An early screening model for preeclampsia: utilizing zero-cost maternal predictors exclusively.

To provide a reliable, low-cost screening model for preeclampsia, this study developed an early screening model in a retrospective cohort (25,709 pregnancies) and validated in a validation cohort (1760 pregnancies). A data augmentation method (α-inverse weighted-GMM + RUS) was applied to a retrospective cohort before 10 machine learning models were simultaneously trained on augmented data, and the optimal model was chosen via sensitivity (at a false positive rate of 10%). The AdaBoost model, utilizing 16 predictors, was chosen as the final model, achieving a performance beyond acceptable with Area Under the Receiver Operating Characteristic Curve of 0.8008 and sensitivity of 0.5190. All predictors were derived from clinical characteristics, some of which were previously unreported (such as nausea and vomiting in pregnancy and menstrual cycle irregularity). Compared to previous studies, our model demonstrated superior performance, exhibiting at least a 50% improvement in sensitivity over checklist-based approaches, and a minimum of 28% increase over multivariable models that solely utilized maternal predictors. We validated an effective approach for preeclampsia early screening incorporating zero-cost predictors, which demonstrates superior performance in comparison to similar studies. We believe the application of the approach in combination with high performance approaches could substantially increase screening participation rate among pregnancies. Machine learning model for early preeclampsia screening, using 16 zero-cost predictors derived from clinical characteristics, was built on a 10-year Chinese cohort. The model outperforms similar research by at least 28%; validated on an independent cohort.

Investigating the Impact of Prompt Engineering on the Performance of Large Language Models for Standardizing Obstetric Diagnosis Text: Comparative Study.

BACKGROUND: The accumulation of vast electronic medical records (EMRs) through medical informatization creates significant research value, particularly in obstetrics. Diagnostic standardization across different health care institutions and regions is vital for medical data analysis. Large language models (LLMs) have been extensively used for various medical tasks. Prompt engineering is key to use LLMs effectively. OBJECTIVE: This study aims to evaluate and compare the performance of LLMs with various prompt engineering techniques on the task of standardizing obstetric diagnostic terminology using real-world obstetric data. METHODS: The paper describes a 4-step approach used for mapping diagnoses in electronic medical records to the International Classification of Diseases, 10th revision, observation domain. First, similarity measures were used for mapping the diagnoses. Second, candidate mapping terms were collected based on similarity scores above a threshold, to be used as the training data set. For generating optimal mapping terms, we used two LLMs (ChatGLM2 and Qwen-14B-Chat [QWEN]) for zero-shot learning in step 3. Finally, a performance comparison was conducted by using 3 pretrained bidirectional encoder representations from transformers (BERTs), including BERT, whole word masking BERT, and momentum contrastive learning with BERT (MC-BERT), for unsupervised optimal mapping term generation in the fourth step. RESULTS: LLMs and BERT demonstrated comparable performance at their respective optimal levels. LLMs showed clear advantages in terms of performance and efficiency in unsupervised settings. Interestingly, the performance of the LLMs varied significantly across different prompt engineering setups. For instance, when applying the self-consistency approach in QWEN, the F1-score improved by 5%, with precision increasing by 7.9%, outperforming the zero-shot method. Likewise, ChatGLM2 delivered similar rates of accurately generated responses. During the analysis, the BERT series served as a comparative model with comparable results. Among the 3 models, MC-BERT demonstrated the highest level of performance. However, the differences among the versions of BERT in this study were relatively insignificant. CONCLUSIONS: After applying LLMs to standardize diagnoses and designing 4 different prompts, we compared the results to those generated by the BERT model. Our findings indicate that QWEN prompts largely outperformed the other prompts, with precision comparable to that of the BERT model. These results demonstrate the potential of unsupervised approaches in improving the efficiency of aligning diagnostic terms in daily research and uncovering hidden information values in patient data.

Tracing the evolving dynamics and research hotspots of microbiota and immune microenvironment from the past to the new era.

Gut microbiota can regulate many physiological processes within gastrointestinal tract and other distal sites. Dysbiosis may not only influence chronic diseases like the inflammatory bowel disease (IBD), metabolic disease, tumor and its therapeutic efficacy, but also deteriorate acute injuries. This article aims to review the documents in this field and summarize the research hotspots as well as developing processes. Gut microbiota and immune microenvironment-related documents from 1976 to 2022 were obtained from the Web of Science Core Collection database. Bibliometrics was used to assess the core authors and journals, most contributive countries and affiliations together with hotspots in this field and keyword co-occurrence analysis. Data were visualized to help comprehension. Nine hundred and twelve documents about gut microbiota and immune microenvironment were retrieved, and the annual publications increased gradually. The most productive author, country, and affiliation were "Zitvogel L," USA and "UNIV TEXAS MD ANDERSON CANC CTR," respectively. FRONTIERS IN IMMUNOLOGY, CANCERS, and INTERNATIONAL JOURNAL OF MOLECULAR SCIENCE were the periodicals with most publications. Keyword co-occurrence analysis identified three clusters, including gut microbiota, inflammation, and IBD. Combined with the visualized analysis of documents and keyword co-occurrence as well as literature reading, we recognized three key topics of gut microbiota: cancer and therapy; immunity, inflammation and IBD; acute injuries and metabolic diseases. This article revealed researches on gut microbiota and immune microenvironment were growing. More attention should be given to the latest hotspots like gut microbiota, inflammation, IBD, cancer and immunotherapy, acute traumas, and metabolic diseases.IMPORTANCEGut microbiota can regulate many physiological processes within gastrointestinal tract and other distal sites. Dysbiosis may not only influence chronic diseases like inflammatory bowel disease (IBD), metabolic disease, tumor and its therapeutic efficacy, but also deteriorate acute injuries. While the application of bibliometrics in the field of gut microbiota and immune microenvironment still remains blank, which focused more on the regulation of the gut microbiota on the immune microenvironment of different kinds of diseases. Here, we intended to review and summarize the presented documents in gut microbiota and immune microenvironment field by bibliometrics. And we revealed researches on gut microbiota and immune microenvironment were growing. More attention should be given to the latest hotspots like gut microbiota, inflammation, IBD, cancer and immunotherapy, acute traumas, and metabolic diseases.

Identification of Chlorophyll Metabolism- and Photosynthesis-Related Genes Regulating Green Flower Color in Chrysanthemum by Integrative Transcriptome and Weighted Correlation Network Analyses.

Green chrysanthemums are difficult to breed but have high commercial value. The molecular basis for the green petal color in chrysanthemum is not fully understood. This was investigated in the present study by RNA sequencing analysis of white and green ray florets collected at three stages of flower development from the F1 progeny of the cross between Chrysanthemum × morifolium "Lüdingdang" with green-petaled flowers and Chrysanthemum vistitum with white-petaled flowers. The chlorophyll content was higher and chloroplast degradation was slower in green pools than in white pools at each developmental stage. Transcriptome analysis revealed that genes that were differentially expressed between the two pools were enriched in pathways related to chlorophyll metabolism and photosynthesis. We identified the transcription factor genes CmCOLa, CmCOLb, CmERF, and CmbHLH as regulators of the green flower color in chrysanthemum by differential expression analysis and weighted gene co-expression network analysis. These findings can guide future efforts to improve the color palette of chrysanthemum flowers through genetic engineering.