Subpopulation-specific machine learning prognosis for underrepresented patients with double prioritized bias correction

Seeing the random forest through the decision trees. Supporting learning health systems from histopathology with machine learning models: Challenges and opportunities

This paper discusses some overlooked challenges faced when working with machine learning models for histopathology and presents a novel opportunity to support "Learning Health Systems" with them. Initially, the authors elaborate on these challenges after separating them according to their mitigation strategies: those that need innovative approaches, time, or future technological capabilities and those that require a conceptual reappraisal from a critical perspective. Then, a novel opportunity to support "Learning Health Systems" by integrating hidden information extracted by ML models from digitalized histopathology slides with other healthcare big data is presented.

Sex-Based Performance Disparities in Machine Learning Algorithms for Cardiac Disease Prediction: Exploratory Study

BACKGROUND

The presence of bias in artificial intelligence has garnered increased attention, with inequities in algorithmic performance being exposed across the fields of criminal justice, education, and welfare services. In health care, the inequitable performance of algorithms across demographic groups may widen health inequalities.

OBJECTIVE

Here, we identify and characterize bias in cardiology algorithms, looking specifically at algorithms used in the management of heart failure.

METHODS

Stage 1 involved a literature search of PubMed and Web of Science for key terms relating to cardiac machine learning (ML) algorithms. Papers that built ML models to predict cardiac disease were evaluated for their focus on demographic bias in model performance, and open-source data sets were retained for our investigation. Two open-source data sets were identified: (1) the University of California Irvine Heart Failure data set and (2) the University of California Irvine Coronary Artery Disease data set. We reproduced existing algorithms that have been reported for these data sets, tested them for sex biases in algorithm performance, and assessed a range of remediation techniques for their efficacy in reducing inequities. Particular attention was paid to the false negative rate (FNR), due to the clinical significance of underdiagnosis and missed opportunities for treatment.

RESULTS

In stage 1, our literature search returned 127 papers, with 60 meeting the criteria for a full review and only 3 papers highlighting sex differences in algorithm performance. In the papers that reported sex, there was a consistent underrepresentation of female patients in the data sets. No papers investigated racial or ethnic differences. In stage 2, we reproduced algorithms reported in the literature, achieving mean accuracies of 84.24% (SD 3.51%) for data set 1 and 85.72% (SD 1.75%) for data set 2 (random forest models). For data set 1, the FNR was significantly higher for female patients in 13 out of 16 experiments, meeting the threshold of statistical significance (-17.81% to -3.37%; P<.05). A smaller disparity in the false positive rate was significant for male patients in 13 out of 16 experiments (-0.48% to +9.77%; P<.05). We observed an overprediction of disease for male patients (higher false positive rate) and an underprediction of disease for female patients (higher FNR). Sex differences in feature importance suggest that feature selection needs to be demographically tailored.

CONCLUSIONS

Our research exposes a significant gap in cardiac ML research, highlighting that the underperformance of algorithms for female patients has been overlooked in the published literature. Our study quantifies sex disparities in algorithmic performance and explores several sources of bias. We found an underrepresentation of female patients in the data sets used to train algorithms, identified sex biases in model error rates, and demonstrated that a series of remediation techniques were unable to address the inequities present.

Enhancing neuro-oncology care through equity-driven applications of artificial intelligence

The disease course and clinical outcome for brain tumor patients depend not only on the molecular and histological features of the tumor but also on the patient's demographics and social determinants of health. While current investigations in neuro-oncology have broadly utilized artificial intelligence (AI) to enrich tumor diagnosis and more accurately predict treatment response, postoperative complications, and survival, equity-driven applications of AI have been limited. However, AI applications to advance health equity in the broader medical field have the potential to serve as practical blueprints to address known disparities in neuro-oncologic care. In this consensus review, we will describe current applications of AI in neuro-oncology, postulate viable AI solutions for the most pressing inequities in neuro-oncology based on broader literature, propose a framework for the effective integration of equity into AI-based neuro-oncology research, and close with the limitations of AI.

A survey of recent methods for addressing AI fairness and bias in biomedicine

OBJECTIVES

Artificial intelligence (AI) systems have the potential to revolutionize clinical practices, including improving diagnostic accuracy and surgical decision-making, while also reducing costs and manpower. However, it is important to recognize that these systems may perpetuate social inequities or demonstrate biases, such as those based on race or gender. Such biases can occur before, during, or after the development of AI models, making it critical to understand and address potential biases to enable the accurate and reliable application of AI models in clinical settings. To mitigate bias concerns during model development, we surveyed recent publications on different debiasing methods in the fields of biomedical natural language processing (NLP) or computer vision (CV). Then we discussed the methods, such as data perturbation and adversarial learning, that have been applied in the biomedical domain to address bias.

METHODS

We performed our literature search on PubMed, ACM digital library, and IEEE Xplore of relevant articles published between January 2018 and December 2023 using multiple combinations of keywords. We then filtered the result of 10,041 articles automatically with loose constraints, and manually inspected the abstracts of the remaining 890 articles to identify the 55 articles included in this review. Additional articles in the references are also included in this review. We discuss each method and compare its strengths and weaknesses. Finally, we review other potential methods from the general domain that could be applied to biomedicine to address bias and improve fairness.

RESULTS

The bias of AIs in biomedicine can originate from multiple sources such as insufficient data, sampling bias and the use of health-irrelevant features or race-adjusted algorithms. Existing debiasing methods that focus on algorithms can be categorized into distributional or algorithmic. Distributional methods include data augmentation, data perturbation, data reweighting methods, and federated learning. Algorithmic approaches include unsupervised representation learning, adversarial learning, disentangled representation learning, loss-based methods and causality-based methods.

Best of Both Worlds: Bridging One Model for All and Group-Specific Model Approaches using Ensemble-based Subpopulation Modeling

Subpopulation models have become of increasing interest in prediction of clinical outcomes because they promise to perform better for underrepresented patient subgroups. However, the personalization benefits gained from these models tradeoff their statistical power, and can be impractical when the subpopulation's sample size is small. We hypothesize that a hierarchical model in which population information is integrated into subpopulation models would preserve the personalization benefits and offset the loss of power. In this work, we integrate ideas from ensemble modeling, personalization, and hierarchical modeling and build ensemble-based subpopulation models in which specialization relies on whole group samples. This approach significantly improves the precision of the positive class, especially for the underrepresented subgroups, with minimal cost to the recall. It consistently outperforms one model for all and one model for each subgroup approaches, especially in the presence of a high class-imbalance, for subgroups with at least 380 training samples.

Personalising intravenous to oral antibiotic switch decision making through fair interpretable machine learning

Antimicrobial resistance (AMR) and healthcare associated infections pose a significant threat globally. One key prevention strategy is to follow antimicrobial stewardship practices, in particular, to maximise targeted oral therapy and reduce the use of indwelling vascular devices for intravenous (IV) administration. Appreciating when an individual patient can switch from IV to oral antibiotic treatment is often non-trivial and not standardised. To tackle this problem we created a machine learning model to predict when a patient could switch based on routinely collected clinical parameters. 10,362 unique intensive care unit stays were extracted and two informative feature sets identified. Our best model achieved a mean AUROC of 0.80 (SD 0.01) on the hold-out set while not being biased to individuals protected characteristics. Interpretability methodologies were employed to create clinically useful visual explanations. In summary, our model provides individualised, fair, and interpretable predictions for when a patient could switch from IV-to-oral antibiotic treatment. Prospectively evaluation of safety and efficacy is needed before such technology can be applied clinically.

Machine Learning Strategies for Improved Phenotype Prediction in Underrepresented Populations

Precision medicine models often perform better for populations of European ancestry due to the over-representation of this group in the genomic datasets and large-scale biobanks from which the models are constructed. As a result, prediction models may misrepresent or provide less accurate treatment recommendations for underrepresented populations, contributing to health disparities. This study introduces an adaptable machine learning toolkit that integrates multiple existing methodologies and novel techniques to enhance the prediction accuracy for underrepresented populations in genomic datasets. By leveraging machine learning techniques, including gradient boosting and automated methods, coupled with novel population-conditional re-sampling techniques, our method significantly improves the phenotypic prediction from single nucleotide polymorphism (SNP) data for diverse populations. We evaluate our approach using the UK Biobank, which is composed primarily of British individuals with European ancestry, and a minority representation of groups with Asian and African ancestry. Performance metrics demonstrate substantial improvements in phenotype prediction for underrepresented groups, achieving prediction accuracy comparable to that of the majority group. This approach represents a significant step towards improving prediction accuracy amidst current dataset diversity challenges. By integrating a tailored pipeline, our approach fosters more equitable validity and utility of statistical genetics methods, paving the way for more inclusive models and outcomes.

Electronic health records and stratified psychiatry: bridge to precision treatment?

The use of a stratified psychiatry approach that combines electronic health records (EHR) data with machine learning (ML) is one potentially fruitful path toward rapidly improving precision treatment in clinical practice. This strategy, however, requires confronting pervasive methodological flaws as well as deficiencies in transparency and reporting in the current conduct of ML-based studies for treatment prediction. EHR data shares many of the same data quality issues as other types of data used in ML prediction, plus some unique challenges. To fully leverage EHR data's power for patient stratification, increased attention to data quality and collection of patient-reported outcome data is needed.

Architectural Design of a Blockchain-Enabled, Federated Learning Platform for Algorithmic Fairness in Predictive Health Care: Design Science Study

BACKGROUND

Developing effective and generalizable predictive models is critical for disease prediction and clinical decision-making, often requiring diverse samples to mitigate population bias and address algorithmic fairness. However, a major challenge is to retrieve learning models across multiple institutions without bringing in local biases and inequity, while preserving individual patients' privacy at each site.

OBJECTIVE

This study aims to understand the issues of bias and fairness in the machine learning process used in the predictive health care domain. We proposed a software architecture that integrates federated learning and blockchain to improve fairness, while maintaining acceptable prediction accuracy and minimizing overhead costs.

METHODS

We improved existing federated learning platforms by integrating blockchain through an iterative design approach. We used the design science research method, which involves 2 design cycles (federated learning for bias mitigation and decentralized architecture). The design involves a bias-mitigation process within the blockchain-empowered federated learning framework based on a novel architecture. Under this architecture, multiple medical institutions can jointly train predictive models using their privacy-protected data effectively and efficiently and ultimately achieve fairness in decision-making in the health care domain.

RESULTS

We designed and implemented our solution using the Aplos smart contract, microservices, Rahasak blockchain, and Apache Cassandra-based distributed storage. By conducting 20,000 local model training iterations and 1000 federated model training iterations across 5 simulated medical centers as peers in the Rahasak blockchain network, we demonstrated how our solution with an improved fairness mechanism can enhance the accuracy of predictive diagnosis.

CONCLUSIONS

Our study identified the technical challenges of prediction biases faced by existing predictive models in the health care domain. To overcome these challenges, we presented an innovative design solution using federated learning and blockchain, along with the adoption of a unique distributed architecture for a fairness-aware system. We have illustrated how this design can address privacy, security, prediction accuracy, and scalability challenges, ultimately improving fairness and equity in the predictive health care domain.

Machine Learning Strategies for Improved Phenotype Prediction in Underrepresented Populations

Precision medicine models often perform better for populations of European ancestry due to the over-representation of this group in the genomic datasets and large-scale biobanks from which the models are constructed. As a result, prediction models may misrepresent or provide less accurate treatment recommendations for underrepresented populations, contributing to health disparities. This study introduces an adaptable machine learning toolkit that integrates multiple existing methodologies and novel techniques to enhance the prediction accuracy for underrepresented populations in genomic datasets. By leveraging machine learning techniques, including gradient boosting and automated methods, coupled with novel population-conditional re-sampling techniques, our method significantly improves the phenotypic prediction from single nucleotide polymorphism (SNP) data for diverse populations. We evaluate our approach using the UK Biobank, which is composed primarily of British individuals with European ancestry, and a minority representation of groups with Asian and African ancestry. Performance metrics demonstrate substantial improvements in phenotype prediction for underrepresented groups, achieving prediction accuracy comparable to that of the majority group. This approach represents a significant step towards improving prediction accuracy amidst current dataset diversity challenges. By integrating a tailored pipeline, our approach fosters more equitable validity and utility of statistical genetics methods, paving the way for more inclusive models and outcomes.

Mitigating Racial And Ethnic Bias And Advancing Health Equity In Clinical Algorithms: A Scoping Review

In August 2022 the Department of Health and Human Services (HHS) issued a notice of proposed rulemaking prohibiting covered entities, which include health care providers and health plans, from discriminating against individuals when using clinical algorithms in decision making. However, HHS did not provide specific guidelines on how covered entities should prevent discrimination. We conducted a scoping review of literature published during the period 2011-22 to identify health care applications, frameworks, reviews and perspectives, and assessment tools that identify and mitigate bias in clinical algorithms, with a specific focus on racial and ethnic bias. Our scoping review encompassed 109 articles comprising 45 empirical health care applications that included tools tested in health care settings, 16 frameworks, and 48 reviews and perspectives. We identified a wide range of technical, operational, and systemwide bias mitigation strategies for clinical algorithms, but there was no consensus in the literature on a single best practice that covered entities could employ to meet the HHS requirements. Future research should identify optimal bias mitigation methods for various scenarios, depending on factors such as patient population, clinical setting, algorithm design, and types of bias to be addressed.

Using Machine Learning in Veterinary Medical Education: An Introduction for Veterinary Medicine Educators

Machine learning (ML) offers potential opportunities to enhance the learning, teaching, and assessments within veterinary medical education including but not limited to assisting with admissions processes as well as student progress evaluations. The purpose of this primer is to assist veterinary educators in appraising and potentially adopting these rapid upcoming advances in data science and technology. In the first section, we introduce ML concepts and highlight similarities/differences between ML and classical statistics. In the second section, we provide a step-by-step worked example using simulated veterinary student data to answer a hypothesis-driven question. Python syntax with explanations is provided within the text to create a random forest ML prediction model, a model composed of decision trees with each decision tree being composed of nodes and leaves. Within each step of the model creation, specific considerations such as how to manage incomplete student records are highlighted when applying ML algorithms within the veterinary education field. The results from the simulated data demonstrate how decisions by the veterinary educator during ML model creation may impact the most important features contributing to the model. These results highlight the need for the veterinary educator to be fully transparent during the creation of ML models and future research is needed to establish guidelines for handling data not missing at random in medical education, and preferred methods for model evaluation.

Evaluating and mitigating bias in machine learning models for cardiovascular disease prediction

OBJECTIVE

The study aims to investigate whether machine learning-based predictive models for cardiovascular disease (CVD) risk assessment show equivalent performance across demographic groups (such as race and gender) and if bias mitigation methods can reduce any bias present in the models. This is important as systematic bias may be introduced when collecting and preprocessing health data, which could affect the performance of the models on certain demographic sub-cohorts. The study is to investigate this using electronic health records data and various machine learning models.

METHODS

The study used large de-identified Electronic Health Records data from Vanderbilt University Medical Center. Machine learning (ML) algorithms including logistic regression, random forest, gradient-boosting trees, and long short-term memory were applied to build multiple predictive models. Model bias and fairness were evaluated using equal opportunity difference (EOD, 0 indicates fairness) and disparate impact (DI, 1 indicates fairness). In our study, we also evaluated the fairness of a non-ML baseline model, the American Heart Association (AHA) Pooled Cohort Risk Equations (PCEs). Moreover, we compared the performance of three different de-biasing methods: removing protected attributes (e.g., race and gender), resampling the imbalanced training dataset by sample size, and resampling by the proportion of people with CVD outcomes.

RESULTS

The study cohort included 109,490 individuals (mean [SD] age 47.4 [14.7] years; 64.5% female; 86.3% White; 13.7% Black). The experimental results suggested that most ML models had smaller EOD and DI than PCEs. For ML models, the mean EOD ranged from -0.001 to 0.018 and the mean DI ranged from 1.037 to 1.094 across race groups. There was a larger EOD and DI across gender groups, with EOD ranging from 0.131 to 0.136 and DI ranging from 1.535 to 1.587. For debiasing methods, removing protected attributes didn't significantly reduced the bias for most ML models. Resampling by sample size also didn't consistently decrease bias. Resampling by case proportion reduced the EOD and DI for gender groups but slightly reduced accuracy in many cases.

CONCLUSIONS

Among the VUMC cohort, both PCEs and ML models were biased against women, suggesting the need to investigate and correct gender disparities in CVD risk prediction. Resampling by proportion reduced the bias for gender groups but not for race groups.