# DeepJoint: Robust Survival Modelling Under Clinical Presence Shift

arXiv: https://arxiv.org/abs/2205.13481 · HTML: https://mlsanity.com/paper/2205.13481/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 72 references that are in the map.
- First posted on arXiv 26 May 2022.

## Builds on (most cited first, 23 of 23)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [An Overview of Multi-Task Learning in Deep Neural Networks](https://mlsanity.com/paper/1706.05098/) (2017)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [End-to-End Multi-Task Learning with Attention](https://mlsanity.com/paper/1803.10704/) (2018)
- [Learning under Concept Drift: A Review](https://mlsanity.com/paper/2004.05785/) (2020)
- [Detecting and Correcting for Label Shift with Black Box Predictors](https://mlsanity.com/paper/1802.03916/) (2018)
- [DeepSurv: Personalized Treatment Recommender System Using A Cox Proportional Hazards Deep Neural Network](https://mlsanity.com/paper/1606.00931/) (2016)
- [RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism](https://mlsanity.com/paper/1608.05745/) (2016)
- [Scalable and accurate deep learning for electronic health records](https://mlsanity.com/paper/1801.07860/) (2018)
- [Doctor AI: Predicting Clinical Events via Recurrent Neural Networks](https://mlsanity.com/paper/1511.05942/) (2015)
- [The Benefit of Multitask Representation Learning](https://mlsanity.com/paper/1505.06279/) (2015)
- [Latent ODEs for Irregularly-Sampled Time Series](https://mlsanity.com/paper/1907.03907/) (2019)
- [MIMIC-Extract: A Data Extraction, Preprocessing, and Representation Pipeline for MIMIC-III](https://mlsanity.com/paper/1907.08322/) (2019)
- [Modeling The Intensity Function Of Point Process Via Recurrent Neural Networks](https://mlsanity.com/paper/1705.08982/) (2017)
- [Interpolation-Prediction Networks for Irregularly Sampled Time Series](https://mlsanity.com/paper/1909.07782/) (2019)
- [Modeling Missing Data in Clinical Time Series with RNNs](https://mlsanity.com/paper/1606.04130/) (2016)
- [Feature Robustness in Non-stationary Health Records: Caveats to Deployable Model Performance in Common Clinical Machine Learning Tasks](https://mlsanity.com/paper/1908.00690/) (2019)
- [DeepCare: A Deep Dynamic Memory Model for Predictive Medicine](https://mlsanity.com/paper/1602.00357/) (2016)
- [Discrete Event, Continuous Time RNNs](https://mlsanity.com/paper/1710.04110/) (2017)
- [Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis](https://mlsanity.com/paper/1705.05267/) (2017)
- [Medical Concept Embedding with Time-Aware Attention](https://mlsanity.com/paper/1806.02873/) (2018)
- [Improving Irregularly Sampled Time Series Learning with Dense Descriptors of Time](https://mlsanity.com/paper/2003.09291/) (2020)
- [Mixed effects models for healthcare longitudinal data with an informative visiting process: a Monte Carlo simulation study](https://mlsanity.com/paper/1808.00419/) (2018)

## Built on by (most cited first, 5 of 5)

- [Accounting For Informative Sampling When Learning to Forecast Treatment Outcomes Over Time](https://mlsanity.com/paper/2306.04255/) (2023)
- [Imputation Strategies Under Clinical Presence: Impact on Algorithmic Fairness](https://mlsanity.com/paper/2208.06648/) (2022)
- [Robust prediction under missingness shifts](https://mlsanity.com/paper/2406.16484/) (2024)
- [SeqRisk: Transformer-augmented latent variable model for robust survival prediction with longitudinal data](https://mlsanity.com/paper/2409.12709/) (2024)
- [EDEN : An Event DEtection Network for the annotation of Breast Cancer recurrences in administrative claims data](https://mlsanity.com/paper/2211.08077/) (2022)

## Abstract (arXiv)

Observational data in medicine arise as a result of the complex interaction between patients and the healthcare system. The sampling process is often highly irregular and itself constitutes an informative process. When using such data to develop prediction models, this phenomenon is often ignored, leading to sub-optimal performance and generalisability of models when practices evolve. We propose a multi-task recurrent neural network which models three clinical presence dimensions -- namely the longitudinal, the inter-observation and the missingness processes -- in parallel to the survival outcome. On a prediction task using MIMIC III laboratory tests, explicit modelling of these three processes showed improved performance in comparison to state-of-the-art predictive models (C-index at 1 day horizon: 0.878). More importantly, the proposed approach was more robust to change in the clinical presence setting, demonstrated by performance comparison between patients admitted on weekdays and weekends. This analysis demonstrates the importance of studying and leveraging clinical presence to improve performance and create more transportable clinical models.