Skip to main content

Table 5 Operating characteristics of EffTox designs with 30 patients in cohorts of 3 and ESS=0.5, 1.3 and 1.5

From: Implementing the EffTox dose-finding design in the Matchpoint trial

Scenario   Dose 1 Dose 2 Dose 3 Dose 4 Stop
  Pr(Eff) 0.20 0.30 0.50 0.60  
1: Pr(Tox) 0.03 0.05 0.10 0.30  
monotonic, Utility -0.33 -0.17 0.16 0.22  
dose 4 ESS=0.5 0.01 0.01 0.34 0.63 0.01
optimal ESS=1.3 <0.01 <0.01 0.22 0.76 <0.01
  ESS=1.5 <0.01 <0.01 0.22 0.77 <0.01
  Pr(Eff) 0.40 0.60 0.75 0.79  
2: Pr(Tox) 0.10 0.25 0.55 0.60  
monotonic, Utility -0.01 0.25 0.12 0.08  
dose 2 ESS=0.5 0.06 0.59 0.32 <0.01 0.03
optimal ESS=1.3 0.03 0.60 0.35 <0.01 0.01
  ESS=1.5 0.03 0.57 0.39 <0.01 0.01
  Pr(Eff) 0.25 0.40 0.60 0.60  
3: Pr(Tox) 0.10 0.20 0.38 0.42  
eff. plateau, Utility -0.26 0.04 0.15 0.12  
dose 3 ESS=0.5 0.03 0.10 0.70 0.13 0.04
optimal ESS=1.3 0.01 0.10 0.73 0.13 0.02
  ESS=1.5 0.01 0.09 0.73 0.15 0.02
  Pr(Eff) 0.50 0.60 0.70 0.80  
4: Pr(Tox) 0.20 0.20 0.20 0.20  
tox. plateau, Utility 0.12 0.28 0.43 0.57  
dose 4 ESS=0.5 0.02 0.03 0.61 0.34 <0.01
optimal ESS=1.3 <0.01 0.02 0.47 0.50 <0.01
  ESS=1.5 <0.01 0.01 0.47 0.51 <0.01
  Pr(Eff) 0.05 0.08 0.20 0.25  
  Pr(Tox) 0.05 0.08 0.12 0.14  
5: Utility -0.58 -0.54 -0.34 -0.26  
all doses ESS=0.5 0.06 0.03 0.01 0.37 0.53
inactive ESS=1.3 0.06 0.07 0.02 0.34 0.51
  ESS=1.5 0.07 0.08 0.02 0.36 0.48
  Pr(Eff) 0.05 0.08 0.12 0.25  
6: Pr(Tox) 0.60 0.65 0.70 0.80  
all doses Utility -0.78 -0.78 -0.76 -0.67  
too toxic ESS=0.5 0.09 0.01 0.01 0.01 0.88
and inactive ESS=1.3 0.06 0.01 0.01 0.01 0.91
  ESS=1.5 0.04 0.01 0.01 0.01 0.93
  1. In Matchpoint, we use the model with ESS=1.3. In each scenario section, the probabilities of efficacy and toxicity are given, in addition to the utility scores determined by (5). Dose i is the probability that dose-level i is recommended for further research, for i=1,…,4. Stop is the probability of stopping and recommending no dose. In rows pertaining to design performance, the correct decision is in bold and the admissible decisions are underlined. When stopping is the correct decision, stopping is the only admissible decision. The EffTox software gives selection probabilities to the nearest whole percent