Prediction of lithium response using genomic data

William Stone, Abraham Nunes, Kazufumi Akiyama, Nirmala Akula, Raffaella Ardau, Jean Michel Aubry, Lena Backlund, Michael Bauer, Frank Bellivier, Pablo Cervantes, Hsi Chung Chen, Caterina Chillotti, Cristiana Cruceanu, Alexandre Dayer, Franziska Degenhardt, Maria Del Zompo, Andreas J. Forstner, Mark Frye, Janice M. Fullerton, Maria Grigoroiu-SerbanescuPaul Grof, Ryota Hashimoto, Liping Hou, Esther Jiménez, Tadafumi Kato, John Kelsoe, Sarah Kittel-Schneider, Po Hsiu Kuo, Ichiro Kusumi, Catharina Lavebratt, Mirko Manchia, Lina Martinsson, Manuel Mattheisen, Francis J. McMahon, Vincent Millischer, Philip B. Mitchell, Markus M. Nöthen, Claire O’Donovan, Norio Ozaki, Claudia Pisanu, Andreas Reif, Marcella Rietschel, Guy Rouleau, Janusz Rybakowski, Martin Schalling, Peter R. Schofield, Thomas G. Schulze, Giovanni Severino, Alessio Squassina, Julia Veeh, Eduard Vieta, Thomas Trappenberg, Martin Alda

Research output: Contribution to journalArticlepeer-review

2 Scopus citations


Predicting lithium response prior to treatment could both expedite therapy and avoid exposure to side effects. Since lithium responsiveness may be heritable, its predictability based on genomic data is of interest. We thus evaluate the degree to which lithium response can be predicted with a machine learning (ML) approach using genomic data. Using the largest existing genomic dataset in the lithium response literature (n = 2210 across 14 international sites; 29% responders), we evaluated the degree to which lithium response could be predicted based on 47,465 genotyped single nucleotide polymorphisms using a supervised ML approach. Under appropriate cross-validation procedures, lithium response could be predicted to above-chance levels in two constituent sites (Halifax, Cohen’s kappa 0.15, 95% confidence interval, CI [0.07, 0.24]; and Würzburg, kappa 0.2 [0.1, 0.3]). Variants with shared importance in these models showed over-representation of postsynaptic membrane related genes. Lithium response was not predictable in the pooled dataset (kappa 0.02 [− 0.01, 0.04]), although non-trivial performance was achieved within a restricted dataset including only those patients followed prospectively (kappa 0.09 [0.04, 0.14]). Genomic classification of lithium response remains a promising but difficult task. Classification performance could potentially be improved by further harmonization of data collection procedures.

Original languageEnglish (US)
Article number1155
JournalScientific reports
Issue number1
StatePublished - Dec 2021

ASJC Scopus subject areas

  • General


Dive into the research topics of 'Prediction of lithium response using genomic data'. Together they form a unique fingerprint.

Cite this