Post written by Hassam Ali, MD, from Gastroenterology & Hepatology, East Carolina University/Brody School of Medicine, Greenville, North Carolina, USA.

The present study investigates GI bleeding in patients with left ventricular assist devices (LVADs). We aimed to understand the risk factors associated with this condition and to develop a predictive model using machine learning.

GI bleeding is a frequent and severe adverse event in LVAD patients. Understanding its incidence, management, and development of a predictive model are essential for enhancing patient care. Our study addresses this gap, contributing to better understanding and managing of GI bleeding in these patients, thereby improving their overall treatment outcomes and quality of life.

In the study, out of 557 LVAD implants, 23.7% experienced GI bleeding, with gastric and non-duodenum small intestinal sites most common. A total of 429 procedures were performed, with EGD the most frequent. Video capsule endoscopy showed the highest diagnostic yield. Most GI bleeds were treated endoscopically, with hemostatic interventions possible in a significant percentage of these procedures.

The study successfully developed a predictive model that identifies patients at high risk for GI bleeding. The findings call for further research to refine these predictive models and explore more effective strategies for managing GI bleeding in LVAD patients.

This study stands out for reporting incidence of GI bleeding in LVAD patients and its management. It also reports the innovative use of machine learning in a clinical setting, representing a step forward for risk stratification and patient management.

Risk prediction nomogram for GI bleeding in left ventricular assist device (LVAD) patients incorporating warfarin use (1 = yes; 0 = no), acute antiplatelet use (1 = yes; 0 = no), and destination therapy as indication of LVAD placement (1 = yes; 0 = no).

Visit iGIE’s Facebook, Twitter, and YouTube accounts for more content from the ASGE peer-reviewed journal that launched in December 2022.

Read the full article online.

The information presented in Endoscopedia reflects the opinions of the authors and does not represent the position of the American Society for Gastrointestinal Endoscopy (ASGE). ASGE expressly disclaims any warranties or guarantees, expressed or implied, and is not liable for damages of any kind in connection with the material, information, or procedures set forth.