@article{discovery10146805,
          volume = {8},
            note = {{\copyright} 2022 Springer Nature Limited. This article is licensed under a Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).},
       publisher = {Springer Science and Business Media LLC},
           title = {Multi-modality machine learning predicting Parkinson's disease},
         journal = {npj Parkinson's Disease},
            year = {2022},
           month = {April},
          number = {1},
          author = {Makarious, Mary B and Leonard, Hampton L and Vitale, Dan and Iwaki, Hirotaka and Sargent, Lana and Dadu, Anant and Violich, Ivo and Hutchins, Elizabeth and Saffo, David and Bandres-Ciga, Sara and Kim, Jonggeol Jeff and Song, Yeajin and Maleknia, Melina and Bookman, Matt and Nojopranoto, Willy and Campbell, Roy H and Hashemi, Sayed Hadi and Botia, Juan A and Carter, John F and Craig, David W and Van Keuren-Jensen, Kendall and Morris, Huw R and Hardy, John A and Blauwendraat, Cornelis and Singleton, Andrew B and Faghri, Faraz and Nalls, Mike A},
             url = {https://doi.org/10.1038/s41531-022-00288-w},
        abstract = {Personalized medicine promises individualized disease prediction and treatment. The convergence of machine learning (ML) and available multimodal data is key moving forward. We build upon previous work to deliver multimodal predictions of Parkinson's disease (PD) risk and systematically develop a model using GenoML, an automated ML package, to make improved multi-omic predictions of PD, validated in an external cohort. We investigated top features, constructed hypothesis-free disease-relevant networks, and investigated drug-gene interactions. We performed automated ML on multimodal data from the Parkinson's progression marker initiative (PPMI). After selecting the best performing algorithm, all PPMI data was used to tune the selected model. The model was validated in the Parkinson's Disease Biomarker Program (PDBP) dataset. Our initial model showed an area under the curve (AUC) of 89.72\% for the diagnosis of PD. The tuned model was then tested for validation on external data (PDBP, AUC 85.03\%). Optimizing thresholds for classification increased the diagnosis prediction accuracy and other metrics. Finally, networks were built to identify gene communities specific to PD. Combining data modalities outperforms the single biomarker paradigm. UPSIT and PRS contributed most to the predictive power of the model, but the accuracy of these are supplemented by many smaller effect transcripts and risk SNPs. Our model is best suited to identifying large groups of individuals to monitor within a health registry or biobank to prioritize for further testing. This approach allows complex predictive models to be reproducible and accessible to the community, with the package, code, and results publicly available.}
}