OBJECTIVE: To explore the clinical effect of personalized puncture planning before surgery using Picture Archiving and Communication System (PACS) in the treatment of osteoporotic vertebral compression fractures in the elderly. METHODS: A total of 69 elderly patients with osteoporotic vertebral compression fractures treated by percutaneous vertebroplasty from January 2020 20 to December 2021 with more than 1 year of follow-up were analyzed retrospectively. Thirty-four patients were individualized for preoperative planning with PACS software (observation group), including 8 males and 26 females, with a mean age of (73.30±7.96) years old;and 35 patients were treated with conventional treatment (control group), including 7 males and 28 females, with a mean age of (77.30±7.84) years old. The operation time, the amount of cement injection, cement leakage rate, bone watertight diffusion and refracture within 1 year between two groups were observed and compared. The Cobb's angle, low back pain visual analogue scale(VAS) and the modified Oswsetry disability indexes(ODI) before surgery and 1 day, 1 year after surgery were compared between two groups. RESULTS: Both groups successfully completed the operation without serious surgical complications, 2 refractures occurred in the control group. The operation time in the observation group was(41.9±11.9) min, which was less than that in the control group (52.7±13.6) min (P<0.05). There was no significant difference in the cement injection volume between two groups (P>0.05). Two cases of cement leakage in the observation group was less than 8 in the control group (P<0.05). The bone cement distribution index of two groups had significant difference(P<0.05). There were no significant differences between two groups in Cobb's angle of the injured vertebras and ODI before and 1 day after surgery(P>0.05), however, the comparative differences were statistically significant at 1 year after surgery(P<0.05). There was no significant difference in the VAS between two groups at each time period(P>0.05). CONCLUSION Using the PACS software to plan personalized puncture scheme can reduce the operation time, reduce the cement leakage rate, improve the diffusion of bone cement and longer maintain the postoperative form of vertebral body and the functional state of patients' lumbar back.
Humans ; Male ; Female ; Aged ; Vertebroplasty/methods* ; Fractures, Compression/diagnostic imaging* ; Spinal Fractures/diagnostic imaging* ; Osteoporotic Fractures/diagnostic imaging* ; Aged, 80 and over ; Retrospective Studies ; Radiology Information Systems

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: 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

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

OBJECTIVE: To develop a mortality prediction model for critically ill patients based on multidimensional and dynamic clinical data collected by the hospital information system (HIS) using random forest algorithm, and to compare the prediction efficiency of the model with acute physiology and chronic health evaluation II (APACHE II) model. METHODS: The clinical data of 10 925 critically ill patients aged over 14 years old admitted to the Third Xiangya Hospital of Central South University from January 2014 to June 2020 were extracted from the HIS system, and APACHE II scores of the critically ill patients were extracted. Expected mortality of patients was calculated according to the death risk calculation formula of APACHE II scoring system. A total of 689 samples with APACHE II score records were used as the test set, and the other 10 236 samples were used to establish the random forest model, of which 10% (n = 1 024) were randomly selected as the validation set and 90% (n = 9 212) were selected as the training set. According to the time series of 3 days before the end of critical illness, the clinical characteristics of patients such as general information, vital signs data, biochemical test results and intravenous drug doses were selected to develope a random forest model for predicting the mortality of critically ill patients. Using the APACHE II model as a reference, receiver operator characteristic curve (ROC curve) was drawn, and the discrimination performance of the model was evaluated through the area under the ROC curve (AUROC). According to the precision and recall, Precision-Recall curve (PR curve) was drawn, and the calibration performance of the model was evaluated through the area under the PR curve (AUPRC). Calibration curve was drawn, and the consistency between the predicted event occurrence probability of the model and the actual occurrence probability was evaluated through the calibration index Brier score. RESULTS: Among the 10 925 patients, there were 7 797 males (71.4%) and 3 128 females (28.6%). The average age was (58.9±16.3) years old. The median length of hospital stay was 12 (7, 20) days. Most patients (n = 8 538, 78.2%) were admitted to intensive care unit (ICU), and the median length of ICU stay was 66 (13, 151) hours. The hospitalized mortality was 19.0% (2 077/10 925). Compared with the survival group (n = 8 848), the patients in the death group (n = 2 077) were older (years old: 60.1±16.5 vs. 58.5±16.4, P < 0.01), the ratio of ICU admission was higher [82.8% (1 719/2 077) vs. 77.1% (6 819/8 848), P < 0.01], and the proportion of patients with hypertension, diabetes and stroke history was also higher [44.7% (928/2 077) vs. 36.3% (3 212/8 848), 20.0% (415/2 077) vs. 16.9% (1 495/8 848), 15.5% (322/2 077) vs. 10.0% (885/8 848), all P < 0.01]. In the test set data, the prediction value of random forest model for the risk of death during hospitalization of critically ill patients was greater than that of APACHE II model, which showed by that the AUROC and AUPRC of random forest model were higher than those of APACHE II model [AUROC: 0.856 (95% confidence interval was 0.812-0.896) vs. 0.783 (95% confidence interval was 0.737-0.826), AUPRC: 0.650 (95% confidence interval was 0.604-0.762) vs. 0.524 (95% confidence interval was 0.439-0.609)], and Brier score was lower than that of APACHE II model [0.104 (95% confidence interval was 0.085-0.113) vs. 0.124 (95% confidence interval was 0.107-0.141)]. CONCLUSIONS The random forest model based on multidimensional dynamic characteristics has great application value in predicting hospital mortality risk for critically ill patients, and it is superior to the traditional APACHE II scoring system.
Female ; Male ; Humans ; Aged ; Adult ; Middle Aged ; Adolescent ; Critical Illness ; Hospitalization ; Length of Stay ; APACHE ; Hospital Information Systems

OBJECTIVE: To solve the ESB bus performance and safety problems caused by the explosive growth of the hospital's business, and to ensure the stable interaction of the hospital's business system. METHODS: Taking the construction of our hospital's information system as an example, we used AlwaysOn, load balancing and other technologies to optimize the ESB bus architecture to achieve high availability and scalability of the hospital's ESB bus. RESULTS: The ESB bus high-availability architecture effectively eliminates multiple points of failure. Compared with the traditional dual-machine Cluster solution, the security is significantly improved. The nodes based on load balancing can be scaled horizontally according to the growth of the hospital's business volume. CONCLUSIONS The construction of the ESB bus high-availability architecture effectively solves the performance and security issues caused by business growth, and provides practical experience for medical information colleagues. It has certain guiding significance for the development of regional medical information.
Hospital Information Systems ; Information Systems

Kidney malignant tumor is a type of primary renal cell carcinoma, and mainly refers to renal cancer. The incidence of kidney cancer and the number of hospital cases in China have been increasing. Based on the clinical medicine information of patients in the hospital information system(HIS) database of 37 hospitals in China, the combined medication of patients with kidney malignant tumor were analyzed by Tabu search algorithm, so as to analyze the combined medication of patients with kidney malignant tumor in real world. A total of 7 095 patients with kidney malignant tumor were included, the ratio of males to females was 2.11∶1, and the ratio of male patients increased gradually with age. About 3 933 patients(55.43%) showed a superior effect among those patients. The common therapies of patients with kidney malignant tumor were anti-tumor therapies and symptomatic therapies, including anti-infection, regulation of electrolyte balance, sedation and analgesia, analgesic, regulation of gastrointestinal function. The whole population of patients with kidney malignant tumor were mostly treated with anti-tumor drugs combined with more symptomatic therapies, while the anti-tumor therapies of the superiority population of patients were less combined with other drugs, with less combined medication. The result may be related to the stage of tumor or individual response to the therapeutic regimen. No matter for the whole population or for the superiority population of patients with kidney malignant tumor, the therapies was mainly Western medicines. Based on the pathogenesis of deficiency in origin and excess in superficiality with kidney malignant tumor, Chinese subgroups with formula for clearing heat and removing toxicity, formula for vigorate Qi and replenish the blood, formula for regulate Qi and invigorate the blood, laxative and hemostatic were more commonly used. In the future, further studies shall be conducted for combined therapies for patients of different stages, so as to play the advantages of multi-target, overall regulation, toxicity reduction and efficacy enhancement of traditional Chinese medicine, improve the life quality of patients with kidney malignant tumor, prolong their life time, and improve the survival rate of patients.
Asian Continental Ancestry Group ; China ; Drugs, Chinese Herbal ; Female ; Hospital Information Systems ; Humans ; Kidney Neoplasms ; Male ; Medicine, Chinese Traditional

OBJECTIVE: To explore the integration method and technical realization of artificial intelligence bone age assessment system with the hospital RIS-PACS network and workflow. METHODS: Two sets of artificial intelligence based on bone age assessment systems (CHBoneAI 1.0/2.0) were developed. The intelligent system was further integrated with RIS-PACS based on the http protocol in Python flask web framework. RESULTS: The two sets of systems were successfully integrated into the local network and RIS-PACS in hospital. The deployment has been smoothly running for nearly 3 years. Within the current network setting, it takes less than 3 s to complete bone age assessment for a single patient. CONCLUSIONS The artificial intelligence based bone age assessment system has been deployed in clinical RIS-PACS platform and the "running in parallel", which is marking a success of Stage-I and paving the way to Stage-II where the intelligent systems can evolve to become more powerful in particular of the system self-evolution and the "running alternatively".
Age Determination by Skeleton ; Artificial Intelligence ; Bone and Bones ; Hospital Information Systems ; Hospitals ; Humans ; Radiology Information Systems ; Systems Integration

PURPOSE: The aim of this study was to identify the predictive validity of the Korean Triage and Acuity Scale (KTAS). METHODS: This methodological study used data from National Emergency Department Information System for 2016. The KTAS disposition and emergency treatment results for emergency patients aged 15 years and older were analyzed to evaluate its predictive validity through its sensitivity, specificity, positive predictive value, and negative predictive value. RESULTS: In case of death in the emergency department, or where the intensive care unit admission was considered an emergency, the sensitivity, specificity, positive predictive value, and negative predictive value of the KTAS were 0.916, 0.581, 0.097, and 0.993, respectively. In case of death in the emergency department, or where the intensive or non-intensive care unit admission was considered an emergency, the sensitivity, specificity, and positive predictive value, and negative predictive value were 0.700, 0.642, 0.391, and 0.867, respectively. CONCLUSION: The results of this study showed that the KTAS had high sensitivity but low specificity. It is necessary to constantly review and revise the KTAS level classification because it still results in a few errors of under and over-triage. Nevertheless, this study is meaningful in that it was an evaluation of the KTAS for the total cases of adult patients who sought help at regional and local emergency medical centers in 2016.
Adult ; Classification ; Emergencies ; Emergency Service, Hospital ; Emergency Treatment ; Humans ; Information Systems ; Intensive Care Units ; Methods ; Sensitivity and Specificity ; Triage

OBJECTIVES: A clinical data warehouse (CDW) is part of our hospital information system, and it provides user-friendly ‘data search and extraction’ interfaces for query composition. We carried out a risk factor analysis for the extended use of opioids after coronary artery bypass grafting (CABG), taking advantage of the CDW system. METHODS: From 2015 to 2017, clinical data from 461 patients who had undergone either isolated or concomitant CABG were extracted using the CDW; the extracted data included baseline patient characteristics, various examination results, and opioid prescription information. Supplementary data that could not be extracted with the CDW were collected via manual review of the electronic medical records. RESULTS: Data from a total of 447 patients were analyzed finally. The mean patient age was 66.8 ± 10.9 years, 332 patients (74%) were male, and 235 patients (53%) had diabetes. Among the 447 patients, 90 patients (20.1%) took some type of opioid at the 15th postoperative day. An oral rapid-acting agent was the most frequently used opioid (83%). In the risk factor analysis for extended opioid use, duration of operation was the only significant risk factor (odds ratio = 1.004; 95% confidence interval, 1.001–1.007; p = 0.008). CONCLUSIONS: Longer operation time was associated with the risk of extended opioid use after CABG. CDW was a helpful tool for extracting mass clinical data rapidly, but to maximize its utility, the data should be checked carefully as they are entered in the system so that post-processing can be minimized. Further refinement of the clinical data input and output interface is warranted.
Analgesics, Opioid ; Coronary Artery Bypass ; Coronary Vessels ; Database Management Systems ; Electronic Health Records ; Hospital Information Systems ; Humans ; Male ; Prescriptions ; Risk Factors