【工具】survex一个解释机器学习生存模型的R包

文章目录

介绍

由于其灵活性和优越的性能,机器学习模型经常补充并优于传统的统计生存模型。然而,由于缺乏用户友好的工具来解释其内部操作和预测原理,它们的广泛采用受到阻碍。为了解决这个问题,我们引入了survex R包,它提供了一个内聚框架,通过应用可解释的人工智能技术来解释任何生存模型。所提出的软件的功能包括理解和诊断生存模型,这可以导致它们的改进。通过揭示决策过程的洞察力,例如变量效应和重要性,survex能够评估模型的可靠性和检测偏差。因此,可以在诸如生物医学研究和保健应用等敏感领域促进透明度和责任。

Due to their flexibility and superior performance, machine learning models frequently complement and outperform traditional statistical survival models. However, their widespread adoption is hindered by a lack of user-friendly tools to explain their internal operations and prediction rationales. To tackle this issue, we introduce the survex R package, which provides a cohesive framework for explaining any survival model by applying explainable artificial intelligence techniques. The capabilities of the proposed software encompass understanding and diagnosing survival models, which can lead to their improvement. By revealing insights into the decision-making process, such as variable effects and importances, survex enables the assessment of model reliability and the detection of biases. Thus, transparency and responsibility may be promoted in sensitive areas, such as biomedical research and healthcare applications.

代码

案例

r 复制代码
library(survex)
library(survival)
library(ranger)

vet <- survival::veteran

cph <- coxph(Surv(time, status) ~ ., data = vet, x = TRUE, model = TRUE)
exp <- explain(cph, data = vet[, -c(3,4)], y = Surv(vet$time, vet$status))
#> Preparation of a new explainer is initiated 
#>   -> model label       :  coxph (  default  ) 
#>   -> data              :  137  rows  6  cols 
#>   -> target variable   :  137  values ( 128 events and 9 censored ) 
#>   -> times             :  50 unique time points , min = 1.5 , median survival time = 80 , max = 999 
#>   -> times             :  (  generated from y as uniformly distributed survival quantiles based on Kaplan-Meier estimator  ) 
#>   -> predict function  :  predict.coxph with type = 'risk' will be used (  default  ) 
#>   -> predict survival function  :  predictSurvProb.coxph will be used (  default  ) 
#>   -> predict cumulative hazard function  :  -log(predict_survival_function) will be used (  default  ) 
#>   -> model_info        :  package survival , ver. 3.7.0 , task survival (  default  ) 
#>   A new explainer has been created!


shap <- model_survshap(exp, veteran[c(1:4, 17:20, 110:113, 126:129), -c(3,4)])

plot(shap)

参考

  • survex: an R package for explaining machine learning survival models
相关推荐
沐沐沐沐沐沐8 分钟前
图像认知与OpenCV | Day5:图像预处理(4)
人工智能·opencv·计算机视觉
一水鉴天9 分钟前
关于“PromptPilot” 之3 -Prompt构造器核心专项能力:任务调度
人工智能
陈敬雷-充电了么-CEO兼CTO10 分钟前
强化学习三巨头PK:PPO、GRPO、DPO谁是大模型训练的「王炸」?
人工智能·python·机器学习·chatgpt·aigc·ppo·grpo
Wendy144113 分钟前
【图像噪点消除】——图像预处理(OpenCV)
人工智能·opencv·计算机视觉
大江东去浪淘尽千古风流人物13 分钟前
【prompt】Lyra 提示词深度研究
人工智能·prompt
Adorable老犀牛24 分钟前
AI×运维:从“救火队员”到“预见者”的涅槃:智启下一代IT运维的无限可能
运维·人工智能·aiops
coder_pig27 分钟前
👦抠腚男孩的AI学习之旅 | 3、AI-概念名词 & LLM-模型微调
人工智能·aigc·ai编程
竹子_231 小时前
《零基础入门AI:传统机器学习核心算法解析(KNN、模型调优与朴素贝叶斯)》
人工智能·算法·机器学习
星月昭铭2 小时前
Spring AI集成Elasticsearch向量检索时filter过滤失效问题排查与解决方案
人工智能·spring boot·spring·elasticsearch·ai
大数据魔法师2 小时前
Matplotlib(二)- Matplotlib简单绘图
matplotlib·数据可视化