Mitral Research Articles

Mitral valve regurgitation followed by blunt chest trauma in a paediatric patient: a case report.

We report a paediatric case where severe mitral valve regurgitation occurred led by blunt chest trauma. Medical treatment was undertaken, and surgical mitral valve repair was postponed until half a year after the initial injury, followed by an uneventful postoperative recovery. We highlight the importance of echocardiographic evaluation for traumatic valve insufficiency. The medical strategy and timing of surgical intervention should be individualised.

Permanent pacemaker implantation after concomitant mitral and tricuspid valve surgery.

Permanent pacemaker implantation after concomitant mitral and tricuspid valve surgery.

A Technique Avoiding Cardioplegia Delivery Complications: A Case Using Systemic Hyperkalemia Cardiopulmonary Bypass Combined with Circulatory Arrest

We conducted a high-risk redo mitral valve replacement through a right mini-thoracotomy without rib spreading (redo-MICS MVR) under systemic hyperkalemia combined with circulatory arrest to circumvent complications associated with cardioplegia delivery. The patient, a 75-year-old man, had a predicted mortality rate of 20%. Initial antegrade cardioplegia successfully induced cardiac arrest, which was administered every 30 minutes. However, upon infusion of the second dose of cardioplegia, the aortic root pressure was approximately 20 mmHg. Despite multiple attempts to re-cross clamp, the aortic root pressure did not improve. Consequently, retrograde cardioplegia was considered, but due to significant adhesion of the inferior vena cava, this approach was abandoned. Thus, the procedure was altered to utilize systemic hyperkalemia without aortic cross-clamping. Given the preoperative transesophageal echocardiography (TEE) diagnosis of mild aortic regurgitation, maintaining a clear surgical field was challenging, necessitating the combination of redo-MVR with circulatory arrest. This case exemplifies the successful management of cardioplegia delivery complications using systemic hyperkalemia and circulatory arrest, resulting in a favorable postoperative recovery for the patient.

The Role of Global Longitudinal Strain in Predicting Left Ventricular Reverse Remodeling After Mitral Valve Replacement Surgery in Patients With Primary Mitral Regurgitation.

This study aimed to identify the utility of global longitudinal strain (GLS) as a reliable parameter that can accurately forecast left ventricle reverse remodeling (LVRR) in patients undergoing valve replacement surgery for severe chronic primary mitral regurgitation (MR), thereby aiding in assessing mortality and morbidity risk. This retrospective observational study involved severe primary MR patients who underwent valve replacement surgery between 2018 and 2023. Pre- and postsurgery echocardiography data were collected, with GLS measurements utilized to assess left ventricular function. Various echocardiography parameters, including MR severity and LV dimensions, were analyzed. Bivariate and multivariate analyses were performed to explore relationships between GLS and LVRR. This study enrolled 103 patients (54.4% male; mean age 45.4 ± 13.6 years). Statistical analyses revealed GLS to be an independent predictor of LVRR, with a threshold of -16.25% showing 89% sensitivity and 50% specificity. Each 1% increase in GLS corresponded to a 1.14-fold (odds ratio [OR]: 1.14; 95% confidence interval [CI]: 1.01-1.31; p<0.05) increased likelihood of LVRR. These findings highlight GLS's potential as a prognostic marker for postsurgical outcomes in severe MR patients.

Minimally Invasive Mitral Valve Surgery in Elderly Patients: Results from a Multicenter Study

Background: Minimally invasive mitral valve surgery (MIMVS) has been increasingly adopted worldwide as an alternative to conventional sternotomy, especially for young patients. The remarkable results gained by MIMVS have encouraged its application in more complex and fragile patients, such as the elderly, though results in this subgroup remain controversial. It is the aim of this study to assess the postoperative outcomes of patients older than 75 years old undergoing MIMVS, and to compare these results to those of younger patients. Methods: The data of all patients undergoing MIMVS between 2015 and 2022 were retrospectively collected at seven high-volume cardiac surgery centers. Patients were divided into two age-based groups: the young (&lt;65 years old) and the elderly (&gt;75 years old). A propensity score (PS) matching analysis obtained two comparable groups. Postoperative outcomes were assessed in both the unmatched and PS-matched populations. Results: Out of 1113 patients undergoing MIMVS, 524 were young and 279 were elderly. Elderly patients were more commonly affected by multiple comorbidities, with a higher EuroSCORE II (4.6 ± 5.5% vs. 1.6 ± 3.3%, p &lt; 0.001). There was no difference in postoperative mortality, though the elderly had a greater incidence of postoperative complications, such as re-exploration for bleeding, stroke, reintubation, and a need for hemodialysis and blood transfusions. After PS matching, 119 pairs of young and elderly patients with similar risk profiles (EuroSCORE II 2.5 ± 4.7% vs. 2.7 ± 3.2%, p = 0.7) were compared, and no differences in all postoperative outcomes were found. Conclusions: Adequately selected elderly patients can report hospital outcomes similar to young patients after MIMVS.

Feasibility validation of automatic diagnosis of mitral valve prolapse from multi-view echocardiographic sequences based on deep neural network

Abstract Aims To address the limitations of traditional diagnostic methods for mitral valve prolapse (MVP), specifically fibroelastic deficiency (FED) and Barlow’s disease (BD), by introducing an automated diagnostic approach utilizing multi-view echocardiographic sequences and deep learning. Methods and results An echocardiographic data set, collected from Zhongshan Hospital, Fudan University, containing apical 2 chambers (A2C), apical 3 chambers (A3C), and apical 4 chambers (A4C) views, was employed to train the deep learning models. We separately trained view-specific and view-agnostic deep neural network models, which were denoted as MVP-VS and MVP view-agonistic (VA), for MVP diagnosis. Diagnostic accuracy, precision, sensitivity, F1-score, and specificity were evaluated for both BD and FED phenotypes. MVP-VS demonstrated an overall diagnostic accuracy of 0.94 for MVP. In the context of BD diagnosis, precision, sensitivity, F1-score, and specificity were 0.83, 1.00, 0.90, and 0.92, respectively. For FED diagnosis, the metrics were 1.00, 0.83, 0.91, and 1.00. MVP-VA exhibited an overall accuracy of 0.95, with BD-specific metrics of 0.85, 1.00, 0.92, and 0.94 and FED-specific metrics of 1.00, 0.83, 0.91, and 1.00. In particular, the MVP-VA model using mixed views for training demonstrated efficient diagnostic performance, eliminating the need for repeated development of MVP-VS models and improving the efficiency of the clinical pipeline by using arbitrary views in the deep learning model. Conclusion This study pioneers the integration of artificial intelligence into MVP diagnosis and demonstrates the effectiveness of deep neural networks in overcoming the challenges of traditional diagnostic methods. The efficiency and accuracy of the proposed automated approach suggest its potential for clinical applications in the diagnosis of valvular heart disease.

Reference Ranges and Z-Score Equations for 19 Fetal Cardiac Biometry Structures From 18 to 34 Weeks' Gestation.

To determine equations for calculating the Z-scores of fetal cardiac structures between 18+0 and 34+6 weeks of gestation, create percentile reference tables and curves for the structures, and assess the intra- and inter-observer reproducibility of the measurements. A cross-sectional study was conducted involving 340 normal fetuses from singleton pregnancies between 18 and 34 weeks of gestational age (GA). Nineteen cardiac structures were evaluated: diameters of the mitral, tricuspid, aortic, and pulmonary valve annuli; length, diameter, and area of the left and right ventricles; cardiac area and circumference; and diameters of the ascending aorta, aortic isthmus, main pulmonary artery, right pulmonary artery, left pulmonary artery, and ductus arteriosus. Regression analysis was performed to determine the equations for the mean and standard deviation of all structures using GA, biparietal diameter (BPD), and femur length (FL) as independent variables. All equations had high coefficients of determination (R2). The best performance was achieved using the GA (R2 .819-.944), followed by FL (R2 .813-.937) and BPD (R2 .792-.934). The structure that demonstrated the highest R2 was the cardiac circumference and the smallest was the ductus arteriosus. Reference tables of percentiles 1, 5, 10, 50, 90, 95, and 99, and reference curves of Z-scores were created for all 19 cardiac structures, depending on the GA. All measurements demonstrated good and excellent reproducibility with an inter-observer intraclass correlation coefficient (ICC) of 0.774-0.972 and intra-observer ICC of 0.938-0.993. Equations were produced to calculate Z-scores as well as percentile tables and curves for 19 fetal heart structures. All the measurements demonstrated good reproducibility.

Transcatheter edge-to-edge repair for acute mitral valve regurgitation due to papillary muscle rupture in cardiogenic shock patient with acute myocardial infarction.

Transcatheter edge-to-edge repair for acute mitral valve regurgitation due to papillary muscle rupture in cardiogenic shock patient with acute myocardial infarction.

Lower Levels of Vitamin D Are Associated with Higher Vasoactive–Inotropic Scores in Major Cardiac Surgery

Background: The vasoactive–inotropic score (VIS) predicts unfavorable outcomes after cardiac surgery in both children and adults. In our adult population, we investigated whether preoperative levels of vitamin D can predict the VIS and whether both vitamin D and the VIS can predict adverse outcomes following major heart surgery. Methods: Between 1 October 2021 and 28 February 2022, 300 patients underwent major cardiac surgery at our institution. Eighty-three of them had their 25-OH vitamin D levels measured before surgery. For this cohort, we calculated the VIS based on doses of vasoactive and inotropic medications administered post-surgery. Utilizing receiver operating curves, the predictive accuracy of vitamin D levels and the VIS in predicting acute kidney injury was assessed. Results: The median age of the cohort was 66 (IQR 61–71) years, with 59% being male and a median BMI of 28.4 (IQR 25.2–31.6). The most common procedures were aortic valve replacement, mitral valve replacement, coronary artery bypass grafting, aortic valve and ascending aorta repair, and ASD correction. There was a significant difference in the postoperative VIS between patients with vitamin D deficiency, i.e., &lt;20 ng/mL, and patients with vitamin D values &gt; 20 ng/mL (3.5 vs. 1.3 p &lt; 0.04). We also found a significant correlation between the VIS and the days of hospitalization (r = 0.335; p = 0.002), the days of stay in the intensive care unit (r = 0.547; p &lt; 0.00001), and the mechanical ventilation time (r = 0.327; p = 0.025). Both vitamin D levels and the VIS predicted postoperative acute kidney injury (p &lt; 0.05). Conclusions: Vitamin D deficiency is correlated with the VIS in adults undergoing major cardiac surgery. Both vitamin D levels and the VIS can predict unfavorable postoperative outcomes.

Indirect-Oscillation Sign Suggesting Infective Endocarditis on the Routine Chest CT.

Routine chest CT is not essential for the diagnostic workup for infective endocarditis (IE), but this type of study may be the initial imaging modality in the evaluation of patients ultimately proven to have IE who present to the emergency department with nonspecific clinical symptoms. Although routine chest CT cannot directly assess valvular oscillating motion due to the lack of cine images, we hypothesized that a combination of elongated nodular valve thickening and abnormal orientation to the normal valve with a blind end on routine CT (indirect-oscillation sign) might suggest movable vegetation indirectly. To evaluate this possibility, we studied 27 patients with IE and 35 controls who underwent both routine chest CT and echocardiography. CT scanning was initiated following a delay of 60-80 s after the administration of the contrast medium. Two cardiothoracic radiologists retrospectively analyzed the CT images to assess the indirect-oscillation sign with consensus. The sensitivity, specificity, positive predictive value, and negative predictive value of the indirect-oscillation sign on routine chest CT were 29.6% (8/27), 100% (35/35), 100% (8/8), and 64.8% (35/54), respectively. Although uncommon, the presence of the indirect-oscillation sign involving the aortic or mitral valve on routine chest CT is a suggestive finding for IE.

Early structural valve deterioration following transcatheter aortic valve implantation in a patient with Scheie syndrome: a case report

BackgroundScheie syndrome, an attenuated subtype of mucopolysaccharidosis type I, is a rare storage disease that causes progressive glycosaminoglycans (GAGs) accumulation. Cardiovascular disorders determine the prognosis, and cardiac valve abnormalities are the most common cause. The patients are usually young so mechanical valve replacement is often performed, but because of the features of this disease, the surgical treatment is very risky. Recently, transcatheter aortic valve implantation (TAVI) has been reported as an alternative choice for aortic stenosis, but optimal choice is still unclear. Here, we introduce a patient that underwent TAVI and refer to the histological finding of a biological valve extracted in relation to GAGs accumulation.Case presentationA 54-year-old woman with Scheie syndrome underwent valve surgeries three times throughout her whole life. At age 41, she received a mitral valve replacement with a mechanical valve for mitral stenosis. She promptly developed severe diastolic dysfunction and low output syndrome after the release of aortic clamping, thus requiring temporary mechanical circulatory support4. At age 51, she suffered from heart failure due to severe aortic stenosis and underwent TAVI because conventional aortic valve replacement (AVR) was deemed too risky. Three years later, her heart failure relapsed, and an echocardiogram unexpectedly revealed thickened bioprosthetic valve leaflets and a significant pressure gradient across the valve, consistent with early structural valve deterioration. AVR was performed via median sternotomy with a mechanical valve. As with the first operation, she presented refractory heart failure requiring mechanical circulatory support and was meticulously managed. However, she steadily showed worsening of multiple organ systems and died 9 days after the operation. Pathological autopsy and histological examination revealed accumulation of tissue with GAGs on the leaflets of the bioprosthetic valve of TAVI, which may have been the cause of early structural valve deterioration.ConclusionFor patients with Scheie syndrome, a biological valve can be compromised by the accumulation of GAGs, thereby causing early SVD. These findings may support valve selection for these high-risk patients.

Clinical, laboratory, and echocardiographic characteristics of critical multisystem inflammatory syndrome in children: a retrospective, observational study

ObjectiveMultisystem inflammatory syndrome in children (MIS-C) is a critical childhood disease that is associated with coronavirus disease (COVID-19). We aimed to describe the clinical, laboratory, and echocardiographic characteristics and outcome of critical MIS-C cases in Egyptian children during the first wave of the COVID-19 pandemic.DesignA retrospective, observational study.SettingA single-center tertiary pediatric intensive care unit (PICU).In Ain Shams university hospitals Cairo EgyptMethodsChildren admitted to the PICU diagnosed with severe MIS-C as per the Centers for Disease Control’s definition from June 23, 2020, to August 22, 2020, were included.ResultsThe patient’s mean age was 7.45 (interquartile range [IQR], 4.23) years, and the cause of PICU admission was hypotension and shock. All patients had a fever for 4.8 (IQR, 2.5) days before shock developed. Overall, 68% had a gastrointestinal manifestation, and 55.6% had a rash. Thirty-five of 45 patients had ≥ 4 elevated inflammatory markers. The cardiac troponin I level was elevated in 35 of 45 patients. The most common cardiac condition was valvulitis (tricuspid regurgitation, 29/45; mitral valve regurgitation, 28/45; pulmonary valve regurgitation, 5/45; atrial valve regurgitation, 4/45). Twenty-one patients had an impaired ejection fraction < 50%, and 17 patients had coronary dilatation. Six patients had pericardial effusion, 1 patient had dilated pulmonary arteries, and 6 patients (13.3%) died of their associated comorbidities. The mean PICU length of stay among patients with no associated comorbidities was 7 days.ConclusionsCritical cases of MIS-C had a spectrum of different cardiac conditions, with valvulitis being the most common one. The worst outcome occurred in patients with comorbidities and infants.

A machine-learning algorithm to grade heart murmurs and stage preclinical myxomatous mitral valve disease in dogs.

The presence and intensity of heart murmurs are sensitive indicators of several cardiac diseases in dogs, particularly myxomatous mitral valve disease (MMVD), but accurate interpretation requires substantial clinical expertise. Assess if a machine-learning algorithm can be trained to accurately detect and grade heart murmurs in dogs and detect cardiac disease in electronic stethoscope recordings. Dogs (n = 756) with and without cardiac disease attending referral centers in the United Kingdom. All dogs received full physical and echocardiographic examinations by a cardiologist to grade any murmurs and identify cardiac disease. A recurrent neural network algorithm, originally trained for heart murmur detection in humans, was fine-tuned on a subset of the dog data to predict the cardiologist's murmur grade from the audio recordings. The algorithm detected murmurs of any grade with a sensitivity of 87.9% (95% confidence interval [CI], 83.8%-92.1%) and a specificity of 81.7% (95% CI, 72.8%-89.0%). The predicted grade exactly matched the cardiologist's grade in 57.0% of recordings (95% CI, 52.8%-61.0%). The algorithm's prediction of loud or thrilling murmurs effectively differentiated between stage B1 and B2 preclinical MMVD (area under the curve [AUC], 0.861; 95% CI, 0.791-0.922), with a sensitivity of 81.4% (95% CI, 68.3%-93.3%) and a specificity of 73.9% (95% CI, 61.5%-84.9%). A machine-learning algorithm trained on humans can be successfully adapted to grade heart murmurs in dogs caused by common cardiac diseases, and assist in differentiating preclinical MMVD. The model is a promising tool to enable accurate, low-cost screening in primary care.

Cost-effectiveness analysis of valvular surgery in high- and low- to middle-income countries: A scoping review.

Global disparities in valvular surgery services exist. Cost-effectiveness analysis (CEA) and cost-utility analysis can be used to guide national investment decisions. This scoping review aims to synthesize economic evaluations for valvular surgery by income settings and provide recommendations. A systematic literature review identified primary CEAs or CUAs in English comparing surgical management strategies for valvular heart disease. MEDLINE, Embase, CINAHL, Web of Science, and Business Source Complete were searched using keywords "valvular surgery," "valve disease," "cost-effectiveness," and "cost-benefit analysis". Articles comparing outcomes or costs only were excluded. Search results were uploaded and screened on COVIDENCE. Variables from eligible articles were charted in a spreadsheet. Twenty articles were eligible, six from low- and middle-income countries (LMICs) and 14 from high-income countries (HICs). In HICs, the top conditions were degenerative aortic valve disease (7/14) and mitral valve disease (4/14) compared to congenital (2/6) and rheumatic heart diseases (2/6) in LMICs. HICs evaluated new technologies and techniques, whereas LMICs compared different valve types or surgery versus no intervention. Most articles used published studies (12/20) or databases (7/20) to conduct their CEA and quality-adjusted life years was the most common effectiveness measure (12/20). Comparator interventions were cost-effective in all LMIC articles and in 8/14 for HICs. Economic evaluations are mostly conducted in HICs and for adult conditions. More analyses in LMICs are needed. This can be facilitated by maintaining databases, documenting costs, and implementing quality of life assessments.

Meta-analysis of improved mitral regurgitation after aortic valve replacement.

This meta-analysis aimed to compare survival outcomes among patients experiencing improvement in untreated significant mitral regurgitation (MR) following surgical aortic valve replacement (SAVR) or transcatheter aortic valve replacement (TAVR) for severe aortic stenosis, in contrast to those without improvement. We conducted a comprehensive search through February 2024. Pooled hazard ratios (HR) with 95% confidence intervals (CI) were computed. Kaplan-Meier curves depicting all-cause mortality were reconstructed using individual patient data derived from the included studies. A systematic review identified twelve non-randomized studies encompassing 4040 patients. The pooled all-cause mortality of the meta-analysis demonstrated a significant reduction in patients whose MR improved compared to those with persistent MR after aortic valve replacement (AVR) (HR [95% CI] = 0.55 [0.47-0.64], p < .01). The hazard ratio, derived from reconstructed time-to-event data, indicated lower all-cause mortality in patients with improved MR after AVR relative to the other cohort (HR [95% CI] = 0.50 [0.40-0.62], p < .01 in all patients, 0.48 [0.34-0.68], p < .01 in patients undergoing SAVR, and 0.58 [0.42-0.80], p < .01 in those receiving TAVR). In conclusion, this meta-analysis revealed that improved MR after AVR, whether surgically or by transcatheter approach, correlates with superior survival. The benefits of simultaneous or staged intervention on the mitral valve in individuals undergoing AVR warrant validation in future investigations.

Aortic root parameter analysis for transcatheter aortic valve implantation in the Pakistani population: a retrospective study

BackgroundTranscatheter aortic valve implantation (TAVI) is a growing treatment for aortic stenosis, but anatomical variations exist across populations. Asians tend to have smaller aortic annuli and higher bicuspid valve morphology compared to Westerners, potentially impacting TAVI valve selection and outcomes. This study analyzes aortic root parameters in Pakistani patients undergoing TAVI.ResultsWe conducted a retrospective analysis of 78 patients who underwent TAVI at the Peshawar Institute of Cardiology from January 2021 to March 2024. Pre-procedural CT scans were analyzed for aortic annulus diameters, area, and other relevant parameters. The mean age was 72.41 years (SD ± 11.99), and 61.5% were male. Aortic annulus diameters (minimum, mean, maximum) were 21.18 mm (SD ± 3.99), 24.21 mm (SD ± 3.93), and 27.49 mm (SD ± 4.43), respectively. Bicuspid aortic valves were present in 34.61% of patients.ConclusionsOur findings suggest that Pakistani patients undergoing TAVI may have aortic root dimensions comparable to Western populations, with a substantial prevalence of bicuspid valves. However, coronary heights were similar to those reported in Asian populations with smaller annuli. Further studies are needed to assess TAVI outcomes in Pakistani patients and determine if tailored valve sizing strategies are required.

Mitral Annular Disjunction in Heritable Thoracic Aortic Disease: Insights From the Montalcino Aortic Consortium.

Mitral annular disjunction (MAD), posterior displacement of the mitral valve leaflet hinge point, predisposes to arrhythmias or sudden cardiac death. We evaluated the burden of MAD, mitral valve prolapse (MVP), and mitral regurgitation (MR) by heritable thoracic aortic disease gene in a cross-sectional analysis of 2014-2023 data in the Montalcino Aortic Consortium registry. MAD was determined by direct measurement of echocardiographic images. MR and MVP were defined according to current clinical guidelines. Associations were evaluated using χ2 or Fisher exact tests. MR and MVP were enriched in Montalcino Aortic Consortium participants (672) with pathogenic variants (PV) in transforming growth factor-β pathway genes. The combination of MR and MVP was associated with mitral surgery and arrhythmias. In the subgroup with available images, MAD was enriched in SMAD3 PV compared with other transforming growth factor-β PV (prevalence ratio 1.8 [1.1-2.8], P <0.02). Severe disjunction (>10 mm) was only observed in the transforming growth factor-β subgroup and was further enriched in participants with SMAD3 PV (prevalence ratio 3.1 [1.1-8.6]). MVP (prevalence ratio 5.2 [3.0-9.0]) and MR (PR 2.7 [1.8-3.9]) were increased in participants with MAD, but MAD was not independently associated with adverse cardiac or aortic events. Pathological mitral valve phenotypes are more prevalent in individuals with PV in transforming growth factor-β pathway genes, particularly SMAD3. MR and MVP but not MAD are associated with adverse aortic and cardiac events. Because congenital mitral disease may be the primary presenting feature of SMAD3 PV, genetic testing for heritable thoracic aortic disease should be considered for such individuals, especially if they also have a family history of heritable thoracic aortic disease.

Comprehensive Review of Shone's Syndrome: Pathophysiology, Clinical Manifestations, and Management Strategies

Shone's syndrome, a rare congenital heart disease, encompasses a complex array of obstructive lesions within the left heart. First described in 1963, this syndrome typically presents with a combination of supravalvular mitral ring, parachute mitral valve, subaortic stenosis, and coarctation of the aorta. The intricate nature of these anomalies presents significant diagnostic and therapeutic challenges. This review aims to elucidate the pathophysiological mechanisms underlying Shone's syndrome, provide a detailed account of its clinical manifestations, and discuss current management strategies, including surgical and medical interventions. Through an in-depth analysis of existing literature, we seek to enhance understanding and improve outcomes for patients afflicted with this multifaceted condition.

Heart failure with reduced ejection fraction and chronic kidney disease: a focus on therapies and interventions.

In heart failure with reduced ejection fraction (HFrEF), the presence of concomitant chronic kidney disease (CKD) predicts poorer cardiovascular outcomes, more aggravated heart failure (HF) status, and higher mortality. Physicians might be reluctant to initiate life-saving anti-HF medications out of fear of worsening renal function and a higher incidence of adverse events. Moreover, international guidelines do not give clear recommendations on managing this subgroup of patients as well as advanced CKD was always an exclusion criterion in most major HF trials. Nevertheless, in this review, we will highlight several recent clinical trials and post-hoc analyses of major trials that showed the safety and efficacy of the different therapies in HFrEF patients with CKD, besides several small-scale cohorts that tested guideline-directed medical therapies in End Stage Kidney Disease (ESKD). Regarding interventions in this subgroup of patients, we will provide up-to-date data on implantable cardioverter defibrillators, cardiac resynchronization therapy, and coronary revascularization, in addition to mitral valve transcatheter edge-to-edge repair and implantable pulmonary artery pressure sensors.

Safety and Effectiveness of Oral Anticoagulants in Atrial Fibrillation: Real-World Insights Using Natural Language Processing and Machine Learning.

Background/Objectives: We assessed the effectiveness and safety of vitamin K antagonists (VKAs) versus direct oral anticoagulants (DOACs) in patients with atrial fibrillation (AF) using artificial intelligence techniques. Methods: This is a retrospective study in 15 Spanish hospitals (2014-2020), including adult AF patients with no history of anticoagulation, thrombosis events, rheumatic mitral valvular heart disease, mitral valve stenosis, or pregnancy. We employed EHRead® technology based on natural language processing (NLP) and machine learning (ML), along with SNOMED-CT terminology, to extract clinical data from electronic health records (EHRs). Using propensity score matching (PSM), the effectiveness, safety, and hospital mortality of VKAs versus DOACs were analyzed through Kaplan-Meier curves and Cox regression. Results: Out of 138,773,332 EHRs from 4.6 million individuals evaluated, 44,292 patients were included, 79.6% on VKAs and 20.4% on DOACs. Most patients were elderly [VKA 78 (70, 84) and DOAC 75 (66, 83) years], with numerous comorbidities (75.5% and 70.2% hypertension, 47.2% and 39.9% diabetes, and 40.3% and 34.8% heart failure, respectively). Additionally, 60.4% of VKA and 48.7% of DOAC users had a CHA2DS2-VASc Score ≥4. After PSM, 8929 patients per subgroup were selected. DOAC users showed a lower risk of thrombotic events [HR 0.81 (95% CI 0.70-0.94)], minor bleeding [HR 0.89 (95% CI 0.83-0.96)], and mortality [HR 0.80 (95% CI 0.69-0.92)]. Conclusions: Applying NLP and ML, we generated valuable real-world evidence on anticoagulated AF patients in Spain. Even in complex populations, DOACs have demonstrated a better safety and effectiveness profile than VKAs.