Implementing Time Series Analysis to Detect Adrenal Cortical Carcinoma in its Early Phases

Adrenal cortical carcinoma is a rare and aggressive cancer that arises from the adrenal cortex, with an estimated incidence of 1-2 individuals per million each year. Their early diagnosis is essential to prevent the high mortality rate associated with this type of cancer, which in many cases tends to be diagnosed at later stages. Consequently, more efficient and precise techniques for the early detection of ACC are urgently needed. A type of statistical method studying patterns and trends related to time, Time Series Analysis, has been applied to medicine for disease and prediction. In this work, we also introduce time series analysis to detect ACC at an early stage. In this post, we explore the process of applying time series analysis for ACC, including data collection/preprocessing and model creation. First, data will be sourced from various places, such as electronic health records and imaging data. Data Preprocessing involves preprocessing the data set to avoid any outliers or missing values, and feature selection techniques are applied to determine which are essential independent variables for ACC detection. Following data preprocessing, time series models, including ARIMA and LSTM, will be used to uncover patterns or changes reflecting ACC.