Machine learning estimated probability of relapse in early-stage non-small-cell lung cancer patients with aneuploidy imputation scores and knowledge graph embeddings

Buosi, Samuele; Timilsina, Mohan; Janik, Adrianna; Costabello, Luca; Torrente, María; Provencio, Mariano; Fey, Dirk; Nováček, Vít

doi:10.1016/j.eswa.2023.121127

Cited by 2 publications

(1 citation statement)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Khobragade et al [9] combine a simplified graph attention mechanism with a neural network to learn KG embeddings without negative sampling requirements. Buosi et al [10] use knowledge graph embedding to train models in order to predict recurrence in early stage non-small cell lung cancer patients, which can be used as an effective complement in classification systems and contribute to the treatment of cancer patients. Jiang et al [11] perform link prediction of knowledge graphs based on KG embedding of multi-source hierarchical neural networks to cope with the heterogeneity of KG entities and relationships, and effectively extract complex graph information.…”

Section: A Knowledge Graph Embeddingmentioning

confidence: 99%

Vaccine Coverage and Effectiveness in a School-Based Varicella Outbreak in Jinan Prefecture, Shandong Province

Liu

et al. 2022

Vaccines

View full text Add to dashboard Cite

Background: Licheng District of Jinan Prefecture reported a school-based varicella outbreak. We conducted an investigation to analyze the epidemiology and scope of the outbreak, determine varicella vaccine coverage on the school campus, and estimate varicella vaccine effectiveness (VE). Methods: In the epidemiological investigation, we determined the attack rate, the clinical manifestations of varicella cases, and histories of prior varicella disease and varicella vaccination. We tested students for presence of serum IgM antibodies, and we attempted to isolate the varicella virus from vesicular fluid samples. We used chi-square to compare incidences between classes and floors. VE was estimated using a retrospective cohort study. Results: There were 13 varicella cases in the outbreak. All were among fourth grade students - twelve in Class 7 and one in Class 6. The attack rate in the two classrooms was 14.3% (13/91). Clinical symptoms were rash (100%) and fever (46.15%). All cases were reported within one average incubation period, and the epidemic curve suggested common exposure. Six of the 13 cases previously received one dose of varicella vaccine with a median time between vaccination and infection of 9 years; the other seven cases had not been vaccinated. Varicella vaccine coverage with one or more doses was 81.31%; 2-dose coverage was 38.15%. The median age of receipt of dose 1 was 1.18 years, and median age for receiving dose 2 was 5.12 years. One-dose varicella VE was 73.2% (95% confidence interval: 37.0%, 88.6%), and two-dose VE was 100%. Conclusions: Varicella vaccine coverage has been gradually increasing in recent years, as ≥1-dose and 2-dose coverage rates are higher in younger children than older children. High one-dose vaccination coverage limited the outbreak scope and led to the breakthrough cases being mild. Mild cases were difficult to detect in a timely manner. Varicella vaccine was highly effective, with 1-dose VE of 73% nine years after vaccination and 2-dose VE of 100%. We strongly recommended that all school students receive two doses of varicella vaccine.

show abstract

Section: A Knowledge Graph Embeddingmentioning

confidence: 99%