ABSTRACT
Objective@#To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. @*Materials and Methods@#Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. @*Results@#Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. @*Conclusion@#CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.
ABSTRACT
Objective@#To develop a machine learning (ML) pipeline based on radiomics to predict Coronavirus Disease 2019 (COVID-19) severity and the future deterioration to critical illness using CT and clinical variables. @*Materials and Methods@#Clinical data were collected from 981 patients from a multi-institutional international cohort with real-time polymerase chain reaction-confirmed COVID-19. Radiomics features were extracted from chest CT of the patients. The data of the cohort were randomly divided into training, validation, and test sets using a 7:1:2 ratio. A ML pipeline consisting of a model to predict severity and time-to-event model to predict progression to critical illness were trained on radiomics features and clinical variables. The receiver operating characteristic area under the curve (ROC-AUC), concordance index (C-index), and time-dependent ROC-AUC were calculated to determine model performance, which was compared with consensus CT severity scores obtained by visual interpretation by radiologists. @*Results@#Among 981 patients with confirmed COVID-19, 274 patients developed critical illness. Radiomics features and clinical variables resulted in the best performance for the prediction of disease severity with a highest test ROC-AUC of 0.76 compared with 0.70 (0.76 vs. 0.70, p = 0.023) for visual CT severity score and clinical variables. The progression prediction model achieved a test C-index of 0.868 when it was based on the combination of CT radiomics and clinical variables compared with 0.767 when based on CT radiomics features alone (p < 0.001), 0.847 when based on clinical variables alone (p = 0.110), and 0.860 when based on the combination of visual CT severity scores and clinical variables (p = 0.549). Furthermore, the model based on the combination of CT radiomics and clinical variables achieved time-dependent ROC-AUCs of 0.897, 0.933, and 0.927 for the prediction of progression risks at 3, 5 and 7 days, respectively. @*Conclusion@#CT radiomics features combined with clinical variables were predictive of COVID-19 severity and progression to critical illness with fairly high accuracy.
ABSTRACT
The COVID-19 pandemic has caused millions of deaths and hundreds of millions of confirmed infections worldwide. This pandemic has prompted researchers to produce medications or vaccines to reduce or stop the progression and spread of this disease. A variety of previously licensed and marketed medications are being tested for the treatment and recurrence of SARS-CoV2, including favipiravir (Avigan). Favipiravir was recognized as an influenza antiviral drug in Japan in 2014, and has been known to have a potential in vitro activity against SARS-CoV-2, in addition to its broad therapeutic safety scope. Favipiravir was recently approved and officially used in many countries worldwide. Our review provides insights and up-to-date knowledge of the current role of favipiravir in the treatment of COVID-19 infection, focusing on preclinical and ongoing clinical trials, evidence of its efficacy against SARS-CoV-2 in COVID-19, side effects, anti-viral mechanism, and the pharmacokinetic properties of the drug in the treatment of COVID-19. Due to its teratogenic effects, favipiravir cannot be offered to expectant or pregnant mothers. The practical efficacy of such an intervention regimen will depend on its dose, treatment duration, and cost as well as difficulties in application.
ABSTRACT
The objectives of this study were to optimize the formula of the self-nanoemulsifying drug delivery system (SNEDDS)containing rosuvastatin and to evaluate its physicochemical characteristics. The solubility and compatibility ofrosuvastatin in surfactants, cosurfactants, and oil excipients were evaluated. The D-optimal experimental design,created by JMP 15 software, was used for analyzing the effects of excipients on the physicochemical characteristicsof SNEDDS to optimize the rosuvastatin SNEDDS formula. The generated nanoemulsions from Ros SNEDDS werecharacterized for droplet size, polydispersity index, and entrapment efficiency. As a result, Cremophor RH40, Capryol90, and PEG 400 were selected to develop the pseudoternary phase diagram to identify the area capable of selfforming nanoemulsion. As the percentage of rosuvastatin calcium increased from 8% to 12%, the area for optimizingthe formula of Ros SNEDDS decreased. The Ros SNEDDS prepared according to predicted formulas possessed selfemulsification to form nanoemulsion with average droplet size less than 100 nm, polydispersity index less than 0.3,and rosuvastatin entrapment higher than 90%.
ABSTRACT
OBJECTIVES: Families of ethnic minority persons with dementia often seek help at later stages of the disease. Little is known about the effectiveness of various methods in supporting ethnic minority dementia patients' caregivers. The objective of the study was to identify smartphone and computer usage among family caregivers of dementia patients (i.e., Korean and Vietnamese Americans) to develop dementia-care education programs for them. METHODS: Participants were asked various questions related to their computer or smartphone usage in conjunction with needs-assessment interviews. Flyers were distributed at two ethnic minority community centers in Southern California. Snowball recruitment was also utilized to reach out to the families of dementia patients dwelling in the community. RESULTS: Thirty-five family caregivers, including 20 Vietnamese and 15 Korean individuals, participated in this survey. Thirty participants (30 of 35, 85.7%) were computer users. Among those, 76.7% (23 of 30) reported daily usage and 53% (16 of 30) claimed to use social media. A majority of the participants (31 of 35, 88.6%) reported that they owned smartphones. More than half of smartphone users (18 of 29, 62%) claimed to use social media applications. Many participants claimed that they could not attend in-class education due to caregiving and/or transportation issues. CONCLUSIONS: Most family caregivers of dementia patients use smartphones more often than computers, and more than half of those caregivers communicate with others through social media apps. A smartphone-app-based caregiver intervention may serve as a more effective approach compared to the conventional in-class method. Multiple modalities for the development of caregiver interventions should be considered.