4.6 Article

Expert-augmented automated machine learning optimizes hemodynamic predictors of spinal cord injury outcome

期刊

PLOS ONE
卷 17, 期 4, 页码 -

出版社

PUBLIC LIBRARY SCIENCE
DOI: 10.1371/journal.pone.0265254

关键词

-

资金

  1. Department of Defense/Congressionally Directed Medical Research Programs/Spinal Cord Injury Research Program [SC150198, SC190233]
  2. Craig H. Neilsen Foundation SCI-Center of Excellence Award
  3. National Institute of Health/National Institute of Neurological Disorders and Stroke [R01NS088475, UH3NS106899]
  4. US Department of Veterans Affairs [I01RX002787, 1I01RX002245]
  5. Craig H. Neilsen Foundation
  6. Wings for Life Foundation
  7. National Institute of Health/National Institute of Neurological Disorders and Stroke National Research Service Award [F32NS117728]
  8. CDMRP [SC150198, 893883] Funding Source: Federal RePORTER

向作者/读者索取更多资源

Artificial intelligence and machine learning have the potential to transform biomedicine by optimizing predictive models and enhancing understanding of disease biology. Automated machine learning, in particular, can democratize AI by reducing the need for human input and expertise. However, successful application of AI and machine learning in biomedicine requires reproducible clinical and biological inferences, which is challenging for rare disorders with small patient cohorts. A model-agnostic framework that incorporates explainable and reproducible AI strategies is proposed to enhance AutoML and facilitate clinical interpretation and integration of expert knowledge.
Artificial intelligence and machine learning (AI/ML) is becoming increasingly more accessible to biomedical researchers with significant potential to transform biomedicine through optimization of highly-accurate predictive models and enabling better understanding of disease biology. Automated machine learning (AutoML) in particular is positioned to democratize artificial intelligence (AI) by reducing the amount of human input and ML expertise needed. However, successful translation of AI/ML in biomedicine requires moving beyond optimizing only for prediction accuracy and towards establishing reproducible clinical and biological inferences. This is especially challenging for clinical studies on rare disorders where the smaller patient cohorts and corresponding sample size is an obstacle for reproducible modeling results. Here, we present a model-agnostic framework to reinforce AutoML using strategies and tools of explainable and reproducible AI, including novel metrics to assess model reproducibility. The framework enables clinicians to interpret AutoML-generated models for clinical and biological verifiability and consequently integrate domain expertise during model development. We applied the framework towards spinal cord injury prognostication to optimize the intraoperative hemodynamic range during injury-related surgery and additionally identified a strong detrimental relationship between intraoperative hypertension and patient outcome. Furthermore, our analysis captured how evolving clinical practices such as faster time-to-surgery and blood pressure management affect clinical model development. Altogether, we illustrate how expert-augmented AutoML improves inferential reproducibility for biomedical discovery and can ultimately build trust in AI processes towards effective clinical integration.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.6
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据