JMIR Publications

ABSTRACT

Background:

Smart sensors are developed as new diagnostic tools for rehabilitation to cover the increasing number of geriatric patients. They promise to enable an objective assessment of complex movement patterns.

Objective:

This work aims to analyze the conflicting ethical values associated with smart sensors in geriatric rehabilitation. This may enhance the understanding on how patients respond to this technology.

Methods:

Based on a systematic literature search in the scientific databases PubMed and Science Direct, a document analysis was conducted to identify evidence-based practical implications of ethical relevance. A total of 33 articles were included in the document analysis. Practical implications were extracted inductively. Afterwards an ethical analysis, based on the four principles of biomedical ethics, namely autonomy, beneficence, non-maleficence and justice was carried out.

Results:

We identified eight conflicting aims when using smart sensors. Gains in autonomy come at the cost of the patient’s privacy. Smart sensors at home increase the independence of patients but may reduce social interactions. Independent measurements performed by patients may result in lower diagnostic accuracy. While smart sensors could provide a cost effective and high-quality diagnostic for most patients, minorities could end up with a suboptimal treatment due to their underrepresentation in training data and studies. This could lead to algorithmic biases that are not recognized by the medical professionals when treating patients.

Conclusions:

The application of smart sensors has the potential to improve the rehabilitation of geriatric patients in many ways. It is important that the patient should not have to decide between autonomy over privacy and is well informed about the insights that can be gained from the data. Smart sensors should support and not replace the interactions with medical professionals. Patients and medical professionals need to be educated about the correct application and the limitations of smart sensors. To guarantee fair access, smart sensors should include an adequate representation of minorities in the training data and should be covered by the health insurance.