Pharmacokinetics and Pharmacodynamics of Clofazimine for Treatment of Cryptosporidiosis

Abstract

Infection with Cryptosporidium spp. can cause severe diarrhea, leading to long-term adverse impacts and even death in malnourished children and immunocompromised patients. The only FDA-approved drug for treating cryptosporidiosis, nitazoxanide, has limited efficacy in the populations impacted the most by the diarrheal disease, and safe, effective treatment options are urgently needed. Initially identified by a large-scale phenotypic screening campaign, the antimycobacterial therapeutic clofazimine demonstrated great promise in both in vitro and in vivo preclinical models of Cryptosporidium infection. Unfortunately, a phase 2a clinical trial in HIV-infected adults with cryptosporidiosis did not identify any clofazimine treatment effect on Cryptosporidium infection burden or clinical outcomes. To explore whether clofazimine's lack of efficacy in the phase 2a trial may have been due to subtherapeutic clofazimine concentrations, a pharmacokinetic/pharmacodynamic modeling approach was undertaken to determine the relationship between clofazimine in vivo concentrations and treatment effects in multiple preclinical infection models. Exposure-response relationships were characterized using E_max and logistic models, which allowed predictions of efficacious clofazimine concentrations for the control and reduction of disease burden. After establishing exposure-response relationships for clofazimine treatment of Cryptosporidium infection in our preclinical model studies, it was unmistakable that the clofazimine levels observed in the phase 2a study participants were well below concentrations associated with anti-Cryptosporidium efficacy. Thus, despite a dosing regimen above the highest doses recommended for mycobacterial therapy, it is very likely the lack of treatment effect in the phase 2a trial was at least partially due to clofazimine concentrations below those required for efficacy against cryptosporidiosis. It is unlikely that clofazimine will provide a remedy for the large number of cryptosporidiosis patients currently without a viable treatment option unless alternative, safe clofazimine formulations with improved oral absorption are developed. (This study has been registered in ClinicalTrials.gov under identifier NCT03341767.).

Keywords: Cryptosporidium; PK/PD; cryptosporidiosis; gastrointestinal; gastrointestinal infection; infectious diseases; pharmacodynamics; pharmacokinetics.

FIG 1

Clofazimine in vivo efficacy in mouse model of Cryptosporidium infection. (A) Mean oocyst shedding profile for each clofazimine treatment group plotted over time. A single clofazimine oral dose of various amounts was administered 4 days after oral inoculation with C. parvum. Each dose group contained four mice, and the fecal oocyst concentration for each mouse was quantified by flow cytometry. (B) Rate of reduction in log-transformed fecal oocyst concentration from day 4 to day 6 postinfection, summarized by dose group. The tops and bottoms of the boxes are the 75th and 25th percentiles, respectively, and the center line is the median. The whiskers indicate the range of data distribution that are within 1.5-fold of the interquartile range (IQR). Points that lie out of the reach of the whiskers are outliers by the 1.5 IQR rule. (C) A simple E_max model (black solid line) with 90% confidence interval (gray shaded area) was fitted to describe the relationship between average clofazimine concentration over the 24 h postdosing (Cavg_0–24) and the rate of oocyst reduction, with the model-predicted EC₅₀ marked by the red dashed line. A dichotomous approach was also taken, with an event (“1”) being defined as having less than 10% of baseline oocyst load on day 6 postinfection. (D) Logistic regression model (blue solid line) with 90% confidence interval (gray shaded area), with the model predicted EC₅₀ indicated by the red dashed line. (E and F) Last, a time-to-event outcome variable approach was employed. The number of days each mouse took to reach a 90% reduction in oocyst burden compared to the baseline oocyst concentration is summarized by dose group (E) or compared to Cavg_0–24 (F). The box plots in panel E were generated in the same fashion as those in panel B. A simple E_max model (black solid line) with 90% confidence interval (gray shaded area) was built to describe the correlation between the number of days and clofazimine Cavg_0–24 (F). The red dashed line represents EC₅₀.

FIG 2

Clofazimine pharmacokinetics and pharmacodynamics in a calf model of cryptosporidiosis. Clofazimine was administered to calves with a dosing regimen of 30 mg/kg twice daily over 5 days for a total of 10 doses. (A) Up to 15 blood samples were collected from each calf (n = 6) over time, and mean and individual clofazimine concentrations were plotted. (B) Stool samples were collected every 24 h starting on day 3 postinfection for clofazimine- and vehicle control-treated calves, and fecal oocyst counts were quantified by real-time PCR. Mean and individual oocyst counts are plotted over time. (C to F) Other pharmacodynamic outcomes, including fecal volume (C), fecal consistency score (D), urine volume (E), and clinical evaluation score (F) were recorded daily and are shown as individual values and means (standard deviations are indicated by error bars). An asterisk indicates days on which the treatment group and the control group differed significantly (P ≤ 0.05) at the collection endpoint.

FIG 3

Relationship between clofazimine treatment and pharmacodynamic outcomes in calves. The oocyst count area under the curve (AUC) for the duration of the study was calculated for each calf. The association between oocyst count AUC_24–192 and average clofazimine concentrations, Cavg_0–24 (A) and Cavg_96–108 (B), were investigated using a simple linear regression model, and the results are summarized in Table 2. Clinical outcome AUCs were also calculated for the duration of the study and compared between the treatment and control groups (C). The differences between the groups were not statistically significant after Bonferroni correction adjusting for multiple comparison. The top and bottom bars of the boxes represent the 75th and 25th percentiles, respectively, and the center lines mark the medians. The whiskers extend to the most extreme data point that is within 1.5 times the IQR away from the box. Points that fall beyond the end of the whiskers are outliers as defined by the 1.5 IQR rule.

FIG 4

Clofazimine pharmacokinetics and pharmacodynamics in phase 2a clinical trial. HIV-infected adults with cryptosporidiosis were administered clofazimine with a dosing regimen of 100 mg 3 times daily for participants who weighed ≥50 kg (n = 2 participants) or 50 mg 3 times daily for participants who weighed <50 kg (n = 10 participants) for a duration of 5 days. (A) Mean and individual clofazimine concentrations plotted over time. (B) Stool samples were collected and assessed three times a day, and oocyst shedding was quantified using qPCR. Mean daily oocyst shedding in the first stool was compared between clofazimine treatment group and the control group. (C) For each participant, the rate of reduction in daily oocyst shedding was calculated for the first 3 days of clofazimine treatment, with the result plotted against observed clofazimine Cavg_0–24 to reveal a potential correlation between oocyst excretion rates and clofazimine concentrations. The dashed line marks no change in oocyst shedding rate. No correlation was clearly seen comparing the rate of reduction in oocyst shedding rates to clofazimine Cavg_0–24. (D) A time-to-event approach was attempted, where the time to reach 90% oocyst reduction was compared to clofazimine Cavg_0–24 and a significant correlation was not identified. (E) A Kaplan-Meier survival curve was used to compare the probability of achieving 90% reduction in oocyst count compared to the baseline count between clofazimine treatment group and the control group. A success was defined by having less than 10% of baseline oocyst count, and no significant difference was found, as shown by the log rank test (P = 0.47).