# Exploring Neural Ordinary Differential Equations as Interpretable Healthcare classifiers

arXiv: https://arxiv.org/abs/2503.03129 · HTML: https://mlsanity.com/paper/2503.03129/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 36 references that are in the map.
- First posted on arXiv 5 Mar 2025.

## Builds on (most cited first, 25 of 25)

- [Neural Ordinary Differential Equations](https://mlsanity.com/paper/1806.07366/) (2018)
- [Sanity Checks for Saliency Maps](https://mlsanity.com/paper/1810.03292/) (2018)
- [This Looks Like That: Deep Learning for Interpretable Image Recognition](https://mlsanity.com/paper/1806.10574/) (2018)
- [Neural Controlled Differential Equations for Irregular Time Series](https://mlsanity.com/paper/2005.08926/) (2020)
- [RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanism](https://mlsanity.com/paper/1608.05745/) (2016)
- [A Survey on Neural Network Interpretability](https://mlsanity.com/paper/2012.14261/) (2020)
- [On Neural Differential Equations](https://mlsanity.com/paper/2202.02435/) (2022)
- [The Computational Limits of Deep Learning](https://mlsanity.com/paper/2007.05558/) (2020)
- [Visual Interpretability for Deep Learning: a Survey](https://mlsanity.com/paper/1802.00614/) (2018)
- [Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyond](https://mlsanity.com/paper/2103.10689/) (2021)
- [Deep Learning for Medical Image Processing: Overview, Challenges and Future](https://mlsanity.com/paper/1704.06825/) (2017)
- [Adaptive Checkpoint Adjoint Method for Gradient Estimation in Neural ODE](https://mlsanity.com/paper/2006.02493/) (2020)
- [Interpretability of machine learning based prediction models in healthcare](https://mlsanity.com/paper/2002.08596/) (2020)
- [Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs](https://mlsanity.com/paper/2202.08408/) (2022)
- [Neural ODE control for classification, approximation and transport](https://mlsanity.com/paper/2104.05278/) (2021)
- [SPINE: SParse Interpretable Neural Embeddings](https://mlsanity.com/paper/1711.08792/) (2017)
- [Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systems](https://mlsanity.com/paper/2203.15706/) (2022)
- [Integrating Expert ODEs into Neural ODEs: Pharmacology and Disease Progression](https://mlsanity.com/paper/2106.02875/) (2021)
- [Can Large Language Models abstract Medical Coded Language?](https://mlsanity.com/paper/2403.10822/) (2024)
- [Neural Ordinary Differential Equations for Intervention Modeling](https://mlsanity.com/paper/2010.08304/) (2020)
- [Deep Learning in Finance](https://mlsanity.com/paper/1602.06561/) (2016)
- [DyNODE: Neural Ordinary Differential Equations for Dynamics Modeling in Continuous Control](https://mlsanity.com/paper/2009.04278/) (2020)
- [Text Serialization and Their Relationship with the Conventional Paradigms of Tabular Machine Learning](https://mlsanity.com/paper/2406.13846/) (2024)
- [Deep EHR: Chronic Disease Prediction Using Medical Notes](https://mlsanity.com/paper/1808.04928/) (2018)
- [Enhancing Antibiotic Stewardship using a Natural Language Approach for Better Feature Representation](https://mlsanity.com/paper/2405.20419/) (2024)

## Built on by (most cited first, 1 of 1)

- [Integrating Mechanistic and Data-Driven Models for Neurological Disorders through Differentiable Programming](https://mlsanity.com/paper/2606.06094/) (2026)

## Abstract (arXiv)

Deep Learning has emerged as one of the most significant innovations in machine learning. However, a notable limitation of this field lies in the ``black box" decision-making processes, which have led to skepticism within groups like healthcare and scientific communities regarding its applicability. In response, this study introduces a interpretable approach using Neural Ordinary Differential Equations (NODEs), a category of neural network models that exploit the dynamics of differential equations for representation learning. Leveraging their foundation in differential equations, we illustrate the capability of these models to continuously process textual data, marking the first such model of its kind, and thereby proposing a promising direction for future research in this domain. The primary objective of this research is to propose a novel architecture for groups like healthcare that require the predictive capabilities of deep learning while emphasizing the importance of model transparency demonstrated in NODEs.