INJEX system

An intelligent OCR-LLM prescription review system for inpatient narcotic and psychotropic drugs: Development and retrospective validation.

Ma Rong R, Xu Kai K, Zhang Mingming M, Li Xiangpeng X et al.

This study aimed to construct an intelligent prescription review system for inpatient narcotic and psychotropic drugs based on deep learning-based optical character recognition (OCR) and a local large language model (LLM) and evaluate its review performance and closed-loop management value. This study adopted a combined system development and retrospective validation design. Prescription images were first processed using OCR for text recognition and layout reconstruction. A local LLM was then applied to convert unstructured prescription text into standardized JavaScript Object Notation-formatted data. Subsequently, a locally developed rule base for narcotic and psychotropic drugs was used to evaluate prescription completeness, diagnosis-based dosage limits, medication instructions, physician signatures, and residual drug handling for injectable formulations. Using pharmacists' manual review results as the reference standard, 500 inpatient prescriptions for narcotic and psychotropic drugs were retrospectively included. System performance was evaluated in terms of accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, and Cohen's kappa coefficient. The system successfully implemented prescription image recognition, text structuring, rule-based validation, signature verification, residual drug calculation, and triggers for manual pharmacist review. In the retrospective validation, compared with pharmacists' manual review, the system identified 144 true positives, 16 false positives, 334 true negatives, and 6 false negatives. The overall accuracy was 95.6%, sensitivity was 96.0%, specificity was 95.4%, positive predictive value was 90.0%, negative predictive value was 98.2%, F1 score was 0.929, and Cohen's kappa coefficient was 0.897. The proposed OCR-LLM-based intelligent prescription review system for inpatient narcotic and psychotropic drugs demonstrates high accuracy and strong consistency. It can serve as a front-end screening and decision-support tool for pharmacists and provides technical support for standardized, traceable, and closed-loop management of specially controlled medications.

Schwann Cells in Physical Nerve Injury and Tumor Perineural Invasion: A Functional Overview and Comparison.

Zheng Yanni Y, Chen Xin X, Liu Jiachen J, Chen Jiayi J et al.

The nervous system exhibits remarkable stability, making its repair challenging. Compared to the central nervous system, peripheral nerve injuries demonstrate a greater potential for regeneration. Schwann cells, the unique myelinating glial cells of the peripheral nervous system, possess striking plasticity and support nerve regeneration through phenotypic transformation following injury. While Schwann cells are essential for nerve regeneration after injury, in the context of tumors, their reparative function is exploited to facilitate perineural invasion and the progression of cancer. However, the tumor-promoting effect of Schwann cells is context-dependent, and emerging evidence suggests that under specific conditions, Schwann cells may exert tumor-suppressive functions. This article aims to explore the complex roles of Schwann cells in both physical nerve injury and tumor-induced nerve damage, comparing their similarities and differences and seeking to provide insights for future research and potential therapeutic interventions.

Sexual health in patients with Turner syndrome: Outcomes from patient-reported outcomes measurement information system survey and body image scale.

Boedeker David D, Hunkler Kiley K, Welch Eva E, Neumann Brooke B et al.

Summarizing the evidence on health-system impacts of smart pump interoperability: A scoping review.

Glashan Elizabeth V EV, Nguyen Linh L, Xiong Shi Yi SY, Kung Janice Y JY et al.

Smart pump interoperability integrates infusion pumps with a healthcare facility's electronic health record to reduce the risk of intravenous medication errors. The purpose of this scoping review was to summarize and characterize the literature regarding health-system impacts from implementation of smart pump interoperability and identify gaps in research. A literature search was designed in collaboration with a medical librarian. Articles that studied impacts from implementation of smart pump interoperability in the acute care setting were identified. The following databases were searched from inception to 2025: MEDLINE, Embase, PubMed, Cochrane Library, CINAHL, Scopus, and TRIP (Turning Research Into Practice). The first 200 results from Google Scholar and bibliographies from included articles were screened. A structured search for gray literature was performed in Google. Data relating to the research question was extracted from each included article using a standardized data charting tool. Extracted data was analyzed descriptively to characterize the literature. Using predefined eligibility criteria, 1,452 titles and abstracts were screened, and 82 articles were selected for full-text review. Thirteen articles were included in this review. Varying study designs and methods have been used to examine health-system impacts resulting from the implementation of smart pump interoperability. Outcomes relating to patient safety, organizational finances, workflow and staff perception, documentation, and infusion data have been studied. Implementation is complex. Challenges to implementation and corresponding solutions have been detailed in the literature. Long-term studies with large sample sizes would strengthen the evidence regarding health-system impacts from smart pump interoperability.