Investigating for bias in healthcare algorithms: a sex-stratified analysis of supervised machine learning models in liver disease prediction.
Isabel StrawHonghan WuPublished in: BMJ health & care informatics (2022)
Our 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.
Keyphrases
- healthcare
- machine learning
- artificial intelligence
- big data
- deep learning
- chronic obstructive pulmonary disease
- electronic health record
- palliative care
- public health
- health information
- primary care
- risk assessment
- mental health
- social media
- health insurance
- extracorporeal membrane oxygenation
- respiratory failure
- mechanical ventilation