Dataset Information

Time Series Analysis and Forecasting with Automated Machine Learning on a National ICD-10 Database.

ABSTRACT: The application of machine learning (ML) for use in generating insights and making predictions on new records continues to expand within the medical community. Despite this progress to date, the application of time series analysis has remained underexplored due to complexity of the underlying techniques. In this study, we have deployed a novel ML, called automated time series (AutoTS) machine learning, to automate data processing and the application of a multitude of models to assess which best forecasts future values. This rapid experimentation allows for and enables the selection of the most accurate model in order to perform time series predictions. By using the nation-wide ICD-10 (International Classification of Diseases, Tenth Revision) dataset of hospitalized patients of Romania, we have generated time series datasets over the period of 2008-2018 and performed highly accurate AutoTS predictions for the ten deadliest diseases. Forecast results for the years 2019 and 2020 were generated on a NUTS 2 (Nomenclature of Territorial Units for Statistics) regional level. This is the first study to our knowledge to perform time series forecasting of multiple diseases at a regional level using automated time series machine learning on a national ICD-10 dataset. The deployment of AutoTS technology can help decision makers in implementing targeted national health policies more efficiently.

SUBMITTER: Olsavszky V

PROVIDER: S-EPMC7400312 | biostudies-literature | 2020 Jul

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Time Series Analysis and Forecasting with Automated Machine Learning on a National ICD-10 Database.

Olsavszky Victor V Dosius Mihnea M Vladescu Cristian C Benecke Johannes J

International journal of environmental research and public health 20200710 14

The application of machine learning (ML) for use in generating insights and making predictions on new records continues to expand within the medical community. Despite this progress to date, the application of time series analysis has remained underexplored due to complexity of the underlying techniques. In this study, we have deployed a novel ML, called automated time series (AutoTS) machine learning, to automate data processing and the application of a multitude of models to assess which best ...[more]

PMID: 32664331

Similar Datasets

Project description:ImportanceForecasting the volume of hospital discharges has important implications for resource allocation and represents an opportunity to improve patient safety at periods of elevated risk.ObjectiveTo determine the performance of a new time-series machine learning method for forecasting hospital discharge volume compared with simpler methods.DesignA retrospective cohort study of daily hospital discharge volumes at 2 large, New England academic medical centers between January 1, 2005, and December 31, 2014 (hospital 1), or January 1, 2005, and December 31, 2010 (hospital 2), comparing time-series forecasting methods for prediction was performed. Data analysis was conducted from February 28, 2017, to August 30, 2018. Group-level data for all discharges from inpatient units were included. In addition to conventional methods, a technique originally developed for allocating data center resources, and comparison strategies for incorporating prior data and frequency of model updates, was conducted to identify the model application that optimized forecast accuracy.Main outcomes and measuresModel calibration as measured by R2 and, secondarily, number of days with errors greater than 1 SD of daily volume.ResultsDuring the forecasted year, hospital 1 had 54?411 discharges (daily mean, 149) and hospital 2 had 47?456 discharges (daily mean, 130). The machine learning method was well calibrated at both sites (R2, 0.843 and 0.726, respectively) and made errors greater than 1 SD of daily volume on only 13 and 22 days, respectively, of the forecast year at the 2 sites. Last-value-carried-forward models performed somewhat less well (calibration R2, 0.781 and 0.596, respectively) with 13 and 46 errors of 1 SD or greater, respectively. More frequent retraining and training sets of longer than 1 year had minimal effects on the machine learning method's performance.Conclusions and relevanceVolume of hospital discharges can perhaps be reliably forecasted using simple carry-forward models as well as methods drawn from machine learning. The benefit of the latter does not appear to be dependent on extensive training data and may enable forecasts up to 1 year in advance with superior absolute accuracy to carry-forward models.

Project description:The emergence of new technologies to synthesize and analyze big data with high-performance computing has increased our capacity to more accurately predict crop yields. Recent research has shown that machine learning (ML) can provide reasonable predictions faster and with higher flexibility compared to simulation crop modeling. However, a single machine learning model can be outperformed by a "committee" of models (machine learning ensembles) that can reduce prediction bias, variance, or both and is able to better capture the underlying distribution of the data. Yet, there are many aspects to be investigated with regard to prediction accuracy, time of the prediction, and scale. The earlier the prediction during the growing season the better, but this has not been thoroughly investigated as previous studies considered all data available to predict yields. This paper provides a machine leaning based framework to forecast corn yields in three US Corn Belt states (Illinois, Indiana, and Iowa) considering complete and partial in-season weather knowledge. Several ensemble models are designed using blocked sequential procedure to generate out-of-bag predictions. The forecasts are made in county-level scale and aggregated for agricultural district and state level scales. Results show that the proposed optimized weighted ensemble and the average ensemble are the most precise models with RRMSE of 9.5%. Stacked LASSO makes the least biased predictions (MBE of 53 kg/ha), while other ensemble models also outperformed the base learners in terms of bias. On the contrary, although random k-fold cross-validation is replaced by blocked sequential procedure, it is shown that stacked ensembles perform not as good as weighted ensemble models for time series data sets as they require the data to be non-IID to perform favorably. Comparing our proposed model forecasts with the literature demonstrates the acceptable performance of forecasts made by our proposed ensemble model. Results from the scenario of having partial in-season weather knowledge reveals that decent yield forecasts with RRMSE of 9.2% can be made as early as June 1st. Moreover, it was shown that the proposed model performed better than individual models and benchmark ensembles at agricultural district and state-level scales as well as county-level scale. To find the marginal effect of each input feature on the forecasts made by the proposed ensemble model, a methodology is suggested that is the basis for finding feature importance for the ensemble model. The findings suggest that weather features corresponding to weather in weeks 18-24 (May 1st to June 1st) are the most important input features.

Project description:BACKGROUND:Implementation of the International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) in the U.S. on October 1, 2015 was a significant policy change with the potential to affect established injury morbidity trends. This study used data from a single state to demonstrate 1) the use of a statistical method to estimate the effect of this coding transition on injury hospitalization trends, and 2) interpretation of significant changes in injury trends in the context of the structural and conceptual differences between ICD-9-CM and ICD-10-CM, the new ICD-10-CM-specific coding guidelines, and proposed ICD-10-CM-based framework for reporting of injuries by intent and mechanism. Segmented regression analysis was used for statistical modeling of interrupted time series monthly data to evaluate the effect of the transition to ICD-10-CM on Kentucky hospitalizations' external-cause-of-injury completeness (percentage of records with principal injury diagnoses supplemented with external-cause-of-injury codes), as well as injury hospitalization trends by intent or mechanism, January 2012-December 2017. RESULTS:The segmented regression analysis showed an immediate significant drop in external-cause-of-injury completeness during the transition month, but returned to its pre-transition levels in November 2015. There was a significant immediate change in the percentage of injury hospitalizations coded for unintentional (3.34%) and undetermined intent (-?3.39%). There were immediate significant changes in the level of injury hospitalization rates due to poisoning, suffocation, struck by/against, other transportation, unspecified mechanism, and other specified not elsewhere classifiable mechanism. Significant change in slope after the transition (without immediate level change) was identified for assault, firearm, cut/pierce, and motor vehicle traffic injury rates. The observed trend changes reflected structural and conceptual features of ICD-10-CM coding (e.g., poisoning and suffocations are now captured via diagnosis codes only), new coding guidelines (e.g., requiring coding of injury intent as "accidental" if it is unknown or unspecified), and CDC proposed external-cause-of-injury code groupings by injury intent and mechanism. Researchers can replicate this methodology assessing trends in injuries or other ICD-10-CM-coded conditions using administrative billing data sets. CONCLUSIONS:The CDC 's Proposed Framework for Presenting Injury Data Using ICD-10-CM External Cause of Injury Codes provided a logical transition from the ICD-9-CM-based matrix on injury hospitalization trends by intent and mechanism. Our findings are intended to raise awareness that changes in the ICD-10-CM coding system must be understood to assure accurate interpretation of injury trends.

Dataset Information

Time Series Analysis and Forecasting with Automated Machine Learning on a National ICD-10 Database.

Publications

Time Series Analysis and Forecasting with Automated Machine Learning on a National ICD-10 Database.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure