International Research Journal of Engineering and Technology (IRJET)
e-ISSN: 2395-0056
Volume: 10 Issue: 08 | Aug 2023
p-ISSN: 2395-0072
www.irjet.net
"Predictive Modelling for Overweight and Obesity: Harnessing Machine Learning Methods" Sai Vignesh Chintala1, Lohith Vattikuti2, SrinivasaRao Tummalapalli3, Sohith Malyala4 123UG student Dept of Artificial Intelligence and Data science, VVIT, Andhra Pradesh, India
4UG student Dept of Computer Science, SRM, Andhra Pradesh, India --------------------------------------------------------------------------***---------------------------------------------------------------------------human body is now being undertaken. Computed Abstract -The science of machine learning (ML), which is
tomography, also known as CT, or dual-energy X-ray absorptiometry (DXA), the gold standard to estimate the proportion of body fat in people, carry a threat of radiation exposure when used often. A 3D scanner doesn't subject the human body to irradiation way a CT or DXA system does26. Furthermore, there are several approaches can may be utilized to assess or anticipate health risks rather than a single, ideal one. Due to this, this study acquired coupled 3D body scan and DXA data from Koreans to help classify obesity using anthropometric parameters. The adverse outcomes of obesity affect society as a whole; patients as well as loved ones are not the only ones who experience the consequences. Undernourishment and fat have increased in incidence in Southeast Asia, thereby rendering it more difficult to deal with issues associated with nutrition there. In the academic literature, the use of ML techniques for modelling epidemiological data is gaining popularity. These methods could help in the comprehension of illness prevalence, early disease detection, the causes of diseases, and potential treatment or prevention strategies. On data relevant to obesity, a variety of machine learning (ML) methods and algorithms have been evaluated 8). It is vital to create a precise information categorization to support the process of identifying predicted risk factors from the information offered in order to mitigate the morbidity and mortality put on by obesity.ML has been used to arrive at predictions concerning the possibility of developing obesity based on data encoding dietary advice compliance and other variables. Other applications of ML involve foreseeing childhood obesity before the age of two using electronic health records, anticipating obesity-promoting circumstances for children, and modelling medication dosage responses using aggregated metabolomics, lipidomic, and other clinical data. Based on data being dietary compliance with requirements and other factors, ML has been applied to predict the possibility of obesity. The use of electronic health records for predicting childhood obesity before the age of two the prediction of obesitycausing circumstances for children and the modelling of medication dosage responses using aggregated metabolomics, lipidomic, and other clinical data are further uses of ML
now in fast growth, has the potential to completely alter how we approach the obesity problem. Predictive models that can recognise persons who are at risk of becoming fat have been created in recent years using machine learning (ML). These models may be used to assist individuals make better decisions and focus treatments to those who need them the most. The development of individualized therapies is one of the most fascinating uses of ML for obesity. ML models may be used to design personalized therapies that have a greater probability of success by grasping the specific risk variables that apply to each individual. A person who is at risk of obesity owing to a sedentary lifestyle may be encouraged to join a walking club, whereas a person who is at risk due to a poor diet may be provided with access to healthy meal planning options. The establishment of real-time monitoring systems is a promising additional use for machine learning in the fight against obesity. These systems can monitor people's physical activity, food, and other health markers using wearable technology and other sensors. The information gathered through this may then be utilized to identify early indicators of obesity, as well as to offer feedback and encouragement.
Keywords— Machine Learning, obesity, methods, overweight
1. INTRODUCTION Practitioners in medicine must determine a patient's level of obesity. Only a few of the chronic illnesses for which obesity is a risk factor include type 2 diabetes, heart disease, and various cancers. When you become aware of your weight issue, you could feel more inspired to act. Additionally, losing weight intentionally lowers the risk of sickness and enhances health. Despite the fact that the Body Mass Index, also known as the BMI, alone is insufficient for accurately defining obesity since it fails to account for all body-type factors, the World Health Organization (WHO) has defined criteria for obesity. Every place and person have different dietary requirements. For the purpose of correctly describing body type, anthropometric data is sought. Conventional anthropometric methods, however, cannot be applied in daily life since they require trained specialists., inquiry into the application of a 3D scanner for measuring the
© 2023, IRJET
|
Impact Factor value: 8.226
|
ISO 9001:2008 Certified Journal
|
Page 409