Back

HAI-VECT(SCD): AI-Humanoid Enabled Virtual Clinical Trial for Sickle Cell Disease

Danter, W. R.

2023-10-18 pharmacology and therapeutics
10.1101/2023.10.17.23297152 medRxiv
Show abstract

BackgroundSickle Cell Disease (SCD) remains a globally important disorder with limited therapeutic options. This study utilizes the advanced capabilities of the DeepNEU(C) platform v8.2 and aiHumanoid (Pat. Pend.) simulations to evaluate potential drug combinations for treating SCD, focusing on vaso-occlusive events (VOE) and associated secondary outcomes. MethodsUsing data from 25 virtual patients in each of six treatment groups, therapeutic responses to each treatment were investigated. The study evaluated the primary outcome of VOE and secondary outcomes, including HbA, HbF, Quality of Life (QoL), RBC hemolysis, and Pain. Treatment toxicities were also assessed across all dosage levels. ResultsThe combination of Endari (L-glutamine powder) plus Crizanlizumab (a P-selectin antibody) demonstrated superior efficacy, with significant improvements in primary and secondary endpoints. This regimen, along with Voxelotor (a hemoglobin S polymerization inhibitor) plus Crizanlizumab, showed promising reductions in VOE, RBC hemolysis, and enhanced QoL scores. Notably, these results align with existing literature emphasizing the benefits of combination therapies in SCD management. Furthermore, aiHumanoid simulations indicated that these treatment combinations present lower cumulative multi-organoid toxicity, potentially translating to better patient outcomes and reduced healthcare costs. ConclusionAI-driven virtual clinical trials offer an innovative approach in evaluating drug combinations, presenting a robust case for the efficacy of Endari plus Crizanlizumab in managing SCD. The results warrant further research and real-world trials, potentially reshaping clinical guidelines for SCD treatment.

Matching journals

The top 8 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.