RESUMO
BACKGROUND: In the healthcare domain today, despite the substantial adoption of electronic health information systems, a significant proportion of medical reports still exist in paper-based formats. As a result, there is a significant demand for the digitization of information from these paper-based reports. However, the digitization of paper-based laboratory reports into a structured data format can be challenging due to their non-standard layouts, which includes various data types such as text, numeric values, reference ranges, and units. Therefore, it is crucial to develop a highly scalable and lightweight technique that can effectively identify and extract information from laboratory test reports and convert them into a structured data format for downstream tasks. METHODS: We developed an end-to-end Natural Language Processing (NLP)-based pipeline for extracting information from paper-based laboratory test reports. Our pipeline consists of two main modules: an optical character recognition (OCR) module and an information extraction (IE) module. The OCR module is applied to locate and identify text from scanned laboratory test reports using state-of-the-art OCR algorithms. The IE module is then used to extract meaningful information from the OCR results to form digitalized tables of the test reports. The IE module consists of five sub-modules, which are time detection, headline position, line normalization, Named Entity Recognition (NER) with a Conditional Random Fields (CRF)-based method, and step detection for multi-column. Finally, we evaluated the performance of the proposed pipeline on 153 laboratory test reports collected from Peking University First Hospital (PKU1). RESULTS: In the OCR module, we evaluate the accuracy of text detection and recognition results at three different levels and achieved an averaged accuracy of 0.93. In the IE module, we extracted four laboratory test entities, including test item name, test result, test unit, and reference value range. The overall F1 score is 0.86 on the 153 laboratory test reports collected from PKU1. With a single CPU, the average inference time of each report is only 0.78 s. CONCLUSION: In this study, we developed a practical lightweight pipeline to digitalize and extract information from paper-based laboratory test reports in diverse types and with different layouts that can be adopted in real clinical environments with the lowest possible computing resources requirements. The high evaluation performance on the real-world hospital dataset validated the feasibility of the proposed pipeline.
Assuntos
Algoritmos , Processamento de Linguagem Natural , Humanos , Armazenamento e Recuperação da Informação , Hospitais Universitários , Registros Eletrônicos de SaúdeRESUMO
Prostate cancer (PCa) is a critical global public health issue with its incidence on the rise. Radiation therapy holds a primary role in PCa treatment; however, radiation resistance has become increasingly challenging as we uncover more about PCa's pathogenesis. Our review aims to investigate the multifaceted mechanisms underlying radiation therapy resistance in PCa. Specifically, we will examine how various factors, such as cell cycle regulation, DNA damage repair, hypoxic conditions, oxidative stress, testosterone levels, epithelial-mesenchymal transition, and tumor stem cells, contribute to radiation therapy resistance. By exploring these mechanisms, we hope to offer new insights and directions towards overcoming the challenges of radiation therapy resistance in PCa. This can also provide a theoretical basis for the clinical application of novel ultra-high-dose-rate (FLASH) radiotherapy in the era of PCa.
RESUMO
In this study, the cyanobacterium Phormidium was grown under six different nutrient concentrations, ranging from standard AA medium to a 600× dilutions of that media. After incubation at 25 â and 2000 lx for 8 months, the growth curve for each treatment was measured by direct counting of cell numbers. Additionally, the lytic cycle and mortality rate were determined by monitoring the lytic effect of the host cells using microscopy. The adsorption rate of cyanophage PP was measured using the centrifugation method, where the burst size and lytic cycle were confirmed by measuring the one-step growth curve. Results indicated that elevated TN and TP could significantly promote the growth of Phormidium. Statistical analysis showed that during the mid-log phase (day 6th) cell densities were significantly higher under high nutrient conditions. Additionally, the adsorption rate in standard AA medium was significantly higher than that in the other five dilution media. Although nutrient conditions did not affect mortalityrate significantly, the latent period and lytic cycle of cyanophage PP were obviously shortened. Moreover, the average burst size of cyanophage PP increased significantly with increasing the nutrient concentration. These results not only proved that high nutrient concentration could promote cyanophage infectivity, but also implied that cyanophage might play an important ecological role in adjusting the succession of algal populations in the progress of eutrophication.