A comparison of approaches to improve worst-case predictive model performance over patient subpopulations

• URL: http://arxiv.org/abs/2108.12250v1
• Date: Fri, 27 Aug 2021 13:10:00 GMT
• Title: A comparison of approaches to improve worst-case predictive model performance over patient subpopulations
• Authors: Stephen R. Pfohl, Haoran Zhang, Yizhe Xu, Agata Foryciarz, Marzyeh Ghassemi, Nigam H. Shah
• Abstract summary: Predictive models for clinical outcomes that are accurate on average in a patient population may underperform drastically for some subpopulations. We identify approaches for model development and selection that consistently improve disaggregated and worst-case performance over subpopulations. We find that, with relatively few exceptions, no approach performs better, for each patient subpopulation examined, than standard learning procedures.
• Score: 14.175321968797252
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Predictive models for clinical outcomes that are accurate on average in a patient population may underperform drastically for some subpopulations, potentially introducing or reinforcing inequities in care access and quality. Model training approaches that aim to maximize worst-case model performance across subpopulations, such as distributionally robust optimization (DRO), attempt to address this problem without introducing additional harms. We conduct a large-scale empirical study of DRO and several variations of standard learning procedures to identify approaches for model development and selection that consistently improve disaggregated and worst-case performance over subpopulations compared to standard approaches for learning predictive models from electronic health records data. In the course of our evaluation, we introduce an extension to DRO approaches that allows for specification of the metric used to assess worst-case performance. We conduct the analysis for models that predict in-hospital mortality, prolonged length of stay, and 30-day readmission for inpatient admissions, and predict in-hospital mortality using intensive care data. We find that, with relatively few exceptions, no approach performs better, for each patient subpopulation examined, than standard learning procedures using the entire training dataset. These results imply that when it is of interest to improve model performance for patient subpopulations beyond what can be achieved with standard practices, it may be necessary to do so via techniques that implicitly or explicitly increase the effective sample size.

Related papers

• Comparison of deep learning and conventional methods for disease onset prediction [7.477956812298417]
  Deep learning methods promise enhanced prediction performance by extracting complex patterns from clinical data. This study compares conventional and deep learning approaches to predict lung cancer, dementia, and bipolar disorder.
  arXiv  Detail & Related papers  (2024-10-14T13:46:59Z)
• Learnable Prompt as Pseudo-Imputation: Reassessing the Necessity of Traditional EHR Data Imputation in Downstream Clinical Prediction [16.638760651750744]
  Existing deep learning training protocols require the use of statistical information or imputation models to reconstruct missing values. This paper introduces Learnable Prompt as Pseudo Imputation (PAI) as a new training protocol. PAI no longer introduces any imputed data but constructs a learnable prompt to model the implicit preferences of the downstream model for missing values.
  arXiv  Detail & Related papers  (2024-01-30T07:19:36Z)
• 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)
• Clinical Deterioration Prediction in Brazilian Hospitals Based on Artificial Neural Networks and Tree Decision Models [56.93322937189087]
  An extremely boosted neural network (XBNet) is used to predict clinical deterioration (CD) The XGBoost model obtained the best results in predicting CD among Brazilian hospitals' data.
  arXiv  Detail & Related papers  (2022-12-17T23:29:14Z)
• 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)
• Looking for Out-of-Distribution Environments in Critical Care: A case study with the eICU Database [4.915029686150194]
  Generalizing to new populations and domains in machine learning is still an open problem which has seen increased interest recently. Recent proposed models for domain generalisation promise to alleviate this problem by learning invariant characteristics across environments. We take a principled approach to identifying Out of Distribution environments, motivated by the problem of cross-hospital performance generalization in critical care.
  arXiv  Detail & Related papers  (2022-05-26T14:46:13Z)
• Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation [7.2666838978096875]
  Existing approaches typically train models in a patient-specific fashion due to the highly personalized characteristics of epileptic signals. A patient-specific model can then be obtained with the help of distilled knowledge and additional personalized data. Five state-of-the-art seizure prediction methods are trained on the CHB-MIT sEEG database with our proposed scheme.
  arXiv  Detail & Related papers  (2022-02-25T10:30:29Z)
• Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data [62.29031007761901]
  This paper proposes a novel contrastive regularized clinical classification model. We introduce two unique positive sampling strategies specifically tailored for EHR data. Our framework yields highly competitive experimental results in predicting the mortality risk on real-world COVID-19 EHR data.
  arXiv  Detail & Related papers  (2021-04-07T06:02:04Z)
• Adversarial Sample Enhanced Domain Adaptation: A Case Study on Predictive Modeling with Electronic Health Records [57.75125067744978]
  We propose a data augmentation method to facilitate domain adaptation. adversarially generated samples are used during domain adaptation. Results confirm the effectiveness of our method and the generality on different tasks.
  arXiv  Detail & Related papers  (2021-01-13T03:20:20Z)
• Efficient Estimation and Evaluation of Prediction Rules in Semi-Supervised Settings under Stratified Sampling [6.930951733450623]
  We propose a two-step semi-supervised learning (SSL) procedure for evaluating a prediction rule derived from a working binary regression model. In step I, we impute the missing labels via weighted regression with nonlinear basis functions to account for nonrandom sampling. In step II, we augment the initial imputations to ensure the consistency of the resulting estimators.
  arXiv  Detail & Related papers  (2020-10-19T12:54:45Z)
• Improving Maximum Likelihood Training for Text Generation with Density Ratio Estimation [51.091890311312085]
  We propose a new training scheme for auto-regressive sequence generative models, which is effective and stable when operating at large sample space encountered in text generation. Our method stably outperforms Maximum Likelihood Estimation and other state-of-the-art sequence generative models in terms of both quality and diversity.
  arXiv  Detail & Related papers  (2020-07-12T15:31:24Z)

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.