Reflections on risk prediction




Why is risk prediction so important?In 2019 we make many decisions about prevention and testing based on risk prediction.此外,我们还评估了危害和利益。所有这些预测模型都有优点和缺陷。In making a decision for statin use (another upcoming episode),we have to estimate the risk of cardiovascular events,服用多少他汀类药物可以降低这种风险,and the probability and type of side effects from taking a statin.

These predictions all come from mathematical modelling.数学建模充满了许多危险。我们可以将相同的建模技术应用到不同的数据库,并开发出显著不同的模型。与博士的插曲。Rod Hayward -提高心血管风险评估– gave a great example of how including different databases and even different time periods changes our risk prediction for cardiovascular events.在那一集里,他还解释了时间趋势的问题。心血管风险在过去30多年中有所降低。Thus,我们的预测应该改变。

He also pointed out that we never have data on all the risk factors that one would want in a model.The cardiovascular risk prediction models do not take into consideration family history,肾脏疾病或健康——但我们知道所有这些因素都会改变心血管风险。

The same problems exist for benefit and harm prediction.The promise of big data assumes that we have complete data.Yet in medicine we never have complete data.

These predictive models can help our clinical decision making.We should always use them carefully and thoughtfully.必威体育Understanding that the numbers are estimates with confidence intervals can help us.They can help us start a conversation with our patients about risks and benefits.The numbers are not magic.我们不能把它们输入计算机程序来做临床决策。采用算法决策很快就会变得危险。

Many decisions occur in a "grey zone".We should take into consideration that patient,他或她的顾虑,and the totality of their medical situation.Such decisions are complex and 必威体育understanding these issues makes one wonder about many guidelines and performance measures.We should always remember HL Mencken's quote,“每个人类问题都有一个众所周知的解决方案,整洁,貌似有理的,and wrong".






My problem today is doctors do not want to follow this plan and I have to battle to maintain my existing medication levels.


Steve Lucas

有些事情是相当确定的。Smallpox and polio immunizations eradicate the disease.Type 1 diabetes becomes a chronic disease rather than a malignant one if the person takes insulin.其他事情有一些不确定性,但不太可能做出决定。Among diabetics there is a published study showing reduc tion in cardiovascular events between 1990 and 2010 even as the prevalence of diabetes skyrocketed.You just cannot do that many angioplasties population wide so there is little uncertainty that medications,特别是他汀类药物,大范围的给出了这个结果。有人可能会说,新发现的糖尿病患者数量如此之多,以至于他们没有足够长的时间服用它,but unlikely as the cardiovascular reductions far outpaced other sequelae improvement.So while there is some uncertainty to most things,医疗处方和算法并不像华尔街那样是一次去赌场的旅行。

"All models are wrong but some are useful".George Box

[…]头衔是名誉教授和ACP摄政委员会名誉主席。This post originally appeared at his blog,DB的医疗betway体育报告。Posted by Robert Centor,上午9:00,医学博士[…]