Table 1 Self-Evaluation scheme.

From: A clinical decision support system for AI-assisted decision-making in response-adaptive radiotherapy (ARCliDS)

TC

NTC

Relation

Remark

Positive clinical outcome

 1

0

\(|Al - Cl| \le 10\%\) of \(D_{max}\)

Good

 1

0

\(|Al - Cl| > 10\%\) of \(D_{max}\)

Not sure

Negative clinical outcome

 0

0

\(Al \le Cl\)

Bad

 0

0

\(Al > Cl\)

Good

 0

1

\(Al < Cl\)

Good

 0

1

\(Al \ge Cl\)

Bad

 1

1

\(Al < Cl\)

Good

 1

1

\(Al \ge Cl\)

Bad

  1. Evaluation scheme for AI recommendation is based on the positive relation between radiation dose and treatment outcomes, i.e., both TCP and NTCP increases with an increase in radiation dose. Here TC and NTC are clinical treatment outcome. TC = 1 and NTC = 0 are the only clinically positive outcome. For a patient with known treatment outcome, we can evaluate an AI recommendation by comparing it with the retrospective clinical decision. For instance, for a patient with TC = 0 and NTC = 0, a higher dose recommendation is good, while for a patient with TC = 1 and NTC = 1, a lower dose recommendation is good, and for a patient with TC=0, NTC=1, a lower dose recommendation is good. For the clinically positive cases, we cannot judge for sure if a recommendation is good unless it is within a window of the clinical dose decision. We have set the window to be 10% of the maximum dose used in the modeling.
  2. Al ARCliDS recommendation, Cl clinical decision, TC tumor control, NTC radiation-induced normal tissue complication, \(D_{max}\) maximum dose value used in modeling, 0, no event; 1, event.
Back to article page