A proposal for developing a platform that evaluates algorithmic equity and accuracy

Abstract

We are at a pivotal moment in the development of healthcare artificial intelligence (AI), a point at which enthusiasm for machine learning has not caught up with the scientific evidence to support the equity and accuracy of diagnostic and therapeutic algorithms. This proposal examines algorithmic biases, including those related to race, gender and socioeconomic status, and accuracy, including the paucity of prospective studies and lack of multisite validation. We then suggest solutions to these problems. We describe the Mayo Clinic, Duke University, Change Healthcare project that is evaluating 35.1 billion healthcare records for bias. And we propose ‘Ingredients’ style labels and an AI evaluation/testing system to help clinicians judge the merits of products and services that include algorithms. Said testing would include input data sources and types, dataset population composition, algorithm validation techniques, bias assessment evaluation and performance metrics.

Addressing racial disparities in surgical care with machine learning

“…To ensure that all patients are ensured equal access to high-quality medical care, including surgical services, it is first necessary to analyze the data sets used to determine whether patients of color, women and those in lower socioeconomic groups are accurately represented in the data sets and algorithms used to determine the need for said services. As we have pointed out in a previous publication 26 , this has not always been the case. Obermeyer et al’s 27 analysis of a commercial database has demonstrated that, while Blacks were considerably sicker than White patients, based on signs and symptoms, the dataset did not recognize the greater disease burden in Blacks because it assigned risk scores based on total healthcare costs accrued.…”

“…Commercially available AI bias detection tools that have been used to help identify discrimination include concept activation vectors (TCAV), which are used by Google to measure bias by race, gender, and location 31 , and Audit-AI, which uses a Python library from Pymetrics that can detect discrimination by locating specific patterns in the training data 26 , 32 .…”

Current state and prospects of artificial intelligence in allergy

“…128 This predicament can further amplify the enduring issue of model bias and inequality in medical research-an issue from which the field of allergy is not exempt, 129 as evident in models demonstrating lesser accuracy in underprivileged populations. 130 To alleviate this risk, three strategies are recommended. First, ideally, comprehensive data about a patient's environment, inclusive of historical allergen exposure, should be procured and included in the model training procedure.…”

“…Notable differences in sensitization patterns across geographical regions enhance this challenge 128 . This predicament can further amplify the enduring issue of model bias and inequality in medical research—an issue from which the field of allergy is not exempt, 129 as evident in models demonstrating lesser accuracy in underprivileged populations 130 . To alleviate this risk, three strategies are recommended.…”

Optimization of Multi-pressure Condenser Combining Artificial Intelligence and Deep Learning Algorithm

“…To prevent the problems of infinite loop (feedback algorithm disorder failure)/zero divided amount/delay, the storage module and timing assignment module are properly designed in the model loop algorithm. Therefore, the mathematical model is the basis of this condenser model, and its accuracy and real-time directly affect the accuracy and speed of the model, so the establishment of the mathematical model is very important [5][6]. According to the structural characteristics of power plant condenser, this paper divides its mathematical model into shell side and tube side.…”