Your browser doesn't support javascript.
loading
Mostrar: 20 | 50 | 100
Resultados 1 - 4 de 4
Filtrar
Mais filtros










Base de dados
Intervalo de ano de publicação
1.
Adv Ther ; 38(6): 2954-2972, 2021 06.
Artigo em Inglês | MEDLINE | ID: mdl-33834355

RESUMO

INTRODUCTION: This study aimed to describe the rates and causes of unplanned readmissions within 30 days following carotid artery stenting (CAS) and to use artificial intelligence machine learning analysis for creating a prediction model for short-term readmissions. The prediction of unplanned readmissions after index CAS remains challenging. There is a need to leverage deep machine learning algorithms in order to develop robust prediction tools for early readmissions. METHODS: Patients undergoing inpatient CAS during the year 2017 in the US Nationwide Readmission Database (NRD) were evaluated for the rates, predictors, and costs of unplanned 30-day readmission. Logistic regression, support vector machine (SVM), deep neural network (DNN), random forest, and decision tree models were evaluated to generate a robust prediction model. RESULTS: We identified 16,745 patients who underwent CAS, of whom 7.4% were readmitted within 30 days. Depression [p < 0.001, OR 1.461 (95% CI 1.231-1.735)], heart failure [p < 0.001, OR 1.619 (95% CI 1.363-1.922)], cancer [p < 0.001, OR 1.631 (95% CI 1.286-2.068)], in-hospital bleeding [p = 0.039, OR 1.641 (95% CI 1.026-2.626)], and coagulation disorders [p = 0.007, OR 1.412 (95% CI 1.100-1.813)] were the strongest predictors of readmission. The artificial intelligence machine learning DNN prediction model has a C-statistic value of 0.79 (validation 0.73) in predicting the patients who might have all-cause unplanned readmission within 30 days of the index CAS discharge. CONCLUSIONS: Machine learning derived models may effectively identify high-risk patients for intervention strategies that may reduce unplanned readmissions post carotid artery stenting. CENTRAL ILLUSTRATION: Figure 2: ROC and AUPRC analysis of DNN prediction model with other classification models on 30-day readmission data for CAS subjects.


We present a novel deep neural network-based artificial intelligence prediction model to help identify a subgroup of patients undergoing carotid artery stenting who are at risk for short-term unplanned readmissions. Prior studies have attempted to develop prediction models but have used mainly logistic regression models and have low prediction ability. The novel model presented in this study boasts 79% capability to accurately predict individuals for unplanned readmissions post carotid artery stenting within 30 days of discharge.


Assuntos
Inteligência Artificial , Readmissão do Paciente , Artérias Carótidas , Humanos , Estudos Retrospectivos , Fatores de Risco , Resultado do Tratamento
2.
Cardiol Res ; 9(3): 186-190, 2018 Jun.
Artigo em Inglês | MEDLINE | ID: mdl-29904458

RESUMO

Coronary artery disease is a major cause of morbidity and mortality, and while most commonly is atherosclerotic, it can present with variable manifestations, both congenital and acquired. One such manifestation is coronary aneurysm, which is a localized dilatation of a coronary artery wall segment to greater than 1.5 times the adjacent normal segments. While a dilated outpouching of a coronary artery has been commonly classified as a coronary aneurysm, a non-dilated outpouching is rare and is referred to as a diverticulum, with only one previous case report in the literature. It is conceivable that other cases of coronary artery diverticulum may have been previously reported as an aneurysm, given the overlapping angiographic appearance. We present a case of a 72-year-old female patient with an incidental finding of left main coronary artery diverticulum on diagnostic coronary angiogram done for preoperative liver transplantation evaluation.

3.
Cardiol Res ; 8(3): 134-138, 2017 Jun.
Artigo em Inglês | MEDLINE | ID: mdl-28725332

RESUMO

We report a 42-year-old female who was admitted for abdominal pain, and also endorsed dyspnea, fatigue and chronic palpitations. Past medical history included asthma, patent ductus arteriosus repaired in childhood and ill-defined thyroid disease. Physical examination revealed blood pressure of 136/88 mm Hg and heart rate of 149 beats per minute. Cardiovascular exam revealed an irregularly irregular rhythm, and pulmonary exam revealed mild expiratory wheezing. Abdomen was tender. Electrocardiogram revealed atrial fibrillation with rapid ventricular response which responded to intravenous diltiazem. Labs revealed TSH of < 0.1 mU/L and free T4 of 2.82 ng/dL, a positive TSH-receptor and thyroid peroxidase antibodies suggesting Grave's thyrotoxicosis. A transthoracic echocardiogram reported an ejection fraction of 55-60%, with mild to moderate mitral regurgitation (MR) and moderate to severe tricuspid regurgitation (TR) and dilated right heart chambers. Pulmonary artery systolic pressure was 52 mm Hg. Transesophageal echocardiogram revealed a myxomatous tricuspid valve with thickening and malcoaptation of the leaflets and moderate to severe TR, mild to moderate MR with mild thickening of the mitral valve leaflets. Abdominal ultrasound revealed wall thickening of the gall bladder concerning for acute cholecystitis. She underwent laparoscopic cholecystectomy and was discharged in stable condition on methimazole for her thyroid disease, and on oral diltiazem for rate control and anticoagulation for atrial fibrillation. Follow-up visit with her cardiologist few months later documented absence of cardiac symptoms, and no murmurs were reported on physical examination. This case underscores the importance of maintaining a high index of suspicion for hyperthyroidism when faced with significant newly diagnosed pulmonary hypertension and TR, as treatment of the thyroid abnormalities can reverse these cardiac findings.

4.
Cardiol Res ; 8(2): 68-72, 2017 Apr.
Artigo em Inglês | MEDLINE | ID: mdl-28515825

RESUMO

We report a 63-year-old female with hypertension, hyperlipidemia, and prior pacemaker insertion for atrial fibrillation with symptomatic bradycardia, who was admitted with substernal chest pressure and diaphoresis. Her electrocardiogram revealed atrial fibrillation with demand ventricular pacing and her cardiac biomarkers were negative for acute coronary syndrome. Echocardiogram revealed normal left ventricular systolic function and normal aortic root diameter. Coronary angiography revealed 60-70% obtuse marginal lesion, otherwise mild disease. She was treated medically and discharged in stable condition. She was readmitted 1 month later with recurring chest pain, and shortness of breath which started shortly after her most recent discharge. Blood pressure was 152/93 mm Hg, and heart rate was 105 bpm. BNP was elevated at 1,400 pg/mL, and other cardiac biomarkers were negative. She was treated with diuretics, which resulted in decrease of her blood pressure to 81/51 mm Hg. Repeat echocardiogram revealed severely dilated aortic root, measuring 6.7 cm, with aortic dissection flap and moderate to severe aortic regurgitation. CT angiogram revealed aortic dissection extending proximally to the aortic root above the coronary ostia and distally to the left subclavian artery takeoff. She underwent surgery; she, however, could not be weaned off from cardiopulmonary bypass and died in the operating room. This case illustrates the importance of having a high index of suspicion for iatrogenic aortic dissection following cardiac catheterization as a cause of recurrence of cardiac symptoms, as early detection may help avert a catastrophic outcome, as we report in our patient.

SELEÇÃO DE REFERÊNCIAS
DETALHE DA PESQUISA