Table 3.
Name | Technological Basis | Field of Application | Use | Implemented/Conjectured |
---|---|---|---|---|
Medical Ethical Advisor (METHAD) [17] | Machine Learning, Fuzzy Cognitive Maps | General clinical practice, education |
- encompasses the bioethical principles (Beauchamp, Childress) [20] in machine-readable form - input: patient status and preferences in machine-comparable values - general evaluation; numerical value of zero (against) to one (in favour of) |
Implemented (“proof of concept”) |
Patient Preference Predictor (PPP) [23] | Machine Learning, Population-based | General clinical practice, incapacitated patients |
- takes defining characteristics and circumstances of the patient in question and empirical data on treatment preferences into account - approximates preferences of incapacitated patients regarding treatments |
Conjectured |
Do not attempt resuscitation—Algorithm (DNAR) [24] | Machine Learning | Emergency medicine |
- predicts patients’ preferences on resuscitation measures in emergency situations - compares the patient’s data with that of other patients |
Conjectured |
Surgery Algorithm [25] | Machine Learning | Surgery |
- strives to de-bias decision-making in the selection of patients for major surgery - gives an objective and equitable risk assessment for the patients - improves i.a. racial and socioeconomic justice |
Conjectured |
Autonomy Algorithm [26] | Machine Learning, based on healthcare records and social media | General clinical practice, incapacitated patients |
- harvests information on patients with impaired capacity - predicts their preferences on important healthcare decisions |
Conjectured |