Key points are not available for this paper at this time.
Recent developments in Digital Medicine approaches concern pharmaceutical product optimization. Artificial Intelligence (AI) has multiple applications for pharmaceutical products’ lifecycle, increasing development speed, quality of the products, and efficiency of the therapy. Here, we systematically review the overall approach for AI implementation in pharmaceutical products’ lifecycle. The published studies in PubMed and IEEE Xplore were searched from inception to March 2022. The papers were screened for relevant outcomes, publication types, and data sufficiency, and a total of 73 (1.2%) out of 6131 studies were retrieved after the selection. We extracted the data according to the Preferred Reporting Items for Systematic Review and Meta-Analysis (PRISMA) statement. All Artificial Intelligence systems could be divided into multiple overlapping categories by implementation. For the 177 projects found, the most popular areas of AI implementation are clinical trials and pre-clinical tests (34%). In second place are novel small molecule design systems, with 33% of the total. The third most popular scope for AI implementation is target identification for novel medicines. More than 25% of the systems provide this functionality. It is interesting that most of the systems specialize in only one area (102 systems—57%). None of the systems provide functionality for full coverage of the lifecycle and function in all categories of the tasks. This meta-analysis demonstrated that Artificial Intelligence solutions in pharmaceutical products’ lifecycle could find numerous implementations, and none of the available market solutions covers them all.
Koshechkin et al. (Mon,) studied this question.