PATIENTS AND METHODS: APEC was a nonrandomized phase 2 trial conducted in the Asia-Pacific region. Patients (n = 289) received once-every-2-weeks cetuximab with investigator's choice of chemotherapy (FOLFOX or FOLFIRI). The primary end point was best confirmed overall response rate (BORR); progression-free survival (PFS) and overall survival (OS) were secondary end points. Early tumor shrinkage (ETS) and depth of response (DpR) were also evaluated.
RESULTS: In the KRAS wt population, BORR was 58.8%, median PFS 11.1 months, and median OS 26.8 months. Expanded RAS mutational analysis revealed that patients with RAS wt mCRC had better outcomes (BORR = 64.7%; median PFS = 13.0 months; median OS = 28.4 months). The data suggest that ETS and DpR may be associated with survival outcomes in the RAS wt population. Although this study was not designed to formally assess differences in outcome between treatment subgroups, efficacy results appeared similar for patients treated with FOLFOX and FOLFIRI. There were no new safety findings; in particular, grade 3/4 skin reactions were within clinical expectations.
CONCLUSION: The observed activity and safety profile is similar to that reported in prior first-line pivotal studies involving weekly cetuximab, suggesting once-every-2-weeks cetuximab is effective and tolerable as first-line therapy and may represent an alternative to weekly administration.
OBJECTIVE: The aim of this proof-of-concept study was to evaluate whether combining population pharmacokinetic and machine learning approaches could provide a more accurate prediction of the clearance of renally eliminated drugs in individual neonates.
METHODS: Six drugs that are primarily eliminated by the kidneys were selected (vancomycin, latamoxef, cefepime, azlocillin, ceftazidime, and amoxicillin) as 'proof of concept' compounds. Individual estimates of clearance obtained from population pharmacokinetic models were used as reference clearances, and diverse machine learning methods and nested cross-validation were adopted and evaluated against these reference clearances. The predictive performance of these combined methods was compared with the performance of two other predictive methods: a covariate-based maturation model and a postmenstrual age and body weight scaling model. Relative error was used to evaluate the different methods.
RESULTS: The extra tree regressor was selected as the best-fit machine learning method. Using the combined method, more than 95% of predictions for all six drugs had a relative error of < 50% and the mean relative error was reduced by an average of 44.3% and 71.3% compared with the other two predictive methods.
CONCLUSION: A combined population pharmacokinetic and machine learning approach provided improved predictions of individual clearances of renally cleared drugs in neonates. For a new patient treated in clinical practice, individual clearance can be predicted a priori using our model code combined with demographic data.