Machine Learning-based Models in Prediction of DVT and PTE in AECOPD Patients
Machine LearningChronic Obstructive Pulmonary Disease4 moreChronic Obstructive Pulmonary Disease (COPD) is a common respiratory system disease characterized by persistent respiratory symptoms and irreversible airflow restriction, which seriously endangers people's health. Acute exacerbation of chronic obstructive pulmonary disease (AECOPD) refers to individuals who experience continuous deterioration beyond their daily condition and need to change their routine medication. AECOPD is usually caused by viruses and bacteria, and patients require hospitalization, which brings a huge economic burden to society. AECOPD patients often have limited activities. Because long-term chronic hypoxia causes venous blood stasis, siltation causes secondary red blood cell increase, and blood hypercoagulability, AECOPD patients have a high risk of pulmonary embolism (PE). Pulmonary Thrombo Embolism (PTE) refers to a disease caused by blockage of the pulmonary artery or its branches caused by a thrombus from the venous system or right heart. AECOPD patients experience elevated hemoglobin levels and increased blood viscosity due to long-term hypoxia. At the same time, such patients have decreased activity, venous congestion, and are prone to thrombosis. After the thrombus falls off, it can travel up the vein, causing PTE to occur in the right heart PTE is often secondary to low deep vein thrombosis (DVT). About 70% of patients were diagnosed as deep vein thrombosis in lower limb color ultrasound examination. SteinPD conducted a survey on COPD patients and general patients from multiple hospitals. The results showed that by comparing adult COPD patients with non COPD patients, the relative risk of DVT was 1.30, providing evidence for AECOPD being more likely to combine with PTE AECOPD patients with PTE have similarities in their clinical manifestations. It is difficult to distinguish between the two based solely on symptoms, such as cough, increased sputum production, increased shortness of breath, and difficulty breathing. They lack specificity and are difficult to distinguish between the two based solely on symptoms, which can easily lead to missed diagnosis. CT pulmonary angiography (CTPA) is the gold standard for the diagnosis of PTE, but due to the high cost of testing and high equipment prices, its popularity in grassroots hospitals is not high. Therefore, analyzing the risk factors of AECOPD patients complicated with PTE is of great significance for early identification of PTE. At present, although there are reports on the risk factors for concurrent PTE in AECOPD patients, there is no specific predictive model for predicting PTE in AECOPD patients. In clinical practice, risk assessment tools such as the Caprini risk assessment model and the modified Geneva scale are commonly used for VTE, while the Wells score is the PTE diagnostic likelihood score. The evaluation indicators of these tools are mostly clinical symptoms, and laboratory indicators are less involved, It is difficult to comprehensively reflect the patient's condition, so the specificity of AECOPD patients with PTE is not strong. The column chart model established in this study presents a visual prediction model, which is convenient for clinical use and has positive help for the early detection of AECOPD patients with PTE. In addition, medical staff can present the calculation results of the column chart model to patients, making it easier for patients to understand. It helps improve the early identification and treatment of AECOPD combined with PTE patients, thereby improving prognosis.
Using a Real-Time Risk Prediction Model to Predict Pediatric Venous Thromboembolism (VTE) Events...
Venous ThromboembolismPediatrics2 moreThe study will evaluate the effectiveness of a novel, real-time risk prediction model for identifying pediatric patients at risk for developing in-hospital blood clots (or venous thromboembolism [VTE]) based on data easily extracted from the electronic medical record. The study will assess whether using the risk percentages for developing VTE derived from the model increases the number of high-risk patients screened by the pediatric hematology team, which may may lead to an overall reduction in the number of pediatric VTEs seen at Monroe Carell Jr. Children's Hospital at Vanderbilt.
Catheter-Directed Pulmonary Reperfusion in Treatment of Pulmonary Embolism Patients
Pulmonary EmbolismPrimary objective: to evaluate the success and mortality rates of catheter-directed reperfusion therapy in comparison to traditional use of systemic intravenous fibrinolytic therapy, will focus at safety of such management measured by in-hospital mortality and prevalence of severe adverse events. Secondary objective: to assess the feasibility of catheter-directed reperfusion in management of intermediate and high risk pulmonary embolism in Assiut University hospital and its reflection on pulmonary artery pressure
Construction of Early Warning Model for Pulmonary Complications Risk of Surgical Patients Based...
Pulmonary EmbolismRespiratory Failure2 moreThe goal of this observational study is to establish an intelligent early warning system for acute and critical complications of the respiratory system such as pulmonary embolism and respiratory failure. Based on the electronic case database of the biomedical big data research center and the clinical real-world vital signs big data collected by wearable devices, the hybrid model architecture with multi-channel gated circulation unit neural network and deep neural network as the core is adopted, Mining the time series trends of multiple vital signs and their linkage change characteristics, integrating the structural nursing observation, laboratory examination and other multimodal clinical information to establish a prediction model, so as to improve patient safety, and lay the foundation for the later establishment of a higher-level and more comprehensive artificial intelligence clinical nursing decision support system. Issues addressed in this study The big data of vital signs of patients collected in real-time by wearable devices were used to explore the internal relationship between the change trend of vital signs and postoperative complications (mainly including infection complications, respiratory failure, pulmonary embolism, cardiac arrest). Supplemented with necessary nursing observation, laboratory examination and other information, and use machine learning technology to build a prediction model of postoperative complications. Develop the prediction model into software to provide auxiliary decision support for clinical medical staff, and lay the foundation for the later establishment of a higher-level and more comprehensive AI clinical decision support system.
Clinical Outcomes After Acute Pulmonary Embolism
Pulmonary EmbolismTo investigate safety and effectiveness of PE treatment according to the decision of the multi-disciplinary pulmonary embolism response team (PERT) and to define and optimize treatment indications, institutional algorithms and interventional techniques for PE.
The Prognostic Role and Diagnostic Efficacy of Exercise Right Heart Catheterization With a Simultaneous...
Heart Failure With Preserved Ejection FractionChronic Pulmonary Thromboembolism (Disorder)To evaluate the role of exercise hemodynamic testing in the diagnostic workup for patients with dyspnea on exertion referred to the catheterization lab.
Study of the Long-Term Safety and Outcomes of Treating Pulmonary Embolism With the Indigo Aspiration...
Pulmonary EmbolismThe objective of this study is to evaluate real world long-term functional outcomes, safety and performance of the Indigo Aspiration System for the treatment of pulmonary embolism (PE).
Is Clonal Hematopoiesis of Indeterminate Potential Associated With Unprovoked Pulmonary Embolism?...
Pulmonary EmbolismHematopoiesisThe clonal hematopoiesis of indetermined prognosis (CHIP) has been described as risk factor for juvenile atherosclerosis. Moreover, some of CHIP genes are responsible of myeloproliferative disorders. Venous thrombosis are frequent in these disorders. The purpose of this project is to determine if CHIP is frequent in unprovoked pulmonary embolism and could be part of the pathophysiology.
Point-of-care Ultrasound in Suspected Pulmonary Embolism
Pulmonary EmbolismPulmonary Embolus/EmboliPulmonary embolism (PE) is a common cardiovascular condition with an estimated incidence of 0.60 to 1.12 per 1000 inhabitants in the United States of America, and the diagnosis is challenging as patients with PE present with a wide array of symptoms. Computed tomography pulmonary angriography (CTPA) and lung ventilation-perfusion scintigraphy (VQ) are considered the gold-standards in PE-diagnostics but may not always be feasible. CTPA is contraindicated by contrast allergy or renal failure and both modalities require involvement of multiple staff-members and transport of the patient. Lung scintigraphy cannot be performed in an emergency situation, with unstable patients and patients unable to comply to the examination. Ultrasound represent a possible tool in confirming or dismissing clinical PE suspicion. Ultrasound is non-invasive and can be performed bedside by the clinician, an approach known as point-of-care ultrasound (PoCUS), reducing both time, radiation-exposure and costs. The aim of this study is to investigate whether integrating cardiac, lung and deep venous ultrasound in the clinical evaluation of suspected PE reduces the need for referral to CTPA or lung scintigraphy, during emergency department work up, while maintaining safety standards.
Adjust-Unlikely PE
Pulmonary Embolism (Diagnosis)The aim of this pilot study is to assess the feasibility of a larger study to determine the Adjust-Unlikely algorithm safety and efficiency for diagnosing PE. The pilot study objectives are to: Determine study recruitment rate, per site, per month Determine study 90-day loss to follow up rate Estimate of the proportion of enrolled patients who test negative for PE at initial assessment using the Adjust-Unlikely rule Estimate of the Adjust-Unlikely algorithm efficiency Compare excluded and missed-eligible patients to study participants: age, sex and prevalence of PE diagnoses at initial testing. The pilot study hypothesis is that the investigators can recruit at least 20 patients per month and successfully follow at least 90% of patients for 90 days.