Deep transfer learning provides a Pareto improvement for multi-ancestral clinico-genomic prediction of diseases

Accurate genomic predisposition assessment is essential for the prevention and early detection of diseases. Polygenic scores and machine learning models have been developed for disease prediction based on genetic variants and other risk factors. However, over 80% of existing genomic data were acquired from individuals of European descent. As a result, clinico-genomic risk prediction is less accurate for non-European populations. Here we employ a transfer learning strategy to improve the clinico-genomic prediction of disease occurrence for the data-disadvantaged populations. Our multi-ancestral machine learning experiments on clinico-genomic datasets of cancers and Alzheimers disease and synthetic datasets with built-in data inequality and subpopulation shift show that transfer learning can significantly improve disease prediction accuracy for data-disadvantaged populations. Under the transfer learning scheme, the prediction accuracy for the data-disadvantaged populations can be improved without compromising the prediction accuracy for other populations. Therefore, transfer learning provides a Pareto improvement toward equitable machine learning for genomic medicine.