Many branches of the industry are joining the hype around using deep neural networks or complex machine learning approaches, eg gradient boosting machines, random forests. However, I am sceptical that these “black box” algorithms will make major contributions to drug development, since the problems in clinical trials seems conceptually different from, eg image or speech…
In randomized controlled clinical trials, the confounding of the treatment with other factors (sex, age, other patient characteristics) at baseline is of crucial importance as well as maintaining the integrity of the treatment during the trial. However, an important uncontrolled factor violating the integrity of the treatment is patient behaviour, especially in response to his…
Immuno-oncology drugs stimulate the immune-system of the patient to fight cancer cells. These effects might be enhanced by using Pawlowing conditioning of external stimuli to the drug. For example, Pawlow demonstrated that by exposing dogs (cf patients) to the ringing of a bell (eg white coat of clinician) during feeding time, the unconditioned reaction of…