Abstract Objectives The study aimed to develop a combined model that integrates deep learning (DL), radiomics, and clinical data to classify lung nodules into benign or malignant categories, and to further classify lung nodules into different pathological subtypes and Lung Imaging Reporting and Data System (Lung-RADS) scores. Materials and methods The proposed model was trained, validated, and tested using three datasets: one public dataset, the Lung Nodule Analysis 2016 (LUNA16) Grand challenge dataset ( n = 1004), and two private datasets, the Lung Nodule Received Operation (LNOP) dataset ( n = 1027) and the Lung Nodule in Health Examination (LNHE) dataset ( n = 1525). The proposed model used a stacked ensemble model by employing a machine learning (ML) approach with an AutoGluon-Tabular classifier. The input variables were modified 3D convolutional neural network (CNN) features, radiomics features, and clinical features. Three classification tasks were performed: Task 1: Classification of lung nodules into benign or malignant in the LUNA16 dataset; Task 2: Classification of lung nodules into different pathological subtypes; and Task 3: Classification of Lung-RADS score. Classification performance was determined based on accuracy, recall, precision, and F1-score. Ten-fold cross-validation was applied to each task. Results The proposed model achieved high accuracy in classifying lung nodules into benign or malignant categories in LUNA 16 with an accuracy of 92.8%, as well as in classifying lung nodules into different pathological subtypes with an F1-score of 75.5% and Lung-RADS scores with an F1-score of 80.4%. Conclusion Our proposed model provides an accurate classification of lung nodules based on the benign/malignant, different pathological subtypes, and Lung-RADS system.
BACKGROUND Multidisciplinary rounds (MDRs) are scheduled, patient-focused communication mechanisms among multidisciplinary providers in the intensive care unit (ICU). OBJECTIVE <i>i</i>-Dashboard is a custom-developed visualization dashboard that supports (1) key information retrieval and reorganization, (2) time-series data, and (3) display on large touch screens during MDRs. This study aimed to evaluate the performance, including the efficiency of prerounding data gathering, communication accuracy, and information exchange, and clinical satisfaction of integrating <i>i</i>-Dashboard as a platform to facilitate MDRs. METHODS A cluster-randomized controlled trial was performed in 2 surgical ICUs at a university hospital. Study participants included all multidisciplinary care team members. The performance and clinical satisfaction of <i>i</i>-Dashboard during MDRs were compared with those of the established electronic medical record (EMR) through direct observation and questionnaire surveys. RESULTS Between April 26 and July 18, 2021, a total of 78 and 91 MDRs were performed with the established EMR and <i>i</i>-Dashboard, respectively. For prerounding data gathering, the median time was 10.4 (IQR 9.1-11.8) and 4.6 (IQR 3.5-5.8) minutes using the established EMR and <i>i</i>-Dashboard (<i>P</i><.001), respectively. During MDRs, data misrepresentations were significantly less frequent with <i>i</i>-Dashboard (median 0, IQR 0-0) than with the established EMR (4, IQR 3-5; <i>P</i><.001). Further, effective recommendations were significantly more frequent with <i>i</i>-Dashboard than with the established EMR (<i>P</i><.001). The questionnaire results revealed that participants favored using <i>i</i>-Dashboard in association with the enhancement of care plan development and team participation during MDRs. CONCLUSIONS <i>i</i>-Dashboard increases efficiency in data gathering. Displaying <i>i</i>-Dashboard on large touch screens in MDRs may enhance communication accuracy, information exchange, and clinical satisfaction. The design concepts of <i>i</i>-Dashboard may help develop visualization dashboards that are more applicable for ICU MDRs. CLINICALTRIAL ClinicalTrials.gov NCT04845698; https://clinicaltrials.gov/ct2/show/NCT04845698
Underreporting of occupational injury and illness has been an important issue in Taiwan. We tried to implement an integrated surveillance system in the emergency services of National Cheng Kung University Hospital to screen work-related accidents. The system mobilised staffs of triage, registration and doctors to report occupational causes. A total of 4097 events were identified from Feb 2015 to Feb 2017, among which 2722 were work-related, and 1375 commuting injuries. Work-related events were predominant males (71.7%), but equally in commuting injuries. 1532 events were sent by ambulance, 498 cases hospitalised in the first month, and 4 patients died within 30 days after emergency services and all fatal cases were work-related injuries. The majority of diagnoses were contusions, abrasions and lacerations, totally accounting for 43.1%. However, significant proportion of head injuries (n=751, 18.3%), fractures (n=351, 8.6%), burns (n=264, 6.4%) including 62 cases (1.5%) of chemical burns, and 106 cases (4.4%) of amputations were found. The results were different from the government funded reporting system where most frequently reported were chronic musculoskeletal diseases. The total medical costs were about 2.9 million USD, based on a conservative estimation accounting 90 days from the first encounter. This study revealed the fact of underestimation of occupational injuries and illness resulting in significant health and societal impacts. The emergency room based surveillance system can augment the conventional reporting system. Furthermore, cluster analysis and work associated disability should be investigated to improve occupational safety and labour right.
The superficial location and limited soft tissue coverage make the knee vulnerable to various injuries; and consequently, patellar trauma is commonly encountered. In the busy emergency department, frequent overloads, relative inexperience, and unawareness of proper radiographic assessment commonly lead to diagnostic errors and delay in treatment. Herein we presented 4 neglected patellar lesions from acute knee injuries, whose diagnosis was made later with persistent discomfort and definite radiographic validation. In addition to the complete history and physical examination, we suggest integration of axial projection into the routine radiographic protocol for acute knee trauma to arouse clinical suspicion and avoid associated orthopedic pitfalls.
The proliferation of new psychoactive substances (NPSs) in recent years has posed a significant challenge to public health. Traditional monitoring methods have proven insufficient in tracking these constantly evolving substances, leading to the development of alternative approaches such as wastewater-based epidemiology (WBE). The present study aims to utilize high-resolution mass spectrometry (HRMS)-based targeted and suspect screening to profile NPS, other illicit drugs, and drug-related compounds in a Taiwanese wastewater sample. For the targeted analysis, 8 out 18 standards of illicit drugs have been identified. The suspect screening approach based on approximately 3600 substances in the SWGDRUG library can further identify 92 compounds, including opiate analgesics, synthetic cathinones, phenylalkylamines derivatives, phenethylamine derivatives, tryptamine derivatives, steroids, and ephedrine-related compounds. Additionally, the presence of 5-methoxy-2-aminoindane (MEAI) in the wastewater indicates that drug dealers have recently sold this potential NPS to evade drug regulations. This study firstly reports the HRMS-based comprehensive profile of NPS, other illicit drugs, and drug-related compounds in Taiwan, which could be applied as biomarkers for estimating the consumption of drugs.
Nirmatrelvir/ritonavir (Paxlovid™) is an effective and safe antiviral drug that inhibits the main protease (Mpro), 3CL protease, of SARS-CoV-2. A reduction in COVID-19-related hospitalization or death was observed in patients treated with nirmatrelvir/ritonavir within five days of symptom onset. Moreover, good oral availability enables the usage of nirmatrelvir/ritonavir, not only in hospitalized patients, but also among outpatients. Nirmatrelvir (PF-07321332) has been demonstrated to stop the spread of COVID-19 in animal models. Despite frequent mutations in the viral genomes of SARS-CoV-2, nirmatrelvir shows an effective antiviral effect against recent coronavirus mutants. Despite the promising antiviral effect of nirmatrelvir, there are several unresolved concerns. First, the final results of large-scale clinical trials for early therapy of mild cases of COVID-19 are not yet published. Second, the effectiveness of nirmatrelvir against upcoming variants in the coming years requires close monitoring. Considering the promising preliminary results of the EPIC-HR trial, nirmatrelvir/ritonavir in conjunction with vaccines and non-pharmacological interventions, may represent the dawn in the dark of the COVID-19 pandemic.
Background Limited studies have assessed the association of motor vehicle crashes (MVCs) during pregnancy with adverse maternal outcomes using a population-based nationwide dataset that covers all MVCs. Methods A total of 20 844 births from women who had been involved in MVCs during pregnancy were obtained from the National Birth Notification (BN) Database in Taiwan. We randomly selected 83 274 control births from women in the BN matched on age, gestational age and crash date. All study subjects were linked to medical claims and the Death Registry to identify the maternal outcomes after crashes. Conditional logistic regression models were used to estimate the adjusted odds ratio (aOR) and 95% CI of adverse outcomes associated with MVCs during pregnancy. Results Pregnant women involved in MVCs had significantly higher risks of placental abruption (aOR=1.51, 95% CI 1.30 to 1.74), prolonged uterine contractions (aOR=1.31, 95% CI 1.11 to 1.53), antepartum haemorrhage (aOR=1.19, 95% CI 1.12 to 1.26) and caesarean delivery (aOR=1.05, 95% CI 1.02 to 1.09) than the controls. Such elevated risks tended to be higher in the MVCs with greater severity. Scooter riders had higher ORs of various adverse maternal outcomes than car drivers. Conclusions Women involved in MVCs during pregnancy were at increased risk of various adverse maternal outcomes, especially in those with severe MVCs and riding scooters at MVCs. These findings suggest that clinicians should be aware of these effects, and educational materials that include the above information should be provided as part of prenatal care.
'/%3e%3cuse xlink:href='%23a' transform='rotate(60)'/%3e%3ccircle r='17' fill='%23000095'/%3e%3ccircle r='15' fill='%23fff'/%3e%3c/svg%3e)
