Integrating functional data analysis with case-based reasoning for hypertension prognosis and diagnosis based on real-world electronic health records

Background Hypertension is the fifth chronic disease causing death worldwide. The early prognosis and diagnosis are critical in the hypertension care process. Inspired by human philosophy, CBR is an empirical knowledge reasoning method for early detection and intervention of hypertension by only reusing electronic health records. However, the traditional similarity calculation method often ignores the internal characteristics and potential information of medical examination data. Methods In this paper, we first calculate the weights of input attributes by a random forest algorithm. Then, the risk value of hypertension from each medical examination can be evaluated according to the input data and the attribute weights. By fitting the risk values into a risk curve of hypertension, we calculate the similarity between different community residents, and obtain the most similar case according to the similarity. Finally, the diagnosis and treatment protocol of the new case can be given. Results The experiment data comes from the medical examination of Tianqiao Community (Tongling City, Anhui Province, China) from 2012 to 2021. It contains 4143 community residents and 43,676 medical examination records. We first discuss the effect of the influence factor and the decay factor on similarity calculation. Then we evaluate the performance of the proposed FDA-CBR algorithm against the GRA-CBR algorithm and the CS-CBR algorithm. The experimental results demonstrate that the proposed algorithm is highly efficient and accurate. Conclusions The experiment results show that the proposed FDA-CBR algorithm can effectively describe the variation tendency of the risk value and always find the most similar case. The accuracy of FDA-CBR algorithm is higher than GRA-CBR algorithm and CS-CBR algorithm, increasing by 9.94 and 16.41%, respectively.