Randomized study of doxorubicin-based chemotherapy regimens, with and without sildenafil, with analysis of intermediate cardiac markers

Abstract

Background: Doxorubicin chemotherapy is used across a range of adult and pediatric malignancies. Cardiac toxicity is common, and dysfunction develops over time in many patients. Biomarkers used for predicting late cardiac dysfunction following doxorubicin exposure have shown promise. Preclinical studies have demonstrated potential cardioprotective effects of sildenafil.

Methods: We sought to confirm the safety of adding sildenafil to doxorubicin-based chemotherapy and assess N-terminal Pro-Brain Natriuretic Peptide (NT-proBNP) and high sensitivity cardiac troponin I (hsTnI) as early markers of anthracycline-induced cardiotoxicity. We randomized 27 patients (ages 31-77, 92.3% female) receiving doxorubicin chemotherapy using a blocked randomization scheme with randomly permuted block sizes to receive standard chemotherapy alone or with the addition of sildenafil. The study was not blinded. Sildenafil was dosed at 100 mg by mouth daily during therapy; patients took sildenafil three times daily on the day of doxorubicin. Doxorubicin dosing and schedule were dependent on the treatment regimen. Echocardiography was obtained prior to initiation of treatment and routinely thereafter up to 4 years. NT-proBNP and hsTnI were obtained with each cycle before, 1-3 h after, and 24 h after doxorubicin.

Results: Fourteen patients were randomized to receive standard doxorubicin chemotherapy alone (14 treated and analyzed), while 13 patients were randomized to the experimental doxorubicin and sildenafil arm (10 treated and analyzed). No toxicity signal was seen with the addition of sildenafil to doxorubicin-based regimens. There was no statistical difference between the treatment arms in relation to the change of mean left ventricular ejection fraction (LVEF) between the first and last evaluation. In both arms, hsTnI levels increased over time; however, elevated hsTnI was not associated with declines in LVEF.

Conclusion: Adding sildenafil was safe, but did not offer cardioprotection following doxorubicin treatment. Increases in hsTnI levels were observed over time, but elevations during therapy did not correlate with subsequent decreases in LVEF.

Trial registration: This clinical trial (NCT01375699) was registered at www.clinicaltrials.gov on June 17, 2011.

Keywords: Anthracycline; Biomarker; Cardioprotection; Chemotherapy; Clinical trial; Doxorubicin; Ejection fraction; Strain.

Fig. 1

CONSORT diagram. 31 patients were screened, 27 patients were randomized, and 24 patients were treated with doxorubicin alone or a combination of doxorubicin and sildenafil. Patients were followed up for echocardiograms for up to 4 years after completing chemotherapy

Fig. 2

Changes in LVEF. Of the 24 treated patients, 16 experienced LVEF decline following doxorubicin treatment. 7/10 Patients on doxorubicin-sildenafil and 9/14 patients on doxorubicin only experienced LVEF declines of any grade. LVEF change ranged from a decline of 16.5 percentage points to an increase of 10 percentage points with no significant difference between treatment arms (p = 0.48)

Fig. 3

Mean hsTnI by Cycle. a Mean hsTnI concentrations increased throughout treatment for all outcome groups, indicating cumulative cardiac injury. All values were below what would be clinically detected in a standard troponin screening. Measuring hsTnI during the period of chemotherapy treatment did not predict later heart function decline as measured by either b LVEF or c strain. d There was a statically significant increase between pre- and post- doxorubicin hsTnI values for patients during cycle 2 and cycle 4 (p-value = 0.0029, 0.0059 respectively), an effect not observed with cycle 1 or 3 (p-value = 0.7596, 0.2742 respectively)

Fig. 4

Linear Mixed Model Predictions of Biomarker Concentrations. a and b Linear mixed model analysis of hsTnI concentrations on the day following doxorubicin infusion demonstrated no significant difference between treatment arms or outcome groups. c Linear mixed model analysis of NT-proBNP concentrations on the day following doxorubicin infusion demonstrated significantly higher concentrations in the treatment arm receiving sildenafil

Fig. 5

Mean NT-proBNP by Cycle. All a treatment arms and b and c outcome groups experienced temporary spikes in NT-proBNP levels on the day following doxorubicin infusion. However, these levels did not significantly change over the course of chemotherapy