The Safety Challenges of Deep Learning in Real-World Type 1 Diabetes Management

• URL: http://arxiv.org/abs/2310.14743v1
• Date: Mon, 23 Oct 2023 09:25:50 GMT
• Title: The Safety Challenges of Deep Learning in Real-World Type 1 Diabetes Management
• Authors: Harry Emerson, Ryan McConville and Matthew Guy
• Abstract summary: Blood glucose simulation allows the effectiveness of type 1 diabetes (T1D) management strategies to be evaluated without patient harm. Deep learning algorithms provide a promising avenue for extending simulator capabilities. This work explores the implications of using deep learning algorithms trained on real-world data to model glucose dynamics.
• Score: 4.107887387754702
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Blood glucose simulation allows the effectiveness of type 1 diabetes (T1D) management strategies to be evaluated without patient harm. Deep learning algorithms provide a promising avenue for extending simulator capabilities; however, these algorithms are limited in that they do not necessarily learn physiologically correct glucose dynamics and can learn incorrect and potentially dangerous relationships from confounders in training data. This is likely to be more important in real-world scenarios, as data is not collected under strict research protocol. This work explores the implications of using deep learning algorithms trained on real-world data to model glucose dynamics. Free-living data was processed from the OpenAPS Data Commons and supplemented with patient-reported tags of challenging diabetes events, constituting one of the most detailed real-world T1D datasets. This dataset was used to train and evaluate state-of-the-art glucose simulators, comparing their prediction error across safety critical scenarios and assessing the physiological appropriateness of the learned dynamics using Shapley Additive Explanations (SHAP). While deep learning prediction accuracy surpassed the widely-used mathematical simulator approach, the model deteriorated in safety critical scenarios and struggled to leverage self-reported meal and exercise information. SHAP value analysis also indicated the model had fundamentally confused the roles of insulin and carbohydrates, which is one of the most basic T1D management principles. This work highlights the importance of considering physiological appropriateness when using deep learning to model real-world systems in T1D and healthcare more broadly, and provides recommendations for building models that are robust to real-world data constraints.

Related papers

• Comparative Analysis of LSTM Neural Networks and Traditional Machine Learning Models for Predicting Diabetes Patient Readmission [0.0]
  This study uses the Diabetes 130-US Hospitals dataset for analysis and prediction of readmission patients by various machine learning models. LightGBM turned out to be the best traditional model, while XGBoost was the runner-up. This study demonstrates that model selection, validation, and interpretability are key steps in predictive healthcare modeling.
  arXiv  Detail & Related papers  (2024-06-28T15:06:22Z)
• Extracting Training Data from Unconditional Diffusion Models [76.85077961718875]
  diffusion probabilistic models (DPMs) are being employed as mainstream models for generative artificial intelligence (AI) We aim to establish a theoretical understanding of memorization in DPMs with 1) a memorization metric for theoretical analysis, 2) an analysis of conditional memorization with informative and random labels, and 3) two better evaluation metrics for measuring memorization. Based on the theoretical analysis, we propose a novel data extraction method called textbfSurrogate condItional Data Extraction (SIDE) that leverages a trained on generated data as a surrogate condition to extract training data directly from unconditional diffusion models.
  arXiv  Detail & Related papers  (2024-06-18T16:20:12Z)
• MedDiffusion: Boosting Health Risk Prediction via Diffusion-based Data Augmentation [58.93221876843639]
  This paper introduces a novel, end-to-end diffusion-based risk prediction model, named MedDiffusion. It enhances risk prediction performance by creating synthetic patient data during training to enlarge sample space. It discerns hidden relationships between patient visits using a step-wise attention mechanism, enabling the model to automatically retain the most vital information for generating high-quality data.
  arXiv  Detail & Related papers  (2023-10-04T01:36:30Z)
• Machine Learning based prediction of Glucose Levels in Type 1 Diabetes Patients with the use of Continuous Glucose Monitoring Data [0.0]
  Continuous Glucose Monitoring (CGM) devices offer detailed, non-intrusive and real time insights into a patient's blood glucose concentrations. Leveraging advanced Machine Learning (ML) Models as methods of prediction of future glucose levels, gives rise to substantial quality of life improvements.
  arXiv  Detail & Related papers  (2023-02-24T19:10:40Z)
• Textual Data Augmentation for Patient Outcomes Prediction [67.72545656557858]
  We propose a novel data augmentation method to generate artificial clinical notes in patients' Electronic Health Records. We fine-tune the generative language model GPT-2 to synthesize labeled text with the original training data. We evaluate our method on the most common patient outcome, i.e., the 30-day readmission rate.
  arXiv  Detail & Related papers  (2022-11-13T01:07:23Z)
• Bag of Tricks for Developing Diabetic Retinopathy Analysis Framework to Overcome Data Scarcity [6.802798389355481]
  We present a study for diabetic retinopathy (DR) analysis tasks, including lesion segmentation, image quality assessment, and DR grading. For each task, we introduce a robust training scheme by leveraging ensemble learning, data augmentation, and semi-supervised learning. We propose reliable pseudo labeling that excludes uncertain pseudo-labels based on the model's confidence scores to reduce the negative effect of noisy pseudo-labels.
  arXiv  Detail & Related papers  (2022-10-18T03:25:00Z)
• On the Robustness of Pretraining and Self-Supervision for a Deep Learning-based Analysis of Diabetic Retinopathy [70.71457102672545]
  We compare the impact of different training procedures for diabetic retinopathy grading. We investigate different aspects such as quantitative performance, statistics of the learned feature representations, interpretability and robustness to image distortions. Our results indicate that models from ImageNet pretraining report a significant increase in performance, generalization and robustness to image distortions.
  arXiv  Detail & Related papers  (2021-06-25T08:32:45Z)
• Deep Personalized Glucose Level Forecasting Using Attention-based Recurrent Neural Networks [5.250950284616893]
  We study the problem of blood glucose forecasting and provide a deep personalized solution. We analyze the data and detect important patterns. We empirically show the efficacy of our model on a real dataset.
  arXiv  Detail & Related papers  (2021-06-02T01:36:53Z)
• Data-driven generation of plausible tissue geometries for realistic photoacoustic image synthesis [53.65837038435433]
  Photoacoustic tomography (PAT) has the potential to recover morphological and functional tissue properties. We propose a novel approach to PAT data simulation, which we refer to as "learning to simulate" We leverage the concept of Generative Adversarial Networks (GANs) trained on semantically annotated medical imaging data to generate plausible tissue geometries.
  arXiv  Detail & Related papers  (2021-03-29T11:30:18Z)
• Model-Based Reinforcement Learning for Type 1Diabetes Blood Glucose Control [0.0]
  We investigate the use of model-based reinforcement learning to assist people with Type 1 Diabetes with insulin dose decisions. The proposed architecture consists of multiple Echo State Networks to predict blood glucose levels combined with Model Predictive Controller for planning.
  arXiv  Detail & Related papers  (2020-10-13T10:17:30Z)
• ECG-DelNet: Delineation of Ambulatory Electrocardiograms with Mixed Quality Labeling Using Neural Networks [69.25956542388653]
  Deep learning (DL) algorithms are gaining weight in academic and industrial settings. We demonstrate DL can be successfully applied to low interpretative tasks by embedding ECG detection and delineation onto a segmentation framework. The model was trained using PhysioNet's QT database, comprised of 105 ambulatory ECG recordings.
  arXiv  Detail & Related papers  (2020-05-11T16:29:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.