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.
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.
CAT framework improves AI medical screening fairness and reliability.
problem Imbalanced data, varying performance across cohorts, and patient-level inconsistencies in traditional metrics.
method CAT framework introduces patient-level assessment, entropy-based distribution weighting, and cohort-weighted sensitivity and specificity.
result Enhanced predictive reliability, fairness, and interpretability of AI-driven medical screening models.
Exploring a new method to explain AI models in medical devices.
problem Lack of explainability in AI models used in medical devices.
method Using the Jacobian matrix to measure model response stability to small perturbations.
result A first step towards a perturbation-based explanation of AI models.
AI predicts medical specialty diagnostic choices from EHR records.
problem Predicting timely medical specialty diagnostic workups for patients.
method Ensemble of feed-forward neural networks trained on EHR data.
result Significantly higher accuracy compared to traditional checklists.
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.
The study evaluates AI model performance measures for medical use.
problem Selecting appropriate performance measures for AI models in medical practice.
method Assessed 32 performance measures across five domains for binary outcomes.
result 17 measures are both proper and reflect decision-analytic performance.
New method accounts for uncertainty in medical AI evaluations.
problem Uncertainty in ground truth affects AI model performance estimates.
method Statistical aggregation approach to infer probabilities of medical conditions.
result Performance estimates are significantly lower when uncertainty is accounted for.
New method explains survival analysis models using median-SHAP.
problem Need for explainable AI in medical applications, especially for survival analysis.
method Introduces median-SHAP for explaining survival analysis models.
result Conventionally used mean anchor point can lead to misleading interpretations; median-SHAP provides a better approach.
Hybrid AI and rule-based framework de-identifies medical imaging data.
problem De-identifying medical imaging data to protect PHI and PII.
method Combines rule-based and AI techniques with uncertainty quantification.
result Robust performance across benchmark datasets and regulatory standards.
Artificial intelligence (AI) generally and machine learning (ML) specifically demonstrate impressive practical success in many different application domains, e.g. in autonomous driving, speech recognition, or recommender systems. Deep learning approaches, trained on extremely large data sets or using reinforcement lear…
Framework for AI healthcare products from concept to market.
problem Failure of AI products to reach clinics despite promising potential.
method Decision-making framework for AI healthcare product development.
result Guides through a three-phase process to market launch of validated AI products.
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.
Improved AI lung ultrasound segmentation using expert confidence values.
problem Label uncertainty in lung ultrasound due to subjective interpretation by radiologists.
method Designing a data annotation protocol capturing expert confidence, training AI on binarized labels with confidence thresholds.
result Improved AI segmentation and better clinical outcomes (e.g., S/F oxygenation ratio estimation, patient readmission prediction).
GPT-4 assesses its confidence in answering USMLE questions with and without feedback.
problem Understanding AI's performance in healthcare applications, especially in sensitive areas like medical education.
method Used a prompting technique to evaluate GPT-4's confidence scores before and after answering USMLE questions, categorized into with and without feedback.
result Feedback influences relative confidence but doesn't consistently increase or decrease it.
Despite significant advances in artificial intelligence (AI) for computer vision, its application in medical imaging has been limited by the burden and limits of expert-generated labels. We used images from optical coherence tomography angiography (OCTA), a relatively new imaging modality that measures perfusion of the…
Study benchmarks uncertainty quantification in chest X-ray classification.
problem Reliable uncertainty quantification for medical AI models.
method Evaluation of 13 uncertainty quantification methods on MIMIC-CXR-JPG dataset.
result Insights into effectiveness and disentanglement of epistemic and aleatoric uncertainties.
The paper investigates AI robustness through experiments and statistical analysis.
problem Inaccurate AI predictions can lead to safety and adoption issues.
method Design of experiments framework to study AI classification robustness.
result AI algorithms' robustness is influenced by various factors.
PePR scores assess DL model performance per resource unit, promoting smaller, more efficient models.
problem Limited access to large-scale resources hinders medical image analysis research.
method Introduced PePR score to measure DL model performance per resource unit.
result Small-scale, specialized models outperform large-scale models in resource-constrained settings.
In this paper, we present an effective deep prediction framework based on robust recurrent neural networks (RNNs) to predict the likely therapeutic classes of medications a patient is taking, given a sequence of diagnostic billing codes in their record. Accurately capturing the list of medications currently taken by a …
Experiment shows cognitive biases impact human-AI collaboration, highlighting the need for diverse evaluator samples.
problem Cognitive biases affect human-AI collaboration, leading to suboptimal outcomes.
method Randomized experiment with 2,784 participants, manipulating AI suggestion quality, task burden, and financial incentives.
result Individual attitudes toward AI are the strongest predictor of performance, influencing accuracy and overcorrection.
This work advances collaborative decision making by combining human and AI strengths in uncertainty quantification.
problem Current AI lacks robust decision-making capabilities under uncertainty, especially in high-stakes contexts.
method Introduces Human AI Collaborative Uncertainty Quantification (HACUQ) framework, formalizing AI-human collaboration and developing calibration algorithms.
result Optimal collaborative prediction sets follow a two-threshold structure, and online adaptation algorithms can adapt to evolving human behavior.
Zero-Shot Learning helps learn new concepts without examples, useful for COVID-19 diagnosis.
problem Learning new concepts without examples, especially in medical imaging.
method Uses existing knowledge and auxiliary information to predict unknown concepts.
result Effective in diagnosing COVID-19 from chest X-rays.
This review clarifies XAI for regression models and establishes new theoretical insights.
problem Lack of XAI techniques for regression models, especially in safety-critical applications.
method Clarifies conceptual differences, establishes theoretical insights, provides demonstrations, discusses challenges.
result Novel theoretical insights and demonstrations of XAI for regression models.
Artificial intelligence (AI) will pave the way to a new era in medicine. However, currently available AI systems do not interact with a patient, e.g., for anamnesis, and thus are only used by the physicians for predictions in diagnosis or prognosis. However, these systems are widely used, e.g., in diabetes or cancer pr…
CASCADE improves uncertainty communication in Parkinson's disease medication management.
problem Uncertainty in clinical decision-making for Parkinson's disease patients.
method CASCADE uses a novel conformal prediction framework to adaptively scale prediction intervals based on classification uncertainty.
result CASCADE produces more efficient and robust prediction intervals for Parkinson's disease patients.
Deep learning predicts ICU mortality with enhanced interpretability.
problem Improving mortality prediction accuracy and clinician trust in AI.
method Trained a deep learning model on MIMIC-III to interpret nursing notes.
result Model reaches ROC of 0.8629, outperforming SAPS-II.
AI generates a sequence of death causes from hospital records.
problem Accurate death reporting for vital statistics and policy formulation.
method Neural machine translation models to generate causal chains, incorporating medical domain knowledge.
result Achieved 16.04 BLEU score for generating accurate causal chains.
The paper introduces sanity tests to detect spurious correlations in AI-guided radiology systems.
problem Detecting when AI systems perform well on development data for the wrong reasons.
method Design and implementation of sanity tests to identify spurious correlations.
result Sanity tests can identify spurious correlations in AI-guided radiology systems.
This Perspective provides examples of current and future applications of deep learning in pharmacogenomics, including: (1) identification of novel regulatory variants located in noncoding domains and their function as applied to pharmacoepigenomics; (2) patient stratification from medical records; and (3) prediction of…
Accurate annotation of medical image is the crucial step for image AI clinical application. However, annotating medical image will incur a great deal of annotation effort and expense due to its high complexity and needing experienced doctors. To alleviate annotation cost, some active learning methods are proposed. But …
Study finds AI can predict diverse cardiac and non-cardiac diagnoses from a single ECG.
problem Narrow focus of ECG analysis models for diverse medical conditions.
method Exploratory study using a single AI model to predict multiple ICD codes.
result Model achieved AUROC scores > 0.8 for 253 cardiac and 172 non-cardiac diagnoses.
Artificial intelligence (AI) is intrinsically data-driven. It calls for the application of statistical concepts through human-machine collaboration during generation of data, development of algorithms, and evaluation of results. This paper discusses how such human-machine collaboration can be approached through the sta…
Study reveals AI skin cancer classifiers underperform for darker skin phototypes, advocating for fairness auditing.
problem AI bias in dermatology, particularly for darker skin phototypes.
method Predictive Representativity (PR) framework, evaluating classifiers on HAM10000 and BOSQUE Test sets.
result Substantial performance disparities by skin phototype, highlighting AI bias.
Deep learning model improves X-ray disease detection accuracy in Thai patients.
problem Lack of large-scale validation of AI algorithms for medical image diagnosis in Thailand.
method Development and testing of a deep learning algorithm using 421,859 local chest radiographs.
result Convolutional neural networks achieve remarkable performance in detecting 13 common abnormality conditions on chest X-ray.
Algorithmic insurance tackles financial risks from AI errors, proving CVaR-optimal thresholds reduce tail risk.
problem High-stakes AI errors lead to heterogeneous losses, challenging traditional insurance assumptions.
method Analyzed binary classification performance to tail risk exposure, using CVaR to quantify extreme losses.
result CVaR-optimal thresholds reduce tail risk up to 13-fold compared to accuracy maximization.
New framework assesses AI hallucinations in inverse problems.
problem Artificial intelligence can produce incorrect details in imaging problems.
method Theoretical framework and algorithms to estimate and assess hallucinations.
result Developed necessary and sufficient conditions for hallucinations and computable bounds.
The paper advocates for interpretable, accountable, reproducible machine learning in medicine.
problem Black box models in medicine lack transparency and regulatory approval.
method Intrinsically interpretable modeling approaches and collaborative learning paradigms.
result Interpretable machine learning models can support clinical decisions and gain regulatory approval.
Paper uses AI to improve medical diagnosis accuracy.
problem Improving accuracy of medical diagnoses.
method Heuristic frequentist and Bayesian approaches applied to a nationwide dataset.
result Algorithm outperforms human doctors in detecting abnormal births.
MAGIC-Flow generates and classifies medical images with interpretability.
problem Challenges in generative modeling for medical imaging.
method Conditional multiscale normalizing flow architecture.
result MAGIC-Flow creates realistic, diverse samples and improves classification.
Deep ROC analysis improves model selection and interpretation in medical and AI applications.
problem Inadequate performance measures for binary classifiers.
method Deep ROC analysis, translating AUC and partial AUC into balanced average accuracy and post-test measures.
result Deep ROC analysis provides balanced average accuracy, average sensitivity, and average specificity.
AI models forget statistics' lesson: correlation doesn't imply causation.
problem AI models often produce flawed causal models due to ignoring correlation vs causation.
method Demonstrates examples of flawed AI models and proposes rethinking core models.
result Current efforts to make AI models ethical are insufficient.
3D ConvNets improved with Project & Excite for medical imaging segmentation.
problem Improving segmentation performance in 3D medical imaging.
method Proposed Project & Excite (PE) modules for 3D F-CNNs, extending 2D recalibration methods.
result Project & Excite modules boost segmentation performance up to 0.3 in Dice Score.
Bayesian CNN estimates uncertainty in COVID-19 detection.
problem Uncertainty in deep learning predictions for medical diagnosis.
method Drop-weight based Bayesian Convolutional Neural Networks (BCNN).
result Uncertainty correlates with prediction accuracy.
Enhances understanding of patient healthcare journeys using self-attention.
problem Capturing hidden dependencies in multi-level patient journey data.
method Proposes a multi-level self-attention network (MusaNet) for encoding patient journeys.
result MusaNet produces higher-quality representations than state-of-the-art methods.
With the increasing availability of AI-based decision support, there is an increasing need for their certification by both AI manufacturers and notified bodies, as well as the pragmatic (real-world) validation of these systems. Therefore, there is the need for meaningful and informative ways to assess the performance o…
Aims to integrate AI and modelling for patient health forecasting.
problem Personalized, precise treatment plans for patients.
method Graph neural network (GNNs) and generative adversarial network (GANs) for probabilistic simulations.
result Demonstrated integration of molecular data for predicting physiological state evolution.
Method interprets deep learning models using topological data analysis.
problem Lack of interpretability in deep learning models, especially in high-risk applications.
method Topological and geometric data analysis to infer features and decision-making mechanisms of DL models.
result Extracted subgraphs reveal relevant features for model decisions, demonstrating model's reliance on pertinent data.