Background: Fraud is a pervasive problem and can occur as fabrication, falsification, plagiarism or theft. The scientific community is not exempt from this universal problem and several studies have recently been caught manipulating or fabricating data. Current measures to prevent and deter scientific misconduct come in the form of the peer-review process and on-site clinical trial auditors. As recent advances in high-throughput omics technologies have moved biology into the realm of big-data, fraud detection methods must be updated for sophisticated computational fraud. In the financial sector, machine learning and digit-preference are successfully used to detect fraud.
Results: Drawing from these sources, we develop methods of fabrication detection in biomedical research and show that machine learning can be used to detect fraud in large-scale omic experiments. Using the raw data as input, the best machine learning models correctly predicted fraud with 84-95% accuracy. With digit frequency as input features, the best models detected fraud with 98%-100% accuracy. All of the data and analysis scripts used in this project are available at https://github.com/MSBradshaw/FakeData .
Conclusions: Using digit frequencies as a generalized representation of the data, multiple machine learning methods were able to identify fabricated data with near perfect accuracy.