Search

Background Donepezil, galantamine, rivastigmine and memantine are potentially effective interventions for cognitive impairment in dementia, but the use of these drugs has not been personalised to individual patients yet. We examined whether artificial intelligence-based recommendations can identify the best treatment using routinely collected patient-level information. Methods Six thousand eight hundred four patients aged 59–102 years with a diagnosis of dementia from two National Health Service (NHS) Foundation Trusts in the UK were used for model training/internal validation and external validation, respectively. A personalised prescription model based on the Recurrent Neural Network machine learning architecture was developed to predict the Mini-Mental State Examination (MMSE) and Montreal Cognitive Assessment (MoCA) scores post-drug initiation. The drug that resulted in the smallest decline in cognitive scores between prescription and the next visit was selected as the treatment of choice. Change of cognitive scores up to 2 years after treatment initiation was compared for model evaluation. Results Overall, 1343 patients with MMSE scores were identified for internal validation and 285 [21.22%] took the drug recommended. After 2 years, the reduction of mean [standard deviation] MMSE score in this group was significantly smaller than the remaining 1058 [78.78%] patients (0.60 [0.26] vs 2.80 [0.28]; P = 0.02). In the external validation cohort (N = 1772), 222 [12.53%] patients took the drug recommended and reported a smaller MMSE reduction compared to the 1550 [87.47%] patients who did not (1.01 [0.49] vs 4.23 [0.60]; P = 0.01). A similar performance gap was seen when testing the model on patients prescribed with AChEIs only. Conclusions It was possible to identify the most effective drug for the real-world treatment of cognitive impairment in dementia at an individual patient level. Routine care patients whose prescribed medications were the best fit according to the model had better cognitive performance after 2 years.

Background miRNAs are a class of non-coding RNA molecules that play crucial roles in the regulation of virus-host interactions. The ever-increasing data of known viral miRNAs and human protein interaction network (PIN) has made it possible to study the targeting characteristics of viral miRNAs in the context of these networks. Results We performed topological analysis to explore the targeting propensities of herpesvirus miRNAs from the view of human PIN and found that (1) herpesvirus miRNAs significantly target more hubs, moreover, compared with non-hubs (non-bottlenecks), hubs (bottlenecks) are targeted by much more virus miRNAs and virus types. (2) There are significant differences in the degree and betweenness centrality between common and specific targets, specifically we observed a significant positive correlation between virus types targeting these nodes and the proportion of hubs, and (3) K-core and ER analysis determined that common targets are closer to the global PIN center. Compared with random conditions, the giant connected component (GCC) and the density of the sub-network formed by common targets have significantly higher values, indicating the module characteristic of these targets. Conclusions Herpesvirus miRNAs preferentially target hubs and bottlenecks. There are significant differences between common and specific targets. Moreover, common targets are more intensely connected and occupy the central part of the network. These results will help unravel the complex mechanism of herpesvirus-host interactions and may provide insight into the development of novel anti-herpesvirus drugs.