Artificial Neural Networks as a Way to Predict Future Kidney Cancer Incidence in the United States - Beyond the Abstract

The incidence of kidney cancer is increasing and it could be counteracted with new ways to predict and detect it. Our work has the aim to implement an artificial neural network in order to predict the new cases of renal cell carcinoma in the population starting from population rate, obesity, smoking incidence, uncontrolled hypertension, and life expectancy data in the USA.


Statistics on United States population numbers and life expectancy (from Gapminder web resource), obesity (from work of Wang et al.1), smoking consumption (from the work of Ng et al.2), and hypertension were collected. We used MATLAB R2018 (MathWorks) software to implement an artificial neural network. Data were repeatedly and randomly divided into training (70%) and validation (30%) subsets.

The number of new renal cell carcinoma cases will grow up from 44,400 (2020) to 55,400 (2050), registering an increase of +24.7%. Our data show that preventing hypertension would have the greatest impact on the reduction of the incidence, estimated at -775 and -575 cases/year in 2020 and in 2030 respectively. The prevention of obesity and smoking would have a more limited impact, estimated at -64 and -180 cases/year in 2020 and in 2030 respectively for obesity, -173 and -21 cases/year in 2020 and in 2030 respectively for smoking.

Our study described a neural network trained to predict kidney cancer onset in the United States.  Our data show that preventing hypertension would have the greatest impact on the reduction of renal cell carcinoma (RCC) incidence while the prevention of obesity and smoking would have a more limited impact. However, our data should be further confirmed and taken into account as a resource for future cancer-control programs in RCC in the United States. Moreover, our predictions strongly underline the need for accurate studies on RCC-related risk factors in order to possibly reduce the incidence of RCC in future years.

CLINICAL PRACTICE POINTS
  • In the United States, kidney cancer is the sixth common cancer for men and the tenth for women.
  • Several environmental factors, such as cigarette smoking, obesity, hypertension, alcohol consumption, have been correlated to renal cell carcinoma development.
  • We have implemented an artificial neural network with the aim to predict the new cases of renal cell carcinoma in the population starting from population rate, obesity, smoking incidence, uncontrolled hypertension, and life expectancy data in the USA.
  • We used MATLAB R2018 (MathWorks) software to implement an artificial neural network.
  • In the period from 2020 to 2050, renal cell carcinoma incidence will increase from 44,400 to 55,400 (+24.7%).
  • Our data show that preventing hypertension would have the greatest impact on the reduction of the incidence while the prevention of obesity and smoking would have a more limited impact.
Written by: Matteo Santoni,1* Francesco Piva,2* Camillo Porta,3 Sergio Bracarda,4 Daniel Y Heng,5 Marc R. Matrana,6 Enrique Grande,7 Veronica Mollica,8 Gaetano Aurilio,9 Mimma Rizzo,10 Matteo Giulietti,2 Rodolfo Montironi,11,# Francesco Massari8,#,°

*Equally Contributing First Authors
#Equally Contributing Last Authors

  1. Oncology Unit, Macerata Hospital, Macerata, Italy;
  2. Department of Specialistic Clinical and Odontostomatological Sciences, Polytechnic University of Marche, Ancona, Italy;
  3. Department of Biomedical Sciences and Human Oncology, University of Bari 'A. Moro', Bari, Italy.
  4. Azienda Ospedaliera S. Maria, Terni, Italy;
  5. Division of Medical Oncology, Department of Oncology, Tom Baker Cancer Centre, University of Calgary, Calgary, Canada;
  6. Department of Internal Medicine, Hematology/Oncology, Ochsner Medical Center, New Orleans, LA, United States;
  7. Medical Oncology Department, MD Anderson Cancer Center, Madrid, Spain;
  8. Oncologia Medica, Azienda Ospedaliero-Universitaria di Bologna, Via Albertoni - 15, Bologna –Italia;
  9. Medical Oncology Division of Urogenital and Head and Neck Tumours, IEO, European Institute of Oncology IRCCS, Milan, Italy;
  10. Department of Internal Medicine and Therapeutics, University of Pavia and Division of Translational Oncology, I.R.C.C.S. Istituti Clinici Scientifici Maugeri, Pavia, Italy;
  11. Section of Pathological Anatomy, Polytechnic University of the Marche Region, School of Medicine, United Hospitals, Ancona, Italy.
References:

  1. Y Claire Wang, Klim McPherson, Tim Marsh et al. Health and economic burden of the projected obesity trends in the USA and the UK. Lancet Oncology. 2011 Aug 27;378(9793):815-25.
  2. Marie Ng, Michael K Freeman, Thomas D. Fleming et al. Smoking prevalence and cigarette consumption in 187 countries, 1980-2012. JAMA Oncology. 2014 Jan 8;311(2):183-92.
Read the Abstract