Effectiveness of a Clinical Decision Support System for Pointing Device Prescription

The experiences and perceptions of health-care professionals regarding assistive technology training: A systematic review

Worldwide, there is an increasing demand for assistive technologies (ATs) that can support people to live independently for longer. Health-care professionals (HCPs) often recommend AT devices, however there exists a lack of availability of devices and appropriate training in the field. This systematic review aimed to synthesize the available evidence into the experiences and training needs of HCPs in relation to AT. Six electronic databases were searched without date restrictions: MEDLINE, PsycINFO, SPP, SSCI, CINAHL, and ASSIA. Journal handsearching, searching reference lists of included studies and relevant reviews, and contacting experts in the field of AT were also conducted. Findings were analyzed using narrative synthesis. Data from 7846 participants from 62 studies were synthesized, eliciting perceived challenges in access to and provision of training, resulting in knowledge gaps across disciplines and geographic locations. Mechanisms to mitigate these issues included ongoing support following training and tailoring education to meet individual needs since comprehensive training is essential to maintain and improve competence, knowledge, and confidence. Further research is required to explore the impact and effectiveness of AT training for HCPs to ensure that users of devices are supported to live independent and healthy lives.

Interpretability of Clinical Decision Support Systems Based on Artificial Intelligence from Technological and Medical Perspective: A Systematic Review

Background

Artificial intelligence (AI) has developed rapidly, and its application extends to clinical decision support system (CDSS) for improving healthcare quality. However, the interpretability of AI-driven CDSS poses significant challenges to widespread application.

Objective

This study is a review of the knowledge-based and data-based CDSS literature regarding interpretability in health care. It highlights the relevance of interpretability for CDSS and the area for improvement from technological and medical perspectives.

Methods

A systematic search was conducted on the interpretability-related literature published from 2011 to 2020 and indexed in the five databases: Web of Science, PubMed, ScienceDirect, Cochrane, and Scopus. Journal articles that focus on the interpretability of CDSS were included for analysis. Experienced researchers also participated in manually reviewing the selected articles for inclusion/exclusion and categorization.

Results

Based on the inclusion and exclusion criteria, 20 articles from 16 journals were finally selected for this review. Interpretability, which means a transparent structure of the model, a clear relationship between input and output, and explainability of artificial intelligence algorithms, is essential for CDSS application in the healthcare setting. Methods for improving the interpretability of CDSS include ante-hoc methods such as fuzzy logic, decision rules, logistic regression, decision trees for knowledge-based AI, and white box models, post hoc methods such as feature importance, sensitivity analysis, visualization, and activation maximization for black box models. A number of factors, such as data type, biomarkers, human-AI interaction, needs of clinicians, and patients, can affect the interpretability of CDSS.

Conclusions

The review explores the meaning of the interpretability of CDSS and summarizes the current methods for improving interpretability from technological and medical perspectives. The results contribute to the understanding of the interpretability of CDSS based on AI in health care. Future studies should focus on establishing formalism for defining interpretability, identifying the properties of interpretability, and developing an appropriate and objective metric for interpretability; in addition, the user's demand for interpretability and how to express and provide explanations are also the directions for future research.

Need-based care of multi-morbid patients - supporting general practitioners with algorithm-generated recommendations of healthcare services (telemedicine-project ATMoSPHÄRE)

Background

The patient-oriented and need-based care of multi-morbid patients with healthcare services and assistive products can be a highly complex task for the general practitioners (GPs). An algorithm-based digital recommendation system (DRS) for healthcare services was developed within the context of the telemedicine research project ATMoSPHÄRE. The plausibility of the DRS was tested and the results used to examine if, and to what degree, the DRS provides useful assistance to GPs.

Methods

The plausibility of the recommendations of the DRS were tested with the Delphi procedure (n = 8) and Interviews (n = 4) in collaboration with the GPs. They proposed services and assistive products they considered appropriate for two multi-morbid patients. Furthermore, GPs had to report whether, and to what degree they deemed the algorithm-generated recommendations appropriate. Significant quantitative differences between the GPs’, and the algorithm-generated, recommendations were evaluated with paired-samples-Wilcoxon-test.

Results

The first Delphi round revealed a high variability regarding the amount and character of services recommended by the physicians (1 to 10 recommendations, mean = 5.6, sd = 2.8). These professional recommendations converged after consideration of the algorithm-generated recommendations. The number of algorithm-generated recommendations which were judged as appropriate ranged between 7 and 17 of a total of 20 (mean = 11.9, sd = 2.5). The interviews revealed that the additional algorithm-generated recommendations which were judged appropriate contained mainly social care services.

Conlusion

The DRS provides GPs with additional appropriate recommendations for the need-based care of patients, which may not have been previously considered. It can therefore be assessed as a helpful complement in the primary care of multi-morbid patients.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12875-021-01537-2.