OBJECTIVES

Timely access to appropriate levels of care is essential for improving maternal, newborn,
and child health outcomes. To address persistent service delivery fragmentation and strengthen referral systems, the Philippine Department of Health issued Administrative Order 2020-0019 to guide the design of Health Care Provider Networks (HCPNs) under the Universal Health Care Act of 2019. This study assessed the extent to which sixteen municipalities across four provinces in Eastern Visayas comply with the HCPN service delivery guidelines in the context of maternal and newborn care.

The study employed a descriptive cross-sectional mixed-methods design, utilizing structured facility checklists to assess compliance with HCPN standards. Qualitative data were gathered through key informant interviews and focus group discussions with purposively selected stakeholders—decision makers, health personnel, and mothers—to contextualize findings. A three-lever framework for integrated care (policy, operational, and cross- cutting) guided the analysis

The findings revealed significant gaps between the current capacities of study health facilities and the requirements outlined in the HCPN guidelines. Major gaps included (1) weak cooperative governance mechanisms to support network-wide coordination; (2) limited systematic linkages between facilities, including fragmented referral protocols and non-interoperable health information systems; (3) inadequate investments in infrastructure, health human resources, and medical commodities; and (4) absence of performance monitoring systems across HCPNs.

OBJECTIVE: To investigate the current status of pre-hospital and in-hospital emergency medical information connectivity in China and provide evidence for optimizing the emergency medical system. METHODS: A multi-center cross-sectional study was conducted using a multi-level convenience sampling method to select provincial-level administrative regions and their corresponding capital cities, prefectural cities, and county-level emergency medical institutions. The questionnaire included basic information about respondents, the institutions, the current status of pre-hospital and in-hospital emergency information connectivity, and the satisfaction with the connectivity. The questionnaire has undergone reliability testing and split-half reliability testing, supplemented by semi-structured interviews. Data collection was carried out from January to May 2024, with one responsible person from each institution completing the questionnaire. Multiple Logistic regression analysis to investigated the relevant factors of pre-hospital and in-hospital information connectivity. RESULTS: A total of 225 questionnaires were distributed, and 199 valid responses were collected, with a response rate of 88.4%. Participants were from 199 emergency medical institutions across 13 provincial-level administrative regions. Of the institutions, 112 (56.3%) could achieve pre-hospital and in-hospital information connectivity. The proportion of pre-hospital to in-hospital information connection between emergency institutions in different provinces varies (χ² = 39.398, P < 0.001), with Beijing and Zhejiang having the highest proportion of information connection (both at 100%), and Hainan having the lowest (11.8%). The proportion of information integration in county-level emergency institution was lower than that of provincial and municipal level emergency institutions [40.4% (19/47) vs. 61.7% (29/47), 61.0% (64/105), χ² = 6.304, P = 0.043]. Provinces with high per capita disposable income have a higher proportion of information connectivity than provinces with low per capita disposable income [77.3% (34/44) vs. 50.3% (78/155), χ² = 10.122, P = 0.001]. The information connection ratio of independent pre-hospital emergency centers was higher than that of hospital emergency departments/hospital records [74.6% (47/63) vs. 47.8% (65/136), χ² = 12.581, P < 0.001]. The proportion of information integration in advanced provinces with digital development was higher than that in other provinces [77.6% (38/49) vs. 49.3% (74/150), χ² = 11.849, P = 0.001]. Logistic regression analysis showed that the per capita disposable income of residents in the province was an independent risk factor for the information connection between pre-hospital and in-hospital emergency institutions [odds ratio (OR) = 3.21, 95% confidence interval was 1.56-6.62, P < 0.01]. 72.3% institutions used the information connection mode for less than 5 years. Telephone and WeChat were the main communication methods (83.0%), and 17.0% of emergency institutions use dedicated APP for communication. 52.7% of respondents were very or relatively satisfied with the information integration before and after the hospital. The main deficiencies in current information integration were insufficient, untimely, inaccurate communication and delayed feedback between pre-hospital and in-hospital information. Optimizing top-level design and improving network quality are the directions for improving the integration of pre-hospital and in-hospital information in the future. CONCLUSIONS Pre-hospital and in-hospital emergency information connectivity in some provinces in China remains underdeveloped, with significant regional and institutional disparities. Future efforts should focus on integrating digital technologies and strengthening grassroots-level connectivity systems.
Cross-Sectional Studies ; China ; Humans ; Surveys and Questionnaires ; Emergency Medical Services ; Emergency Service, Hospital ; Hospital Information Systems

Biomanufacturing is an advanced manufacturing method that integrates biology, chemistry, and engineering. It utilizes renewable biomass and biological organisms as production media to scale up the production of target products through fermentation. Compared with petrochemical routes, biomanufacturing offers significant advantages in reducing CO₂ emissions, lowering energy consumption, and cutting costs. With the development of systems biology and synthetic biology and the accumulation of bioinformatics data, the integration of information technologies such as artificial intelligence, large models, and high-performance computing with biotechnology is propelling biomanufacturing into a data-driven era. This paper reviews the latest research progress on databases, knowledge bases, and large language models for biomanufacturing. It explores the development directions, challenges, and emerging technical methods in this field, aiming to provide guidance and inspiration for scientific research in related areas.
Biotechnology/methods* ; Knowledge Bases ; Synthetic Biology ; Databases, Factual ; Artificial Intelligence ; Systems Biology ; Computational Biology ; Fermentation

Natural components serve the survival instincts of cells that are obtained through long-term evolution, while they often fail to meet the demands of engineered cells for efficiently performing biological functions in special industrial environments. Enzymes, as biological catalysts, play a key role in biosynthetic pathways, significantly enhancing the rate and selectivity of biochemical reactions. However, the catalytic efficiency, stability, substrate specificity, and tolerance of natural enzymes often fall short of industrial production requirements. Therefore, exploring and modifying enzymes to suit specific biomanufacturing processes has become crucial. In recent years, artificial intelligence (AI) has played an increasingly important role in the discovery, evaluation, engineering, and de novo design of proteins. AI can accelerate the discovery and optimization of proteins by analyzing large amounts of bioinformatics data and predicting protein functions and characteristics by machine learning and deep learning algorithms. Moreover, AI can assist researchers in designing new protein structures by simulating and predicting their performance under different conditions, providing guidance for protein design. This paper reviews the latest research advances in protein discovery, evaluation, engineering, and de novo design for biomanufacturing and explores the hot topics, challenges, and emerging technical methods in this field, aiming to provide guidance and inspiration for researchers in related fields.
Protein Engineering/methods* ; Artificial Intelligence ; Proteins/genetics* ; Computational Biology ; Machine Learning ; Data Mining ; Algorithms ; Deep Learning

The application of artificial intelligence (AI) technology in the field of radiation protection is gradually becoming a key force driving industrial development. This paper focuses on the applications of AI technology in radiation monitoring, shielding design, and nuclear science data mining, and prospects its future development. Through real-time monitoring and predictive analysis, AI technology has significantly improved the accuracy and efficiency of radiation monitoring, optimized the selection and configuration of shielding materials, and effectively reduced radiation exposure. Additionally, AI's data mining capabilities provide powerful tools for nuclear reactor design and optimization, promoting innovation in nuclear and radiological sciences. Despite technical challenges and ethical issues such as accuracy, data processing, and algorithmic transparency, the application prospects of AI in radiation protection remain broad. This paper emphasizes the critical role of AI technology in enhancing medical safety and efficiency, and foresees more future innovations and applications in the field of radiation protection.
Radiation Protection/methods* ; Artificial Intelligence ; Radiation Monitoring ; Humans ; Data Mining ; Algorithms

OBJECTIVE: To implement radiological diagnostic guidelines and improve the standardization level of radiological reports. METHODS: A multimodal structured reporting system was designed. An integrated strategy of "standard coding + structural items + key images" was adopted to develop report templates for different diseases or anatomical sites, covering both text-only structured reports and comprehensive text-image structured reports. Horizontal comparisons with traditional (unstructured) reports were conducted to evaluate differences across four dimensions: efficiency, acceptability, completeness of disease sign description, and accuracy of data classification. RESULTS: The quality of comprehensive text-image structured reports was significantly superior to that of traditional reports ( P<0.01), while there was no statistically significant difference between text-only structured reports and traditional reports ( P>0.01). The information completeness and compliance with diagnostic guidelines of text-image reports were significantly higher than those of both traditional reports and text-only structured reports. The acceptability of text-image reports among senior radiologists (4.04±0.55) and clinicians (4.19±0.58) was higher than that among junior radiologists (3.04±1.55). In terms of data classification accuracy, the retrieval accuracy of structured reports based on natural language processing (NLP) (F1-Score: 0.85-1.00) was significantly better than the keyword retrieval method used for traditional reports. CONCLUSION Image-text-integrated structured reporting reduces heterogeneity in traditional reports and aids competency development among junior radiologists in primary care.
Radiology Information Systems ; Diagnostic Imaging ; Humans

OBJECTIVES: Hepatocellular carcinoma is one of the most common primary malignant tumors with the third highest mortality rate worldwide. This study aims to identify key genes associated with hepatocellular carcinoma prognosis using the Gene Expression Omnibus (GEO) database and provide a theoretical basis for discovering novel prognostic biomarkers for hepatocellular carcinoma. METHODS: Hepatocellular carcinoma-related datasets were retrieved from the GEO database. Differentially expressed genes (DEGs) were identified using the GEO2R tool. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) enrichment analyses were performed using the Database for Annotation, Visualization, and Integrated Discovery (DAVID). A protein-protein interaction (PPI) network was constructed using the Search Tool for the Retrieval of Interacting Genes/Proteins (STRING), and key genes were identified using Cytoscape software. The University of Alabama at Birmingham Cancer Data Analysis Resource (UALCAN) was used to analyze the expression levels of key genes in normal and hepatocellular carcinoma tissues, as well as their associations with pathological grade, clinical stage, and patient survival. The Human Protein Atlas (THPA) was used to further validate the impact of key genes on overall survival. Expression levels of key genes in the blood of hepatocellular carcinoma patients were evaluated using the expression atlas of blood-based biomarkers in the early diagnosis of cancers (BBCancer). RESULTS: A total of 78 DEGs were identified from the GEO database. GO and KEGG analyses indicated that these genes may contribute to hepatocellular carcinoma progression by promoting cell division and regulating protein kinase activity. Sixteen key genes were screened via Cytoscape and validated using UALCAN and THPA. These genes were overexpressed in hepatocellular carcinoma tissues and were associated with disease progression and poor prognosis. Finally, BBCancer analysis showed that ASPM and NCAPG were also elevated in the blood of hepatocellular carcinoma patients. CONCLUSIONS This study identified 16 key genes as potential prognostic biomarkers for hepatocellular carcinoma, among which ASPM and NCAPG may serve as promising blood-based markers for hepatocellular carcinoma.
Humans ; Carcinoma, Hepatocellular/mortality* ; Liver Neoplasms/pathology* ; Prognosis ; Computational Biology/methods* ; Protein Interaction Maps/genetics* ; Biomarkers, Tumor/genetics* ; Gene Expression Regulation, Neoplastic ; Gene Expression Profiling ; Gene Ontology ; Databases, Genetic

OBJECTIVES: We propose a Contrastive Regional Attention and Prior Knowledge-Infused U-Transformer model (CRAKUT) to address the challenges of imbalanced text distribution, lack of contextual clinical knowledge, and cross-modal information transformation to enhance the quality of generated radiology reports. METHODS: The CRAKUT model comprises 3 key components, including an image encoder that utilizes common normal images from the dataset for extracting enhanced visual features, an external knowledge infuser that incorporates clinical prior knowledge, and a U-Transformer that facilitates cross-modal information conversion from vision to language. The contrastive regional attention in the image encoder was introduced to enhance the features of abnormal regions by emphasizing the difference between normal and abnormal semantic features. Additionally, the clinical prior knowledge infuser within the text encoder integrates clinical history and knowledge graphs generated by ChatGPT. Finally, the U-Transformer was utilized to connect the multi-modal encoder and the report decoder in a U-connection schema, and multiple types of information were used to fuse and obtain the final report. RESULTS: We evaluated the proposed CRAKUT model on two publicly available CXR datasets (IU-Xray and MIMIC-CXR). The experimental results showed that the CRAKUT model achieved a state-of-the-art performance on report generation with a BLEU-4 score of 0.159, a ROUGE-L score of 0.353, and a CIDEr score of 0.500 in MIMIC-CXR dataset; the model also had a METEOR score of 0.258 in IU-Xray dataset, outperforming all the comparison models. CONCLUSIONS The proposed method has great potential for application in clinical disease diagnoses and report generation.
Humans ; Radiology Information Systems ; Radiology

Identification of disease-specific cell subtypes (DSCSs) has profound implications for understanding disease mechanisms, preoperative diagnosis, and precision therapy. However, achieving unified annotation of DSCSs in heterogeneous single-cell datasets remains a challenge. In this study, we developed the gPRINT algorithm (generalized approach for cell subtype identification with single cell's voicePRINT). Inspired by the principles of speech recognition in noisy environments, gPRINT transforms gene position and gene expression information into voiceprints based on ordered and clustered gene expression phenomena, obtaining unique "gene print" patterns for each cell. Then, we integrated neural networks to mitigate the impact of background noise on cell identity label mapping. We demonstrated the reproducibility of gPRINT across different donors, single-cell sequencing platforms, and disease subtypes, and its utility for automatic cell subtype annotation across datasets. Moreover, gPRINT achieved higher annotation accuracy of 98.37% when externally validated based on the same tissue, surpassing other algorithms. Furthermore, this approach has been applied to fibrosis-associated diseases in multiple tissues throughout the body, as well as to the annotation of fibroblast subtypes in a single tissue, tendon, where fibrosis is prevalent. We successfully achieved automatic prediction of tendinopathy-specific cell subtypes, key targets, and related drugs. In summary, gPRINT provides an automated and unified approach for identifying DSCSs across datasets, facilitating the elucidation of specific cell subtypes under different disease states and providing a powerful tool for exploring therapeutic targets in diseases.
Humans ; Algorithms ; Single-Cell Analysis ; Databases, Genetic ; Molecular Sequence Annotation

BACKGROUND AND OBJECTIVE

data-mce-style="text-align: justify;">There are mixed reports on nurses’ satisfaction with electronic medical records (EMR) in literature, and facilitators and barriers to its adoption were reported frequently. A Philippine public tertiary hospital developed an EMR to facilitate remote access to patient charts outside its COVID-designated areas during the pandemic. This study aims to assess nurses’ satisfaction with EMR use in order to improve their user experience. The Delone and McLean Information System (D&M IS) Success Model was used as its framework. This offers a unique perspective to EMR adoption by accounting for the effects of the pandemic.

data-mce-style="text-align: justify;">A descriptive, cross-sectional, quantitatively driven, concurrent mixed-methods design was employed. Nurses from the hospital were recruited for the survey (n=353) and the focus group discussions (n=14). Ethical approval was obtained prior to its conduct. Analysis was done through descriptive statistics, multiple linear regression, and thematic analysis. Data were integrated to appreciate the differences in their experiences from the point of adoption up to their current experiences.

data-mce-style="text-align: justify;">Nurses initially faced challenges with the EMR when it was introduced, but improvements and continuous use have led to their current high satisfaction. Despite mandatory use and high usage scores, some daily tasks are still done manually. Use, length of service, number of patients handled, designation, and area of assignment were found to be associated with satisfaction. Thematic analysis highlighted several adoption prerequisites in this setup, including assessment of user competence and experience, and the provision of training, structural necessities, and organizational support.

data-mce-style="text-align: justify;">This study found high use and satisfaction scores, aligning with the D&M IS Success Model, despite initial adoption challenges. Recommendations include maintaining high EMR use and improving efficiency, communication, and collaboration. Emphasis was placed on the provisions of better training and continuous feedback gathering.