Search

BackgroundPublic health authorities have been recommending interventions such as physical distancing and face masks, to curtail the transmission of coronavirus disease (COVID-19) within the community. Public perceptions toward such interventions should be identified to enable public health authorities to effectively address valid concerns. The Health Belief Model (HBM) has been used to characterize user-generated content from social media during previous outbreaks, with the aim of understanding the health behaviors of the public. ObjectiveThis study is aimed at developing and evaluating deep learning–based text classification models for classifying social media content posted during the COVID-19 outbreak, using the four key constructs of the HBM. We will specifically focus on content related to the physical distancing interventions put forth by public health authorities. We intend to test the model with a real-world case study. MethodsThe data set for this study was prepared by analyzing Facebook comments that were posted by the public in response to the COVID-19–related posts of three public health authorities: the Ministry of Health of Singapore (MOH), the Centers for Disease Control and Prevention, and Public Health England. The comments made in the context of physical distancing were manually classified with a Yes/No flag for each of the four HBM constructs: perceived severity, perceived susceptibility, perceived barriers, and perceived benefits. Using a curated data set of 16,752 comments, gated recurrent unit–based recurrent neural network models were trained and validated for text classification. Accuracy and binary cross-entropy loss were used to evaluate the model. Specificity, sensitivity, and balanced accuracy were used to evaluate the classification results in the MOH case study. ResultsThe HBM text classification models achieved mean accuracy rates of 0.92, 0.95, 0.91, and 0.94 for the constructs of perceived susceptibility, perceived severity, perceived benefits, and perceived barriers, respectively. In the case study with MOH Facebook comments, specificity was above 96% for all HBM constructs. Sensitivity was 94.3% and 90.9% for perceived severity and perceived benefits, respectively. In addition, sensitivity was 79.6% and 81.5% for perceived susceptibility and perceived barriers, respectively. The classification models were able to accurately predict trends in the prevalence of the constructs for the time period examined in the case study. ConclusionsThe deep learning–based text classifiers developed in this study help to determine public perceptions toward physical distancing, using the four key constructs of HBM. Health officials can make use of the classification model to characterize the health behaviors of the public through the lens of social media. In future studies, we intend to extend the model to study public perceptions of other important interventions by public health authorities.

BackgroundThe coronavirus disease (COVID-19) pandemic presents one of the most challenging global crises at the dawn of a new decade. Public health authorities (PHAs) are increasingly adopting the use of social media such as Facebook to rapidly communicate and disseminate pandemic response measures to the public. Understanding of communication strategies across different PHAs and examining the public response on the social media landscapes can help improve practices for disseminating information to the public. ObjectiveThis study aims to examine COVID-19-related outreach efforts of PHAs in Singapore, the United States, and England, and the corresponding public response to these outreach efforts on Facebook. MethodsPosts and comments from the Facebook pages of the Ministry of Health (MOH) in Singapore, the Centers for Disease Control and Prevention (CDC) in the United States, and Public Health England (PHE) in England were extracted from January 1, 2019, to March 18, 2020. Posts published before January 1, 2020, were categorized as pre-COVID-19, while the remaining posts were categorized as peri-COVID-19 posts. COVID-19-related posts were identified and classified into themes. Metrics used for measuring outreach and engagement were frequency, mean posts per day (PPD), mean reactions per post, mean shares per post, and mean comments per post. Responses to the COVID-19 posts were measured using frequency, mean sentiment polarity, positive to negative sentiments ratio (PNSR), and positive to negative emotions ratio (PNER). Toxicity in comments were identified and analyzed using frequency, mean likes per toxic comment, and mean replies per toxic comment. Trend analysis was performed to examine how the metrics varied with key events such as when COVID-19 was declared a pandemic. ResultsThe MOH published more COVID-19 posts (n=271; mean PPD 5.0) compared to the CDC (n=94; mean PPD 2.2) and PHE (n=45; mean PPD 1.4). The mean number of comments per COVID-19 post was highest for the CDC (mean CPP 255.3) compared to the MOH (mean CPP 15.6) and PHE (mean CPP 12.5). Six major themes were identified, with posts about prevention and safety measures and situation updates being prevalent across the three PHAs. The themes of the MOH’s posts were diverse, while the CDC and PHE posts focused on a few themes. Overall, response sentiments for the MOH posts (PNSR 0.94) were more favorable compared to response sentiments for the CDC (PNSR 0.57) and PHE (PNSR 0.55) posts. Toxic comments were rare (0.01%) across all PHAs. ConclusionsPHAs’ extent of Facebook use for outreach purposes during the COVID-19 pandemic varied among the three PHAs, highlighting the strategies and approaches that other PHAs can potentially adopt. Our study showed that social media analysis was capable of providing insights about the communication strategies of PHAs during disease outbreaks.

Psychological and social factors are known to influence blood pressure (BP) and risk of hypertension and associated cardiovascular diseases. To identify novel BP loci, we carried out genome-wide association meta-analyses of systolic, diastolic, pulse, and mean arterial BP taking into account the interaction effects of genetic variants with three psychosocial factors: depressive symptoms, anxiety symptoms, and social support. Analyses were performed using a two-stage design in a sample of up to 128,894 adults from 5 ancestry groups. In the combined meta-analyses of Stages 1 and 2, we identified 59 loci (p value

This study aims to describe Facebook users' beliefs toward physical distancing measures implemented during the Coronavirus disease (COVID-19) pandemic using the key constructs of the health belief model. A combination of rule-based filtering and manual classification methods was used to classify user comments on COVID-19 Facebook posts of three public health authorities: Centers for Disease Control and Prevention of the United States, Public Health England, and Ministry of Health, Singapore. A total of 104,304 comments were analyzed for posts published between 1 January, 2020, and 31 March, 2020, along with COVID-19 cases and deaths count data from the three countries. Findings indicate that the perceived benefits of physical distancing measures (n = 3,463; 3.3%) was three times higher than perceived barriers (n = 1,062; 1.0%). Perceived susceptibility to COVID-19 (n = 2,934; 2.8%) was higher compared with perceived severity (n = 2,081; 2.0%). Although susceptibility aspects of physical distancing were discussed more often at the start of the year, mentions on the benefits of intervention emerged stronger toward the end of the analysis period, highlighting the shift in beliefs. The health belief model is useful for understanding Facebook users' beliefs at a basic level, and it provides a scope for further improvement.

Adverse drug reactions (ADRs) contribute to hospitalization but data on its economic burden is scant. Pre-emptive pharmacogenetic (PGx) testing can potentially reduce ADRs and its associated costs. The objectives of this study were to quantify the economic burden of ADRs and to estimate the breakeven cost of pre-emptive PGx testing in Singapore. We collected itemized costs for 1000 random non-elective hospitalizations of adults admitted to a tertiary-care general hospital in Singapore. The presence of ADRs at admission and their clinical characteristics were reported previously. The economic burden of ADRs was assessed from two perspectives: (1) Total cost and (2) incremental costs. The breakeven cost of PGx testing was estimated by dividing avoidable hospitalization costs for ADRs due to selected drugs by the number of patients taking those drugs. The total cost of 81 admissions caused by ADRs was US$570,404. Costs were significantly higher for bleeding/elevated international normalized ratio (US$9906 vs. US$2251, p = 6.58 × 10-3) compared to other ADRs, and for drugs acting on the blood coagulation system (US$9884 vs. US$2229, p = 4.41 × 10-3) compared to other drug classes. There were higher incremental laboratory costs due to ADRs causing or being present at admission. The estimated breakeven cost of a pre-emptive PGx test for patients taking warfarin, clopidogrel, chemotherapeutic and neuropsychiatric drugs was US$114 per patient. These results suggest that future studies designed to directly measure the clinical and cost impact of a pre-emptive genotyping program will help inform clinical practice and health policy decisions.

ObjectiveThis study aims to compare the cost-effectiveness of various strategies of myeloid growth factor prophylaxis for reducing the risk of febrile neutropenia (FN) in patients with non-Hodgkin lymphoma in Singapore who are undergoing R-CHOP chemotherapy with curative intent.MethodsA Markov model was created to compare seven prophylaxis strategies: 1) primary prophylaxis (PP) with nivestim (biosimilar filgrastim) throughout all cycles of chemotherapy; 2) PP with nivestim during the first two cycles of chemotherapy; 3) secondary prophylaxis (SP) with nivestim; 4) PP with pegfilgrastim throughout all cycles of chemotherapy; 5) PP with pegfilgrastim during the first two cycles of chemotherapy; 6) SP with pegfilgrastim; and 7) no prophylaxis (NP). The perspective of a hospital was taken and cost-effectiveness was expressed as the cost per episode of FN avoided over six cycles of chemotherapy. A probabilistic sensitivity analysis was conducted.ResultsStrategies 3, 6, and 7 were dominated in the base case analysis by strategy 5. The costs associated with strategies 2, 5, 1, and 4 were US$3,813, US$4,056, US$4,545, and US$5,331, respectively. The incremental cost-effectiveness ratios for strategy 5 vs. strategy 2, strategy 1 vs. strategy 5, and strategy 4 vs. strategy 1 were US$13,532, US$22,565, and US$30,452, respectively, per episode of FN avoided. Strategy 2 has the highest probability to be cost-effective (ranged from 48% to 60%) when the willingness to pay (WTP) threshold is lower than US$10,000 per FN episode prevented.ConclusionIn Singapore, routine PP with granulocyte colony-stimulating factor (nivestim or pegfilgrastim) is cost-effective for reducing the risk of FN in patients receiving R-CHOP.