Fairness in Contextual Resource Allocation Systems: Metrics and Incompatibility Results

In wireless networks many nodes contend for available resources creating a challenge in resource allocation. With shared resources, fairness in allocation is a serious issue. Fairness metrics have been defined to measure the fairness level of resource decisions in allocations. Therefore, fairness metrics significantly influence network and node performances emphasizing the need for due diligence to fairness metrics. It can be seen that fairness metrics in many of the allocation strategies and algorithms in the literature are not analyzed in depth to show the overall fairness of allocations from different perspectives. Hence, we propose a series of fairness metrics for resource allocation in wireless networks, which evaluate individual, system, short and long term fairness. Our metrics are general enough to be adapted in either multiple or single resource sharing scenarios. Algorithms using these metrics for channel allocation problem in peer-to-peer wireless regional area network is proposed and simulated, and the results show that our metrics in conjunction with smart channel allocation strategies guarantee both the fairness and performances.

Machine Learning (ML) has advanced disease diagnosis in healthcare, but raises fairness concerns, as model biases can perpetuate social inequalities. This study aims to evaluate and mitigate bias in diabetes diagnosis prediction models. We conducted experiments considering ethnicity and gender as protected attributes, evaluating bias using the fairness metrics Statistical Parity Difference, Equal Opportunity Difference, and Average Odds Difference. We applied the bias mitigation techniques Reweighing and Prejudice Remover, which showed improvements in fairness metrics, with a reduction in disparities between groups, while maintaining model accuracy. These findings reinforce the need to integrate fairness considerations into ML models for healthcare applications.

Fairness gaps in Machine learning models for hospitalization and emergency department visit risk prediction in home healthcare patients with heart failure

Although several fairness definitions and bias mitigation techniques exist in the literature, all existing solutions evaluate fairness of Machine Learning (ML) systems after the training stage. In this paper, we take the first steps towards evaluating a more holistic approach by testing for fairness both before and after model training. We evaluate the effectiveness of the proposed approach and position it within the ML development lifecycle, using an empirical analysis of the relationship between model dependent and independent fairness metrics. The study uses 2 fairness metrics, 4 ML algorithms, 5 real-world datasets and 1600 fairness evaluation cycles. We find a linear relationship between data and model fairness metrics when the distribution and the size of the training data changes. Our results indicate that testing for fairness prior to training can be a "cheap" and effective means of catching a biased data collection process early; detecting data drifts in production systems and minimising execution of full training cycles thus reducing development time and costs.

Machine learning has potential to transform cancer care by helping clinicians prioritize patients for serious illness conversations. However, models need to be evaluated for unequal performance across racial groups (ie, racial bias) so that existing racial disparities are not exacerbated. To evaluate whether racial bias exists in a predictive machine learning model that identifies 180-day cancer mortality risk among patients with solid malignant tumors. In this cohort study, a machine learning model to predict cancer mortality for patients aged 21 years or older diagnosed with cancer between January 2016 and December 2021 was developed with a random forest algorithm using retrospective data from the Mount Sinai Health System cancer registry, Social Security Death Index, and electronic health records up to the date when databases were accessed for cohort extraction (February 2022). Race category. The primary outcomes were model discriminatory performance (area under the receiver operating characteristic curve [AUROC], F1 score) among each race category (Asian, Black, Native American, White, and other or unknown) and fairness metrics (equal opportunity, equalized odds, and disparate impact) among each pairwise comparison of race categories. True-positive rate ratios represented equal opportunity; both true-positive and false-positive rate ratios, equalized odds; and the percentage of predictive positive rate ratios, disparate impact. All metrics were estimated as a proportion or ratio, with variability captured through 95% CIs. The prespecified criterion for the model's clinical use was a threshold of at least 80% for fairness metrics across different racial groups to ensure the model's prediction would not be biased against any specific race. The test validation dataset included 43 274 patients with balanced demographics. Mean (SD) age was 64.09 (14.26) years, with 49.6% older than 65 years. A total of 53.3% were female; 9.5%, Asian; 18.9%, Black; 0.1%, Native American; 52.2%, White; and 19.2%, other or unknown race; 0.1% had missing race data. A total of 88.9% of patients were alive, and 11.1% were dead. The AUROCs, F1 scores, and fairness metrics maintained reasonable concordance among the racial subgroups: the AUROCs ranged from 0.75 (95% CI, 0.72-0.78) for Asian patients and 0.75 (95% CI, 0.73-0.77) for Black patients to 0.77 (95% CI, 0.75-0.79) for patients with other or unknown race; F1 scores, from 0.32 (95% CI, 0.32-0.33) for White patients to 0.40 (95% CI, 0.39-0.42) for Black patients; equal opportunity ratios, from 0.96 (95% CI, 0.95-0.98) for Black patients compared with White patients to 1.02 (95% CI, 1.00-1.04) for Black patients compared with patients with other or unknown race; equalized odds ratios, from 0.87 (95% CI, 0.85-0.92) for Black patients compared with White patients to 1.16 (1.10-1.21) for Black patients compared with patients with other or unknown race; and disparate impact ratios, from 0.86 (95% CI, 0.82-0.89) for Black patients compared with White patients to 1.17 (95% CI, 1.12-1.22) for Black patients compared with patients with other or unknown race. In this cohort study, the lack of significant variation in performance or fairness metrics indicated an absence of racial bias, suggesting that the model fairly identified cancer mortality risk across racial groups. It remains essential to consistently review the model's application in clinical settings to ensure equitable patient care.

We present a distributed algorithm for obtaining a fair time slot allocation for link activation in a multihop radio network. We introduce the concept of maximal fairness in which the termination of a fair allocation algorithm is related to maximal reuse of the channel under a given fairness metric. The fairness metric can be freely interpreted as the expected link traffic load demands, link priorities, etc. Since respective demands for time slot allocation will not necessarily be equal, we define fairness in terms of the closeness of allocation to respective link demands while preserving the collision free property. The algorithm can be used in conjunction with existing link activation algorithms to provide a fairer and fuller utilization of the channel.

Pharmacoepidemiology and “in silico” drug evaluation: is there common ground?

Active learning with fairness-aware clustering for fair classification considering multiple sensitive attributes

Over the last few decades, machine learning (ML) applications have grown exponentially, yielding several benefits to society. However, these benefits are tempered with concerns of discriminatory behaviours exhibited by ML models. In this regard, fairness in machine learning has emerged as a priority research area. Consequently, several fairness metrics and algorithms have been developed to mitigate against discriminatory behaviours that ML models may possess. Yet still, very little attention has been paid to the problem of naturally occurring changes in data patterns (aka data distributional drift), and its impact on fairness algorithms and metrics. In this work, we study this problem comprehensively by analyzing 4 fairness-unaware baseline algorithms and 7 fairness-aware algorithms, carefully curated to cover the breadth of its typology, across 5 datasets including public and proprietary data, and evaluated them using 3 predictive performance and 10 fairness metrics. In doing so, we show that (1) data distributional drift is not a trivial occurrence, and in several cases can lead to serious deterioration of fairness in so-called fair models; (2) contrary to some existing literature, the size and direction of data distributional drift is not correlated to the resulting size and direction of unfairness; and (3) choice of, and training of fairness algorithms is impacted by the effect of data distributional drift which is largely ignored in the literature. Emanating from our findings, we synthesize several policy implications of data distributional drift on fairness algorithms that can be very relevant to stakeholders and practitioners.

Recent research has revealed that many machine-learning models and the datasets they are trained on suffer from various forms of bias, and a large number of different fairness metrics have been created to measure this bias. However, determining which metrics to use, as well as interpreting their results, is difficult for a non-expert due to a lack of clear guidance and issues of ambiguity or alternate naming schemes between different research papers. To address this knowledge gap, we present the Fairness Metrics Ontology (FMO), a comprehensive and extensible knowledge resource that defines each fairness metric, describes their use cases, and details the relationships between them. We include additional concepts related to fairness and machine learning models, enabling the representation of specific fairness information within a resource description framework (RDF) knowledge graph. We evaluate the ontology by examining the process of how reasoning-based queries to the ontology were used to guide the fairness metric-based evaluation of a synthetic data model.

Fairness metrics have become a useful tool to measure how fair or unfair a machine learning system may be for its stakeholders. In the context of recommender systems, previous research has explored how various stakeholders experience algorithmic fairness or unfairness, but it is also important to capture these experiences in the design of fairness metrics. Therefore, we conducted four focus groups with providers (those whose items, content, or profiles are being recommended) of two different domains: content creators and dating app users. We explored how our participants experience unfairness on their associated platforms, and worked with them to co-design fairness goals, definitions, and metrics that might capture these experiences. This work represents an important step towards designing fairness metrics with the stakeholders who will be impacted by their operationalizations. We analyze the efficacy and challenges of enacting these metrics in practice and explore how future work might benefit from this methodology.

Artificial intelligence (AI) meets real-world disparities: A SEER-based study of Acute Myeloid Leukemia (AML) across race, ethnicity and gender

6553 Background: Although the JCOG9501 phase III trial demonstrated that standard D2 plus extended lymphadenectomy (D3) could not improve the survival in cT2b-T4 gastric cancer (ASCO2006 Abs#LBA4015), it is important to examine the variation in the treatment effects for evaluating the generalizability, as written in international statistical guideline (ICH-E9). In addition, investigating the ranges of baseline risks among hospitals gives important information for the standardization of cancer treatment. Methods: Mixed effect models were applied to survival and surgical outcome data for 521 (D2: 263, D3: 258) gastric cancer patients from 23 Japanese hospitals, which were the leading institutions of gastric cancer surgery in Japan. After adjustment with 10 clinicopathological factors, the variation in the treatment effects and the baseline risks among hospitals were estimated. If heterogeneity was identified, we further estimated the Spearman’s correlation coefficients between the variation and hospital characteristics. Results: In the treatment effects, the ranges of the hazard ratio of overall survival (OS) and recurrence-free survival (RFS) for D3 compared with D2 were 1.05–1.48 and 1.03–1.77, respectively. The ranges of baseline risks for D2 were shown in Table . The correlation coefficients between hospital volume of gastrectomy and the heterogeneity in operation time, blood loss and postoperative complication were -0.31 (p=0.15), −0.40 (p=0.06), −0.52 (p=0.01), respectively. Any institutional characteristics showed little correlation with OS or RFS. Conclusions: The final result of JCOG9501 seemed to be generalizable to the target populations, although some degree of heterogeneity of treatment effects existed. The hospitals entered in this trial had some variation also in the baseline risks for D2. The heterogeneities of some surgical outcomes may be correlated with hospital volume of gastrectomy. No significant financial relationships to disclose. [Table: see text]

Fairness in machine learning refers to the development of models that do not systematically disadvantage individuals or groups based on sensitive attributes. One commonly adopted principle is fairness through unawareness, which holds that models should not explicitly incorporate sensitive attributes into the decision-making process. However, in some scenarios, such as healthcare, variables like sex and age are essential for accurate diagnoses and prognoses. Previous studies have assessed the influence of including or excluding such information during model training. Nonetheless, they have not considered Adversarial Debiasing, a classification algorithm specifically designed to promote equitable results. To address this gap, we propose a comprehensive empirical analysis to investigate the role of sensitive attributes in this algorithm. We experimentally evaluated Adversarial Debiasing across 20 settings using 23 datasets from varying domains, one predictive performance metric, three group fairness metrics, and a non-parametric statistical test. Our findings indicate that classifiers trained without including sensitive information in the input feature set produce more precise and fairer outcomes.

BackgroundRacial bias is a key concern regarding the development, validation, and implementation of machine learning (ML) models in clinical settings. Despite the potential of bias to propagate health disparities, racial bias in clinical ML has yet to be thoroughly examined and best practices for bias mitigation remain unclear.ObjectiveOur objective was to perform a scoping review to characterize the methods by which the racial bias of ML has been assessed and describe strategies that may be used to enhance algorithmic fairness in clinical ML.MethodsA scoping review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) Extension for Scoping Reviews. A literature search using PubMed, Scopus, and Embase databases, as well as Google Scholar, identified 635 records, of which 12 studies were included.ResultsApplications of ML were varied and involved diagnosis, outcome prediction, and clinical score prediction performed on data sets including images, diagnostic studies, clinical text, and clinical variables. Of the 12 studies, 1 (8%) described a model in routine clinical use, 2 (17%) examined prospectively validated clinical models, and the remaining 9 (75%) described internally validated models. In addition, 8 (67%) studies concluded that racial bias was present, 2 (17%) concluded that it was not, and 2 (17%) assessed the implementation of bias mitigation strategies without comparison to a baseline model. Fairness metrics used to assess algorithmic racial bias were inconsistent. The most commonly observed metrics were equal opportunity difference (5/12, 42%), accuracy (4/12, 25%), and disparate impact (2/12, 17%). All 8 (67%) studies that implemented methods for mitigation of racial bias successfully increased fairness, as measured by the authors’ chosen metrics. Preprocessing methods of bias mitigation were most commonly used across all studies that implemented them.ConclusionsThe broad scope of medical ML applications and potential patient harms demand an increased emphasis on evaluation and mitigation of racial bias in clinical ML. However, the adoption of algorithmic fairness principles in medicine remains inconsistent and is limited by poor data availability and ML model reporting. We recommend that researchers and journal editors emphasize standardized reporting and data availability in medical ML studies to improve transparency and facilitate evaluation for racial bias.