Fast Parameters Estimation in Medication Efficacy Assessment Model for Heart Failure Treatment

Abstract

Introduction. Heart failure (HF) is a common and potentially fatal condition. Cardiovascular research has focused on medical therapy for HF. Theoretical modelling could enable simulation and evaluation of the effectiveness of medications. Furthermore, the models could also help predict patients' cardiac response to the treatment which will be valuable for clinical decision-making. Methods. This study presents a fast parameters estimation algorithm for constructing a cardiovascular model for medicine evaluation. The outcome of HF treatment is assessed by hemodynamic parameters and a comprehensive index furnished by the model. Angiotensin-converting enzyme inhibitors (ACEIs) were used as a model drug in this study. Results. Our simulation results showed different treatment responses to enalapril and lisinopril, which are both ACEI drugs. A dose-effect was also observed in the model simulation. Conclusions. Our results agreed well with the findings from clinical trials and previous literature, suggesting the validity of the model.

Predicting Physiological Response in Heart Failure Management: A Graph Representation Learning Approach using Electronic Health Records

“…Among the three single data sources, Lab performs the best across all the metrics followed by Comorbidity, with Demographics performing the worst. The Lab tests DBP, SBP and SVR are considered as risk factors imperative in HF prognosis 33 and are routinely monitored as part of the EHR, so the good results are not surprising. The HF cohort predominantly consists of older patients (e.g., 74 was the most prevalent age in our ACEI cohort), who are also more likely to have multiple comorbidities 34 , such as hypertension, diabetes mellitus, atrial fibrillation, and hyperlipidemia, which further contribute to the heterogeneity of HF 35 .…”

Phase 4 Studies in Heart Failure - What is Done and What is Needed?

“…There are no right or wrong trial designs for this line of work. As there are more tools including mathematical modelling [ 163 , 164 ] or quasi-intervention, the process could be less rigorous than RCT. There will also be situations where trial level evidence is unambiguously needed to answer the questions.…”

Predicting Effectiveness of Antihypertensive Medications for Heart Failure based on Longitudinal Patient Records and Deep Learning

“…In particular, we leverage the laboratory (lab) tests as the predictive features as they signify numerical values related to various physiological measurements and could potentially provide discriminative signals indicating the course of the HF treatment. For instance, BP lab tests (i.e., DBP, SBP) monitor the overall hemodynamic evolution in HF patients [16], whereupon a relative increase in BP measurement would mean deterioration of patient's clinical status while a relative decrease in BP value likely reflects the patient's HF condition is improving. Second, unlike statistical and classical machine learning approaches, deep learning is data-driven and automatically models the complex, non-linear and long-term dependencies in EHR.…”