1
|
Peng Y, Chen Z, Luo Z, Luo G, Chu Y, Zhou B, Zhu S. Identifying prognostic factors for pulmonary embolism patients with hemodynamic decompensation admitted to the intensive care unit. Medicine (Baltimore) 2024; 103:e36392. [PMID: 38241540 PMCID: PMC10798768 DOI: 10.1097/md.0000000000036392] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/18/2023] [Accepted: 11/09/2023] [Indexed: 01/21/2024] Open
Abstract
We aimed to determine prognostic indicators of PE patients with hemodynamic decompensation admitted to the ICU. PE patients with hemodynamic decompensation at ICU admission from Medical Information Mart for Intensive Care IV database were included. Least absolute shrinkage and selection operator with 2 specific lambdas were performed to reduce the dimension of variables after univariate analysis. Then we conducted multivariate logistic regression analysis and 2 models were built. A total of 548 patients were included, among whom 187 died. Lactate, creatine-kinase MB, troponin-T were significantly higher in death group. Eight common factors were screened out from first model statistically mostly in consistent with second model: older age, decreased hemoglobin, elevated anion gap, elevated International Standard Ratio (INR), elevated respiratory rate, decreased temperature, decreased blood oxygen saturation (SpO2) and the onset of cardiac arrest were significantly risk factors for in-Hospital mortality. The nonlinear relationships between these indicators and mortality were showed by the restricted cubic spline and cutoff values were determined. Our study demonstrated that age, hemoglobin levels, anion gap levels, INR, respiratory rate, temperature, SpO2 levels, the onset of cardiac arrest could be applied to predict mortality of PE patients with hemodynamic decompensation at ICU admission.
Collapse
Affiliation(s)
- Yanbin Peng
- Department of Hand Microsurgical Technique Surgery, Peking University Shenzhen Hospital, Shenzhen City, Guangdong Province, China
| | - Zhong Chen
- Department of Hand Microsurgical Technique Surgery, Peking University Shenzhen Hospital, Shenzhen City, Guangdong Province, China
| | - Zhongkai Luo
- Baise Tiandong County People’s Hospital, Tiandong County, Baise City, Guangxi Zhuang Autonomous Region Province, China
| | - Gaosheng Luo
- Department of Orthopaedics Surgery, Baise Tiandong County People’s Hospital, Tiandong County, Baise City, Guangxi Zhuang Autonomous Region Province, China
| | - Yunfeng Chu
- Department of Hand Microsurgical Technique Surgery, Peking University Shenzhen Hospital, Shenzhen City, Guangdong Province, China
| | - Bo Zhou
- Department of Hand Microsurgical Technique Surgery, Peking University Shenzhen Hospital, Shenzhen City, Guangdong Province, China
| | - Siqi Zhu
- Department of Hand Microsurgical Technique Surgery, Peking University Shenzhen Hospital, Shenzhen City, Guangdong Province, China
| |
Collapse
|
2
|
Xu J, Hu Z, Miao J, Cao L, Tian Z, Yao C, Huang K. MACHINE LEARNING FOR PREDICTING HEMODYNAMIC DETERIORATION OF PATIENTS WITH INTERMEDIATE-RISK PULMONARY EMBOLISM IN INTENSIVE CARE UNIT. Shock 2024; 61:68-75. [PMID: 38010031 DOI: 10.1097/shk.0000000000002261] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/29/2023]
Abstract
ABSTRACT Background: Intermediate-risk pulmonary embolism (PE) patients in the intensive care unit (ICU) are at a higher risk of hemodynamic deterioration than those in the general ward. This study aimed to construct a machine learning (ML) model to accurately identify the tendency for hemodynamic deterioration in the ICU patients with intermediate-risk PE. Method: A total of 704 intermediate-risk PE patients from the MIMIC-IV database were retrospectively collected. The primary outcome was defined as hemodynamic deterioration occurring within 30 days after admission to ICU. Four ML algorithms were used to construct models on the basis of all variables from MIMIC IV database with missing values less than 20%. The extreme gradient boosting (XGBoost) model was further simplified for clinical application. The performance of the ML models was evaluated by using the receiver operating characteristic curve, calibration plots, and decision curve analysis. Predictive performance of simplified XGBoost was compared with the simplified Pulmonary Embolism Severity Index score. SHapley Additive explanation (SHAP) was performed on a simplified XGBoost model to calculate the contribution and impact of each feature on the predicted outcome and presents it visually. Results: Among the 704 intermediate-risk PE patients included in this study, 120 patients experienced hemodynamic deterioration within 30 days after admission to the ICU. Simplified XGBoost model demonstrated the best predictive performance with an area under the curve of 0.866 (95% confidence interval, 0.800-0.925), and after recalibrated by isotonic regression, the area under the curve improved to 0.885 (95% confidence interval, 0.822-0.935). Based on the simplified XGBoost model, a web app was developed to identify the tendency for hemodynamic deterioration in ICU patients with intermediate-risk PE. Conclusion: A simplified XGBoost model can accurately predict the occurrence of hemodynamic deterioration for intermediate-risk PE patients in the ICU, assisting clinical workers in providing more personalized management for PE patients in the ICU.
Collapse
Affiliation(s)
| | - Zhensheng Hu
- Zhongshan School of Medicine, Sun Yat-Sen University, Guangzhou, China
| | - Jianhang Miao
- Department of Vascular Surgery, Zhongshan City People's Hospital, Zhongshan, China
| | - Lin Cao
- The First Clinical College of Guangzhou Medical University, Guangzhou Medical University, Guangzhou, China
| | - Zhenluan Tian
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Breast Tumor Center, Sun Yat-sen Memorial Hospital, Sun Yat-sen University, Guangzhou, China
| | - Chen Yao
- Department of Vascular Surgery, the First Affiliated Hospital of Sun Yat-sen University, Sun Yat-Sen University, Guangzhou, China
| | | |
Collapse
|
3
|
Haner Wasserstein D, Frishman WH. FlowTriever System for Pulmonary Embolism: A Review of Clinical Evidence. Cardiol Rev 2023:00045415-990000000-00166. [PMID: 37909737 DOI: 10.1097/crd.0000000000000605] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/03/2023]
Abstract
Pulmonary embolism (PE) is a significant cause of cardiovascular mortality, and its incidence has been increasing due to the growing aging population. Systemic or catheter-directed thrombolytic treatment for PE has an increased risk of bleeding that may offset the benefit in some patients. Mechanical thrombectomy devices such as the FlowTriever System are designed to resolve vascular occlusion and correct ventilation-perfusion mismatch without the need for thrombolytic drugs. This review covers the FlowTriever system, clinical data from the FlowTriever Pulmonary Embolectomy Clinical Study, FlowTriever for Acute Massive Pulmonary Embolism, and FlowTriever All-comer Registry for Patient Safety and Hemodynamics trials, and real-world experiences, demonstrating its safety and effectiveness in treating intermediate-risk and high-risk PE. Additionally, we explore off-label uses of the FlowTriever System for various large vessel thromboses.
Collapse
Affiliation(s)
| | - William H Frishman
- Department of Internal Medicine, New York Medical College at Westchester Medical Center, Valhalla, NY
| |
Collapse
|
4
|
Wang G, Xu J, Lin X, Lai W, Lv L, Peng S, Li K, Luo M, Chen J, Zhu D, Chen X, Yao C, Wu S, Huang K. Machine learning-based models for predicting mortality and acute kidney injury in critical pulmonary embolism. BMC Cardiovasc Disord 2023; 23:385. [PMID: 37533004 PMCID: PMC10399014 DOI: 10.1186/s12872-023-03363-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2023] [Accepted: 06/22/2023] [Indexed: 08/04/2023] Open
Abstract
OBJECTIVES We aimed to use machine learning (ML) algorithms to risk stratify the prognosis of critical pulmonary embolism (PE). MATERIAL AND METHODS In total, 1229 patients were obtained from MIMIC-IV database. Main outcomes were set as all-cause mortality within 30 days. Logistic regression (LR) and simplified eXtreme gradient boosting (XGBoost) were applied for model constructions. We chose the final models based on their matching degree with data. To simplify the model and increase its usefulness, finally simplified models were built based on the most important 8 variables. Discrimination and calibration were exploited to evaluate the prediction ability. We stratified the risk groups based on risk estimate deciles. RESULTS The simplified XGB model performed better in model discrimination, which AUC were 0.82 (95% CI: 0.78-0.87) in the validation cohort, compared with the AUC of simplified LR model (0.75 [95% CI: 0.69-0.80]). And XGB performed better than sPESI in the validation cohort. A new risk-classification based on XGB could accurately predict low-risk of mortality, and had high consistency with acknowledged risk scores. CONCLUSIONS ML models can accurately predict the 30-day mortality of critical PE patients, which could further be used to reduce the burden of ICU stay, decrease the mortality and improve the quality of life for critical PE patients.
Collapse
Affiliation(s)
- Geng Wang
- Department of Vascular Interventional Radiology, Zhongshan Hospital of Traditional Chinese Medicine, Zhongshan, China
| | - Jiatang Xu
- Department of Cardiovascular Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, No.33, Yingfeng Road, Haizhu District, Guangdong Province, 510000, Guangzhou, China
- Zhongshan School of Medicine, Sun Yat-Sen University, Guangzhou, China
| | - Xixia Lin
- Department of Medicine, Sun Yat-Sen Memorial Hospital South Campus Clinic, Guangzhou, China
| | - Weijie Lai
- Zhongshan School of Medicine, Sun Yat-Sen University, Guangzhou, China
| | - Lin Lv
- Zhongshan School of Medicine, Sun Yat-Sen University, Guangzhou, China
| | - Senyi Peng
- Zhongshan School of Medicine, Sun Yat-Sen University, Guangzhou, China
| | - Kechen Li
- Hospital of Stomatology, Guanghua School of Stomatology, Sun Yat-Sen University, Guangzhou, China
| | - Mingli Luo
- Zhongshan School of Medicine, Sun Yat-Sen University, Guangzhou, China
- Department of Urology, SunYat-Sen Memorial Hospital, SunYat-Sen University, Guangzhou, China
| | - Jiale Chen
- Zhongshan School of Medicine, Sun Yat-Sen University, Guangzhou, China
| | - Dongxi Zhu
- Zhongshan School of Medicine, Sun Yat-Sen University, Guangzhou, China
| | - Xiong Chen
- Department of Urology, SunYat-Sen Memorial Hospital, SunYat-Sen University, Guangzhou, China
| | - Chen Yao
- Department of Vascular Surgery, First Affiliated Hospital of Sun Yat-Sen University, Guangzhou, China
| | - Shaoxu Wu
- Department of Urology, SunYat-Sen Memorial Hospital, SunYat-Sen University, Guangzhou, China.
- Guangdong Provincial Key Laboratory of Malignant Tumor Epigenetics and Gene Regulation, Guangzhou, China.
| | - Kai Huang
- Department of Cardiovascular Surgery, Sun Yat-Sen Memorial Hospital, Sun Yat-Sen University, No.33, Yingfeng Road, Haizhu District, Guangdong Province, 510000, Guangzhou, China.
| |
Collapse
|
5
|
Ajmal F, Haroon M, Kaleem U, Gul A, Khan J. Comparison of Chemical and Mechanical Prophylaxis of Venous Thromboembolism in Non-surgical Mechanically Ventilated Patients. Cureus 2021; 13:e19548. [PMID: 34917432 PMCID: PMC8668419 DOI: 10.7759/cureus.19548] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Accepted: 11/12/2021] [Indexed: 11/13/2022] Open
Abstract
To compare the efficacy of mechanical and chemical prophylaxis in non-surgically mechanically ventilated patients in terms of reduction in mortality and length of hospital stay. A total of 200 patients admitted to intensive care units (ICUs) were recruited retrospectively. Half participants received mechanical prophylaxis and half received chemical prophylaxis. Patients with medical diseases with age 18 years or above, both genders, Pakistani nationals, receiving mechanical ventilation for more than 48 hours or receiving subcutaneous low molecular weight (LMW) heparin or subcutaneous unfractionated heparin were included. Cases who undergone surgery and were then admitted to ICU, those who received both mechanical and chemical therapies, and patients who received anticoagulant treatment before admission to ICU were excluded from the study. The patient’s age, gender, length of stay in ICU, and mortality were recorded in each group. Chi-square test was used to compare categorical data and Student t-test for continuous variables. The mean age was 55.51±8.37 years. The males were 108(54%) and females were 92(46%). The mortality rate was higher in the mechanical prophylaxis group (49%) than chemical (31%) statistically significantly (P=0.014). Similarly, the length of hospital stay was also higher in the mechanical prophylaxis group (7.27±0.897 days) than chemical (6.67±1.045) statistically (P<0.001). Chemical prophylaxis can reduce mortality and length of hospital stay more effectively than mechanical prophylaxis in ICUs admitted patients.
Collapse
Affiliation(s)
- Fahad Ajmal
- Critical Care Medicine, Bahria International Hospital, Rawalpindi, Rawalpindi, PAK
| | - Mohammad Haroon
- Internal Medicine, Bahria International Hospital, Rawalpindi, Rawalpindi, PAK
| | - Umar Kaleem
- Critical Care Medicine, Bahria International Hospital, Rawalpindi, Rawalpindi, PAK
| | - Aisha Gul
- Critical Care Medicine, Bahria International Hospital, Rawalpindi, Rawalpindi, PAK
| | - Jawad Khan
- Critical Care Medicine, Bahria International Hospital, Rawalpindi, Rawalpindi, PAK
| |
Collapse
|
6
|
Mojibian HR, Chow E, Pollak J. FlowTriever System for mechanical thromboembolectomy. Future Cardiol 2020; 17:585-592. [PMID: 33084387 DOI: 10.2217/fca-2020-0104] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/15/2022] Open
Abstract
The systemic or catheter-directed infusion of thrombolytics benefits patients with massive and probably submassive pulmonary embolism. However, the risk of bleeding may offset benefits in a substantial number of patients. Percutaneous mechanical thromboembolectomy is an alternative to thrombolysis in those patients with contraindications to the lytic therapy, also potentially a way to avoid systemic or catheter-directed infusion of the thrombolytic all together. The Inari FlowTriever System (Inari Medical Inc, CA, USA) is the first US FDA-cleared large-bore aspiration thrombectomy device with pulmonary embolism thrombectomy indication. This article is a review of the FlowTriever System, its clinical use, current supportive literates and future research directions.
Collapse
Affiliation(s)
- Hamid R Mojibian
- Department of Radiology & Biomedical Imaging, Section of Vascular & Interventional Radiology, Yale University School of Medicine, New Haven, CT 06510, USA
| | - Eric Chow
- Department of Radiology & Biomedical Imaging, Section of Vascular & Interventional Radiology, Yale University School of Medicine, New Haven, CT 06510, USA
| | - Jeffery Pollak
- Department of Radiology & Biomedical Imaging, Section of Vascular & Interventional Radiology, Yale University School of Medicine, New Haven, CT 06510, USA
| |
Collapse
|