Defining the Therapeutic Range for Adalimumab and Predicting Response in Psoriasis: A Multicenter Prospective Observational Cohort Study

Abstract

Biologics have transformed management of inflammatory diseases. To optimize outcomes and reduce costs, dose adjustment informed by circulating drug levels has been proposed. We aimed to determine the real-world clinical utility of therapeutic drug monitoring in psoriasis. Within a multicenter (n = 60) prospective observational cohort, 544 psoriasis patients were included who were receiving adalimumab monotherapy and had at least one serum sample and Psoriasis Area and Severity Index (PASI) score available within the first year. We present models giving individualized probabilities of response for any given drug level: a minimally effective drug level of 3.2 μg/ml discriminates responders (PASI75 indicates 75% improvement in baseline PASI) from nonresponders, and gives an estimated PASI75 probability of 65% (95% confidence interval = 60-71). At 7 μg/ml, PASI75 probability is 81% (95% CI = 76-86); beyond 7 μg/ml, the drug level/response curve plateaus. Crucially, drug levels are predictive of response 6 months later, whether sampled early or at steady state. We confirm serum drug level to be the most important factor determining treatment response, highlighting the need to take drug levels into account when searching for biomarkers of response. This real-world study with pragmatic drug level sampling provides evidence to support the proactive measurement of adalimumab levels in psoriasis to direct treatment strategy, and is relevant to other inflammatory diseases.

Figure 1

Flow diagram of patients and samples. Flow diagram showing the rules applied to derive the three datasets. PASI, Psoriasis Area and Severity Index.

Figure 2

Timeline of drug levels and response in each dataset. Timeline showing when drug level and response were measured in each of the three datasets. In the therapeutic range dataset, response was measured on the same day as drug level. The other two datasets were derived to investigate use of drug levels to predict response 6 months later: in the early dataset, response was measured at 6 months after start of treatment; in the steady state dataset, response was measured 6 months after drug level. Statistical analyses conducted using each dataset are also shown. ROC, receiver operating characteristic.

Figure 3

(a) Empirical ROC curve. (b) Concentration effect curve. (a) Empirical ROC curve for PASI75 response. Cutpoint (red dot) chosen to provide a minimum sensitivity of 80%. (b) Concentration effect curve of median percentage change in PASI against median drug level. These summaries are calculated for approximately equally sized groups of observations (between 23 and 52) having similar drug levels. Vertical bars: interquartile range (IQR); grey horizontal lines: indicators of PASI75 and PASI90 response; red dot: drug level beyond which clinical response plateaus. IQR, interquartile range; PASI, Psoriasis Area and Severity Index; PASI75, 75% improvement in baseline PASI; ROC, receiver operating characteristic.

Figure 4

Probability of PASI75 based on same-day drug level (therapeutic range dataset). Probability of response is split by ethnicity (red = white ethnicity, teal = all other ethnicities). The grey vertical line is at a drug level of 7 μg/ml, where there is at least 80% probability of response on average for all patients. This line crosses the red curve for patients of white ethnicity at a probability of response greater than 80%, but the probability is lower for the non-white group (teal line).The orange dots indicate the proportion of patients per group achieving PASI75. The groups are calculated in the same way as for the concentration effect curve in Figure 2b, and they are not split by other covariates. The probabilities are marginal predicted means because of the inclusion of a random effect in the model. Similar curves are seen for probability of PASI75 in the other datasets (early and steady state). PASI75, 75% improvement in baseline PASI.