AI-assisted face mask wearing (AiMASK)
Constant face mask detection is required in order to gather information about the public’s compliance with recommendations regarding wearing face masks. While previous studies have used manual methods to acquire this information, AiMASK-assisted face mask detection methods have allowed us to monitor a large number of people in a short period of time with high accuracy. AiMASK’s accuracy has been assessed using actual images captured from CCTVs through external validation processes. This study is the first to use AI-assisted face mask detection in real world settings. Previous studies from Egypt and China also developed a machine-learning device to detect face masks, but they only performed internal validation, with reported accuracy ranging from between 98–100%. (23, 24)
Overall data
The overall rate of mask-wearing in Bangkok was 95.98%. At the beginning of the year 2021 (January 22 to February 28), the percentage of unprotected people was 2.95%, during which the number of new COVID-19 patients was at around 8.7 cases per day. Two weeks before the first cluster was announced, the proportion of unprotected individuals increased to 5.31%, reaching its maximum at 8.38%. The increase in the unprotected group was due to the lower number of new infections per day, averaging at 4.2 cases, the low number of new cases resulting in people letting their guard down.
Immediately after the first cluster was announced, the size of the unprotected group started to decline gradually. Not long after the first, the announcement of the second cluster brought about a further decrease in the size of the unprotected group, which dropped to 2.61%. When the number of patients increase rapidly, people tend to exercise more care to protect themselves. The government has emphasized the importance of social distancing and self-protection ever since the pandemic began in Thailand in 2020. Even when the situation was improving, the public health department still encouraged everyone to keep their distance and to not drop their guard. Data provided by AiMASK showed that measures taken have not been effective enough to maintain adequate prevention. Awareness has been raised by the announcement of new outbreaks, and the longer the duration of sustained increases in new COVID-19 patients, the more the proportion of unprotected people decreases, with high correlations. This illustrates that when the public see that the situation is not showing signs of improving, they are more aware of the high risk of contracting the virus.
Interestingly, the unprotected group consisted more of incorrect mask-wearing people than of non-mask-wearing ones. The reason for improper usage of face masks might be carelessness or lack of knowledge; either way, measures should be taken to ensure not only mask usage but also correct mask usage. During the first COVID-19 outbreak in Thailand, availability of face masks was a problem, resulting in people not wearing masks; however, this was no longer a problem at the time this study was conducted.
Global comparison
A study of the rate of mask-wearing in public in Poland, which observed 2,353 people over 3 days, found that 65–75% of people wore masks.(25) Other studies used series of photographs to estimate rates of mask wearing from 3–5 April 2020, and they found rates in Cambodia, Peru, India, Mexico, and USA of 97%, 86%, 41%, 25%, and 21% respectively.(26, 27) Facemask wearing in France, Iran, and Hong Kong was reported at 56.4%, 45.6%, and 87% respectively. (28–30) A study in India reported that 64.9% of health-care workers in a tertiary care hospital wore face masks.(31)
A comparison of the rate of face mask wearing with the number of COVID-19 patients per 1 million population shows that the USA, Poland, Peru, Mexico, and India had high percentages of patients with lower rates of mask wearing; in contrast, Thailand and Cambodia have relatively higher rates of mask wearing and lower proportions of patients with COVID-19. We believe that effective face mask wearing, which reduces virus transmission in the community, is partly reflected through the numbers of COVID-19 patients, with countries with higher rates of compliance tending to have lower rates of COVID-19 infections. (Table 4)
Table 4
A comparison among different countries of the rates of wearing masks, the number of COVID-19 cases per one million population, and the ranking of number of COVID-19 cases per one million. (Last update July 3rd, 2021) (2)
Country
|
Rate of wearing mask
|
Number of cases per
one million
|
Ranking of number of cases per one million
|
Cambodia (26)
|
97%
|
3,144
|
156
|
Thailand (This study)
|
96%
|
3,961
|
151
|
Peru (26)
|
86%
|
61,631
|
61
|
Poland (25)
|
65–75%
|
76,186
|
39
|
France (29)
|
56%
|
88,365
|
25
|
Iran (28)
|
46%
|
38,100
|
81
|
India (26)
|
41%
|
21,896
|
108
|
Mexico (26)
|
25%
|
19,428
|
112
|
USA (26)
|
21%
|
103,862
|
15
|
Face mask wearing divided by place
From our observation, the locations with the lowest unprotected rate was inside markets (2.64%). Since the start of the COVID-19 spread in Thailand, before the Bang Kae market cluster, another market cluster was reported in Samut Sakhon in December 2020. Markets became regarded as high-risk places for the SARS-COV-2 virus, leading people to believe that they had a greater chance of contracting the virus if they went to the market, leading to their taking on self-protective measures such as wearing masks. In reality, although markets have a high density of people occupying a limited amount of space, conditions which lead to rapid spread, other places such as malls and closed spaces also present a high risk of virus infection. Anywhere occupied by people carries a risk of virus spread, whether low or high, and it is important to emphasize this to the community.
Face mask wearing divided by date and time
Higher rates of unprotected behaviour were found during the holidays, with Sunday evening showing the highest percentage, while the lowest rates were observed on Mondays, and this could be due to the desire for relaxation after a long week of working. People want to get dressed up, take nice photos, eat good food, and chat. Before the pandemic, wearing masks was not habitual; now, it is now mandatory on public transportation and in the workplace. Gradual adoption of this new habit might be the reason why on days when people are not strictly required to wear masks, they prefer not to.
There was a higher percentage of people in the unprotected group in the evenings than in the morning, showing that people have a tendency to relax protective measures more often in the evening than during the day. In the morning people get ready to go to work where they are required to wear masks, but in the evening after a long day at work, they travel back home where they do not need to. Since they are going straight home or going for dinner to places where masks are not worn, they might choose to leave the office without wearing one. Iran and Hong Kong reported that the rate of mask wearing in the morning was significantly higher than in the evening. (28, 32)
Knowing that during holidays and evenings people are prone to be under-protected, measures should be taken to emphasize the need to maintain mask wearing throughout the day and week. Offices and schools can help encourage people to check their protection before leaving and entering their premises. Strategies to boost the economy by promoting holidays might not be the best idea during this ongoing pandemic.
Face mask in different districts
The 5 districts containing the highest number of people in the unprotected group are all adjacent to each other and situated in central business areas. A study from France also reported the presence of independent associations between correct mask position with rural areas. (29) In contrast, the 5 districts with the highest number of COVID-19 patients were not those with the largest unprotected group. No correlation was found between reported cases and unprotected group according to districts, and this may be because the cases found in each district were reported according to where the people resided rather than where they contracted the virus.
Strengths and Limitations
This study is the first to use AI machines to detect mask wearing in public populations and had the largest number of participants in the world. The rates of mask wearing are counted by validated machines which are more reliable than the observations or questionnaires used in previous studies. (28, 29, 31, 33–35) We provided data over a period of 90 days which included both time frames of low contraction rates and high spread. We obtained data from various places across different districts and sub categorized this data according to distinct times of day and days of the week. Not only did we gather information on the percentage of people who wore a mask, but we also identified those who wore it incorrectly, which is tantamount to not wearing one.
In the hopes of providing a foundation for health care policies, we provided quantitative evidence of percentages of patients correctly and incorrectly wearing masks, and correlations with increased numbers of covid infections. Highlighting areas of higher rates of non-compliance with protective measures could possibly raise awareness of the issue in those places and lead to new improved strategies aimed at decreasing the risk of incorrectly worn masks. The fact that a number of people still wear masks incorrectly means that the information currently available is not adequate to raise the public’s awareness of the danger of infection. This data is very important for policy makers, not only for COVID-19, but also for other future cases of droplet-borne respiratory tract infections.
One limitation of this study was that information was collected from a single city, Bangkok, which might not be representative of the total rates of mask wearing in Thailand. Another limitation is that the study did not address demographic data and the reasons for the lack of protection, such as whether people were careless, lacked knowledge, or had difficulties gaining access to masks. Lastly, our current AI machine could not differentiate the different types of masks used such as N95, cloth, and medical masks.