Machine learning analysis and risk prediction of weather-sensitive mortality related to cardiovascular disease during summer in Tokyo, Japan.

Climate-sensitive diseases developing from heat or cold stress threaten human health. Therefore, the future health risk induced by climate change and the aging of society need to be assessed. We developed a prediction model for mortality due to cardiovascular diseases such as myocardial infarction and cerebral infarction, which are weather or climate sensitive, using machine learning (ML) techniques. We evaluated the daily mortality of ischaemic heart disease (IHD) and cerebrovascular disease (CEV) in Tokyo and Osaka City, Japan, during summer. The significance of delayed effects of daily maximum temperature and other weather elements on mortality was previously demonstrated using a distributed lag nonlinear model. We conducted ML by a LightGBM algorithm that included specified lag days, with several temperature- and air pressure-related elements, to assess the respective mortality risks for IHD and CEV, based on training and test data for summer 2010-2019. These models were used to evaluate the effect of climate change on the risk for IHD mortality in Tokyo by applying transfer learning (TL). ML with TL predicted that the daily IHD mortality risk in Tokyo would averagely increase by 29% and 35% at the 95th and 99th percentiles, respectively, using a high-level warming-climate scenario in 2045-2055, compared to the risk simulated using ML in 2009-2019.

Impact of the COVID-19 pandemic on changes in temperature-sensitive cardiovascular and respiratory disease mortality in Japan.

Some cardiovascular and respiratory diseases are triggered by changes in ambient temperature or extremes of temperature. This study aimed to clarify the changes in mortality associated with temperature-sensitive diseases in Japan during the COVID-19 pandemic. We used data from three major cities (Sapporo City, Tokyo 23 wards, and Osaka City) from 2010 to 2019 to determine disease mortality rates and monthly mean temperatures from April to December. If the pandemic had not occurred in 2020, the results showed that temperature-sensitive disease death counts would have increased from 324 to 980, based on a 95% confidence interval estimated from the past 10 years in Sapporo (19-56% increase in actual deaths from 2020), from 651 to 2,653 in Tokyo (10-39% increase), and from 235 to 1,343 in Osaka (8-48% increase). Analyses of meshed population data during the COVID-19 pandemic indicated that inhibiting people's behaviour and outdoor mobility, especially in older men, caused a decrease in mortality.

Human cold stress of strong local-wind "Hijikawa-arashi" in Japan, based on the UTCI index and thermo-physiological responses.

We investigated the cold stress caused by a strong local wind called "Hijikawa-arashi," through in situ vital measurements and the Universal Thermal Climate Index (UTCI). This wind is a very interesting winter phenomenon, localized in an area within 1 km of the seashore in Ozu City, Ehime Prefecture in Japan. When a strong Hijikawa-arashi (HA) occurred at 14-15 m s-1, the UTCI decreased to - 30 °C along the bridge where commuting residents are the most exposed to strong and cold winds. On the bridge, most participants in our experiment felt "very cold" or "extremely cold." The UTCI of HA can be predicted from a multiple regression equation using wind speed and air temperature. The cold HA wind is also harmful to human thermo-physiological responses. It leads to higher blood pressure and increased heart rate, both of which act as cardiovascular stress triggers. Increases of 6-10 mmHg and 3-6 bpm for every 10 °C reduction in UTCI were seen on all observational days, including HA and non-HA days. In fact, the participants' body skin temperatures decreased by approximately 1.2 to 1.7 °C for every 10 °C reduction in UTCI. Thus, the UTCI variation due to the HA outbreak corresponded well with the cold sensation and thermo-physiological responses in humans. This result suggests that daily UTCI monitoring enables the prediction of thermo-physiological responses to the HA cold stress.

The phenology of cherry blossom (Prunus yedoensis "Somei-yoshino") and the geographic features contributing to its flowering.

We investigated relationships between the flowering phenology of Prunus yedoensis "Somei-yoshino" (cherry blossom) and the local temperatures in Japan. Our observations were carried out across the Okayama Plain, which included Okayama City (about 700,000 inhabitants), from the winter of 2008 to the spring of 2009. Local air temperature (AT) and the globe temperature (GT) were recorded at the tree height. The flowering dates (FDs) of P. yedoensis were earliest in the central commercial area (located at the center of the plain), followed by the north residential area (further inland), and finally the south residential area (seaward). The recorded FDs were related to the period-averaged daily maximum/minimum AT and GT, and the phenologically effective AT and GT defined in this study. Of these parameters, the phenologically effective GTs correlated most with the FDs. Since the GT is determined by AT, solar and infrared radiations, and wind speed, our previous result suggests that a combination of these three components surrounding the tree is more important for budding and flowering than is AT alone. The supposition is supported by the flowering of P. yedoensis being the latest at the coastal region of the Okayama Plain where the AT were higher than at the inland region, excluding the urban area; it is probably caused by stronger winds there than at the other sites.