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

Abstract

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.

Keywords

• Peripherally inserted central catheter
• Thrombosis
• Deep learning
• Prediction model