Stefano Sinisi, Vadim Alimguzhin, Toni Mancini, Enrico Tronci, Federico Mari, Brigitte Leeners.
Optimal personalised treatment computation through in silico clinical trials on patient digital twins.
Fundamenta Informaticae, 174(3-4), pages 283-310, 2020.
DOI: 10.3233/FI-2020-1943

BibTex entry

@ARTICLE{sinisi-etal:2020:fundam,
  TITLE = {Optimal Personalised Treatment Computation through In Silico Clinical Trials on Patient Digital Twins},
  AUTHOR = {Sinisi, S. and Alimguzhin, V. and Mancini, T. and Tronci, E. and Mari, F. and Leeners, B.},
  DOI = {10.3233/FI-2020-1943},
  JOURNAL = {Fundamenta Informaticae},
  NUMBER = {3--4},
  PAGES = {283--310},
  PUBLISHER = {IOS Press},
  VOLUME = {174},
  YEAR = {2020}
}

In Silico Clinical Trials (ISCT), i.e., clinical experimental campaigns carried out by means of computer simulations, hold the promise to decrease time and cost for the safety and efficacy assessment of pharmacological treatments, reduce the need for animal and human testing, and enable precision medicine.

We developed methods and an algorithm that, by means of extensive computer simulation-based experimental campaigns (ISCT) guided by intelligent search, optimise a pharmacological treatment for an individual patient (precision medicine).

Starting from clinical data collected from a real patient, our approach first computes their digital twin, which defines a digital representation of that patient physiology. Then, by means of intelligent search on such a digital twin over large High Performance Computing (HPC) infrastructures, our algorithm computes, in silico, the lightest (in terms of overall amount of administered drug) treatment still effective for that patient.

• Effectiveness shown on a case study involving a real pharmacological treatment, namely the downregulation phase of a complex clinical protocol for assisted reproduction in humans
• Multi-arm ISCT conducted, involving 21 patients. Each patient defined a distinct arm of our ISCT.
• For each such patient, the optimal (lightest) still-effective downregulation treatment was synthesised
• Computed treatments save, on average, 59.18% of the drug administered in the reference treatment (stddev: 13%).