Evans S, Lemon S J, Deters C A, Fusaro R M, Lynch H T
Hereditary Cancer Institute, Creighton University School of Medicine, Omaha, NE, USA.
Comput Biomed Res. 1997 Oct;30(5):337-48. doi: 10.1006/cbmr.1997.1454.
Computer-based data mining methodology applied to family history clinical data can algorithmically create highly accurate, clinically oriented hereditary disease pattern recognizers. For the example of hereditary colon cancer, the data mining's selection of relevant factors to assess for hereditary colon cancer was statistically significant (P < 0.05). All final recognizer-formulated patterns of hereditary colon cancer were independently confirmed by a clinical expert. Applied to previously analyzed family histories, the recognizer identified the definitive hereditary histories, correctly responded negatively to the putative hereditary histories, and correctly responded negatively to empirically elevated colon cancer risk situations. This capability facilitates patient selection for DNA studies in search of gene mutations. When genetic mutations are included as parameters in a patient database for a genetic disease, the process yields an expert system which characterizes variations in clinical disease presentations in terms of genetic mutations. Such information can greatly improve the efficiency of gene testing.
应用于家族病史临床数据的基于计算机的数据挖掘方法，可以通过算法创建高度准确、以临床为导向的遗传性疾病模式识别器。以遗传性结肠癌为例，数据挖掘对评估遗传性结肠癌相关因素的选择具有统计学意义（P < 0.05）。所有最终由识别器制定的遗传性结肠癌模式均由临床专家独立确认。应用于先前分析的家族病史时，该识别器能识别出明确的遗传病史，对假定的遗传病史给出正确的否定回应，并对经经验判断结肠癌风险升高的情况给出正确的否定回应。这种能力有助于选择患者进行寻找基因突变的DNA研究。当将基因突变作为遗传疾病患者数据库中的参数时，该过程会产生一个专家系统，该系统根据基因突变来描述临床疾病表现的差异。此类信息可大大提高基因检测的效率。
