Functional requirements to mitigate the Risk of Harm to Patients from Artificial Intelligence in Healthcare

The Directorate General for Parliamentary Research Services of the European Parliament has prepared a report to the Members of the European Parliament where they enumerate seven main risks of Artificial Intelligence (AI) in medicine and healthcare: patient harm due to AI errors, misuse of medical AI tools, bias in AI and the perpetuation of existing inequities, lack of transparency, privacy and security issues, gaps in accountability, and obstacles in implementation. In this study, we propose fourteen functional requirements that AI systems may implement to reduce the risks associated with their medical purpose: AI passport, User management, Regulation check, Academic use only disclaimer, data quality assessment, Clinicians double check, Continuous performance evaluation, Audit trail, Continuous usability test, Review of retrospective/simulated cases, Bias check, eXplainable AI, Encryption and use of field-tested libraries, and Semantic interoperability. Our intention here is to provide specific high-level specifications of technical solutions to ensure continuous good performance and use of AI systems to benefit patients in compliance with the future EU regulatory framework.

Design of one-year mortality forecast at hospital admission based: a machine learning approach

Background: Palliative care is referred to a set of programs for patients that suffer life-limiting illnesses. These programs aim to guarantee a minimum level of quality of life (QoL) for the last stage of life. They are currently based on clinical evaluation of risk of one-year mortality. Objectives: The main objective of this work is to develop and validate machine-learning based models to predict the exitus of a patient within the next year using data gathered at hospital admission. Methods: Five machine learning techniques were applied in our study to develop machine-learning predictive models: Support Vector Machines, K-neighbors Classifier, Gradient Boosting Classifier, Random Forest and Multilayer Perceptron. All models were trained and evaluated using the retrospective dataset. The evaluation was performed with five metrics computed by a resampling strategy: Accuracy, the area under the ROC curve, Specificity, Sensitivity, and the Balanced Error Rate. Results: All models for forecasting one-year mortality achieved an AUC ROC from 0.858 to 0.911. Specifically, Gradient Boosting Classifier was the best model, producing an AUC ROC of 0.911 (CI 95%, 0.911 to 0.912), a sensitivity of 0.858 (CI 95%, 0.856 to 0.86) and a specificity of 0.807 (CI 95%, 0.806 to 0808) and a BER of 0.168 (CI 95%, 0.167 to 0.169). Conclusions: The analysis of common information at hospital admission combined with machine learning techniques produced models with competitive discriminative power. Our models reach the best results reported in state of the art. These results demonstrate that they can be used as an accurate data-driven palliative care criteria inclusion.