Addressing bias in big data and AI for health care: A call for open science

Norori, Natalia; Hu, Qinglong; Aellen, Florence M.; Faraci, Francesca Dalia; Tzovara, Athina

doi:10.1016/j.patter.2021.100347

Cited by 306 publications

(168 citation statements)

References 64 publications

Supporting

Mentioning

166

Contrasting

Unclassified

Order By: Relevance

“…However, its test result in the WSI was not good and the correlation determinant ( Figure 5 E) was very low between the annotation and the result analyzed by AI model under the WSI, real world environment. The figures of infiltration and inflammation seemed confused because they have shared similar cellular components to some extent [ 34 ], and more diverse and complex figures would exist in the real world than in a dataset environment [ 35 ]. This categorization of infiltration and inflammation did not seem advisable in this study.…”

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence-Assisted Image Analysis of Acetaminophen-Induced Acute Hepatic Injury in Sprague-Dawley Rats

et al. 2022

View full text Add to dashboard Cite

Although drug-induced liver injury (DILI) is a major target of the pharmaceutical industry, we currently lack an efficient model for evaluating liver toxicity in the early stage of its development. Recent progress in artificial intelligence-based deep learning technology promises to improve the accuracy and robustness of current toxicity prediction models. Mask region-based CNN (Mask R-CNN) is a detection-based segmentation model that has been used for developing algorithms. In the present study, we applied a Mask R-CNN algorithm to detect and predict acute hepatic injury lesions induced by acetaminophen (APAP) in Sprague-Dawley rats. To accomplish this, we trained, validated, and tested the model for various hepatic lesions, including necrosis, inflammation, infiltration, and portal triad. We confirmed the model performance at the whole-slide image (WSI) level. The training, validating, and testing processes, which were performed using tile images, yielded an overall model accuracy of 96.44%. For confirmation, we compared the model’s predictions for 25 WSIs at 20× magnification with annotated lesion areas determined by an accredited toxicologic pathologist. In individual WSIs, the expert-annotated lesion areas of necrosis, inflammation, and infiltration tended to be comparable with the values predicted by the algorithm. The overall predictions showed a high correlation with the annotated area. The R square values were 0.9953, 0.9610, and 0.9445 for necrosis, inflammation plus infiltration, and portal triad, respectively. The present study shows that the Mask R-CNN algorithm is a useful tool for detecting and predicting hepatic lesions in non-clinical studies. This new algorithm might be widely useful for predicting liver lesions in non-clinical and clinical settings.

show abstract

Section: Discussionmentioning

confidence: 99%

Artificial Intelligence-Assisted Image Analysis of Acetaminophen-Induced Acute Hepatic Injury in Sprague-Dawley Rats

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Although the existence of systemic sex and race-based bias in the healthcare system is highly documented [34][35][36][37][38][39][40] , this study is one of the largest to examine several areas of EHR-embedded biases that have the potential to impact the performance of AI diagnosis tools. To our knowledge, this is also the rst study to examine sex and race differences in EHR data missingness, time to troponin order, and time to treatment initiation in a multisite ED setting.…”

Section: Discussionmentioning

confidence: 99%

Assessment of sex and racial biases in electronic health records of emergency department patients with acute coronary syndrome

Zeng

Xiang

Allen

et al. 2022

Preprint

View full text Add to dashboard Cite

Background Electronic health records (EHRs) contain individualized patient data that can be used to develop diagnostic and risk prediction models with artificial intelligence (AI) algorithms. Explicit and implicit sources of bias embedded in EHRs may hinder generalizable model performance and perpetuate bias. Objective This study explores the question of how existing sex and racial disparities in the clinical assessment and management of acute coronary syndrome (ACS) are reflected in patients’ EHRs. We outlined recommendations on how these sources of bias should be examined and mitigated within the framework of development and validation of AI-based diagnosis and risk stratification algorithms. Methods This retrospective study examined several previously unrecognized EHR-embedded biases in a multisite emergency departments (ED) setting. We assessed sex and race differences in EHR data missingness and timeliness of several key ED procedures following ACS suspicion. We additionally conducted a data-driven clustering analysis to detect latent groups of ACS patients. Results 10,043 ACS-associated ED visits were included. We identified sex and race differences in the prevalence of ACS symptoms, data missingness (vitals and labs), and waiting time for troponin order and treatment initiation within 24 hours post-admission. Our cluster analysis discovered four groups of ACS patients corresponding to common symptoms. Additionally, we identified differences in clinical management and patient demographics across these clusters. Conclusions We discovered several sources of bias inherent in the clinical practice of ACS diagnosis and treatment that are also present in EHR data. Our study supports the inclusion of a wider range of symptoms into AI-based diagnosis and risk stratification tools. These models should be also validated in ED admissions without chest pain and in patients who experience a longer waiting time for ED procedures.

show abstract

“…7 In this way, there is potential for synthetic data to help mitigate algorithmic bias in healthcare uses of machine learning, both in constructing algorithms and responding to dataset shift. 8,9 Synthetic data may also be used to audit medical applications of machine learning by exposing algorithms to novel simulated data in adversarial testing. 10 Similarly, GANs may also be used in the construction of synthetic digital twins, whereby an artificial construction of a system is created that preserves all the patterns of the true system.…”

Section: Clinical Researchmentioning

confidence: 99%

Generative adversarial networks and synthetic patient data: current challenges and future perspectives

Arora

2022

Future Healthcare Journal

View full text Add to dashboard Cite

Artificial intelligence (AI) has been heralded as one of the key technological innovations of the 21st century. Within healthcare, much attention has been placed upon the ability of deductive AI systems to analyse large datasets to find patterns that would be unfeasible to program. Generative AI, including generative adversarial networks, are a newer type of machine learning that functions to create fake data after learning the properties of real data. Artificially generated patient data has the potential to revolutionise clinical research and protect patient privacy. Using novel techniques, it is increasingly possible to fully anonymise datasets to the point where no datapoint is traceable to any real individual. This can be used to expand and balance datasets as well as to replace the use of real patient data in certain contexts. This paper focuses upon three key uses of synthetic data: clinical research, data privacy and medical education. We also highlight ethical and practical concerns that require consideration.

show abstract

Addressing bias in big data and AI for health care: A call for open science

Cited by 306 publications

References 64 publications

Artificial Intelligence-Assisted Image Analysis of Acetaminophen-Induced Acute Hepatic Injury in Sprague-Dawley Rats

Artificial Intelligence-Assisted Image Analysis of Acetaminophen-Induced Acute Hepatic Injury in Sprague-Dawley Rats

Assessment of sex and racial biases in electronic health records of emergency department patients with acute coronary syndrome

Generative adversarial networks and synthetic patient data: current challenges and future perspectives

Contact Info

Product

Resources

About