大数据，由于与医疗保健相关，已经出现在个性化医疗革命的中心。简单地说，数据的增长给诊断精准性的提高提供了巨大的可能性，因为研究人员能够深入探寻从而创造更多的，尤其是在分子和组织水平的，有针对性的治疗。
美国Definiens公司是生命科学领域里，对生物标志物诊断和医疗保健行业的定量数字化病理图像分析和数据挖掘解决方案的领先供应商。该公司的首席执行官，托马斯黑德勒，和我们探讨了大数据推进个性化医疗事业的五大原因。
1. 能解开未知
科技可以帮助我们从实验样品和活组织切片中获取大量的数据。这就使我们有机会发现与疾病相关的未知因子，并用来当作药物靶点或疾病分子标记。数据还可以用来帮助揭示疾病尤其是癌症的复杂性，从而为每个患者找到不同的药物及治疗方案。
2. 能关联多种诊断信息来源并制定治疗方案
来自临床结果、遗传图谱和组织形态的大数据分析将是个性化医学的一大动力。随着我们对来自不同来源的数据对比整合，为每个患者量身定制治疗方案也将成为可能。
3. 能更多基于事实而非主观理解作出治疗决定
传统而言，大多数诊断是通过显微镜观察活检样本然后给出主观视觉分析。这样根据每位临床医生的具体背景和经验，他们的诊断就有可能不同。因此，对患者样品经常要求多次“第二意见”。病人病理样本的数据化，也就是从定性样品中提取多次离散数据点，就会产生广阔数据量，以便用来进行统计分析，并迅速做出切实可行的临床诊断和治疗建议。
4. 能对组织切片和基因组信息进行系统分析
通过患者的组织切片和特定基因组信息，临床医生可以避免多轮测试，而系统地提取每个病人的详细信息。因为同时拥有所有可用信息从而确定诊断和患者预后，医生就能够以更快的速度在个体基础上给出最好的治疗决定。
5. 临床医师能在自身以及与其他医师之间高度重复
临床上测试结果再现非常重要。每名临床医师在不同的时间应该都能够做出相同的诊断，医师之间也应该同样给出相同的诊断结果。通过使用从临床样本和测试所产生的大数据，测试结果的持续重复性更加可能，临床医师和医生也就能够给出更准确的诊断判断以及更合适的治疗选择。
附原文：
Top Five Reasons Big Data Is Advancing Personalized Medicine
Big Data as it pertains to health care has emerged at the center of the revolution in personalized medicine. Simply put, the proliferation of data offers great possibilities for more precise diagnosis, as researchers are able to drill down to see what’s happening and create more targeted therapies, specifically at the molecular and tissue levels.
In this slideshow, Thomas Heydler, CEO of Definiens, a leading provider of image analysis and data mining solutions for quantitative digital pathology in the life sciences, diagnostic biomarkers and health care industries, explores the top five reasons Big Data is advancing personalized medicine as we know it.
Exposing the unknown
Technologies that can now extract large amounts of data out of samples or biopsies are allowing for previously unknown factors involved in disease to be discovered and utilized as drug targets or disease biomarkers. Data is also able to expose the complexity of a disease, especially cancer, and that there will never be one drug or treatment option that works for every patient
Correlating multiple sources for diagnosis and therapy decisions
Big Data analysis of clinical outcomes, genetic profiles and tissue morphology will be a big driver of personalized medicine. As we are able to align and compare multiple data points from various sources, tailoring individualized treatment plans for each patient will be possible.
Decisions based on hard facts, and less on subjective interpretation
Historically, much diagnosis has been based on subjective visual analysis of a biopsy sample viewed through a microscope. Depending on the clinician’s experience or background, the diagnosis could be different from clinician to clinician. Hence, the oft requested “second opinion.” The datafication of patient samples, where discrete data points are extracted from qualitative samples, yields a vast quantity of knowledge that can be statistically analyzed and quickly reviewed by multiple clinicians for solid diagnosis and therapy recommendations.
Systematic analysis of tissue and genomic information
Through the datafication of patient tissue samples and genomic fingerprints, clinicians can systematically extract more information from each patient without requiring multiple rounds of testing. By having all available information at the same time while determining diagnosis and the patient prognosis, the best treatment decisions can be made on an individual basis at a faster rate.
Reproducibility within and between clinicians
Reproducing testing results in the clinic is very important. Each clinician should be able to produce the same diagnosis from day to day and diagnoses should be the same between clinicians. By using Big Data generated from clinical samples and testing, consistently reproducible test results are possible between clinicians and doctors for more accurate diagnosis and appropriate spending on therapy options.
原文发布时间为：2014-09-03
本文来自云栖社区合作伙伴“大数据文摘”，了解相关信息可以关注“BigDataDigest”微信公众号
