Synthetic data is becoming an increasingly promising technology, and successful applications can improve privacy, fairness, and data democratization. While there are many methods for generating synthetic tabular data, the task remains non-trivial and unexplored for specific scenarios. One such scenario is survival data. Here, the key difficulty is censoring: for some instances, we are not aware of the time of event, or if one even occurred. Imbalances in censoring and time horizons cause generative models to experience three new failure modes specific to survival analysis: (1) generating too few at-risk members; (2) generating too many at-risk members; and (3) censoring too early. We formalize these failure modes and provide three new generative metrics to quantify them. Following this, we propose SurvivalGAN, a generative model that handles survival data firstly by addressing the imbalance in the censoring and event horizons, and secondly by using a dedicated mechanism for approximating time-to-event/censoring. We evaluate this method via extensive experiments on medical datasets. SurvivalGAN outperforms multiple baselines at generating survival data, and in particular addresses the failure modes as measured by the new metrics, in addition to improving downstream performance of survival models trained on the synthetic data.
Synthetic Survival Data Generation for Heart Failure Prognosis Using Deep Generative Models
Chakri Naruebodindra Medical Institute, Faculty of Medicine Ramathibodi Hospital, Mahidol University(玛希隆大学拉马蒂博迪医院医学院查克里·纳鲁博丁医学研究所);Department of Clinical Epidemiology and Biostatistics, Faculty of Medicine Ramathibodi Hospital, Mahidol University(玛希隆大学拉马蒂博迪医院医学院临床流行病学与生物统计学系);Department of Systems Design Engineering, University of Waterloo(滑铁卢大学系统设计工程系);Cardiovascular Unit, Department of Internal Medicine, Police General Hospital(警察总医院内科心血管科)
AutoScore-Survival: Developing interpretable machine learning-based time-to-event scores with right-censored survival data
Duke-NUS Medical School(杜克-新加坡国立大学医学院);Duke University(杜克大学);Singapore General Hospital(新加坡中央医院);National University of Singapore(新加坡国立大学);Singapore Health Services(新加坡保健服务集团)
Attention-Based Synthetic Data Generation for Calibration-Enhanced Survival Analysis: A Case Study for Chronic Kidney Disease Using Electronic Health Records
Centre for Big Data Research in Health (CBDRH)(健康大数据研究中心);The University of New South Wales(新南威尔士大学)
4D VQ-GAN: Synthesising Medical Scans at Any Time Point for Personalised Disease Progression Modelling of Idiopathic Pulmonary Fibrosis
Hawkes Institute, University College London(伦敦大学学院霍克斯研究所);Department of Computer Science, University College London(伦敦大学学院计算机科学系);Department of Med. Physics & Biomedical Engineering, University College London(伦敦大学学院医学物理与生物医学工程系);Department of Respiratory Medicine, University Hospitals Leuven(鲁汶大学医院呼吸医学科);NIHR Southampton Biomedical Research Centre and Clinical and Experimental Sciences, University of Southampton(南安普顿大学NIHR南安普顿生物医学研究中心与临床与实验科学系);UCL Respiratory, University College London(伦敦大学学院呼吸科)
Generating Reliable Synthetic Clinical Trial Data: The Role of Hyperparameter Optimization and Domain Constraints
Center for Scalable Data Analytics and Artificial Intelligence (ScaDS.AI) Dresden/Leipzig(德累斯顿/莱比锡可扩展数据分析与人工智能中心(ScaDS.AI));Technical University Dresden(德累斯顿工业大学);University Hospital Carl Gustav Carus, Technical University Dresden(德累斯顿工业大学卡尔·古斯塔夫·卡鲁斯大学医院)