Could generative artificial intelligence replace fieldwork in pain research?

BACKGROUND: Generative artificial intelligence (AI) models offer potential assistance in pain research data acquisition, yet concerns persist regarding data accuracy and reliability. In a comparative study, we evaluated open generative AI models' capacity to acquire data on acute pain in rock climbers comparable to field research. METHODS: Fifty-two rock climbers (33 m/19 f; age 29.0 [24.0-35.75] years) were asked to report pain location and intensity during a single climbing session. Five generative pretrained transformer models were tasked with responses to the same questions. RESULTS: Climbers identified the back of the forearm (19.2%) and toes (17.3%) as primary pain sites, with reported median pain intensity at 4 [3-5] and median maximum pain intensity at 7 [5-8]. Conversely, AI models yielded divergent findings, indicating fingers, hands, shoulders, legs, and feet as primary pain localizations with average and maximum pain intensity ranging from 3 to 4.4 and 5 to 10, respectively. Only two AI models provided references that were untraceable in PubMed and Google searches. CONCLUSION: Our findings reveal that, currently, open generative AI models cannot match the quality of field-collected data on acute pain in rock climbers. Moreover, the models generated nonexistent references, raising concerns about their reliability.

LTBP4, SPP1, and CD40 Variants: Genetic Modifiers of Duchenne Muscular Dystrophy Analyzed in Serbian Patients.

BACKGROUND: Clinical course variability in Duchenne muscular dystrophy (DMD) is partially explained by the mutation location in the DMD gene and variants in modifier genes. We assessed the effect of the SPP1, CD40, and LTBP4 genes and DMD mutation location on loss of ambulation (LoA). METHODS: SNPs in SPP1-rs28357094, LTBP4-rs2303729, rs1131620, rs1051303, rs10880, and CD40-rs1883832 were genotyped, and their effect was assessed by survival and hierarchical cluster analysis. RESULTS: Patients on glucocorticoid corticosteroid (GC) therapy experienced LoA one year later (p = 0.04). The modifying effect of SPP1 and CD40 variants, as well as LTBP4 haplotypes, was not observed using a log-rank test and multivariant Cox regression analysis. Cluster analysis revealed two subgroups with statistical trends in differences in age at LoA. Almost all patients in the cluster with later LoA had the protective IAAM LTBP4 haplotype and statistically significantly fewer CD40 genotypes with harmful T allele and "distal" DMD mutations. CONCLUSIONS: The modifying effect of SPP1, CD40, and LTBP4 was not replicated in Serbian patients, although our cohort was comparable in terms of its DMD mutation type distribution, SNP allele frequencies, and GC-positive effect with other European cohorts. Cluster analysis may be able to identify patient subgroups carrying a combination of the genetic variants that modify LoA.