Artificial Intelligence Approach for Variant Reporting

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journal

3 Scopus Citations
View graph of relations


  • Michael G. Zomnir
  • Lev Lipkin
  • Maciej Pacula
  • Enrique Dominguez Meneses
  • Allison MacLeay
  • Sekhar Duraisamy
  • Nishchal Nadhamuni
  • Saeed H. Al Turki
  • Miguel Rivera
  • Valentina Nardi
  • Dora Dias-Santagata
  • A. John Iafrate
  • Long P. Le
  • Jochen K. Lennerz


Original languageEnglish
Number of pages13
Journal / PublicationJCO Clinical Cancer Informatics
Publication statusPublished - 22 Mar 2018
Externally publishedYes


Purpose Next-generation sequencing technologies are actively applied in clinical oncology. Bioinformatics pipeline analysis is an integral part of this process; however, humans cannot yet realize the full potential of the highly complex pipeline output. As a result, the decision to include a variant in the final report during routine clinical sign-out remains challenging.

Methods We used an artificial intelligence approach to capture the collective clinical sign-out experience of six board-certified molecular pathologists to build and validate a decision support tool for variant reporting. We extracted all reviewed and reported variants from our clinical database and tested several machine learning models. We used 10-fold cross-validation for our variant call prediction model, which derives a contiguous prediction score from 0 to 1 (no to yes) for clinical reporting.

Results For each of the 19,594 initial training variants, our pipeline generates approximately 500 features, which results in a matrix of > 9 million data points. From a comparison of naive Bayes, decision trees, random forests, and logistic regression models, we selected models that allow human interpretability of the prediction score. The logistic regression model demonstrated 1% false negativity and 2% false positivity. The final models’ Youden indices were 0.87 and 0.77 for screening and confirmatory cutoffs, respectively. Retraining on a new assay and performance assessment in 16,123 independent variants validated our approach (Youden index, 0.93). We also derived individual pathologist-centric models (virtual consensus conference function), and a visual drill-down functionality allows assessment of how underlying features contributed to a particular score or decision branch for clinical implementation.

Conclusion: Our decision support tool for variant reporting is a practically relevant artificial intelligence approach to harness the next-generation sequencing bioinformatics pipeline output when the complexity of data interpretation exceeds human capabilities.

Citation Format(s)

Artificial Intelligence Approach for Variant Reporting. / Zomnir, Michael G.; Lipkin, Lev; Pacula, Maciej; Dominguez Meneses, Enrique; MacLeay, Allison; Duraisamy, Sekhar; Nadhamuni, Nishchal; Al Turki, Saeed H.; Zheng, Zongli; Rivera, Miguel; Nardi, Valentina; Dias-Santagata, Dora; Iafrate, A. John; Le, Long P.; Lennerz, Jochen K.

In: JCO Clinical Cancer Informatics, Vol. 2, 22.03.2018.

Research output: Journal Publications and Reviews (RGC: 21, 22, 62)21_Publication in refereed journal