An assessment of the value of deep neural networks in genetic risk prediction for surgically relevant outcomes

Introduction Postoperative complications affect up to 15% of surgical patients constituting a major part of the overall disease burden in a modern healthcare system. While several surgical risk calculators have been developed, none have so far been shown to decrease the associated mortality and morbidity. Combining deep neural networks and genomics with the already established clinical predictors may hold promise for improvement. Methods The UK Biobank was utilized to build linear and deep learning models for the prediction of surgery relevant outcomes. An initial GWAS for the relevant outcomes was initially conducted to select the Single Nucleotide Polymorphisms for inclusion in the models. Model performance was assessed with Receiver Operator Characteristics of the Area Under the Curve and optimum precision and recall. Feature importance was assessed with SHapley Additive exPlanations. Results Models were generated for atrial fibrillation, venous thromboembolism and pneumonia as genetics only, clinical features only and a combined model. For venous thromboembolism, the ROC-AUCs were 59.6% [59.0%-59.7%], 63.4% [63.2%-63.4%] and 66.1% [65.7%-66.1%] for the linear models and 60.0% [57.8%-61.8%], 63.2% [61.2%-65.0%] and 65.4% [63.6%-67.2%] for the deep learning SNP, clinical and combined models, respectively. For atrial fibrillation, the ROC-AUCs were 60.9% [60.6%-61.0%], 78.7% [78.7%-78.7%] and 80.1% [80.0%-80.1%] for the linear models and 59.9% [.6%-61.3%], 78.8% [77.8%-79.8%] and 79.4% [78.8%-80.5%] for the deep learning SNP, clinical and combined models, respectively. For pneumonia, the ROC-AUCs were 57.3% [56.5%-57.4%], 69.2% [69.1%-69.2%] and 70.5% [70.2%-70.6%] for the linear models and 55.5% [54.1%-56.9%], 69.7% [.5%-70.8%] and 69.9% [68.7%-71.0%] for the deep learning SNP, clinical and combined models, respectively. Conclusion In this report we presented linear and deep learning predictive models for surgery relevant outcomes. Overall, predictability was similar between linear and deep learning models and inclusion of genetics seemed to improve accuracy. ### Competing Interest Statement The authors have declared no competing interest. ### Funding Statement Funded by a grant from the Novo Nordisk Foundation to MS (Grant #NNF20SA0062879) ### Author Declarations I confirm all relevant ethical guidelines have been followed, and any necessary IRB and/or ethics committee approvals have been obtained. Yes The details of the IRB/oversight body that provided approval or exemption for the research described are given below: I confirm that all necessary patient/participant consent has been obtained and the appropriate institutional forms have been archived, and that any patient/participant/sample identifiers included were not known to anyone (e.g., hospital staff, patients or participants themselves) outside the research group so cannot be used to identify individuals. Yes I understand that all clinical trials and any other prospective interventional studies must be registered with an ICMJE-approved registry, such as ClinicalTrials.gov. I confirm that any such study reported in the manuscript has been registered and the trial registration ID is provided (note: if posting a prospective study registered retrospectively, please provide a statement in the trial ID field explaining why the study was not registered in advance). Yes I have followed all appropriate research reporting guidelines, such as any relevant EQUATOR Network research reporting checklist(s) and other pertinent material, if applicable. Yes Data is not publicly available but can be applied for at . Analytic methods will be made public at [github.com][1] at request. Requests to access these datasets should be directed to . . [1]: https://github.com