2
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

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

      research-article

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          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.

          Related collections

          Most cited references49

          • Record: found
          • Abstract: found
          • Article: found
          Is Open Access

          Mortality From Ischemic Heart Disease

          Background: Ischemic heart disease (IHD) has been considered the top cause of mortality globally. However, countries differ in their rates and there have been changes over time. Methods and Results: We analyzed mortality data submitted to the World Health Organization from 2005 to 2015 by individual countries. We explored patterns in relationships with age, sex, and income and calculated age-standardized mortality rates for each country in addition to crude death rates. In 5 illustrative countries which provided detailed data, we analyzed trends of mortality from IHD and 3 noncommunicable diseases (lung cancer, stroke, and chronic lower respiratory tract diseases) and examined the simultaneous trends in important cardiovascular risk factors. Russia, United States, and Ukraine had the largest absolute numbers of deaths among the countries that provided data. Among 5 illustrative countries (United Kingdom, United States, Brazil, Kazakhstan, and Ukraine), IHD was the top cause of death, but mortality from IHD has progressively decreased from 2005 to 2015. Age-standardized IHD mortality rates per 100 000 people per year were much higher in Ukraine (324) and Kazakhstan (97) than in United States (60), Brazil (54), and the United Kingdom (46), with much less difference in other causes of death. All 5 countries showed a progressive decline in IHD mortality, with a decline in smoking and hypertension and in all cases a rise in obesity and type II diabetes mellitus. Conclusions: IHD remains the single largest cause of death in countries of all income groups. Rates are different between countries and are falling in most countries, indicating great potential for further gains. On the horizon, future improvements may become curtailed by increasing hypertension in some developing countries and more importantly global growth in obesity.
            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            When Google got flu wrong.

              Bookmark
              • Record: found
              • Abstract: found
              • Article: found
              Is Open Access

              Deep learning based tissue analysis predicts outcome in colorectal cancer

              Image-based machine learning and deep learning in particular has recently shown expert-level accuracy in medical image classification. In this study, we combine convolutional and recurrent architectures to train a deep network to predict colorectal cancer outcome based on images of tumour tissue samples. The novelty of our approach is that we directly predict patient outcome, without any intermediate tissue classification. We evaluate a set of digitized haematoxylin-eosin-stained tumour tissue microarray (TMA) samples from 420 colorectal cancer patients with clinicopathological and outcome data available. The results show that deep learning-based outcome prediction with only small tissue areas as input outperforms (hazard ratio 2.3; CI 95% 1.79–3.03; AUC 0.69) visual histological assessment performed by human experts on both TMA spot (HR 1.67; CI 95% 1.28–2.19; AUC 0.58) and whole-slide level (HR 1.65; CI 95% 1.30–2.15; AUC 0.57) in the stratification into low- and high-risk patients. Our results suggest that state-of-the-art deep learning techniques can extract more prognostic information from the tissue morphology of colorectal cancer than an experienced human observer.
                Bookmark

                Author and article information

                Journal
                Int J Environ Res Public Health
                Int J Environ Res Public Health
                ijerph
                International Journal of Environmental Research and Public Health
                MDPI
                1661-7827
                1660-4601
                10 July 2020
                July 2020
                : 17
                : 14
                : 4979
                Affiliations
                [1 ]Department of Dermatology, Venereology and Allergy, University Medical Center and Medical Faculty Mannheim, University of Heidelberg, and Center of Excellence in Dermatology, Theodor-Kutzer-Ufer 1–3, 68167 Mannheim, Germany; Victor.Olsavszky@ 123456medma.uni-heidelberg.de (V.O.); johannes.benecke@ 123456umm.de (J.B.)
                [2 ]National School of Public Health Management and Professional Development, Str. Vaselor, nr. 31, 030167 Bucharest, Romania; MDosius@ 123456snspms.ro
                [3 ]University of Medicine and Pharmacy Victor Babes, Piaţa Eftimie Murgu, nr.2, 300041 Timisoara, Romania
                Author notes
                [* ]Correspondence: cristian.vladescu@ 123456gmail.com ; Tel.: +40-021-2527834
                Author information
                https://orcid.org/0000-0001-6083-5534
                Article
                ijerph-17-04979
                10.3390/ijerph17144979
                7400312
                32664331
                686ebced-fb92-4351-bd43-bba875c58405
                © 2020 by the authors.

                Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ( http://creativecommons.org/licenses/by/4.0/).

                History
                : 31 May 2020
                : 07 July 2020
                Categories
                Article

                Public health
                automated machine learning,deep learning,artificial intelligence,deadliest diseases,time series,disease prediction

                Comments

                Comment on this article