Clinical trial of an AI-augmented intervention for HIV prevention in youth experiencing homelessness

Wilder, Bryan; Onasch‐Vera, Laura; DiGuiseppi, Graham; Petering, Robin; Hill, Chyna; Yadav, Amulya; Rice, Eric; Tambe, Milind

doi:10.48550/arxiv.2009.09559

Cited by 3 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Academic collaborations leading to publicly implemented platforms have been deployed in a wide number of problem specific domains, we will highlight three here. Wilder [35], Wilder et al [36] build a site which identifies influential nodes in partially-known networks for the dissemination of public health information. Flanigan et al [14,15], Shah [32] implement a website to help determine fair and transparent allocations.…”

Section: Literature Reviewmentioning

confidence: 99%

Project 412Connect: Bridging Students and Communities

DiChristofano

Hamilton

Linardi

et al. 2021

Equity and Access in Algorithms, Mechanisms, and Optimization

View full text Add to dashboard Cite

In this work, we describe some of the challenges Black-owned businesses face in the United States and specifically in the city of Pittsburgh. Taking into account local dynamics and the communicated desires of Black-owned businesses in the Pittsburgh region, we determine that university students represent an under-utilized market for these businesses. We investigate the root causes for this inefficiency and design and implement a platform, 412Connect (https://www.412connect.org/), to increase online support for Pittsburgh Black-owned businesses from students in the Pittsburgh university community.The site operates by coordinating interactions between student users and participating businesses via targeted recommendations. We describe the project from its conception, paying special attention to our motivation and design choices. These choices are aided by two simple models for badge design and recommendation systems that may be of theoretical interest. Along the way, we highlight challenges and lessons from coordinating a grassroots volunteer project working in conjunction with community partners and the opportunities and pitfalls of engaged scholarship.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Project 412Connect: Bridging Students and Communities

DiChristofano

Hamilton

Linardi

et al. 2021

Equity and Access in Algorithms, Mechanisms, and Optimization

View full text Add to dashboard Cite

show abstract

“…With AI models starting to be deployed in the real world it is essential that the benefits of AI are shared equitably according to race, gender and other demographic characteristics, and so efforts to ensure the fairness of deployed models have generated much interest. Most work so far has focused on computer vision problems but some applications in healthcare are starting to emerge [15,22].…”

Section: Introductionmentioning

confidence: 99%

Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentation

Puyol‐Antón¹,

Ruijsink²,

Neubauer³

et al. 2021

Preprint

View full text Add to dashboard Cite

The subject of 'fairness' in artificial intelligence (AI) refers to assessing AI algorithms for potential bias based on demographic characteristics such as race and gender, and the development of algorithms to address this bias. Most applications to date have been in computer vision, although some work in healthcare has started to emerge. The use of deep learning (DL) in cardiac MR segmentation has led to impressive results in recent years, and such techniques are starting to be translated into clinical practice. However, no work has yet investigated the fairness of such models. In this work, we perform such an analysis for racial/gender groups, focusing on the problem of training data imbalance, using a nnU-Net model trained and evaluated on cine short axis cardiac MR data from the UK Biobank dataset, consisting of 5,903 subjects from 6 different racial groups. We find statistically significant differences in Dice performance between different racial groups. To reduce the racial bias, we investigated three strategies: (1) stratified batch sampling, in which batch sampling is stratified to ensure balance between racial groups; (2) fair meta-learning for segmentation, in which a DL classifier is trained to classify race and jointly optimized with the segmentation model; and (3) protected group models, in which a different segmentation model is trained for each racial group. We also compared the results to the scenario where we have a perfectly balanced database.To assess fairness we used the standard deviation (SD) and skewed error ratio (SER) of the average Dice values. Our results demonstrate that the racial bias results from the use of imbalanced training data, and that all proposed bias mitigation strategies improved fairness, with the best SD and SER resulting from the use of protected group models.

show abstract

“…However, the factors that govern these protective behaviors are complex, multi-dimensional and under-studied. With a high burden of HIV and limited resources, developing countries could benefit the most from data-driven evidence and machine learning approaches that can prioritize interventions [2] . In India, community-led organizations (COs) working towards HIV prevention are increasingly using digital tools and collecting massive data, thus opening the possibility of understanding these complex influences.…”

Section: Introductionmentioning

confidence: 99%

Learning Explainable Interventions to Mitigate HIV Transmission in Sex Workers Across Five States in India

Awasthi¹,

Patel²,

Joshi³

et al. 2020

Preprint

View full text Add to dashboard Cite

Female sex workers(FSWs) are one of the most vulnerable and stigmatized groups in society. As a result, they often suffer from a lack of quality access to care. Grassroot organizations engaged in improving health services are often faced with the challenge of improving the effectiveness of interventions due to complex influences. This work combines structure learning, discriminative modeling, and grass-root level expertise of designing interventions across five different Indian states to discover the influence of non-obvious factors for improving safe-sex practices in FSWs. A bootstrapped, ensemble-averaged Bayesian Network structure was learned to quantify the factors that could maximize condom usage as revealed from the model. A discriminative model was then constructed using XgBoost and random forest in order to predict condom use behavior The best model achieved 83% sensitivity, 99% specificity, and 99% area under the precision-recall curve for the prediction. Both generative and discriminative modeling approaches revealed that financial literacy training was the primary influence and predictor of condom use in FSWs. These insights have led to a currently ongoing field trial for assessing the real-world utility of this approach. Our work highlights the potential of explainable models for transparent discovery and prioritization of anti-HIV interventions in female sex workers in a resource-limited setting.

show abstract

Clinical trial of an AI-augmented intervention for HIV prevention in youth experiencing homelessness

Cited by 3 publications

References 28 publications

Project 412Connect: Bridging Students and Communities

Project 412Connect: Bridging Students and Communities

Fairness in Cardiac MR Image Analysis: An Investigation of Bias Due to Data Imbalance in Deep Learning Based Segmentation

Learning Explainable Interventions to Mitigate HIV Transmission in Sex Workers Across Five States in India

Contact Info

Product

Resources

About