Forecasting Cancer Incidence Trends in Indian States and Union Territories (2019–2033): A Data-Driven Approach

Objectives: Our aim is to analyse the cancer prevalence in the Indian States and Union territories, Using the Statistical and the Machine Learning Method. India has been facing a rise in cancer incidence over the past few years, and is expected to rise faster in the upcoming years. Use of the ML and Statistical model helps to access future insight into the growth pattern in cancer incidence. Materials and Methods: The publicly available data of the past 4 years is extracted from the source ‘data.gov. in’. Descriptive measures, statistical and machine learning forecasting technique is used to see the current trend and identify the hotspot states/union territories (UTs) having the higher growth rate and will have the major contribution in the cancer incidence in India. Results: The significant difference in cancer incidence has been observed in Indian States/UT. Daman (8.1%), Dadra and Nagar Haveli (7.9%), Sikkim and Manipur have the highest cancer growth rates. The log-linear model outperformed the autoregressive integrated moving average, exponential smoothing and random forest models in terms of fit (R 2 = 0.9998, p < 0.001). By 2033, the incidence of cancer in the hotspot region is expected to double what it is at present. Conclusion: The study gives a new concept of hotspot regions for the cancer-prone states and will be helpful in making the policy for early cancer detection and making a plan for providing health infrastructure to those in need.