Practice of structured electronic medical record design and quality management / 中华医院管理杂志

In order to assist in the standardization and maturity evaluation of national hospital information interconnection, and further standardize the application and management of hospital medical record data, a hospital carried out the practice of design of structured medical records and the corresponding quality management from April 2021. Based on the six sigma quality management method, the hospital had developed universal templates for electronic medical records and a list of candidate electronic medical record templates. The problems faced by medical record data had been analyzed, and improvement strategies had been proposed from three levels: template design, software functionality and management services. The clinical departments were guided to design and develop various structured electronic medical record templates for specialties and specialized diseases, and established a medical record template design and quality management method. The hospital had ultimately designed a total of 614 structured electronic medical record templates that met the actual needs of the hospital. This practice enhanced the scalability of structured templates and quality of the data, and achieved localization and specialization of medical record templates while meeting the requirements of information interconnection and sharing, providing reference for promoting the interconnection and sharing of electronic medical records of hospitals in China.

Automatic segmentation of lung fields in chest radiographs based on dense matching of local features / 南方医科大学学报

<p><b>OBJECTIVE</b>Accurate segmentation of lung fields in chest radiographs (CXR) is very useful for automatic analysis of CXR. In this work, we propose to use dense matching of local features and label fusion to automatically segment the lung fields in CXR.</p><p><b>METHODS</b>For an input CXR, the dense Scale Invariant Feature Transform (SIFT) descriptors and raw image patches were extracted as the local features for each pixel. The nearest neighbors of the local features were then quickly searched by dense matching directly from the whole feature dataset of the reference images. The dense matching included three steps: limited random initialization, propagation of nearest neighbor field, and limited random search, with iteration of the last two steps for several times. The label image patches for each pixel were extracted according to the nearest neighbor field and weighted by the matching similarity. Finally, the weighted label patches were rearranged as the label class probability image of the input CXR, from which thresholds were obtained for segmentation of the lung fields.</p><p><b>RESULTS</b>The Jaccard index of the proposed method reached 95.5% on the public JSRT dataset.</p><p><b>CONCLUSION</b>A high accuracy and robustness can be obtained by adopting dense matching of local features and label fusion to segment the lung fields in CXR, and the result is better than that of current segmentation method.</p>