Introduction to medical data mining / 生物医学工程学杂志

Modern medicine generates a great deal of information stored in the medical database. Extracting useful knowledge and providing scientific decision-making for the diagnosis and treatment of disease from the database increasingly becomes necessary. Data mining in medicine can deal with this problem. It can also improve the management level of hospital information and promote the development of telemedicine and community medicine. Because the medical information is characteristic of redundancy, multi-attribution, incompletion and closely related with time, medical data mining differs from other one. In this paper we have discussed the key techniques of medical data mining involving pretreatment of medical data, fusion of different pattern and resource, fast and robust mining algorithms and reliability of mining results. The methods and applications of medical data mining based on computation intelligence such as artificial neural network, fuzzy system, evolutionary algorithms, rough set, and support vector machine have been introduced. The features and problems in data mining are summarized in the last section.

Algorithm of real-time QRS complex detection for the GPRS mobile ECG telemonitoring system / 第三军医大学学报

Objective To develop a real-time QRS complex detection algorithm of dynamic ECG signals for the GPRS mobile telemonitoring system. Methods Before the first and second derivatives of ambulatory ECG signals were processed by moving average method, the signals sampled from CM5 monitoring lead were filtered with the average of continuous four ECG sample signal points. The R waves could be detected precisely by local minima of second derivatives and Q & S waves were located correctly by cross-zero points of first derivatives of ambulatory ECG signals in a short-time searching windows. The QRS recognition thresholds, which could revise themselves according to the detected values and vary with the analyzing signals, were designed in this paper. Results With a polynomial computation complexity, the novel algorithm insensitive to baseline draft and noise caused by mobile communication filtered power-line interference and most of muscle noise and reduced the search time below 0.02 s during detecting each Q wave, R wave and S wave. For the normal and clinical patients, this algorithm correctly detected up to 99.8% of the QRS complex of ambulatory ECG signals. Conclusion The algorithm can meet the need of real-time QRS complex detection and analysis for the GRRS mobile ECG telemonitoring system.