View

The Study

Machine learning algorithm validation with a limited sample size

In simple terms

This study is like a science experiment about science experiments. It uses fake data to test how different ways of checking a computer program's guesses can trick us into thinking it's better than it really is. It shows that some common checking methods give too-good-to-be-true results, especially when there isn't much data.

0%

Analysis score

0/ 0

Maximum 0 for a computational/algorithm study.

Where the score came from

Reporting100
Methodology0
Publication100
Statistical54
Study type (basis of the score)
Computational/Algorithm Study
Level 5 - Expert opinion
What’s the bottom line?

When scientists use small amounts of data to train AI, they can accidentally trick themselves into thinking it works better than it does. This happens when the AI gets to 'peek' at the test data during training, especially when picking which data features to use.

Where does this study sit?

Reviews of RCTs (Meta-analyses)

Max 100

Randomized Trials

Max 90

Reviews of Cohort Studies

Max 85

Cohort Studies

Max 72

Reviews of Case-Control Studies

Max 63

Case-Control Studies

Max 58

Cross-Sectional & Case Series

Max 50

Expert Opinion

Max 5
StrongerWeaker
Expert Opinion
Level 5
0

0 / 100

Quality score

Based on clinical experience or non-systematic literature reviews. The lowest level of evidence as they are most susceptible to bias and personal perspective.

Cannot establish causation

Save studies & get personalized insights

Create a free account to save this study, track new evidence as it comes in, and get breakdowns of studies in the topics you care about.

Key takeaways

Summary

Based on the study abstract and findings.

  1. 1If a study says AI can diagnose a disease with 90% accuracy using only 50 people, it might be wrong—especially if it used the wrong testing method.
  2. 2With small data, regular testing tricks made AI seem 10-30% more accurate than it really was.
  3. 3Nested testing and simple train/test splits gave honest results.
  4. 4Choosing features before testing caused bigger lies than adjusting settings.

Score breakdown, methodology, conflicts of interest, evidence analysis & raw study data

Publication

Journal

PLoS ONE

Year

2019

Authors

A. Vabalas, E. Gowen, E. Poliakoff, A. Casson

Open Access
1350 citations
Analysis v5

Related Content

Claims (6)

Assertion

When a study doesn't include enough people, the results might just be due to chance and not reflect what's really going on for most people.

Causal
Read analysis
Assertion

If you're testing a machine learning model using a common method called K-fold cross-validation, you might think it's working better than it really is—especially if you're tuning the model using all your data first. This can trick you into believing your model is accurate when it won't work as well on new data.

Mechanistic
Read analysis
Assertion

Nested cross-validation is like having two layers of checkups when testing a model—it keeps the test data totally separate so the model doesn’t cheat, giving a fairer score no matter how much data you have.

Mechanistic
Read analysis
Assertion

If you pick the most important features using all your data — including the test set — your model might look better than it really is, because it's secretly cheating by seeing data it shouldn't see yet.

Mechanistic
Read analysis
Assertion

Splitting data into training and testing sets gives a fair measure of how well a machine learning model works—just as reliable as more complex methods—because it keeps the test data completely separate so the model doesn't cheat by seeing it early.

Mechanistic
Read analysis
Assertion

If a machine learning model has more features (like traits or measurements) than data points (like people or samples), it can 'cheat' by finding fake patterns in random noise, especially when tested the wrong way — making it look better than it really is.

Mechanistic
Read analysis
Fit Body Science verdict — we translate health studies into clear verdicts backed by peer-reviewed research.

Not medical advice. For informational purposes only. Always consult a qualified healthcare professional before making health decisions.