Investigating for bias in healthcare algorithms: a sex-stratified analysis of supervised machine learning models in liver disease prediction

ObjectivesThe Indian Liver Patient Dataset (ILPD) is used extensively to create algorithms that predict liver disease. Given the existing research describing demographic inequities in liver disease diagnosis and management, these algorithms require scrutiny for potential biases. We address this over...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	BMJ health & care informatics Ročník 29; číslo 1; s. e100457
Hlavní autoři:	Straw, Isabel, Wu, Honghan
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	England BMJ Publishing Group Ltd 01.04.2022 BMJ Publishing Group LTD BMJ Publishing Group
Témata:	Algorithms Artificial Intelligence Bayes Theorem Bias Biomarkers BMJ Health Informatics Delivery of Health Care Female Gender differences Health Equity Health informatics Humans Liver Diseases Machine Learning Male Original Research Public health informatics Supervised Machine Learning United Kingdom > UK Public health informatics BMJ Health Informatics Health Equity Artificial intelligence Machine Learning
ISSN:	2632-1009, 2632-1009
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Popis
Shrnutí:	ObjectivesThe Indian Liver Patient Dataset (ILPD) is used extensively to create algorithms that predict liver disease. Given the existing research describing demographic inequities in liver disease diagnosis and management, these algorithms require scrutiny for potential biases. We address this overlooked issue by investigating ILPD models for sex bias.MethodsFollowing our literature review of ILPD papers, the models reported in existing studies are recreated and then interrogated for bias. We define four experiments, training on sex-unbalanced/balanced data, with and without feature selection. We build random forests (RFs), support vector machines (SVMs), Gaussian Naïve Bayes and logistic regression (LR) classifiers, running experiments 100 times, reporting average results with SD.ResultsWe reproduce published models achieving accuracies of >70% (LR 71.31% (2.37 SD) – SVM 79.40% (2.50 SD)) and demonstrate a previously unobserved performance disparity. Across all classifiers females suffer from a higher false negative rate (FNR). Presently, RF and LR classifiers are reported as the most effective models, yet in our experiments they demonstrate the greatest FNR disparity (RF; −21.02%; LR; −24.07%).DiscussionWe demonstrate a sex disparity that exists in published ILPD classifiers. In practice, the higher FNR for females would manifest as increased rates of missed diagnosis for female patients and a consequent lack of appropriate care. Our study demonstrates that evaluating biases in the initial stages of machine learning can provide insights into inequalities in current clinical practice, reveal pathophysiological differences between the male and females, and can mitigate the digitisation of inequalities into algorithmic systems.ConclusionOur findings are important to medical data scientists, clinicians and policy-makers involved in the implementation medical artificial intelligence systems. An awareness of the potential biases of these systems is essential in preventing the digital exacerbation of healthcare inequalities.
Bibliografie:	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 ObjectType-Review-3 content type line 23
ISSN:	2632-1009 2632-1009
DOI:	10.1136/bmjhci-2021-100457