An IoT based efficient hybrid recommender system for cardiovascular disease Fouzia Jabeen 1 & Muazzam Maqsood 1 & Mustansar Ali Ghazanfar 2 & Farhan Aadil 1 & Salabat Khan 1 & Muhammad Fahad Khan 1 & Irfan Mehmood 3 Received: 4 July 2018 /Accepted: 17 February 2019 # Springer Science+Business Media, LLC, part of Springer Nature 2019 Abstract A fog-based IoT model can be helpful for patients from remote areas with cardiovascular disease. An expert cardiologist is usually not available in such remote areas. There are some systems available to classify heart disease and provide recommendations but these existing systems only use classification for recommendations. From this line of research, we propose an IoT based efficient community-based recommender system that diagnoses cardiac disease and its type and provides recommendations related to the physical and dietary plan. The first part intent to collect the data from the patient remotely by using the bio sensors. The IoT based environment is used to transmit the data to the server. Afterward, heart disease prediction model is implemented, that can diagnose the cardiovascular disease and classify into eight available cardiovascular classes i.e. Myocardial Infarction (MI stable), Myocardial Infarction (MI unstable), Acute Coronary Syndrome (ACS), Atrial Fibrillation (AF), Hypertension (HTN), Ischemic Heart Disease (IHD), Left Ventricular Hypertrophy (LVH), Chronic Heart Failure/ Left Ventricle Function (CCF/LVF), Supraventricular Tachycardia (SVT). The second part pursues to provide physical and dietary plan recommendation to the cardiac patient according to gender and age groups. A dataset for diseases and corresponding recommendations is collected from a well-renowned hospital with the help of an expert cardiologist. The performance of the system is evaluated in terms of precision, recall and Mean absolute error and achieves 98% accuracy. Keywords Cardiovascular disease prediction . CVD . Recommender system . Classification . IoT 1 Introduction In recent years, fog computing has been used to provide frame- works to design IoT based medical solutions. Cardiovascular disease (CVD) is a life-threatening disease that needs such so- lutions. Cardiovascular disease includes a list of diseases that affect heart functionality. The effects of heart disease are very severe, that reach from high hypertension, arrhythmia to strokes, heart attacks, and even death. In recent years, one- third of deaths across the globe are due to heart diseases [1, 2]. Pakistan is among those countries that have a high risk of coronary heart diseases. In Pakistan, 30% to 40% of deaths are due to cardiovascular disease. Heart diseases are, therefore, considered as life-threatening diseases, which, if not diagnosed in time and is not treated properly, can cause complications, including death [3]. In some cases, it becomes more complicat- ed and difficult to cure due to various reasons like unavailability of an expert cardiologist. The modern technology can be useful to identify and to provide healthy lifestyle suggestions to car- diac patients. Using machine learning and data mining tech- niques can reduce the cost and time of treatment [4]. One use of machine learning and data mining technique is to diagnose chronic diseases and provide recommendations to improve the lifestyle of the patient which ultimately help them to improve their health. In the past, cardiovascular disease was mostly found in old age people but now almost every age group is facing the risk of cardiovascular disease. Due to the advancements in technology, medical facilities have improved a lot as compared to the past years. However, people living in rural areas have fewer medical facilities and they struggle more for their survival. E-health systems provide This article is part of the Topical Collection: Special issue on Fog Computing for Healthcare Guest Editors: Han-Chieh Chao, Sana Ullah, Christos Verikoukis, and Ki-Il Kim * Irfan Mehmood irfanmehmood@ieee.org 1 Department of Computer Science, COMSATS University Islamabad, Attock Campus, Attock, Pakistan 2 School of Architecture, Computing and Engineering, University of East London, London, UK 3 Department of Software, Sejong University, Seoul, South Korea Peer-to-Peer Networking and Applications https://doi.org/10.1007/s12083-019-00733-3