In these instances, it may be beneficial to not give up access to left atrium. METHODS: We retrospectively reviewed all iASD closures during MitraClip implantation at our institution from 2015 to 2020. Cases where an ASD occluder was deployed directly through SGC were included. RESULTS: Eleven patients had immediate iASD closure through the SGC. Indications for using this method included concern for paradoxical embolus, large defect size and/or significant shunting. Closure device sizes ranged from 8 to 22 mm. Mean time from removal of clip delivery system to occlusion of iASD was 14.6 minutes. There were no procedural complications related to iASD closure using this method. CONCLUSION: Closure of iASD intra-procedurally directly through transseptal guide sheath via the method described was safe and allowed for continuous left atrium access.

The Yin-Yang Sign of Severe Mitral Regurgitation.

In select patients with severe, eccentric mitral regurgitation, we have observed that the regurgitant jet may entrain blood along the left atrial wall to produce a Chinese yin-yang symbol on color Doppler. This clinical imaging series demonstrates this unique phenomenon in an 81-year-old woman with symptomatic, severe, functional mitral regurgitation secondary to non-ischemic cardiomyopathy who was referred for transcatheter mitral valve repair. The yin-yang symbol resolved on transthoracic echocardiography after placement of 2 MitraClip NTR devices.

MitraClip Implantation Guided by Volumetric Intracardiac Echocardiography: Technique and Feasibility in Patients Intolerant to Transesophageal Echocardiography.

Transesophageal echo (TEE) guidance is essential for successful MitraClip implantation. In patients intolerant to TEE, options are limited. Three patients, with contraindications to TEE, underwent MitraClip implantation using volumetric intracardiac echo (vICE). All patients had severe symptomatic degenerative mitral regurgitation (MR) and had successful implantation of at least one clip with reduction of MR to ≤2+ maintained at 30d follow-up. All patients had improvement in functional status without any adverse clinical, clip, or vICE related events. We discuss in detail the technical considerations and limitations to performing the MitraClip procedure with vICE guidance.

Adjunctive use of fluoroscopy during MitraClip implantation reduces procedural complexity: The parallax technique.

BACKGROUND: During MitraClip implantation sub-valvular correction of trajectory and/or alignment may increase adverse clip or leaflet events. With systematic adjunctive use of fluoroscopy ("Parallax technique"), we aimed to assess parameters that minimize the need for corrective measures and help increase procedural efficiency. METHODS: We retrospectively analyzed 30 patients without (Fl-) and 39 patients utilizing adjunctive fluoroscopy (Fl+) during MitraClip implantation. After establishing trajectory and supra-valvular alignment, the Parallax technique was utilized. Trajectory and alignment are maintained during advancement. RESULTS: All patients had 3 or 4+ MR. There were no differences in baseline demographics. The average number of clips (Fl- vs Fl+) was 1.72 ± 0.8 vs 1.59 ± 0.5, p = .57. For the first clip, the need for sub-valvular alignment (80% vs. 36%, p = .0001), eversion with retraction back to left atrium (23% vs. 10%, p = .001) and the number of grasps (2.3 ± 1.2 vs 1.4 ± 0.9) was reduced. The time from transseptal puncture to first clip deployment (71 ± 21 vs 44 ± 16 min, p = .01) was reduced. Procedural success was achieved in all but one patient in the Fl- group (p = ns). There were no differences noted for in-hospital or 30-day outcomes. CONCLUSIONS: Systematic use of a simple and easy to implement "Parallax technique" was associated with reduced need for sub-valvular manipulation and was associated with improved procedural times. Further larger scale studies are needed to assess the applicability of the technique.

A case report of an infiltrative cardiomyopathy in everyday practice: a specific cause that cannot be missed in the elderly.

BACKGROUND: Transthyretin amyloid cardiomyopathy (ATTR-CM) is a commonly misdiagnosed cardiac condition due to low disease awareness and perceived rarity, which frequently results in incorrect management and poor outcomes. Early and prompt diagnosis has become critical with emerging therapies that improve patient survival. CASE SUMMARY: A 68-year-old woman presented to a tertiary care centre with acute decompensated heart failure following recurrent hospitalizations for the same issue over the past several months. Transthoracic echocardiography revealed severe concentric left ventricular hypertrophy with grade III diastolic dysfunction. However, QRS voltage by 12-lead electrocardiogram (ECG) was discordant with the degree of left ventricular hypertrophy seen by echocardiography, and the patient had recurrent non-sustained ventricular tachycardia that necessitated implantable cardioverter-defibrillator implantation a few months prior. After aggressive diuresis, the patient completed cardiac magnetic resonance imaging that raised concern for cardiac amyloidosis. Subsequent serum and urine protein electrophoresis with associated immunofixation were within normal limits. Finally, ATTR-CM was confirmed by technetium-99m pyrophosphate scintigraphy with plans to initiate tafamidis after genetic testing. DISCUSSION: Patients >60 years of age with diastolic heart failure phenotypically similar to hypertrophic cardiomyopathy and/or hypertensive heart disease should always be evaluated for ATTR-CM. Features that increase suspicion include discordance between left ventricular wall thickness and ECG voltage, and signs/symptoms of a primary peripheral and autonomic neuropathy. Useful non-invasive diagnostic testing has also made the diagnosis of ATTR-CM inexpensive and possible without the need for an endomyocardial biopsy. Unfortunately, this patient's diagnosis of ATTR-CM came late in her disease course, which delayed the onset of definitive therapy.

Echocardiographic guidance for transcatheter mitral valve repair using edge-to-edge clip.

Percutaneous intervention for mitral valve disease has been established as an alternative to open surgical repair in high risk and inoperable candidates. Edge-to-edge leaflet plication with Mitraclip (Abbott, Menlo Park, CA, USA) is indicated for primary and secondary mitral valve diseases. Echocardiography provides a better understanding of mitral valve anatomy and allows us to classify and quantify mitral regurgitation. Transesophageal echocardiography is essential in patient screening, intraprocedural guidance, and post-procedure evaluation for patients undergoing edge-to-edge plication with MitraClip.

Supervised exercise to reduce agitation in severely cognitively impaired persons.

BACKGROUND: Several studies have shown an improvement in depression, activities of daily living, and agitation in cognitively impaired subjects who undergo a long-term exercise program. These studies have not considered the short-term effects of exercise. OBJECTIVES: The purpose of this study was to investigate the short-term effects of a limited, supervised exercise program on agitation, depression, and activities of daily living in cognitively impaired patients residing in the special needs unit of a nursing home. METHODS: This study was a prospective comparative study. A 3-week exercise program was implemented at the special needs units of 2 nursing homes. The exercise program involved 30 minutes of exercise (15 minutes of aerobic and 15 minutes of resistance), 3 days per week. There were 50 residents in this study (76% female, 24% male) and they had a mean age of 79.2 +/- 9.7 years. The subjects had a mean SLUMS (Saint Louis Mental Status Examination) score of 1.5 +/- 2.1 (SLUM score range 0-30, 30 meaning full cognitive faculty). Each subject had his or her depression, agitation, activities of daily living, and 6-meter walk time measured before and after the 3-week exercise program. The Cornell Scale for Depression, Pittsburgh Agitation Scale (PAS)/Cohen-Mansfield Agitation Inventory, and ADCS-ADL (Alzheimer's disease cooperative study-activities of daily living) were used to measure depression, agitation, and activities of daily living, respectively. Multiple paired t tests were calculated for each outcome measurement. RESULTS: The post-study scales showed an improvement in the 6-meter walk test and, using the PAS (0-16, 0 meaning no agitation), an improvement in agitation. The improvement in agitation in the entire population was P less than .05; mean PAS pre-study scores were 5.8 +/- 4.8 and mean PAS poststudy scores were 4.5 +/- 3.7 . Among the patients with PAS Pre-Exercise Program Scores greater than 3, thus categorized as agitated, there was a greater decrease in agitation; PAS Pre-Study Scores were 9.1 +/- 3.4 and PAS Study Scores were 6.1 +/- 3.4 (P < .001). There was also an improvement in 6-meter walk times; pre-study times were 12.5 +/- 5.2 and post-exercise program times were 10.1 +/- 4.4 (P < .001). CONCLUSION: There was an improvement in agitation scores and the 6-meter walk times in the subjects after their engagement in the 3-week exercise program. Further study is needed in order to expand on these results.