Abstract
Together with population ageing, the number of people suffering from multimorbidity is increasing, up to more than half of the population by 2035. This part of the population is composed by the highest-risk patients, who are, at the same time, the major users of the healthcare systems. The early identification of this sub-population can really help to improve people’s quality of life and reduce healthcare costs. In this paper, we describe a population health management tool based on state-of-the-art intelligent algorithms, starting from administrative and socio-economic data, for the early identification of high-risk patients. The study refers to the population of the Local Health Unit of Central Tuscany in 2015, which amounts to 1,670,129 residents. After a trade-off on machine learning models and on input data, Random Forest applied to 1-year of historical data achieves the best results, outperforming state-of-the-art models. The most important variables for this model, in terms of mean minimal depth, accuracy decrease and Gini decrease, result to be age and some group of drugs, such as high-ceiling diuretics. Thanks to the low inference time and reduced memory usage, the resulting model allows for real-time risk prediction updates whenever new data become available, giving General Practitioners the possibility to early adopt personalised medicine.
Highlights
Received: 30 November 2020 Accepted: 19 December 2020 Published: 25 December 2020Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.Thanks to advances in therapies and treatments, to declining of fertility and to immigration, the population is getting older and older [1,2]
This paper presents the trade-off of machine learning algorithms, taking as input datasets composed by administrative and socio-economic data deriving from periods of study of different lengths, to develop an explainable Population Health Management (PHM) first level screening tool
The early identification of complex patients becomes crucial, but state-of-the-art approaches are used for the identification of sub-populations with a single chronic condition or use clinical data, which are not available in Italy
Summary
Received: 30 November 2020 Accepted: 19 December 2020 Published: 25 December 2020Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.Thanks to advances in therapies and treatments, to declining of fertility and to immigration, the population is getting older and older [1,2]. It is expected that one fourth of the U.S population will be over 65 years old by 2060 [3]. This situation will not be different in the other countries. Nowadays more than half of the elderly population is affected by more than 2 co-existing chronic diseases (multimorbidity), with increasing prevalence in very old people. Over the 15 years, the number of old people affected by chronic diseases will increase by more than 50% [6]. These “complex” patients are the major users of the healthcare systems, because of their higher risk of hospitalisation and death, leading to higher healthcare expenditures than people with no chronic conditions or with a single chronic condition [7,8]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
