Back

Machine learning detects hidden treatment response patterns only in the presence of comprehensive clinical phenotyping

Auger, S. D.; Scott, G.

2024-10-09 health informatics
10.1101/2024.10.09.24315155 medRxiv
Show abstract

Inferential statistics traditionally used in clinical trials can miss relationships between clinical phenotypes and treatment responses. We simulated a randomised clinical trial to explore how gradient boosting (XGBoost) machine learning (ML) compares with traditional analysis when ground truth treatment responsiveness depends on the interaction of multiple phenotypic variables. As expected, traditional analysis detected a significant treatment benefit (outcome measure change from baseline = 4.23; 95% CI 3.64-4.82). However, recommending treatment based upon this evidence would lead to 56.3% of patients failing to respond. In contrast, ML correctly predicted treatment response in 97.8% (95% CI 96.6- 99.1) of patients, with model interrogation showing the critical phenotypic variables and the values determining treatment response had been identified. Importantly, when a single variable was omitted, accuracy dropped to 69.4% (95% CI 65.3-73.4). This proof of principle underscores the significant potential of ML to maximise the insights derived from clinical research studies. However, the effectiveness of ML in this context is highly dependent on the comprehensive capture of phenotypic data.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.