Li Shen

Background Urinary tract infections (UTIs) have been one of the most common bacterial infections in clinical practice worldwide. Artificial intelligence (AI) and machine learning (ML) based algorithms have been increasingly applied in UTI case identification and prediction. However, the overall performance of AI/ML algorithms in identifying and predicting UTI has not been evaluated. The purpose of this paper is to quantitatively evaluate the application value of AI/ML in identifying and predicting UTI cases. Methods MEDLINE, EMBASE, Web of Science, and PubMed databases were systematically searched for articles published up to December 31, 2023. Quality Assessment of Diagnostic Accuracy Studies tool (QUADAS-2) and Prediction Model Risk of Bias Assessment Tool (PROBAST) were used to assess the risk of bias. Study characteristics and detailed algorithm information were extracted. Pooled sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) were synthesized using a bivariate mix-effects model. Meta-regression and subgroup analysis were conducted to test the source of heterogeneity. Results In total, 11 studies with 14 AI/ML models were included in the final meta-analysis. The overall pooled AUC was 0.89 (95%CI 0.86–0.92). Additionally, the pooled Sen, Spe, PLR, NLR, and DOR were 0.78 (95%CI 0.71–0.84), 0.89 (95%CI 0.83–0.93), 6.99 (95%CI 4.38–11.14), 0.25 (95%CI 0.18–0.34) and 28.07 (95%CI 14.27–55.20), respectively. The results of meta-regression suggested that reference standard definitions might be the source of heterogeneity. Conclusion AI/ML algorithms appear to be promising to help clinicians detect and identify patients at high risk of UTIs. However, further studies are demanded to evaluate the application value of AI/ML more thoroughly.

Hand hygiene (HH) is an essential component for preventing and controlling of healthcare-associated infection (HAI), whereas compliance with HH among health care workers (HCWs) is frequently poor. This study aimed to assess compliance and correctness with HH before and after the implementation of a multimodal HH improvement strategy launched by the World Health Organization (WHO). A quasi-experimental study design including questionnaire survey generalizing possible factors affecting HH behaviors of HCWs and direct observation method was used to evaluate the effectiveness of WHO multimodal HH strategy in a hospital of Traditional Chinese Medicine. Multimodal HH improvement strategy was drawn up according to the results of questionnaire survey. Compliance and correctness with HH among HCWs were compared before and after intervention. Also HH practices for different indications based on WHO “My Five Moments for Hand Hygiene” were recorded. In total, 553 HCWs participated in the questionnaire survey and multimodal HH improvement strategy was developed based on individual, environment and management levels. A total of 5044 observations in 23 wards were recorded in this investigation. The rate of compliance and correctness with HH improved from 66.27% and 47.75% at baseline to 80.53% and 88.35% after intervention. Doctors seemed to have better compliance with HH after intervention (84.04%) than nurses and other HCWs (81.07% and 69.42%, respectively). When stratified by indication, compliance with HH improved for all indications after intervention (P < 0.05) except for “after body fluid exposure risk” and “after touching patient surroundings”. Implementing the WHO multimodal HH strategy can significantly improve HH compliance and correctness among HCWs.

LAPTM4B is a newly cloned gene that shows an active role in many solid tumors progression in substantial researches, mainly through the autophage function. Accumulated studies have been conducted to determine the association of LAPTM4B polymorphism with cancer risk. While the results are inconsistent, we conducted the meta-analysis to determine the strength of the relationship. Results showed that allele*2 carriers exhibited a significantly increased risk of cancer development with comparison to allele*1 homozygote (for *1/2, OR = 1.55, 95% CI 1.367-1.758; for *2/2, OR = 2.093, 95%CI 1.666-2.629; for *1/2 + *2/2, OR = 1.806, 95%CI 1.527-2.137). We also observed a significant association between *2/2 homozygote and cancer risk with comparison to allele*1 containing genotypes (OR = 1.714, 95%CI 1.408-2.088). Allele*2 is a risk factor for cancer risk (OR = 1.487, 95%CI 1.339-1.651). Stratified analysis by tumor type exhibits the significant association of this genetic variants with various cancers. In conclusion, LAPTM4B polymorphism is associated with cancer risk and allele*2 is a risk factor.