Ensemble forecasting of a continuously decreasing trend in bladder cancer incidence in Taiwan.
Ontology highlight
ABSTRACT:
SUBMITTER: Hsiao BY
PROVIDER: S-EPMC8052324 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Objective:Tuberculosis (TB) is a major public health problem in China, and contriving a long-term forecast is a useful aid for better launching prevention initiatives. Regrettably, such a forecasting method with robust and accurate performance is still lacking. Here, we aim to investigate its potential of the error-trend-seasonal (ETS) framework through a series of comparative experiments to analyze and forecast its secular epidemic seasonality and trends of TB incidence in China. Methods:We collected the TB incidence data from January 1997 to August 2019, and then partitioning the data into eight different training and testing subsamples. Thereafter, we constructed the ETS and seasonal autoregressive integrated moving average (SARIMA) models based on the training subsamples, and multiple performance indices including the mean absolute deviation, mean absolute percentage error, root-mean-squared error, and mean error rate were adopted to assess their simulation and projection effects. Results:In the light of the above performance measures, the ETS models provided a pronounced improvement for the long-term seasonality and trend forecasting in TB incidence rate over the SARIMA models, be it in various training or testing subsets apart from the 48-step ahead forecasting. The descriptive results to the data revealed that TB incidence showed notable seasonal characteristics with predominant peaks of spring and early summer and began to be plunging at on average 3.722% per year since 2008. However, this rate reduced to 2.613% per year since 2015 and furthermore such a trend would be predicted to continue in years ahead. Conclusion:The ETS framework has the ability to conduct long-term forecasting for TB incidence, which may be beneficial for the long-term planning of the TB prevention and control. Additionally, considering the predicted dropping rate of TB morbidity, more particular strategies should be formulated to dramatically accelerate progress towards the goals of the End TB Strategy.
| S-EPMC7062399 | biostudies-literature
Project description:Tick paralysis resulting from bites from Ixodes holocyclus and I. cornuatus is one of the leading causes of emergency veterinary admissions for companion animals in Australia, often resulting in death if left untreated. Availability of timely information on periods of increased risk can help modulate behaviors that reduce exposures to ticks and improve awareness of owners for the need of lifesaving preventative ectoparasite treatment. Improved awareness of clinicians and pet owners about temporal changes in tick paralysis risk can be assisted by ecological forecasting frameworks that integrate environmental information into statistical time series models. Using an 11-year time series of tick paralysis cases from veterinary clinics in one of Australia's hotspots for the paralysis tick Ixodes holocyclus, we asked whether an ensemble model could accurately forecast clinical caseloads over near-term horizons. We fit a series of statistical time series (ARIMA, GARCH) and generative models (Prophet, Generalised Additive Model) using environmental variables as predictors, and then combined forecasts into a weighted ensemble to minimise prediction interval error. Our results indicate that variables related to temperature anomalies, levels of vegetation moisture and the Southern Oscillation Index can be useful for predicting tick paralysis admissions. Our model forecasted tick paralysis cases with exceptional accuracy while preserving epidemiological interpretability, outperforming a field-leading benchmark Exponential Smoothing model by reducing both point and prediction interval errors. Using online particle filtering to assimilate new observations and adjust forecast distributions when new data became available, our model adapted to changing temporal conditions and provided further reduced forecast errors. We expect our model pipeline to act as a platform for developing early warning systems that can notify clinicians and pet owners about heightened risks of environmentally driven veterinary conditions.
| S-EPMC8887734 | biostudies-literature
Project description:Life expectancy is increasing in many parts of the world. Using proportional hazard models for competing risks, we investigated whether this increase has changed outcomes after radical cystectomy in a sample of 1419 consecutive patients treated between 1993 and 2018. During the observation period, the mean age and the proportion of patients with American Society of Anesthesiologists physical status class 3 or 4 increased, whereas the proportion of patients with heart disease decreased. Competing mortality (causes other than bladder cancer) decreased in all subgroups (hazard ratios [HRs] per year ranged from 0.931 to 0.963) and after controlling for increasing age (HRs ranged from 1.018 to 1.081). In an optimal model resulting from an analysis including age (HR per year 1.048, 95% confidence interval [CI] 1.027-1.070; p < 0.0001), comorbidity, tumor-related variables, body mass index, (neoadjuvant and adjuvant) chemotherapy and smoking status, the HR per increment for year of surgery was 0.928 (95% CI 0.886-0.973; p = 0.0019). The effect of year of surgery was greater than the decrease in competing mortality that may be expected with increasing life expectancy (4 yr for females, 6 yr for males).Patient summaryIn a review of data for 1993-2018, we found that death from other causes after removal of the bladder (radical cystectomy) for bladder cancer decreased over time. This decreasing trend might increase the age limit at which bladder cancer patients can benefit from radical cystectomy in the future.
| S-EPMC8317886 | biostudies-literature
Project description:BackgroundChangeful seasonal influenza activity in subtropical areas such as Taiwan causes problems in epidemic preparedness. The Taiwan Centers for Disease Control has maintained real-time national influenza surveillance systems since 2004. Except for timely monitoring, epidemic forecasting using the national influenza surveillance data can provide pivotal information for public health response.ObjectiveWe aimed to develop predictive models using machine learning to provide real-time influenza-like illness forecasts.MethodsUsing surveillance data of influenza-like illness visits from emergency departments (from the Real-Time Outbreak and Disease Surveillance System), outpatient departments (from the National Health Insurance database), and the records of patients with severe influenza with complications (from the National Notifiable Disease Surveillance System), we developed 4 machine learning models (autoregressive integrated moving average, random forest, support vector regression, and extreme gradient boosting) to produce weekly influenza-like illness predictions for a given week and 3 subsequent weeks. We established a framework of the machine learning models and used an ensemble approach called stacking to integrate these predictions. We trained the models using historical data from 2008-2014. We evaluated their predictive ability during 2015-2017 for each of the 4-week time periods using Pearson correlation, mean absolute percentage error (MAPE), and hit rate of trend prediction. A dashboard website was built to visualize the forecasts, and the results of real-world implementation of this forecasting framework in 2018 were evaluated using the same metrics.ResultsAll models could accurately predict the timing and magnitudes of the seasonal peaks in the then-current week (nowcast) (ρ=0.802-0.965; MAPE: 5.2%-9.2%; hit rate: 0.577-0.756), 1-week (ρ=0.803-0.918; MAPE: 8.3%-11.8%; hit rate: 0.643-0.747), 2-week (ρ=0.783-0.867; MAPE: 10.1%-15.3%; hit rate: 0.669-0.734), and 3-week forecasts (ρ=0.676-0.801; MAPE: 12.0%-18.9%; hit rate: 0.643-0.786), especially the ensemble model. In real-world implementation in 2018, the forecasting performance was still accurate in nowcasts (ρ=0.875-0.969; MAPE: 5.3%-8.0%; hit rate: 0.582-0.782) and remained satisfactory in 3-week forecasts (ρ=0.721-0.908; MAPE: 7.6%-13.5%; hit rate: 0.596-0.904).ConclusionsThis machine learning and ensemble approach can make accurate, real-time influenza-like illness forecasts for a 4-week period, and thus, facilitate decision making.
| S-EPMC7439145 | biostudies-literature
Project description:Salmonella infections remain an important public health issue in Canada and worldwide. Although the majority of Salmonella cases are self-limiting, some will lead to severe symptoms and occasionally severe invasive infections, especially in vulnerable populations such as seniors. This study was performed to assess temporal trends of Salmonella cases in seniors over 15 years (2014-2028) and assess possible impact of demographic shift on national incidence; taking into account of trends in other age groups. The numbers of reported Salmonella cases in seniors (60 years and over) in eight provinces and territories for a period of fifteen years were analysed (1998-2013) using a time-adjusted Poisson regression model. With the demographic changes predicted in the age-structure of the population and in the absence of any targeted interventions, our analysis showed the incidence of Salmonella cases in seniors could increase by 16% by 2028 and the multi-provincial incidence could increase by 5.3%. As a result, the age distribution amongst the Salmonella cases is expected to change with a higher proportion of cases in seniors and a smaller proportion in children (0-4 years old). Over the next decades, cases of infection, hospitalizations and deaths associated with Salmonella in seniors could represent a challenge to public health due to an aging population in Canada. As life expectancy increases in Canada, identification of unique risk factors and targeted prevention in seniors should be pursued to reduce the impact of the demographic shift on disease incidence.
| S-EPMC6258544 | biostudies-literature
Project description:BackgroundThis study aimed to evaluate the updated burden and temporal trends of cancer incidence and mortality in Asian countries.MethodologyThe data used in this study were retrieved from the Global Cancer Observatory, Cancer Incidence in Five Continents volumes I-XI, and the World Health Organization mortality database. These data were used to calculate the Average Annual Percentage Change (AAPC), with a 95% confidence interval (CI) by joinpoint regression analysis to determine the epidemiological trend in the past decade.ResultsIn 2020, the cancer incidence in Asia was 169.1 per 1 00 000, accounting for 49.3% of the global cancer incidence. The most common cancers included lung (13.8%), breast (10.8%) and colorectal (10.6%) cancers. Its mortality was 101.6 per 1 00 000 (58.3% of the global cancer death) with lung (19.2%), liver (10.5%) and stomach (9.9%) cancers being the most common causes of cancer death. The cancer incidence had been increasing in female population, with Korea (AAPC = 5.73, 95% CI [5.30, 6.17], P < .001), Japan (AAPC = 2.67, 95% CI [2.12, 3.23], P < .001) and Kuwait (AAPC = 2.08, 95% CI [.49, 3.69], P = .016) showing the most significant increases in the past decade. The incidence increase was also observed among population aged <40 years old, with Korea (female AAPC = 8.42, 95% CI [7.40, 9.45], P < .001; male AAPC = 5.28, 95% CI [4.23, 6.33], P <.001), China (female AAPC = 2.94, 95% CI [2.07, 3.81], P < .001; male AAPC = 1.37, 95% CI [.57, 2.18], P = .004) and Japan (female AAPC = 2.88, 95% CI [1.88, 3.88], P = .016; male AAPC = 1.59, 95% CI [.40, 2.78], P = .015) showing the most significant increases. However, there was an overall decreasing trend of cancer mortality.ConclusionsThere was a substantial burden of cancer incidence and mortality in Asia. Although there was a decreasing trend in cancer mortality, its incidence had been increasing especially among female and younger populations. Future studies could be done to further investigate the potential reasons for these epidemiologic trends.
| S-EPMC9252010 | biostudies-literature
Project description:BackgroundThe ability to accurately forecast census counts in hospital departments has considerable implications for hospital resource allocation. In recent years several different methods have been proposed forecasting census counts, however many of these approaches do not use available patient-specific information.MethodsIn this paper we present an ensemble-based methodology for forecasting the census under a framework that simultaneously incorporates both (i) arrival trends over time and (ii) patient-specific baseline and time-varying information. The proposed model for predicting census has three components, namely: current census count, number of daily arrivals and number of daily departures. To model the number of daily arrivals, we use a seasonality adjusted Poisson Autoregressive (PAR) model where the parameter estimates are obtained via conditional maximum likelihood. The number of daily departures is predicted by modeling the probability of departure from the census using logistic regression models that are adjusted for the amount of time spent in the census and incorporate both patient-specific baseline and time varying patient-specific covariate information. We illustrate our approach using neonatal intensive care unit (NICU) data collected at Women & Infants Hospital, Providence RI, which consists of 1001 consecutive NICU admissions between April 1st 2008 and March 31st 2009.ResultsOur results demonstrate statistically significant improved prediction accuracy for 3, 5, and 7 day census forecasts and increased precision of our forecasting model compared to a forecasting approach that ignores patient-specific information.ConclusionsForecasting models that utilize patient-specific baseline and time-varying information make the most of data typically available and have the capacity to substantially improve census forecasts.
| S-EPMC3680345 | biostudies-literature
Project description: Not available
| S-BSST1416 | biostudies-other
Project description:This study proposes a gradient-boosting-based machine learning approach for predicting the PM2.5 concentration in Taiwan. The proposed mechanism is evaluated on a large-scale database built by the Environmental Protection Administration, and Central Weather Bureau, Taiwan, which includes data from 77 air monitoring stations and 580 weather stations performing hourly measurements over 1 year. By learning from past records of PM2.5 and neighboring weather stations' climatic information, the forecasting model works well for 24-h prediction at most air stations. This study also investigates the geographical and meteorological divergence for the forecasting results of seven regional monitoring areas. We also compare the prediction performance between Taiwan, Taipei, and London; analyze the impact of industrial pollution; and propose an enhanced version of the prediction model to improve the prediction accuracy. The results indicate that Taipei and London have similar prediction results because these two cities have similar topography (basin) and are financial centers without domestic pollution sources. The results also suggest that after considering industrial impacts by incorporating additional features from the Taichung and Thong-Siau power plants, the proposed method achieves significant improvement in the coefficient of determination (R2) from 0.58 to 0.71. Moreover, for Taichung City the root-mean-square error decreases from 8.56 for the conventional approach to 7.06 for the proposed method.
| S-EPMC7057956 | biostudies-literature
Project description:ObjectiveTo determine the nationwide incidence of subarachnoid hemorrhage (SAH) and report nationwide changes in smoking rates between 1998 and 2012 in Finland.MethodsIn this register-based study, we utilized the nationwide Causes of Death Register and Hospital Discharge Register in identifying SAH events between 1998 and 2012. Population statistics in Finland, which were obtained through a database of Statistics Finland, were used to calculate crude annual incidence rates of SAH. For the direct age standardization of crude incidence rates, we used the European Standard Population (ESP) 2013. Data on changes in nationwide smoking rates between 1998 and 2012 were extracted from a database of the National Institute for Health and Welfare.ResultsFor the total of 79,083,579 cumulative person-years, we identified 6,885 people with SAH. Sudden deaths from SAH away from hospitals or in emergency rooms accounted for 1,771 (26%) of the events. Crude nationwide annual incidence rates varied between 6.2 and 10.0 per 100,000 persons, and increased by age particularly in women. Among 70- to 75-year-old women, the incidence of SAH was highest (22.5 per 100,000 persons). The 3-year average of ESP standardized incidence decreased 24% from 11.7 in 1998-2000 to 8.9 per 100,000 persons in 2010-2012. Daily smoking decreased 30% between 1998 and 2012.ConclusionsThe incidence of SAH seems to be decreasing. This tendency may be coupled with changes in smoking rates. The incidence of SAH in Finland is similar to other Nordic countries.
| S-EPMC5027805 | biostudies-literature