The effect of systemic and local risk factors on triggering peripherally inserted central catheter-related thrombosis in cancer patients: A prospective cohort study based on ultrasound examination and structural equation modeling

Development of a machine learning predictive model for central venous catheter-associated thrombosis in patients undergoing abdominal surgery

BACKGROUND

Central venous catheters (CVCs) are placed where the vena cava meets the right atrium. Their common use raises the risk of catheter-related thrombosis (CRT), a potentially life-threatening complication.

AIM

This study leverages machine learning to develop a CRT predictive model for abdominal surgery patients, aiming to refine clinical decisions and elevate treatment quality.

STUDY DESIGN

The data were split into training and validation sets using the caret package in R. Decision Trees (DT), Extra Trees (ET), Ada Boost, Gradient Boosting (GB), Light Gradient Boosting Machine (LGBM), K Neighbours Classifier (KNN) and Random Forest (RF) algorithms were used for model construction. Receiver operating characteristic (ROC) curve, area under curve (AUC), accuracy, recall, precision, F1 score, sensitivity and specificity were used to evaluate the performance of the model. Decision curve analysis (DCA) was used to evaluate the clinical utility of each model.

RESULTS

Among the 400 subjects, 184 had thrombosis, with an incidence of 46%. Basic characteristics analysis and univariate analysis showed that there were significant differences in the history of radiotherapy or chemotherapy, age, mobility score, retention time, D-dimer, fibrinogen and urea (p < .05). Among the models constructed by the seven algorithms, the performance of DT model was relatively balanced. The AUC of the validation set was 0.782, the sensitivity was 0.618, and the specificity was 0.781.

CONCLUSION

The predictive model for CRT developed using machine learning algorithms demonstrates good discrimination and clinical applicability among abdominal surgery patients, offering valuable guidance for CRT prevention strategies.

RELEVANCE TO CLINICAL PRACTICE

By integrating risk prediction models into the Hospital Information System (HIS), nurses can assess catheter status in a timely and accurate manner, understand the risks of thrombosis for patients, and implement targeted preventive measures. This approach can enhance the efficiency and accuracy of nursing care, holding clinical significance in critical care practice.

A multi-center big-data approach for precise PICC-RVT prognosis and identification of major risk factors in clinical practice

Background

The Peripherally Inserted Central Catheter (PICC) is a widely used technique for delivering intravenous fluids and medications, especially in critical care units. PICC may induce venous thrombosis (PICC-RVT), which is a frequent and serious complication. In clinical practice, Color Doppler Flow Imaging (CDFI) is regarded as the gold standard for diagnosing PICC-RVT. However, CDFI not only requires prominent time and effort from experienced healthcare professionals, but also relies on the formation and development of PICC-RVT, especially at early stages of PICC-RVT, when PICC-RVT is not apparent. A prognosis tool for PICC-RVT is crucial to bridge the gap between its diagnosis and treatment, especially in resource-limited settings, such as remote healthcare facilities.

Objective

Evaluate over 14,885 models from various machine learning techniques to identify an effective prognostic model (referred to as PRAD - PICC-RVT Assessment via Deep-learning) for quantifying the risks associated with PICC-RVT.

Methods

To tackle the challenges associated with PICC-RVT diagnosis, we gathered a comprehensive dataset of 5,272 patients from 27 healthcare centers across China. From a pool of 14885 models from various machine learning techniques, we systematically screened a data-driven prognostic model to quantify the risks associated with PICC-RVT. This model aims to provide objective evidence, and facilitate timely interventions.

Results

The proposed model displayed exceptional predictive accuracy, achieving an accuracy of 86.4 % and an AUC of 0.837. Based on the prognosis model, we further incorporated a weight analysis to identify the major contributing factors for PICC-RVT risk during catheterization. Albumin levels, primary diagnosis, hemoglobin levels, platelet levels, and education level are emphasized as important risk factors.

Conclusions

Our method excels in predicting early PICC-RVT risks, especially in asymptomatic patients. The findings in this paper offers insights into controllable PICC risk factors that could benefit vast patients and reduce disease burden through stratification and early intervention.

Effects of dietary habits and catheterization type on breast cancer-related lymphedema: a retrospective cohort study

BACKGROUND

Understanding the factors that contribute to variability in breast cancer-related lymphedema (BCRL) is an important first step in developing targeted interventions to improve quality of life in breast cancer patients. Although previous research studies have has identified many risk factors for BCRL, dietary habits and catheterization type have rarely been studied until the present.

AIM

This study aims to explore the effects of nursing factors such as dietary habits and catheterization type on breast cancer-related lymphedema (BCRL).

METHODS

This retrospective cohort study included 1,476 breast cancer patients who underwent surgery between January 1, 2012, and September 1, 2020. Lymphedema was assessed with a validated self-report questionnaire. All research data were obtained from medical records and a follow-up database. Multivariate Cox regression was conducted to explore the effects of dietary habits and catheterization type on BCRL.

RESULTS

The results showed an increased risk for BCRL among breast cancer patients who followed a high-fat diet prehospitalization (HR = 2.47; 95% CI = 1.55-3.94; P < 0.001), indwelling totally implantable venous access ports (TIVAPs) compared with indwelling needles (HR = 0.56; 95% CI = 0.35-0.90;P = 0.017) or indwelling peripherally inserted central catheters (PICCs) (HR = 0.69; 95% CI = 0.45-1.05; P = 0.086).

CONCLUSION

High-fat diet pre-hospitalization was an independent risk factor for lymphedema. The TIVAPs did not exert a protective effect on lymphedema compared with the PICC and indwelling needle. This study finding offers new insights to develop targeted interventions to decrease the incidence of lymphedema.

Machine Learning Predicts Peripherally Inserted Central Catheters-Related Deep Vein Thrombosis Using Patient Features and Catheterization Technology Features

This study aims to use patient feature and catheterization technology feature variables to train the corresponding machine learning (ML) models to predict peripherally inserted central catheters-deep vein thrombosis (PICCs-DVT) and analyze the importance of the two types of features to PICCs-DVT from the aspect of "input-output" correlation. To comprehensively and systematically summarize the variables used to describe patient features and catheterization technical features, this study combined 18 literature involving the two types of features in predicting PICCs-DVT. A total of 21 variables used to describe the two types of features were summarized, and feature values were extracted from the data of 1,065 PICCs patients from January 1, 2021 to August 31, 2022, to construct a data sample set. Then, 70% of the sample set is used for model training and hyperparameter optimization, and 30% of the sample set is used for PICCs-DVT prediction and feature importance analysis of three common ML classification models (i.e. support vector classifier [SVC], random forest [RF], and artificial neural network [ANN]). In terms of prediction performance, this study selected four metrics to evaluate the prediction performance of the model: precision (P), recall (R), accuracy (ACC), and area under the curve (AUC). In terms of feature importance analysis, this study chooses a single feature analysis method based on the "input-output" sensitivity principle-Permutation Importance. For the mean model performance, the three ML models on the test set are P = 0.92, R = 0.95, ACC = 0.88, and AUC = 0.81. Specifically, the RF model is P = 0.95, R = 0.96, ACC = 0.92, AUC = 0.86; the ANN model is P = 0.92, R = 0.95, ACC = 0.88, AUC = 0.81; the SVC model is P = 0.88, R = 0.94, ACC = 0.85, AUC = 0.77. For feature importance analysis, Catheter-to-vein rate (RF: 91.55%, ANN: 82.25%, SVC: 87.71%), Zubrod-ECOG-WHO score (RF: 66.35%, ANN: 82.25%, SVC: 44.35%), and insertion attempt (RF: 44.35%, ANN: 37.65%, SVC: 65.80%) all occupy the top three in the ML models prediction task of PICCs-DVT, showing relatively consistent ranking results. The ML models show good performance in predicting PICCs-DVT and reveal a relatively consistent ranking of feature importance from the data. The important features revealed might help clinical medical staff to better understand and analyze the formation mechanism of PICCs-DVT from a data-driven perspective.

Appraising the quality standard of clinical practice guidelines related to central venous catheter-related thrombosis prevention: a systematic review of clinical practice guidelines

OBJECTIVE

To evaluate the quality and analyse the content of clinical practice guidelines regarding central venous catheter-related thrombosis (CRT) to provide evidence for formulating an evidence-based practice protocol and a risk assessment scale to prevent it.

DESIGN

Scoring and analysis of the guidelines using the AGREE II and AGREE REX scales.

DATA SOURCES

Pubmed, Embase, Cochrane Library, Web of Science, CNKI, Wanfang, VIP, and the Chinese Biomedical Literature, and the relevant websites of the guideline, were searched from 1 January 2017 to 26 March 2022.

ELIGIBILITY CRITERIA

Guidelines covering CRT treatment, prevention, or management were included from 1 January 2017 to 26 March 2022.

DATA EXTRACTION AND SYNTHESIS

Three independent reviewers systematically trained in using the AGREE II and AGREE REX scales were selected to evaluate these guidelines.

RESULTS

Nine guidelines were included, and the quality grade results showed that three were at A-level and six were at B-level. The included guidelines mainly recommended the prevention measure of central venous CRT from three aspects: risk screening, prevention strategies, and knowledge training, with a total of 22 suggestions being recommended.

CONCLUSION

The overall quality of the guidelines is high, but there are few preventive measures for central venous CRT involved in the guidelines. All preventive measures have yet to be systematically integrated and evaluated, and no risk assessment scale dedicated to this field has been recommended. Therefore, developing an evidence-based practice protocol and a risk assessment scale to prevent it is urgent.

Implementation of Tunneled Peripherally Inserted Central Catheters Placement in Cancer Patients: A Randomized Multicenter Study

This study sought to evaluate the impact of the subcutaneous tunneling technique on peripherally inserted central catheter (PICC) placement. We randomized 694 patients who needed PICC placement to either the tunneled PICCs (experimental group) or the non-tunneled PICCs (control group) from August to December 2021. The cumulative frequency of complications was assessed as the primary outcome. Secondary outcomes comprised of the amount of bleeding, catheter insertion time, self-reported pain score, and one-puncture success rate. After 6 months of follow-up, the tunneled PICCs group showed a significant decrease in the frequency of total complications, especially in infection (3.0% vs. 7.1%, p = .021) and catheter-related thrombosis (3.3% vs. 8.3%, p = .008), although approximately 0.5 ml bleeding and 3.5 min time were increased. This randomized multicenter study supports the efficacy of subcutaneous tunneling technology in reducing PICC-related complications, enhancing patient comfort, and encouraging using subcutaneous tunneling technology for PICC placement.

The clinical topography of peripherally inserted central catheter-related thrombosis in cancer patients: A prospective and longitudinal observational study based on ultrasound scans every two days

AIMS

To delineate the clinical topography of peripherally inserted central catheter (PICC)-related thrombosis in cancer patients.

BACKGROUND

Most of the clinical features of PICC-related thrombosis are based on a single follow-up, which is insufficient to reflect the full topography of a thrombosis.

DESIGN

This is an observational study conducted at West China Hospital, according to the STROBE guidelines.

METHODS

Cancer patients scheduled for PICC placement were potentially eligible; patients with contraindications to PICC placement or existing diseases affecting blood flow were excluded; and those who later withdrew or did not reply to our contact request during the follow-up period were eliminated from this study. Ultrasound was used to detect thrombosis from the insertion site, proximal insertion site, axillary vein to the subclavian vein once every two days for two weeks post insertion. The thrombosis and its involved venous segments, onset time and symptoms and signs were recorded.

RESULTS

Among the 173 included patients, 126 (72.8 %) were identified as having thrombosis. Specifically, 113 and 126 patients were identified as having thrombosis within the first three days and the first week post insertion, respectively. In the 126 patients, thrombosis occurred at the insertion site (72.8 %) concurrently with thrombosis at the proximal insertion site (n = 120, 69.4 %), thrombosis in the axillary vein (n = 94, 54.3 %), and/or thrombosis in the subclavian vein (n = 41, 23.7 %). The log-rank test demonstrated that thrombosis in these four venous segments decreased significantly from the distal to the proximal central vein (log-rank test = 117.128, P < .001). Of 31 patients (17.9 %) who presented symptomatic thrombosis, only five patients experienced obvious swelling in the upper arm, and the other 26 patients exhibited atypical symptoms, such as soreness, tightness, numbness, tingling, or other discomforts in the palm, arm, armpit, and/or shoulder. In some thrombotic cases, ultrasonic assessment of PICC-related thrombosis did not parallel clinical symptoms and signs.

CONCLUSION

PICC-related thrombosis is common and can occur very early post insertion in cancer patients, and most thromboses present atypical symptoms. More than half of the cases with thrombosis evaluated involve multiple venous segments, and the farther the venous segments are from the central vein, the higher the incidence of thrombosis tend to be and the earlier the onset time are.

RELEVANCE TO CLINICAL PRACTICE

The results highlight the importance that medical staff pay particular attention to patients with catheters in the first week post insertion and be alert to thrombosis presenting atypical symptoms while keeping in mind that clinical symptoms and signs are not reliable for diagnosing thrombosis.

CLINICAL REGESTRATION

Clinical Trials ChiCTR1900024890.

Postoperative intermittent pneumatic compression for preventing venous thromboembolism in Chinese lung cancer patients: a randomized clinical trial

BACKGROUND

Postoperative lung cancer patients belong to the high-risk group for venous thromboembolism (VTE). The standardized preventive measures for perioperative VTE in lung cancer are not perfect, especially for the prevention and treatment of catheter-related thrombosis (CRT) caused by carried central venous catheters (CVCs) in lung cancer surgery.

PATIENTS AND METHODS

This study included 460 patients with lung cancer undergoing video-assisted thoracic surgery (VATS) in our center from July 2020 to June 2021. Patients were randomized into two groups, and intraoperatively-placed CVCs would be carried to discharge. During hospitalization, the control group was treated with low-molecular-weight heparin (LMWH), and the experimental group with LMWH + intermittent pneumatic compression (IPC). Vascular ultrasound was performed at three time points which included before surgery, before discharge, and one month after discharge. The incidence of VTE between the two groups was studied by the Log-binomial regression model.

RESULTS

CRT occurred in 71.7% of the experimental group and 79.7% of the control group. The multivariate regression showed that the risk of developing CRT in the experimental group was lower than in the control group (Adjusted RR = 0.889 [95%CI0.799-0.989], p = 0.031), with no heterogeneity in subgroups (P for Interaction > 0.05). Moreover, the fibrinogen of patients in the experimental group was lower than control group at follow-up (P = 0.019).

CONCLUSION

IPC reduced the incidence of CRT during hospitalization in lung cancer patients after surgery.

TRIAL REGISTRATION

No. ChiCTR2000034511.

Development and validation of a prediction model of catheter-related thrombosis in patients with cancer undergoing chemotherapy based on ultrasonography results and clinical information

Central venous catheters can be used conveniently to deliver medications and improve comfort in patients with cancer. However, they can cause major complications. The current study aimed to develop and validate an individualized nomogram for early prediction of the risk of catheter-related thrombosis (CRT) in patients with cancer receiving chemotherapy. In total, 647 patients were included in the analysis. They were randomly assigned to the training (n = 431) and validation (n = 216) cohorts. A nomogram for predicting the risk of CRT in the training cohort was developed based on logistic regression analysis results. The accuracy and discriminatory ability of the model were determined using area under the receiver operating characteristic curve (AUROC) values and calibration plots. Multivariate logistic regression analysis showed that body mass index, risk of cancer-related thrombosis, D-dimer level, and blood flow velocity were independent risk factors of CRT. The calibration plot showed an acceptable agreement between the predicted and actual probabilities of CRT. The AUROC values of the nomogram were 0.757 (95% confidence interval: 0.717-0.809) and 0.761 (95% confidence interval: 0.701-0.821) for the training and validation cohorts, respectively. Our model presents a novel, user-friendly tool for predicting the risk of CRT in patients with cancer receiving chemotherapy. Moreover, it can contribute to clinical decision-making.

Conditional catheter-related thrombosis free probability and risk-adapted choices of catheter for lung cancer

Background

Current predictive tools assess catheter‐related thrombosis (CRT) in patients with lung cancer in a static manner at a single time point of catheterization. The subsequent hazard changes over time are unknown. The conditional catheter‐related thrombosis‐free probability (CCFP) can provide dynamic information on continual CRT‐free expectations. This study aimed to assess the CCFP and hazard rates based on risk categories and various venous access devices (VADs).

Methods

This retrospective study reviewed 939 patients with lung cancer with peripherally inserted central venous catheters (PICCs) or central venous catheters (CVCs) identified at the National Clinical Research Center for Cancer between January 1, 2015 and December 31, 2018. The incidence of CRT has also been reported. Patients were stratified into low‐ and high‐risk groups according to multivariate Cox regression analyses. CCFP is defined as the CRT‐free probability given that patients have no CRT for a definite time.

Results

A total of 507 patients with PICCs and 432 patients with CVCs were included in this study. The 3‐month CCFP increased from 74.2% at catheter insertion to 93.6% at 3 months. The hazards of CRT in the first month were highest (16.4%) and slightly thereafter. The high‐risk group initially had a higher (21.4%) but significantly decreased CRT hazard after 2 months (8.3%), whereas the low‐risk group maintained a comparable lower risk hazard of less than 5% after 1 month. In the overall cohort, patients with CVCs had lower CRT probability than those with PICCs (HR, 1.76; 95% CI: 1.28–2.41; p < 0.01). Further analysis demonstrated that compared with PICCs, CVCs provided a CRT‐free benefit in low‐risk patients (p = 0.02) but not in high‐risk patients (p = 0.06).

Conclusions

CCFP increased, and the hazards of CRT decreased over time in a risk‐dependent manner in patients with lung cancer. These valuable dynamic data may help optimize risk‐adjusted choices of VADs and risk‐adjusted prophylactic anticoagulation strategies for patients.