Search

Abstract The recent rise of artificial intelligence represents a revolutionary way of improving current medical practices, including cardiovascular (CV) assessment scores. Retinal vascular alterations may reflect systemic processes such as the presence of CV risk factors. The value of swept-source retinal optical coherence tomography–angiography (SS OCT-A) imaging is significantly enhanced by image analysis tools that provide rapid and accurate quantification of vascular features. We report on the interest of using machine-learning (ML) and deep-learning (DL) models for CV assessment from SS OCT-A microvasculature imaging. We assessed the accuracy of ML and DL algorithms in predicting the CHA2DS2-VASc neurocardiovascular score based on SS OCT-A retinal images of patients from the open-source RASTA dataset. The ML and DL models were trained on data from 491 patients. The ML models tested here achieved good performance with area under the curve (AUC) values ranging from 0.71 to 0.96. According to a classification into two neurocardiovascular risk groups, the EfficientNetV2-B3, a well suited DL model for retinal OCT-A images, predicted risk correctly in 68% of cases, with a mean absolute error (MAE) of approximately 0.697. Our models enable a confident prediction of the CHA2DS2-VASc score from SS OCT-A imaging, which could be a useful tool contributing to the assessment of neurocardiovascular profiles in the future.

The recent rise of artificial intelligence represents a revolutionary way of improving current medical practices, including cardiovascular (CV) assessment scores. Retinal vascular alterations may reflect systemic processes such as the presence of CV risk factors. The value of swept-source retinal optical coherence tomography–angiography (SS OCT-A) imaging is significantly enhanced by image analysis tools that provide rapid and accurate quantification of vascular features. We report on the interest of using machine-learning (ML) and deep-learning (DL) models for CV assessment from SS OCT-A microvasculature imaging. We assessed the accuracy of ML and DL algorithms in predicting the CHA2DS2-VASc neurocardiovascular score based on SS OCT-A retinal images of patients from the open-source RASTA dataset. The ML and DL models were trained on data from 491 patients. The ML models tested here achieved good performance with area under the curve (AUC) values ranging from 0.71 to 0.96. According to a classification into two neurocardiovascular risk groups, the EfficientNetV2-B3, a well suited DL model for retinal OCT-A images, predicted risk correctly in 68% of cases, with a mean absolute error (MAE) of approximately 0.697. Our models enable a confident prediction of the CHA2DS2-VASc score from SS OCT-A imaging, which could be a useful tool contributing to the assessment of neurocardiovascular profiles in the future. [ABSTRACT FROM AUTHOR]

Background: The head-up tilt test (HUTT) is a useful diagnostic tool in patients with suspected vasovagal syncope (VVS).Objectives: We aimed to investigate the direct drug-potentiated HUTT in patients with recurrent syncope or precursor syncope and to assess the diagnostic value of the direct drug-potentiated HUTT.Methods: The medical history and direct drug-potentiated HUTT records of patients who complained of syncope or precursor syncope and who visited The Xianyang Central Hospital from January 2016 to December 2020 were retrospectively reviewed.Results: A total of 4,873 patients (age = 43.8 ± 17.6 years; male = 2,064 [42.4%]) were enrolled in our study. Overall, 2,343 (48.1%) showed positive responses as follows: 1,260 (25.9%) with the mixed type, 34 (0.7%) with the cardioinhibitory type, 580 (11.9%) with the vasodepressor type, 179 (3.7%) with postural tachycardia syndrome (POTS), and 290 (6.0%) with orthostatic hypotension (OH). The study showed that prior to syncope or near-syncope symptoms, patients first presented an increase in heart rate (HR), followed by decreases in blood pressure (BP) and HR successively. Among the patients in the syncope group, the sensitivity of the HUTT was 65.9%, which was significantly higher than a sensitivity of 44.8% for patients in the non-syncope group (P < 0.01). The sensitivity of the HUTT was higher for females than males in both the syncope group (52.6% in males and 77.9% in females, P < 0.01) and the non-syncope group (36.5% in males and 50.6% in females, P < 0.01). Within the four age groups (60 years old), the sensitivities were 74.7%, 67.7%, 45.6%, and 31.2%, respectively. And all gender, age and symptom (whether suffered from a syncope or not) significantly affected the positive responses of HUTT. There were two adverse events and no deaths during the HUTT in this study.Conclusion: The direct drug-potentiated HUTT is a safe and highly sensitive tool with which to diagnose VVS. Patients with precursor syncope symptoms without syncope should undergo a HUTT, especially young females presenting with weakness and sweating, which can decrease the probability of a misdiagnosis or a missed diagnosis.

Background: Atrial fibrillation (AF) and coagulation disorder, two common complications of sepsis, are associated with the mortality. However, the relationship between early coagulation disorder and AF in sepsis remains elusive. This study aimed to evaluate the interaction between AF and early coagulation disorder on mortality.Methods: In this retrospective study, all data were extracted from the Medical Information Mart for Intensive Care III (MIMIC-III) database. Septic patients with coagulation tests during the first 24 h after admission to intensive care units (ICUs) meeting study criteria were included in the analysis. Early coagulation disorder is defined by abnormalities in platelet count (PLT), international normalized ratio (INR) and activated partial thromboplastin time (APTT) within the first 24 h after admission, whose score was defined with reference to sepsis-induced coagulopathy (SIC) and coagulopathy. Patients meeting study criteria were divided into AF and non-AF groups.Results: In total, 7,528 septic patients were enrolled, including 1,243 (16.51%) with AF and 5,112 (67.91%) with early coagulation disorder. Compared with patients in the non-AF group, patients in the AF group had higher levels of INR and APTT (P < 0.001). Multivariable logistic regression analyses showed that stroke, early coagulation disorder, age, gender, congestive heart failure (CHF), chronic pulmonary disease, renal failure, and chronic liver disease were independent risk factors for AF. In addition, AF was related to in-hospital mortality and 90-day mortality. In the subgroup analysis stratified by the scores of early coagulation disorder, AF was associated with an increased risk of 90-day mortality when the scores of early coagulation disorder were 1 or 2 and 3 or 4.Conclusion: In sepsis, coagulation disorder within the first 24 h after admission to the ICUs is an independent risk factor for AF. The effect of AF on 90-day mortality varies with the severity of early coagulation disorder.

Vasovagal syncope (VVS) is the most common cause of recurrent syncope which has a good prognosis, but has a high morbidity. structural heart disease is absent in most of the patients. It is thought to be the result of neurocardiovascular system abnormality which provides the systemic and cerebral perfusion. Although VVS has a high incidence, no satisfactory treatment has been found yet. The main purpose of the treatment is to prevent the recurrent syncope episodes and injuries that may occur due to syncope and to improve the quality of life. Treatment of VVS is divided into three as nonpharmacological treatment, pharmacological treatment and cardiac pacemaker implantation. The treatment of VVS is difficult. The patient should be given detailed information about the disease, proper diet should be recommended by the life-style changes, triggerering factors of the syncope should be explained and advised to avoid these triggers. Psychological support is very important and should be maintained in these patients. Patients should be strongly encouraged to implement physical maneuvers. Medical treatment can be tried if the patients’ complaints continue. In case of recurrent syncope despite ongoing medical treatment, permanent pacemaker implantation should be considered.