Dataset Information

Heatstroke predictions by machine learning, weather information, and an all-population registry for 12-hour heatstroke alerts.

ABSTRACT: This study aims to develop and validate prediction models for the number of all heatstroke cases, and heatstrokes of hospital admission and death cases per city per 12 h, using multiple weather information and a population-based database for heatstroke patients in 16 Japanese cities (corresponding to around a 10,000,000 population size). In the testing dataset, mean absolute percentage error of generalized linear models with wet bulb globe temperature as the only predictor and the optimal models, respectively, are 43.0% and 14.8% for spikes in the number of all heatstroke cases, and 37.7% and 10.6% for spikes in the number of heatstrokes of hospital admission and death cases. The optimal models predict the spikes in the number of heatstrokes well by machine learning methods including non-linear multivariable predictors and/or under-sampling and bagging. Here, we develop prediction models whose predictive performances are high enough to be implemented in public health settings.

SUBMITTER: Ogata S

PROVIDER: S-EPMC8319225 | biostudies-literature | 2021 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Heatstroke predictions by machine learning, weather information, and an all-population registry for 12-hour heatstroke alerts.

Ogata Soshiro S Takegami Misa M Ozaki Taira T Nakashima Takahiro T Onozuka Daisuke D Murata Shunsuke S Nakaoku Yuriko Y Suzuki Koyu K Hagihara Akihito A Noguchi Teruo T Iihara Koji K Kitazume Keiichi K Morioka Tohru T Yamazaki Shin S Yoshida Takahiro T Yamagata Yoshiki Y Nishimura Kunihiro K

Nature communications 20210728 1

This study aims to develop and validate prediction models for the number of all heatstroke cases, and heatstrokes of hospital admission and death cases per city per 12 h, using multiple weather information and a population-based database for heatstroke patients in 16 Japanese cities (corresponding to around a 10,000,000 population size). In the testing dataset, mean absolute percentage error of generalized linear models with wet bulb globe temperature as the only predictor and the optimal models ...[more]

PMID: 34321480

Similar Datasets

Project description:Even with the powerful statistical parameters derived from the Extreme Gradient Boost (XGB) algorithm, it would be advantageous to define the predicted accuracy to the level of a specific case, particularly when the model output is used to guide clinical decision-making. The probability density function (PDF) of the derived intracranial pressure predictions enables the computation of a definite integral around a point estimate, representing the event's probability within a range of values. Seven hold-out test cases used for the external validation of an XGB model underwent retinal vascular pulse and intracranial pressure measurement using modified photoplethysmography and lumbar puncture, respectively. The definite integral ±1 cm water from the median (DIICP) demonstrated a negative and highly significant correlation (-0.5213±0.17, p< 0.004) with the absolute difference between the measured and predicted median intracranial pressure (DiffICPmd). The concordance between the arterial and venous probability density functions was estimated using the two-sample Kolmogorov-Smirnov statistic, extending the distribution agreement across all data points. This parameter showed a statistically significant and positive correlation (0.4942±0.18, p< 0.001) with DiffICPmd. Two cautionary subset cases (Case 8 and Case 9), where disagreement was observed between measured and predicted intracranial pressure, were compared to the seven hold-out test cases. Arterial predictions from both cautionary subset cases converged on a uniform distribution in contrast to all other cases where distributions converged on either log-normal or closely related skewed distributions (gamma, logistic, beta). The mean±standard error of the arterial DIICP from cases 8 and 9 (3.83±0.56%) was lower compared to that of the hold-out test cases (14.14±1.07%) the between group difference was statistically significant (p<0.03). Although the sample size in this analysis was limited, these results support a dual and complementary analysis approach from independently derived retinal arterial and venous non-invasive intracranial pressure predictions. Results suggest that plotting the PDF and calculating the lower order moments, arterial DIICP, and the two sample Kolmogorov-Smirnov statistic may provide individualized predictive accuracy parameters.

Project description:FOR SOCIAL MEDIA: @AliciaCastongu2, @FazalZaidi9, @oozaidat, @Mouhammad_Jumaa OBJECTIVE: Machine learning (ML) algorithms have emerged as powerful predictive tools in the field stroke. Here, we examine the predictive accuracy of ML models for predicting functional outcomes using 24-hour post-treatment characteristics in the Systematic Evaluation of Patients Treated With Neurothrombectomy Devices for Acute Ischemic Stroke (STRATIS) Registry.MethodsML models, adaptive boost, random forest (RF), classification and regression trees (CART), C5.0 decision tree (C5.0), support vector machine (SVM), least absolute shrinkage and selection operator (LASSO), and logistic regression (LR), and traditional LR models were used to predict 90-day functional outcome (modified Rankin Scale score 0-2). Twenty-four-hour National Institutes of Health Stroke Scale (NIHSS) was examined as a continuous or dichotomous variable in all models. Model accuracy was assessed using the area under characteristic curve (AUC).ResultsThe 24-hour NIHSS score was a top-predictor of functional outcome in all models. ML models using the continuous 24-hour NIHSS scored showed moderate-to-good predictive performance (range mean AUC: 0.76-0.92); however, RF (AUC: 0.92 ± 0.028) outperformed all ML models, except LASSO (AUC: 0.89 ± 0.023, p = 0.0958). Importantly, RF demonstrated a significantly higher predictive value than LR (AUC: 0.87 ± 0.031, p = 0.048) and traditional LR (AUC: 85 ± 0.06, p = 0.035) when using the 24-hour continuous NIHSS score. Predictive accuracy was similar between the 24-hour NIHSS score dichotomous and continuous ML models.InterpretationIn this substudy, we found similar predictive accuracy for functional outcome when using the 24-hour NIHSS score as a continuous or dichotomous variable in ML models. ML models had moderate-to-good predictive accuracy, with RF outperforming LR models. External validation of these ML models is warranted. ANN NEUROL 2023;93:40-49.

Project description:IntroductionHeatstroke is a serious clinical condition caused by exposure to high temperature and high humidity environment, which leads to a rapid increase of the core temperature of the body to more than 40°C, accompanied by skin burning, consciousness disorders and other organ system damage. This study aims to analyze the effect of meteorological factors on the incidence of heatstroke using machine learning, and to construct a heatstroke forecasting model to provide reference for heatstroke prevention.MethodsThe data of heatstroke incidence and meteorological factors in a city in South China from May to September 2014-2019 were analyzed in this study. The lagged effect of meteorological factors on heatstroke incidence was analyzed based on the distributed lag non-linear model, and the prediction model was constructed by using regression decision tree, random forest, gradient boosting trees, linear SVRs, LSTMs, and ARIMA algorithm.ResultsThe cumulative lagged effect found that heat index, dew-point temperature, daily maximum temperature and relative humidity had the greatest influence on heatstroke. When the heat index, dew-point temperature, and daily maximum temperature exceeded certain thresholds, the risk of heatstroke was significantly increased on the same day and within the following 5 days. The lagged effect of relative humidity on the occurrence of heatstroke was different with the change of relative humidity, and both excessively high and low environmental humidity levels exhibited a longer lagged effect on the occurrence of heatstroke. With regard to the prediction model, random forest model had the best performance of 5.28 on RMSE and dropped to 3.77 after being adjusted.DiscussionThe incidence of heatstroke in this city is significantly correlated with heat index, heatwave, dew-point temperature, air temperature and zhongfu, among which the heat index and dew-point temperature have a significant lagged effect on heatstroke incidence. Relevant departments need to closely monitor the data of the correlated factors, and adopt heat prevention measures before the temperature peaks, calling on citizens to reduce outdoor activities.

Dataset Information

Heatstroke predictions by machine learning, weather information, and an all-population registry for 12-hour heatstroke alerts.

Publications

Heatstroke predictions by machine learning, weather information, and an all-population registry for 12-hour heatstroke alerts.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets