Proposes guidelines for developing medical AI products.
problem Lack of clear pathways for regulating medical AI.
method Statistical risk perspective and deep understanding of machine learning methodologies.
result Enhanced development of medical AI products and regulations.
This guide introduces machine learning for medical data analysis.
problem Handling large, complex datasets in healthcare.
method Explains common machine learning algorithms and tasks.
result Illustrates machine learning applications in healthcare.
What has happened in machine learning lately, and what does it mean for the future of medical image analysis? Machine learning has witnessed a tremendous amount of attention over the last few years. The current boom started around 2009 when so-called deep artificial neural networks began outperforming other established…
This paper benchmarks privacy-preserving machine learning on medical images.
problem Ensuring privacy in medical image analysis while maintaining model accuracy.
method Comparing Local-DP and DP-SGD for differential privacy in medical imagery.
result Theoretical privacy guarantees do not fully align with real-world performance.
Machine learning constructs problem-based medical records from electronic health records.
problem Difficulty in finding relevant medical information for clinical questions.
method Knowledge base completion using machine learning on electronic health records.
result Automatic construction of problem-based groupings of medications, procedures, and lab tests.
Survey of deep learning methods for medical anomaly detection.
problem Medical anomaly detection using machine learning.
method Thorough review of deep learning techniques across various medical domains.
result Comparison and contrast of deep learning models and their limitations.
This chapter introduces reproducibility in machine learning for medical imaging.
problem Lack of reproducibility in machine learning for medical imaging.
method Distinguishes and defines types of reproducibility, outlines requirements, and discusses utility.
result Discussion on benefits and a plea for a non-dogmatic approach to reproducibility.
Hidden stratification causes machine learning models to fail on rare but important patient subgroups.
problem Machine learning models fail on rare patient subgroups not identified during training or testing.
method Assessed techniques for measuring and describing hidden stratification effects on multiple medical imaging datasets.
result Evidence of hidden stratification leading to over 20% performance differences on clinically important subsets.
Paper shows how to quantify uncertainty in medical ML models.
problem Uncertainty in opaque ML models can lead to safety risks in medical applications.
method Introduces Uncertainty Wrapper to quantify uncertainty transparently.
result Demonstrates practical utility of Uncertainty Wrapper in flow cytometry.
Study on diagnosing unseen medical conditions using open-set learning.
problem Training models for unseen medical conditions is impractical.
method Frame diagnosis as an open-set learning problem, compare state-of-the-art approaches, and experiment with distributed training data.
result Explicitly modeling unseen conditions leads to consistent gains, but optimal training strategy varies.
This study applies neural models to automatically recognize medical entities from natural language.
problem Automated recognition of medical entities from natural language is complex and time-consuming.
method Utilizes deep neural sequence models trained on a large dataset of death certificates.
result Deep neural models can efficiently recognize medical entities from natural language.
The medical field stands to see significant benefits from the recent advances in deep learning. Knowing the uncertainty in the decision made by any machine learning algorithm is of utmost importance for medical practitioners. This study demonstrates the utility of using Bayesian LSTMs for classification of medical time…
Study finds little progress in medical machine learning benchmarks over 3 years.
problem Lack of meaningful progress in medical machine learning benchmarks for structured healthcare data.
method Comprehensive review and meta-analysis of benchmarks in medical machine learning for structured data.
result Deep recurrent models perform only better than logistic regression on certain clinical prediction tasks.
Deep learning helps predict epileptic seizures from EEG data.
problem Challenging prediction of epileptic seizures in medical domain.
method Applied deep learning and machine learning models to EEG data.
result Improved prediction of epileptic seizures.
Deep learning improves medical ultrasound image segmentation accuracy.
problem Improving accuracy in medical ultrasound image segmentation.
method Categorizes deep learning methods into six groups and analyzes current representative algorithms.
result Current methods show significant improvement in image segmentation accuracy.
Improves reliability of medical diagnosis uncertainty estimates.
problem Label uncertainty in medical diagnosis.
method Post-hoc alpha-calibration method for neural network classifiers. result Significantly enhances reliability of uncertainty estimates.
Smart bin monitors predict medication adherence with high accuracy.
problem Predicting chronic medication adherence to improve healthcare efficiency.
method Machine learning models trained on IoT device data.
result High predictive performance (ROC AUC 0.86).
This paper tackles label noise in deep learning for medical image analysis.
problem Label noise impacts deep learning models in medical image analysis.
method Review of state-of-the-art techniques and experiments with label noise in medical datasets.
result Developed new methods to combat label noise in deep models for medical image analysis.
A method for data encryption makes data look identical to humans but misleading to machine learning.
problem Data leakage in data sharing for medical purposes.
method Proposes a method inspired by adversarial attacks for data encryption.
result Encrypted data look identical to humans but misleading to machine learning methods.
This paper addresses privacy in federated learning for medical imaging by estimating model uncertainty.
problem Privacy concerns in federated learning for medical imaging.
method Federated Learning (FL) for collaborative model training while preserving patient data privacy.
result Accurate uncertainty estimation in federated learning for medical imaging.
Machine learning detects NASH patients from medical claims data.
problem Detecting undiagnosed NASH patients for screening and management.
method Gradient-boosted decision trees trained on administrative medical claims data.
result Model precision for NASH detection is significantly higher than NASH incidence.
The paper investigates deep neural networks for medical imaging applications, providing interpretable results.
problem Uninterpretable decisions made by deep neural networks in medical imaging applications.
method Investigation of deep neural networks for malaria, diabetic retinopathy, brain tumor, and tuberculosis detection in various imaging modalities. Visualization of class activation mappings provided.
result Visualization of class activation mappings enhances understanding of deep neural networks and aids doctors in decision-making.
This study interprets machine learning models to identify biomarkers for severe COVID-19 infection.
problem The black-box nature of machine learning models makes it difficult for medical researchers to understand and trust their predictions.
method The study uses permutation feature importance, Partial Dependence Plot, Individual Conditional Expectation, Accumulated Local Effects, Local Interpretable Model-agnostic Explanations, and Shapley Additive Explanation to interpret four machine learning models.
result The study identifies NTproBNP, CRP, LDH, LYM, leukocytes, eosinophils, and platelets as biomarkers associated with severe COVID-19 infection.
Review of deep learning methods in medical image registration.
problem Improving accuracy and efficiency of medical image registration.
method Classification and detailed analysis of seven categories of DL-based registration methods.
result Comprehensive comparison of DL-based methods for lung and brain registration.
Paper detects biases in medical imaging ML models using counterfactual analysis.
problem Bias in medical imaging ML models negatively impacts generalization performance.
method Counterfactual invariance framework combining conditional latent diffusion models and statistical hypothesis testing.
result The method identifies and quantifies biases without direct access to counterfactual data.
YouTube presents an unprecedented opportunity to explore how machine learning methods can improve healthcare information dissemination. We propose an interdisciplinary lens that synthesizes machine learning methods with healthcare informatics themes to address the critical issue of developing a scalable algorithmic sol…
New research finds uncertainty estimation techniques fail to reliably detect abnormal medical cases.
problem Uncertainty estimation does not reliably detect out-of-distribution patients in medical tabular data.
method A series of tests on various uncertainty estimation techniques on real-world medical data.
result Almost all techniques fail to identify out-of-distribution patients, contradicting earlier findings.
With the expeditious advancement of information technologies, health-related data presented unprecedented potentials for medical and health discoveries but at the same time significant challenges for machine learning techniques both in terms of size and complexity. Those challenges include: the structured data with var…
Study compares non-parametric models for predicting medical insurance reimbursement delays.
problem Estimating the time-lapse between medical insurance reimbursement.
method Comparative study of four non-parametric regression models (KNNs, SVMs, Decision Trees, Random Forests) using R-squared metric.
result Each model's performance varies with training data size, feature space, and hyperparameters.
XLabel tool reduces medical experts' workload by 40% and explains its decisions.
problem Efficiently labeling large electronic health records.
method Visual-interactive tool using Explainable Boosting Machine (EBM) for classification and explanation.
result EBM achieves high accuracy and explainability, even with mislabeled data.
Counterfactual diagnosis improves medical accuracy and safety.
problem Existing diagnostic algorithms struggle with distinguishing correlation from causation.
method Reformulated diagnosis as a counterfactual inference task and derived new counterfactual diagnostic algorithms.
result Counterfactual diagnostic algorithms significantly improve accuracy and safety compared to standard Bayesian algorithms.
Cloud based medical image analysis has become popular recently due to the high computation complexities of various deep neural network (DNN) based frameworks and the increasingly large volume of medical images that need to be processed. It has been demonstrated that for medical images the transmission from local to clo…
Study tackles database variability in medical data using ensemble models and CNNs.
problem Achieving robust generalization in machine learning models across multiple medical databases.
method Ensemble of local models based on convolutional neural networks (CNNs) and various data preprocessing techniques.
result Improved inter-database generalization performance and scalability of models.
Tensor networks improve medical image classification performance.
problem Improving medical image classification accuracy.
method Extending tensor networks to medical image analysis, focusing on 2D images.
result Tensor networks achieve comparable performance to deep learning methods with fewer hyperparameters and resources.
The treatment effects of medications play a key role in guiding medical prescriptions. They are usually assessed with randomized controlled trials (RCTs), which are expensive. Recently, large-scale electronic health records (EHRs) have become available, opening up new opportunities for more cost-effective assessments. …
Improves model accuracy in medical imaging with small datasets using transfer learning.
problem Challenges in training neural networks on small medical imaging datasets.
method Comparison of current techniques, proposing one cycle training, discriminative learning rates, gradual freezing, and parameter modification.
result Transfer learning is crucial for small datasets, especially when images from the same part of the body are available.
Paper proposes sharing models instead of data for smart health predictions.
problem Sharing sensitive medical data is legally restricted and challenging.
method Train a teacher model on sensitive data, then transfer its knowledge to a student model without accessing original data.
result Student model mimics teacher model performance in making accurate predictions.
Machine learning predicts trauma patient mortality risk.
problem Predicting mortality risk in trauma patients using traditional regression models.
method Transfer learning-based machine learning algorithm applied to trauma patient data.
result Machine learning model achieved similar performance to contemporary models without restrictive criteria.
Deep learning algorithms produces state-of-the-art results for different machine learning and computer vision tasks. To perform well on a given task, these algorithms require large dataset for training. However, deep learning algorithms lack generalization and suffer from over-fitting whenever trained on small dataset,…
Paper introduces a method to process medical images efficiently.
problem High computational cost in processing large medical image data.
method Framelet-pooling aided deep learning method to reduce complexity.
result Significant reduction in computational costs with comparable performance.
Bayesian models improve trustworthiness in ICU by providing uncertainty.
problem Uncertainty in machine learning predictions can lead to catastrophic medical decisions.
method Bayesian Neural Network and predictive uncertainty analysis.
result Bayesian models can mitigate prediction loss and identify out-of-domain examples.
The issue of disagreements amongst human experts is a ubiquitous one in both machine learning and medicine. In medicine, this often corresponds to doctor disagreements on a patient diagnosis. In this work, we show that machine learning models can be trained to give uncertainty scores to data instances that might result…
Paper uses ML to classify liver diseases from clinical data.
problem Classifying liver diseases from clinical data.
method Multiple imputation, PCA, data visualizations, binary classifier algorithms (ANN, RF, SVM).
result SVM showed better accuracy (98.23%).
The computer-aided analysis of medical scans is a longstanding goal in the medical imaging field. Currently, deep learning has became a dominant methodology for supporting pathologists and radiologist. Deep learning algorithms have been successfully applied to digital pathology and radiology, nevertheless, there are st…
Enhances medical code predictions for multi-morbidity patients using text classification.
problem Improving accuracy in predicting medical codes for patients with multiple illnesses.
method Used machine learning techniques, including multi-label medical text classification, to enhance predictions.
result High dimensional embeddings pre-trained on health data significantly improve multi-label classification performance.
The paper analyzes how incentives and information affect ROC curves in medical diagnosis.
problem Understanding how incentives and information asymmetry influence ROC curves in medical diagnosis.
method Theoretical analysis and illustration with a real-world dataset.
result Different models of incentives and information asymmetry affect the relationship between human decisions and ROC curves.
Paper detects bias in AI medical models using CART.
problem Ensuring fairness in AI medical decision support systems.
method Uses Classification and Regression Trees (CART) algorithm to identify bias.
result Validated the CART approach in both synthetic and real-world data.
Proposes a strategy to train models with minimal labeled data.
problem Scarce and expensive labeled data for medical tasks.
method Recursive training strategy to use image-level annotations for pixel-level segmentation.
result Improved segmentation of intracranial hemorrhage in CT scans.