| Abstract: |  Assocation rules and their application are of the main concern of this diploma thesis. The aim is to obtain useful information from real obstetrics database of singleton deliveries. Data mining softwares (RapidMiner, Lisp-Miner and Orange) are used to help with this problem. State of the art data mining of obstetrics field is stated as well.
Our obstetrics data consist of approximately 500 potential features. Most of them are redundant, therefore it was possible to reduce the set to 106 attributes based on literature and with the aid of obstetricians of FN Brno hospital even more to 54 significant features.
This thesis investigates outcome of newborn, influences of parameters on delivery by Caesarean section and macrosomnia of newborn via association rules with Fisher quantifier. Among the most significant results are: support medicine such as oxytocin does not influence positive outcome of newborn, hypoxia of fetus mostly leads to Caesaren section, the more previous deliveries, the better result in spontaneous delivery and that body mass index has impact on macrosomnia.
Resulting features are also evaluated by classification accuracy, sensitivity and specificity of Random Forest classification.
Among the biggest problems encountered were data preparation, low computing power and interpretation of association rules – common problems in such a research task.
|
|---|