Influence of AI-based decision support on shared decision making in hemodialysis: a Wizard of Oz experiment
Osmanodja, B.; Samhammer, D.; Roller, R.; Beck, S.; Burchardt, A.; Duettmann, W.; Dabrock, P.; Gerndt, S.; Moeller, S.; Ronicke, S.; Budde, K.
Show abstract
Artificial Intelligence-based decision support systems (AI-DSS) to improve hemodialysis therapy are currently under development. However, the influence of AI-DSS on shared decision making (SDM) in hemodialysis patients has not been studied so far. We performed a Wizard of Oz experiment, using a sham AI-DSS suggesting ultrafiltration volume at the beginning of each dialysis session. We performed 10 patient interviews in 5 patients, and investigated views towards AI, different aspects of the SDM, and the influence of an AI-DSS on SDM in a real-life scenario. Five main topics were identified: (1) the patient as self-determined, (2) role of the medical staff, (3) other forms of automation, (4) attitude towards AI, (5) needs and preferences for future use of AI. The patients describe novel AI-DSS in dialysis as an opportunity to promote self-determination and to ensure more efficient therapy. At the same time, they describe the special relationship with the nursing staff and physicians, who, from the patients point of view, must be given control over an AI-DSS. This study provides first evidence regarding the influence of AI-DSS on SDM in the context of hemodialysis. Further studies should focus on other aspects that require SDM such as initiation of dialysis, and selection of dialysis modality.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Fatigue in Incident Peritoneal Dialysis and Mortality: A Real-World Side-by-Side Study in Brazil and the United States 95%
- Organising outpatient dialysis services during the COVID-19 pandemic. A simulation and mathematical modelling study. 95%
- Chronic Kidney Disease in Ecuador: An Epidemiological and Health System Analysis of an Emerging Public Health Crisis 94%
Similar papers in this journal
- Machine learning for classifying chronic kidney disease and predicting creatinine levels using at-home measurements 92%
- Pool walking may temporarily improve renal function by suppressing renin-angiotensin-aldosterone system in pregnant women 91%
- AKI Risk Score (AKI-RiSc): Developing an Interpretable Clinical Score for Early Identification of Acute Kidney Injury for Patients Presenting to the Emergency Department 90%
Similar papers in this journal
- Development and Validation of a Machine Learning Model Integrated with the Clinical Workflow for Inpatient Discharge Date Prediction 90%
- Using Machine Learning to Predict Mortality for COVID-19 Patients on Day Zero in the ICU 89%
- Using wearable and nearable devices in telerehabilitation for COPD: A review of digital endpoints in home-based programs 88%
Similar papers in this journal
- Prediction of Unplanned 30- day Readmission for ICU Patients with Heart Failure 91%
- Development and Validation of ‘Patient Optimizer’ (POP) Algorithms for Predicting Surgical Risk with Machine Learning 91%
- Implicit bias in Critical Care Data: Factors affecting sampling frequencies and missingness patterns of clinical and biological variables in ICU Patients 90%
Similar papers in this journal
- ‘Self-Management Intervention through Lifestyle Education for Kidney health’ (the SMILE-K study): protocol for a single-blind longitudinal randomised control trial with nested pilot study 92%
- Protocol for a prospective cohort study on the feasibility of application of nutritional ultrasound in the diagnosis and follow-up of patients with nutritional risk at hospital discharge: Study on body composition and function (DRECO) 90%
- An individualized risk prediction model for new-onset, progression and regression of chronic kidney disease in a retrospective cohort of patients with type 2 diabetes under primary care in Hong Kong 90%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.