Investigating public behavior with artificial intelligence-assisted detection of face mask wearing during the COVID-19 pandemic.

OBJECTIVES: Face masks are low-cost, but effective in preventing transmission of COVID-19. To visualize public's practice of protection during the outbreak, we reported the rate of face mask wearing using artificial intelligence-assisted face mask detector, AiMASK. METHODS: After validation, AiMASK collected data from 32 districts in Bangkok. We analyzed the association between factors affecting the unprotected group (incorrect or non-mask wearing) using univariate logistic regression analysis. RESULTS: AiMASK was validated before data collection with accuracy of 97.83% and 91% during internal and external validation, respectively. AiMASK detected a total of 1,124,524 people. The unprotected group consisted of 2.06% of incorrect mask-wearing group and 1.96% of non-mask wearing group. Moderate negative correlation was found between the number of COVID-19 patients and the proportion of unprotected people (r = -0.507, p<0.001). People were 1.15 times more likely to be unprotected during the holidays and in the evening, than on working days and in the morning (OR = 1.15, 95% CI 1.13-1.17, p<0.001). CONCLUSIONS: AiMASK was as effective as human graders in detecting face mask wearing. The prevailing number of COVID-19 infections affected people's mask-wearing behavior. Higher tendencies towards no protection were found in the evenings, during holidays, and in city centers.

Characteristics of road traffic mortality and distribution of healthcare resources in Thailand.

Road traffic mortalities (RTMs), a leading cause of death globally, mostly occur in low- and middle-income countries, and having sufficient healthcare resources could lower the number of these fatalities. Our study aimed to illustrate the incidence of RTMs per 100,000 population and to compare the distribution of healthcare resources from 2011 to 2021 with rates of RTMs in the 77 provinces of Thailand. We divided the population into adults (≥ 15 years) and children (0-14 years). Lorenz curve and Gini coefficient were used to measure the level of distribution and equality of hospital resources and in relation to RTMs across the country. The average number of deaths was 30.34 per 100,000 per year, with male predominance. The RTM rates for adults and children were 32.71 and 19.08 per 100,000 respectively, and motorcycle accidents accounted for the largest percentage of deaths across all age groups. The Gini coefficient showed that operating rooms (0.42) were the least equally distributed hospital resource, while physicians were the most equally distributed (0.34). Anomalies were identified between the distribution of RTMs and available hospital resources. We hope our study will be beneficial in reallocating these resources more fairly to reflect the different numbers of traffic accidents in each province with the aim of reducing lower traffic-related deaths.

Forecasting COVID-19 cases using time series modeling and association rule mining.

BACKGROUND: The aim of this study was to evaluate the most effective combination of autoregressive integrated moving average (ARIMA), a time series model, and association rule mining (ARM) techniques to identify meaningful prognostic factors and predict the number of cases for efficient COVID-19 crisis management. METHODS: The 3685 COVID-19 patients admitted at Thailand's first university field hospital following the four waves of infections from March 2020 to August 2021 were analyzed using the autoregressive integrated moving average (ARIMA), its derivative to exogenous variables (ARIMAX), and association rule mining (ARM). RESULTS: The ARIMA (2, 2, 2) model with an optimized parameter set predicted the number of the COVID-19 cases admitted at the hospital with acceptable error scores (R2 = 0.5695, RMSE = 29.7605, MAE = 27.5102). Key features from ARM (symptoms, age, and underlying diseases) were selected to build an ARIMAX (1, 1, 1) model, which yielded better performance in predicting the number of admitted cases (R2 = 0.5695, RMSE = 27.7508, MAE = 23.4642). The association analysis revealed that hospital stays of more than 14 days were related to the healthcare worker patients and the patients presented with underlying diseases. The worsening cases that required referral to the hospital ward were associated with the patients admitted with symptoms, pregnancy, metabolic syndrome, and age greater than 65 years old. CONCLUSIONS: This study demonstrated that the ARIMAX model has the potential to predict the number of COVID-19 cases by incorporating the most associated prognostic factors identified by ARM technique to the ARIMA model, which could be used for preparation and optimal management of hospital resources during pandemics.

Effects of digital devices and online learning on computer vision syndrome in students during the COVID-19 era: an online questionnaire study.

PURPOSE: Computer vision syndrome (CVS) describes a group of eye and vision-related problems that result from prolonged digital device use. This study aims to assess the prevalence and associated factors of CVS among students during the lockdown resulting from the COVID-19 pandemic. METHODS: A cross-sectional, online, questionnaire-based study performed among high school students in Thailand. RESULTS: A total of 2476 students, with mean age of 15.52±1.66 years, were included in this study. The mean number of hours of digital device use per day (10.53±2.99) increased during the COVID-19 pandemic compared with before its advent (6.13±2.8). The mean number of hours of online learning was 7.03±2.06 hours per day during the pandemic. CVS was found in 70.1% of students, and its severity correlated with both the number of hours of online learning and the total number of hours of digital device usage (p<0.001). Multiple logistic regression analysis revealed that the factors associated with CVS included age ≤15 years (adjusted OR (AOR)=2.17), overall digital device usage >6 hours per day (AOR=1.91), online learning >5 hours per day (AOR=4.99), multiple digital device usage (AOR=2.15), refractive errors (AOR=2.89), presence of back pain (AOR=2.06) and presence of neck pain (AOR=2.36). CONCLUSIONS: The number of hours of digital device usage increased during lockdown. Over 70% of children had CVS, whose associated factors, including hours of digital device usage, hours of online learning, ergonomics and refractive errors, should be adjusted to decrease the risk of acquiring this condition. Online learning will remain, along with CVS, after this pandemic, and we hope our research will be taken into account in remodelling our education system accordingly.

Analysis of Characteristics and Clinical Outcomes for Crisis Management during the Four Waves of the COVID-19 Pandemic.

This study aims to analyze the patient characteristics and factors related to clinical outcomes in the crisis management of the COVID-19 pandemic in a field hospital. We conducted retrospective analysis of patient clinical data from March 2020 to August 2021 at the first university-based field hospital in Thailand. Multivariable logistic regression models were used to evaluate the factors associated with the field hospital discharge destination. Of a total of 3685 COVID-19 patients, 53.6% were women, with the median age of 30 years. General workers accounted for 97.5% of patients, while 2.5% were healthcare workers. Most of the patients were exposed to coronavirus from the community (84.6%). At the study end point, no patients had died, 97.7% had been discharged home, and 2.3% had been transferred to designated high-level hospitals due to their condition worsening. In multivariable logistic regression analysis, older patients with one or more underlying diseases who showed symptoms of COVID-19 and whose chest X-rays showed signs of pneumonia were in a worse condition than other patients. In conclusion, the university-based field hospital has the potential to fill acute gaps and prevent public agencies from being overwhelmed during crisis events.

Deep Learning for Anterior Segment Optical Coherence Tomography to Predict the Presence of Plateau Iris.

Purpose: The purpose of this study was to evaluate the diagnostic performance of deep learning (DL) anterior segment optical coherence tomography (AS-OCT) as a plateau iris prediction model. Design: We used a cross-sectional study of the development and validation of the DL system. Methods: We conducted a collaboration between a referral eye center and an informative technology department. The study enrolled 179 eyes from 142 patients with primary angle closure disease (PACD). All patients had remaining appositional angle after iridotomy. Each eye was scanned in four quadrants for both AS-OCT and ultrasound biomicroscopy (UBM). A DL algorithm for plateau iris prediction of AS-OCT was developed from training datasets and was validated in test sets. Sensitivity, specificity, and area under the receiver operating characteristics curve (AUC-ROC) of the DL for predicting plateau iris were evaluated, using UBM as a reference standard. Results: Total paired images of AS-OCT and UBM were from 716 quadrants. Plateau iris was observed with UBM in 276 (38.5%) quadrants. Trainings dataset with data augmentation were used to develop an algorithm from 2500 images, and the test set was validated from 160 images. AUC-ROC was 0.95 (95% confidence interval [CI] = 0.91 to 0.99), sensitivity was 87.9%, and specificity was 97.6%. Conclusions: DL revealed a high performance in predicting plateau iris on the noncontact AS-OCT images. Translational Relevance: This work could potentially assist clinicians in more practically detecting this nonpupillary block mechanism of PACD.

Corrigendum to "Distant Supervision with Transductive Learning for Adverse Drug Reaction Identification from Electronic Medical Records".

[This corrects the article DOI: 10.1155/2017/7575280.].

Distant Supervision with Transductive Learning for Adverse Drug Reaction Identification from Electronic Medical Records.

Information extraction and knowledge discovery regarding adverse drug reaction (ADR) from large-scale clinical texts are very useful and needy processes. Two major difficulties of this task are the lack of domain experts for labeling examples and intractable processing of unstructured clinical texts. Even though most previous works have been conducted on these issues by applying semisupervised learning for the former and a word-based approach for the latter, they face with complexity in an acquisition of initial labeled data and ignorance of structured sequence of natural language. In this study, we propose automatic data labeling by distant supervision where knowledge bases are exploited to assign an entity-level relation label for each drug-event pair in texts, and then, we use patterns for characterizing ADR relation. The multiple-instance learning with expectation-maximization method is employed to estimate model parameters. The method applies transductive learning to iteratively reassign a probability of unknown drug-event pair at the training time. By investigating experiments with 50,998 discharge summaries, we evaluate our method by varying large number of parameters, that is, pattern types, pattern-weighting models, and initial and iterative weightings of relations for unlabeled data. Based on evaluations, our proposed method outperforms the word-based feature for NB-EM (iEM), MILR, and TSVM with F1 score of 11.3%, 9.3%, and 6.5% improvement, respectively.

Predict subcellular locations of singleplex and multiplex proteins by semi-supervised learning and dimension-reducing general mode of Chou's PseAAC.

Predicting protein subcellular location is one of major challenges in Bioinformatics area since such knowledge helps us understand protein functions and enables us to select the targeted proteins during drug discovery process. While many computational techniques have been proposed to improve predictive performance for protein subcellular location, they have several shortcomings. In this work, we propose a method to solve three main issues in such techniques; i) manipulation of multiplex proteins which may exist or move between multiple cellular compartments, ii) handling of high dimensionality in input and output spaces and iii) requirement of sufficient labeled data for model training. Towards these issues, this work presents a new computational method for predicting proteins which have either single or multiple locations. The proposed technique, namely iFLAST-CORE, incorporates the dimensionality reduction in the feature and label spaces with co-training paradigm for semi-supervised multi-label classification. For this purpose, the Singular Value Decomposition (SVD) is applied to transform the high-dimensional feature space and label space into the lower-dimensional spaces. After that, due to limitation of labeled data, the co-training regression makes use of unlabeled data by predicting the target values in the lower-dimensional spaces of unlabeled data. In the last step, the component of SVD is used to project labels in the lower-dimensional space back to those in the original space and an adaptive threshold is used to map a numeric value to a binary value for label determination. A set of experiments on viral proteins and gram-negative bacterial proteins evidence that our proposed method improve the classification performance in terms of various evaluation metrics such as Aiming (or Precision), Coverage (or Recall) and macro F-measure, compared to the traditional method that uses only labeled data.

Multidimensional text classification for drug information.

This paper proposes a multidimensional model for classifying drug information text documents. The concept of multidimensional category model is introduced for representing classes. In contrast with traditional flat and hierarchical category models, the multidimensional category model classifies each document using multiple predefined sets of categories, where each set corresponds to a dimension. Since a multidimensional model can be converted to flat and hierarchical models, three classification approaches are possible, i.e., classifying directly based on the multidimensional model and classifying with the equivalent flat or hierarchical models. The efficiency of these three approaches is investigated using drug information collection with two different dimensions: 1) drug topics and 2) primary therapeutic classes. In the experiments, k-nearest neighbor, naive Bayes, and two centroid-based methods are selected as classifiers. The comparisons among three approaches of classification are done using two-way analysis of variance, followed by the Scheffé's test for post hoc comparison. The experimental results show that multidimensional-based classification performs better than the others, especially in the presence of a relatively small training set. As one application, a category-based search engine using the multidimensional category concept was developed to help users retrieve drug information.