RESUMEN
The potential of artificial intelligence (AI) in medicine lies in its ability to enhance clinicians' capacity to analyse medical images, thereby improving diagnostic precision and accuracy and thus enhancing current tests. However, the integration of AI within health care is fraught with difficulties. Heterogeneity among health care system applications, reliance on proprietary closed-source software, and rising cybersecurity threats pose significant challenges. Moreover, before their deployment in clinical settings, AI models must demonstrate their effectiveness across a wide range of scenarios and must be validated by prospective studies, but doing so requires testing in an environment mirroring the clinical workflow, which is difficult to achieve without dedicated software. Finally, the use of AI techniques in health care raises significant legal and ethical issues, such as the protection of patient privacy, the prevention of bias, and the monitoring of the device's safety and effectiveness for regulatory compliance. This review describes challenges to AI integration in health care and provides guidelines on how to move forward. We describe an open-source solution that we developed that integrates AI models into the Picture Archives Communication System (PACS), called PACS-AI. This approach aims to increase the evaluation of AI models by facilitating their integration and validation with existing medical imaging databases. PACS-AI may overcome many current barriers to AI deployment and offer a pathway toward responsible, fair, and effective deployment of AI models in health care. In addition, we propose a list of criteria and guidelines that AI researchers should adopt when publishing a medical AI model to enhance standardisation and reproducibility.
RESUMEN
BACKGROUND: Deep learning models may combat widening racial disparities in heart failure outcomes through early identification of individuals at high risk. However, demographic biases in the performance of these models have not been well-studied. METHODS: This retrospective analysis used 12-lead ECGs taken between 2008 and 2018 from 326â 518 patient encounters referred for standard clinical indications to Stanford Hospital. The primary model was a convolutional neural network model trained to predict incident heart failure within 5 years. Biases were evaluated on the testing set (160â 312 ECGs) using the area under the receiver operating characteristic curve, stratified across the protected attributes of race, ethnicity, age, and sex. RESULTS: There were 59 817 cases of incident heart failure observed within 5 years of ECG collection. The performance of the primary model declined with age. There were no significant differences observed between racial groups overall. However, the primary model performed significantly worse in Black patients aged 0 to 40 years compared with all other racial groups in this age group, with differences most pronounced among young Black women. Disparities in model performance did not improve with the integration of race, ethnicity, sex, and age into model architecture, by training separate models for each racial group, or by providing the model with a data set of equal racial representation. Using probability thresholds individualized for race, age, and sex offered substantial improvements in F1 scores. CONCLUSIONS: The biases found in this study warrant caution against perpetuating disparities through the development of machine learning tools for the prognosis and management of heart failure. Customizing the application of these models by using probability thresholds individualized by race, ethnicity, age, and sex may offer an avenue to mitigate existing algorithmic disparities.
Asunto(s)
Aprendizaje Profundo , Insuficiencia Cardíaca , Humanos , Femenino , Insuficiencia Cardíaca/diagnóstico , Insuficiencia Cardíaca/terapia , Estudios Retrospectivos , Etnicidad , ElectrocardiografíaRESUMEN
The electrocardiogram (ECG) is the most frequently performed cardiovascular diagnostic test, but it is unclear how much information resting ECGs contain about long term cardiovascular risk. Here we report that a deep convolutional neural network can accurately predict the long-term risk of cardiovascular mortality and disease based on a resting ECG alone. Using a large dataset of resting 12-lead ECGs collected at Stanford University Medical Center, we developed SEER, the Stanford Estimator of Electrocardiogram Risk. SEER predicts 5-year cardiovascular mortality with an area under the receiver operator characteristic curve (AUC) of 0.83 in a held-out test set at Stanford, and with AUCs of 0.78 and 0.83 respectively when independently evaluated at Cedars-Sinai Medical Center and Columbia University Irving Medical Center. SEER predicts 5-year atherosclerotic disease (ASCVD) with an AUC of 0.67, similar to the Pooled Cohort Equations for ASCVD Risk, while being only modestly correlated. When used in conjunction with the Pooled Cohort Equations, SEER accurately reclassified 16% of patients from low to moderate risk, uncovering a group with an actual average 9.9% 10-year ASCVD risk who would not have otherwise been indicated for statin therapy. SEER can also predict several other cardiovascular conditions such as heart failure and atrial fibrillation. Using only lead I of the ECG it predicts 5-year cardiovascular mortality with an AUC of 0.80. SEER, used alongside the Pooled Cohort Equations and other risk tools, can substantially improve cardiovascular risk stratification and aid in medical decision making.
RESUMEN
INTRODUCTION: Acute MR due to mechanical mitral valve (MV) complications frequently results in cardiogenic shock and requires emergency surgical intervention. There was limited evidence for alternative treatment like MitraClip for patients at prohibitive surgical risk. We aimed to study the technical features and outcomes of emergency transcatheter edge-to-edge repair (TEER) using the MitraClip system for patients with cardiogenic shock (CS) secondary to acute mitral regurgitation (MR) and mechanical MV complication. MATERIAL AND METHODS: We performed institutional review and systemic literature review to identify all TEER for CS patients due to acute mitral regurgitation and mechanical MV complication. Clinical endpoints included device success rate assessed at the end of procedure, ability to wean off MCS, all-cause and cardiovascular mortality at 30-day. RESULTS: Eight patients were identified from institutional review. Detail anatomical analysis found that patients with mechanical MV complications related to myocardial infarction had a lower transseptal height achieved during MitraClip (3.6 ± 0.1 cm vs 4.3 ± 0.3 cm, p = 0.03) than those not related. Pooled analysis for cases from institutional review (n = 8) and systemic literature review (n = 16) was performed. The device success rate was 68.8 %. Seventy-five percent (n = 18) cases required mechanical circulatory support (MCS), and 94.4 % were able to wean off MCS. At 30-day, the cardiovascular mortality was 4.5 % and the all-cause mortality was 9.1 %. CONCLUSIONS: In CS patients due to acute MR and mechanical MV complications, TEER with/without MCS was feasible with a reasonable device success rate.
Asunto(s)
Choque Cardiogénico , Humanos , Choque Cardiogénico/diagnóstico , Choque Cardiogénico/etiología , Choque Cardiogénico/terapiaRESUMEN
BACKGROUND: The aim of this study was to evaluate the role of the distance between the aortic valve in projected position to the coronary ostium to determine risk of coronary artery obstruction after transcatheter aortic valve replacement (TAVR). METHODS: An Expected Leaflet-to-ostium Distance (ELOD) was obtained on pre-TAVR planning computed tomography by subtracting leaflet thickness and the distances from the center to the annular rim at annulus level and from the center to the coronary ostium at mid-ostial level. Variables were compared between patients with and without coronary obstruction and the level of association between variables was assessed using log odds ratio (OR). RESULTS: A total of 177 patients with 353 coronary arteries was analyzed. Mean annulus diameters (22.8 ± 2.8 mm and 23.4 ± 1.0 mm, p > 0.05) and mean sinus of Valsalva (SOV) diameters (31.2 ± 3.6 mm and 31.9 ± 3.6 mm, p > 0.05) were similar between patients with lower and higher coronary heights, respectively. There were three coronary obstruction cases. ELOD ≤ 2 mm in combination with leaflet length longer than mid-ostial height allowed for discrimination of cases with and without coronary obstruction. There was a significant association between coronary obstruction event and ELOD ≤ 2 mm (log OR = 6.180, p < 0.001). CONCLUSIONS: Our study showed that a combination of ELOD < 2 mm and a longer leaflet length than mid-ostial height may be associated with increased risk for coronary obstruction during TAVR.
RESUMEN
BACKGROUND: Women have a higher rate of adverse events after mitral valve surgery. We sought to evaluate whether outcomes after transcatheter edge-to-edge repair intervention by sex have similar trends to mitral valve surgery. METHODS: The primary outcome was 1-year major adverse events defined as a composite of all-cause mortality, stroke, and any bleeding in the overall study cohort. Patients who underwent transcatheter edge-to-edge repair for mitral regurgitation with the MitraClip system in the Society of Thoracic Surgery/American College of Cardiology Transcatheter Valve Therapy registry were evaluated. Linked administrative claims from the Centers for Medicare and Medicaid Services were used to evaluate 1-year clinical outcomes. Associations between sex and outcomes were evaluated using a multivariable logistic regression model for in-hospital outcomes and Cox model for 1-year outcomes. RESULTS: From November 2013 to March 2017, 5295 patients, 47.6% (n=2523) of whom were female, underwent transcatheter edge-to-edge repair. Females were less likely to have >1 clip implanted (P<0.001) and had a lower adjusted odds ratio of device success (adjusted odds ratio, 0.78 [95% CI, 0.67-0.90]), driven by lower odds of residual mitral gradient <5 mm Hg (adjusted odds ratio, 0.54 [CI, 0.46-0.63]) when compared with males. At 1-year follow-up, the primary outcome did not differ by sex. Female sex was associated with lower adjusted 1-year risk of all-cause mortality (adjusted hazard ratio, 0.80 [CI, 0.68-0.94]), but the adjusted 1-year risk of stroke and any bleeding did not differ by sex. CONCLUSIONS: No difference in composite outcome of all-cause mortality, stroke, and any bleeding was observed between females and males. Adjusted 1-year all-cause mortality was lower in females compared with males.
Asunto(s)
Implantación de Prótesis de Válvulas Cardíacas , Insuficiencia de la Válvula Mitral , Anciano , Femenino , Implantación de Prótesis de Válvulas Cardíacas/efectos adversos , Humanos , Masculino , Medicare , Insuficiencia de la Válvula Mitral/diagnóstico por imagen , Insuficiencia de la Válvula Mitral/epidemiología , Insuficiencia de la Válvula Mitral/cirugía , Sistema de Registros , Resultado del Tratamiento , Estados Unidos/epidemiologíaRESUMEN
The landmark results of the low surgical risk pivotal transcatheter aortic valve replacement (TAVR) trials fueled speculation that the role of surgical aortic valve replacement (SAVR) would be limited in the future. Instead, the field has pivoted away from reductive surgical risk stratification toward understanding the complex interplay of anatomy, timing, and surgical risk to optimize the lifetime management of aortic stenosis. In this review, we systematically explore the subtleties that influence the choice between TAVR and surgery in the low-risk TAVR era.
Asunto(s)
Estenosis de la Válvula Aórtica , Implantación de Prótesis de Válvulas Cardíacas , Reemplazo de la Válvula Aórtica Transcatéter , Válvula Aórtica/cirugía , Estenosis de la Válvula Aórtica/cirugía , Humanos , Resultado del TratamientoRESUMEN
Background Transesophageal echocardiogram is currently the standard preprocedural imaging for left atrial appendage occlusion. This study aimed to assess the additive value of preprocedural computed tomography (CT) planning versus stand-alone transesophageal echocardiogram imaging guidance to left atrial appendage occlusion. Methods and Results We retrospectively reviewed 485 Watchman implantations at a single center to compare the outcomes of using additional CT preprocedural planning (n=328, 67.6%) versus stand-alone transesophageal echocardiogram guidance (n=157, 32.4%) for left atrial appendage occlusion. The primary end point was the rate of successful device implantation without major peri-device leak (>5 mm). Secondary end points included major adverse events, total procedural time, delivery sheath and devices used, risk of major peri-device leak and device-related thrombus at follow-up imaging. A single/anterior-curve delivery sheath was used more commonly in those who underwent CT imaging (35.9% versus 18.8%; P<0.001). Additional preprocedural CT planning was associated with a significantly higher successful device implantation rate (98.5% versus 94.9%; P=0.02), a shorter procedural time (median, 45.5 minutes versus 51.0 minutes; P=0.03) and a less frequent change of device size (5.6% versus 12.1%; P=0.01), particularly device upsize (4% versus 9.4%; P=0.02). However, there was no significant difference in the risk of major adverse events (2.1% versus 1.9%; P=0.87). Only 1 significant peri-device leak (0.2%) and 5 device-related thrombi were detected in follow-up (1.2%) with no intergroup difference. Conclusions Additional preprocedural planning using CT in Watchman implantation was associated with a higher successful device implantation rate, a shorter total procedural time, and a less frequent change of device sizes.
Asunto(s)
Apéndice Atrial , Fibrilación Atrial , Ecocardiografía Transesofágica , Trombosis , Tomografía Computarizada por Rayos X , Apéndice Atrial/diagnóstico por imagen , Apéndice Atrial/cirugía , Fibrilación Atrial/diagnóstico por imagen , Fibrilación Atrial/cirugía , Cateterismo Cardíaco , Humanos , Estudios Retrospectivos , Trombosis/diagnóstico por imagen , Trombosis/etiología , Resultado del TratamientoRESUMEN
INTRODUCTION: Hydroxychloroquine has been used for rheumatological diseases for many decades and is considered a safe medication. With the COVID-19 outbreak, there has been an increase in reports associating cardiotoxicity with hydroxychloroquine. It is unclear if the cardiotoxic profile of hydroxychloroquine is previously underreported in the literature or is it a manifestation of COVID-19 and therapeutic interventions. This manuscript evaluates the incidence of cardiotoxicity associated with hydroxychloroquine prior to the onset of COVID-19. METHODS: PubMED, EMBASE, and Cochrane databases were searched for keywords derived from MeSH terms prior to April 9, 2020. Inclusion eligibility was based on appropriate reporting of cardiac conditions and study design. RESULTS: A total of 69 articles were identified (58 case reports, 11 case series). The majority (84%) of patients were female, with a median age of 49.2 (range 16-92) years. 15 of 185 patients with cardiotoxic events were in the setting of acute intentional overdose. In acute overdose, the median ingestion was 17,857 ± 14,873 mg. 2 of 15 patients died after acute intoxication. In patients with long-term hydroxychloroquine use (10.5 ± 8.9 years), new onset systolic heart failure occurred in 54 of 155 patients (35%) with median cumulative ingestion of 1,493,800 ± 995,517 mg. The majority of patients improved with the withdrawal of hydroxychloroquine and standard therapy. CONCLUSION: Millions of hydroxychloroquine doses are prescribed annually. Prior to the COVID-19 pandemic, cardiac complications attributed to hydroxychloroquine were uncommon. Further studies are needed to understand the impact of COVID-19 on the cardiovascular system to understand the presence or absence of potential medication interactions with hydroxychloroquine in this new pathophysiological state.
Asunto(s)
Cardiotoxinas/efectos adversos , Cardiopatías , Hidroxicloroquina/efectos adversos , Adolescente , Adulto , Anciano , Anciano de 80 o más Años , COVID-19 , Femenino , Cardiopatías/inducido químicamente , Cardiopatías/epidemiología , Humanos , Masculino , Persona de Mediana Edad , Adulto JovenRESUMEN
BACKGROUND: Detailed procedural analysis and long-term data is limited for coronary protection (CP) during transcatheter aortic valve replacement (TAVR) for patients with high anatomical risk for coronary occlusion (CO). We aim to assess the procedural and mid-term outcomes of CP during TAVR. METHODS: We retrospectively analyzed patients who underwent TAVR at Henry Ford Hospital, USA from January 2015 to August 2019 and identified those considered at risk of CO and underwent pre-emptive CP with or without subsequent "chimney" stenting (i.e. coronary stenting with intentional protrusion into the aorta). Procedural features, immediate and mid-term clinical outcomes were reviewed. RESULTS: Twenty-five out of 1166 (2.1%) patients underwent TAVR with CP, including 10 (40%) valve-in-valve procedures. Twenty-eight coronary arteries (Left: n = 11, Right: n = 11; Left + Right: n = 3) were protected. Eleven coronaries (39.3%) were electively "chimney"-stented due to angiographic evidence of coronary impingement (63.6%), tactile resistance while withdrawing stent (27.3%) and electrocardiogram change (9.1%). Twenty-four patients (24/25, 96%) had successful TAVR without CO. Procedure-related complications included stent-balloon entrapment (n = 1), stent entrapment (n = 1) and occlusive distal stent edge dissection (n = 1). After a mean follow-up of 19.1 months, there was 1 cardiac death but no target vessel re-intervention or myocardial infarction. CONCLUSIONS: Our study found that angiographic evidence of coronary impingement (63.6%) was the most common reason for stent deployment during TAVR with CP. The mid-term clinical outcome of CP with TAVR was favorable.
Asunto(s)
Estenosis de la Válvula Aórtica , Oclusión Coronaria , Reemplazo de la Válvula Aórtica Transcatéter , Válvula Aórtica/diagnóstico por imagen , Válvula Aórtica/cirugía , Estenosis de la Válvula Aórtica/diagnóstico por imagen , Estenosis de la Válvula Aórtica/cirugía , Oclusión Coronaria/diagnóstico por imagen , Oclusión Coronaria/cirugía , Humanos , Estudios Retrospectivos , Factores de Riesgo , Reemplazo de la Válvula Aórtica Transcatéter/efectos adversos , Resultado del TratamientoAsunto(s)
Estenosis de la Válvula Aórtica , Válvula Aórtica , Valvuloplastia con Balón , Prótesis Valvulares Cardíacas , Reemplazo de la Válvula Aórtica Transcatéter , Válvula Aórtica/cirugía , Estenosis de la Válvula Aórtica/cirugía , Humanos , Diseño de Prótesis , Factores de Riesgo , Resultado del TratamientoAsunto(s)
Embolia Intracraneal , Estenosis de la Válvula Aórtica/cirugía , Humanos , Imagenología Tridimensional , Embolia Intracraneal/diagnóstico por imagen , Valor Predictivo de las Pruebas , Tomografía Computarizada por Rayos X , Reemplazo de la Válvula Aórtica Transcatéter , Resultado del TratamientoRESUMEN
OBJECTIVES: To evaluate whether a preoperative diagnosis of atrial septal defect (ASD) or patent foramen ovale (PFO) is associated with perioperative stroke in noncardiac surgery and their outcomes. DESIGN: Retrospective cohort analysis. SETTING: United States hospitals. PARTICIPANTS: Adults patients (≥18 years old) who underwent major noncardiac surgery from 2010 to 2015 were identified using the Healthcare Cost and Utilization Project's National Readmission Database. INTERVENTIONS: Preoperative diagnosis of ASD or patent foramen ovale. MEASUREMENTS AND MAIN RESULTS: Among the 19,659,161 hospitalizations for major noncardiac surgery analyzed, 12,248 (0.06%) had a preoperative diagnosis of ASD/PFO. Perioperative ischemic stroke occurred in 723 (5.9%) of patients with ASD/PFO and 373,291 (0.02%) of those without ASD/PFO (adjusted odds ratio [aOR], 16.7; 95% confidence interval [CI]: 13.9-20.0). Amongst the different types of noncardiac surgeries, obstetric, endocrine, and skin and burn surgery were associated with higher risk of stroke in patients with pre-existing ASD/PFO. Moreover, patients with ASD/PFO also had an increased in-hospital mortality (aOR, 4.6, 95% CI: 3.6-6.0), 30-day readmission (aOR, 1.2, 95% CI: 1.04-1.38), and 30-day stroke (aOR, 7.2, 95% CI: 3.1-16.6). After adjusting for atrial fibrillation, ischemic stroke remained significantly high in the ASD/PFO group (aOR: 23.7, 95%CI 19.4-28.9), as well as in-hospital mortality (aOR: 5.6, 95% CI 4.1-7.7), 30-day readmission (aOR: 1.19, 95%CI 1.0-1.4), and 30-day stroke (aOR: 9.3, 95% CI 3.7-23.6). CONCLUSIONS: Among adult patients undergoing major noncardiac surgery, pre-existing ASD/PFO is associated with increased risk of perioperative ischemic stroke, in-hospital mortality, 30-day stroke, and 30-day readmission after surgery.
Asunto(s)
Isquemia Encefálica , Foramen Oval Permeable , Accidente Cerebrovascular Isquémico , Accidente Cerebrovascular , Adolescente , Adulto , Isquemia Encefálica/diagnóstico , Isquemia Encefálica/epidemiología , Isquemia Encefálica/etiología , Foramen Oval Permeable/complicaciones , Foramen Oval Permeable/diagnóstico , Foramen Oval Permeable/epidemiología , Humanos , Estudios Retrospectivos , Factores de Riesgo , Accidente Cerebrovascular/diagnóstico , Accidente Cerebrovascular/epidemiología , Accidente Cerebrovascular/etiología , Estados UnidosAsunto(s)
Insuficiencia de la Válvula Aórtica , Estenosis de la Válvula Aórtica , Implantación de Prótesis de Válvulas Cardíacas , Prótesis Valvulares Cardíacas , Reemplazo de la Válvula Aórtica Transcatéter , Válvula Aórtica/diagnóstico por imagen , Válvula Aórtica/cirugía , Insuficiencia de la Válvula Aórtica/diagnóstico por imagen , Insuficiencia de la Válvula Aórtica/etiología , Insuficiencia de la Válvula Aórtica/cirugía , Estenosis de la Válvula Aórtica/diagnóstico por imagen , Estenosis de la Válvula Aórtica/cirugía , Cateterismo Cardíaco/efectos adversos , Prótesis Valvulares Cardíacas/efectos adversos , Implantación de Prótesis de Válvulas Cardíacas/efectos adversos , Humanos , Reemplazo de la Válvula Aórtica Transcatéter/efectos adversosAsunto(s)
Válvula Aórtica/cirugía , Cateterismo Cardíaco , Implantación de Prótesis de Válvulas Cardíacas/instrumentación , Prótesis Valvulares Cardíacas , Válvula Mitral/cirugía , Complicaciones Posoperatorias/terapia , Reemplazo de la Válvula Aórtica Transcatéter/instrumentación , Anciano , Válvula Aórtica/diagnóstico por imagen , Válvula Aórtica/fisiopatología , Valvuloplastia con Balón , Implantación de Prótesis de Válvulas Cardíacas/efectos adversos , Hemodinámica , Humanos , Válvula Mitral/diagnóstico por imagen , Válvula Mitral/fisiopatología , Complicaciones Posoperatorias/diagnóstico por imagen , Complicaciones Posoperatorias/fisiopatología , Diseño de Prótesis , Reemplazo de la Válvula Aórtica Transcatéter/efectos adversos , Resultado del TratamientoRESUMEN
Spontaneous coronary artery dissection is an increasingly recognized cause of acute coronary syndrome in younger patients. Management remains challenging and involves weighing the benefits of revascularization with the potential to worsen the dissection. We present a case of spontaneous coronary artery dissection with the superimposed complexity of an anomalous intramural coronary artery. (Level of Difficulty: Intermediate.).
RESUMEN
Current remote monitoring devices for heart failure have been shown to reduce hospitalizations but are invasive and costly; accurate non-invasive options remain limited. The EuleriAn Video Magnification ApPLications In Heart Failure StudY (AMPLIFY) pilot aimed to evaluate the accuracy of a novel noninvasive method that uses Eulerian video magnification. Video recordings were performed on the neck veins of 50 patients who were scheduled for right heart catheterization at the Palo Alto VA Medical Center. The recorded jugular venous pulsations were then enhanced by applying Eulerian phase-based motion magnification. Assessment of jugular venous pressure was compared across three categories: (1) physicians who performed bedside exams, (2) physicians who reviewed both the amplified and unamplified videos, and (3) direct invasive measurement of right atrial pressure from right heart catheterization. Motion magnification reduced inaccuracy of the clinician assessment of central venous pressure compared to the gold standard of right heart catheterization (mean discrepancy of -0.80 cm H2O; 95% CI -2.189 to 0.612, p = 0.27) when compared to both unamplified video (-1.84 cm H2O; 95% CI -3.22 to -0.46, p = 0.0096) and the bedside exam (-2.90 cm H2O; 95% CI -4.33 to 1.40, p = 0.0002). Major categorical disagreements with right heart catheterization were significantly reduced with motion magnification (12%) when compared to unamplified video (25%) or the bedside exam (27%). This novel method of assessing jugular venous pressure improves the accuracy of the clinical exam and may enable accurate remote monitoring of heart failure patients with minimal patient risk.
RESUMEN
Since the first-in-man transcatheter delivery of an aortic valve prosthesis in 2002, the landscape of aortic stenosis therapeutics has shifted dramatically. While initially restricted to non-surgical cases, progressive advances in transcatheter aortic valve replacement and our understanding of its safety and efficacy have expanded its use in intermediate and possibly low surgical risk patients. In this review, we explore the past, present, and future of transcatheter aortic valve replacement.