Statistical Modelling and Forecasting of Cervix Cancer Casesin Radiation Oncology Treatment: A Hospital Based Studyfrom Western Nepal


Background: To estimate the numbers and trends in cervix cancer cases visiting the Radiotherapy Departmentat Manipal Teaching Hospital, Pokhara, Nepal, statistical modelling from retrospective data was applied.Materials and
Methods: A retrospective study was carried out on data for a total of 159 patients treated forcervix cancer at Manipal Teaching Hospital, Pokhara, Nepal, between 28th September 2000 and 31st December2008. Theoretical statistics were used for statistical modelling and forecasting.
Results: Using curve fittingmethod, Linear, Logarithmic, Inverse, Quadratic, Cubic, Compound, Power and Exponential growth modelswere validated. Including the constant term, none of the models fit the data well. Excluding the constant term, thecubic model demonstrated the best fit, with R2=0.871 (p=0.004). In 2008, the observed and estimated numbers ofcases were same (12). According to our model, 273 patients with cervical cancer are expected to visit the hospitalin 2015.
Conclusions: Our data predict a significant increase in cervical cancer cases in this region in the nearfuture. This observation suggests the need for more focus and resource allocation on cervical cancer screeningand treatment.