Biomarker Stroke Prediction

This project explores the link between mitochondrial oxidative phosphorylation (OxPhos) abnormalities and stroke risk in patients with advanced congestive heart failure (CHF) undergoing continuous-flow left ventricular assist device (CF-LVAD) implantation. Stroke remains a significant complication for this patient population, and prior ischemic events may predispose individuals to systemic mitochondrial dysfunction, exacerbating their risk of new strokes post-implantation.

In this study, OxPhos complex proteins (complex I [C.I] through complex V [C.V]) were measured in blood leukocytes of 50 CF-LVAD patients, evenly split between those with and without prior stroke histories. Key findings revealed:

Patients with a history of stroke exhibited significantly lower levels of C.I, C.II, C.IV, and C.V proteins in both pre-and post-CF-LVAD implantation compared to those without prior strokes. Post-CF-LVAD, oxidative phosphorylation protein levels were markedly reduced in the prior-stroke group compared to baseline. Using machine learning techniques, including Least Absolute Shrinkage and Selection Operator (LASSO) and Random Forest models, the study identified six prognostic factors that accurately predicted postoperative stroke risk, achieving an area under the receiver operating characteristic (ROC) curve (AUC) of 0.93. These findings highlight a novel association between mitochondrial dysfunction at the systemic level and stroke risk in this patient group.

The project underscores the potential of OxPhos protein expression as a biomarker for identifying patients at heightened risk of stroke following CF-LVAD implantation. Further research will refine these biomarkers and explore targeted interventions to mitigate postoperative stroke risk in CHF patients.

Paper published in American Society for Artificial Internal Organs (ASAIO): Machine Learning Assisted Stroke Prediction in Mechanical Circulatory Support: Predictive Role of Systemic Mitochondrial Dysfunction