Nature Communications· 2020Q1
Improving the accuracy of medical diagnosis with causal machine learning
- 604citations
- Q1SCImago
- 2020year
Short summary
A new counterfactual machine learning algorithm achieved expert clinical accuracy in diagnosing patients, placing in the top 25% of doctors in a clinical vignette test, significantly outperforming standard associative algorithms (top 48%).
AI-generated from the title and abstract; the full text is not read.
Key points
- Existing machine learning diagnostic tools are purely associative, leading to potential errors by confusing correlation with causation.
- The study reformulates medical diagnosis as a counterfactual inference task.
- A novel counterfactual diagnostic algorithm was developed and tested.
- The counterfactual algorithm achieved expert clinical accuracy, ranking in the top 25% of doctors on a clinical vignette test.
- Standard associative algorithms performed less effectively, ranking in the top 48%.
AI-generated from the title and abstract; the full text is not read.
Abstract
Machine learning promises to revolutionize clinical decision making and diagnosis. In medical diagnosis a doctor aims to explain a patient's symptoms by determining the diseases causing them. However, existing machine learning approaches to diagnosis are purely associative, identifying diseases that are strongly correlated with a patients symptoms. We show that this inability to disentangle correlation from causation can result in sub-optimal or dangerous diagnoses. To overcome this, we reformulate diagnosis as a counterfactual inference task and derive counterfactual diagnostic algorithms. We compare our counterfactual algorithms to the standard associative algorithm and 44 doctors using a test set of clinical vignettes. While the associative algorithm achieves an accuracy placing in the top 48% of doctors in our cohort, our counterfactual algorithm places in the top 25% of doctors, achieving expert clinical accuracy. Our results show that causal reasoning is a vital missing ingredient for applying machine learning to medical diagnosis.
The authors' abstract, as published at the source. Nature Communications, 2020 · DOI ↗
Continue with a free account
Ask the paper: 3 free questions a day about this paper; save it, get its citation, new summaries every day for your field. Takeaways are Premium.
Continue free on the webSign in with Google or Apple; no card needed. You come back to this paper.
On your phone:
Field: Family Practice
Family PracticeMedicine