Comparison of SHAP and clinician friendly explanations reveals effects on clinical decision behaviour
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
View abstract on PubMed
Summary
This summary is machine-generated.Clinical decision support systems (CDSSs) using explainable AI (XAI) were evaluated. Providing clinical explanations, rather than just results or SHAP values, significantly improved clinician acceptance and trust.
Area Of Science
- Medical Informatics
- Artificial Intelligence in Healthcare
- Human-Computer Interaction
Background
- Clinical decision-making significantly impacts patient outcomes and quality of life.
- AI-powered Clinical Decision Support Systems (CDSSs) often function as "black boxes", hindering trust and adoption.
- Explainable AI (XAI) aims to demystify AI decision-making, but its effectiveness in clinical settings requires empirical validation.
Purpose Of The Study
- To compare the acceptance, trust, satisfaction, and usability of different XAI explanation methods in CDSSs among clinicians.
- To identify factors influencing clinician acceptance of XAI-driven CDSSs.
- To provide evidence-based recommendations for implementing XAI in clinical practice.
Main Methods
- A counterbalanced study design involving 63 surgeons and physicians who had previously prescribed blood products.
- Participants made decisions using a CDSS with one of three explanation methods (results only, results with SHAP, or clinical explanation) presented via six vignettes.
- Questionnaires assessed acceptance, trust, satisfaction, and usability, with further analysis exploring factors associated with acceptance.
Main Results
- Providing a clinical explanation significantly enhanced clinician acceptance compared to 'results only' or 'results with SHapley Additive exPlanations (SHAP)'.
- Clinician trust, satisfaction, and usability were found to be positively correlated with acceptance of the CDSS.
- The study provides empirical evidence supporting the superiority of clinical explanations for XAI-CDSS adoption.
Conclusions
- Clinical explanations are more effective than 'results only' or SHAP explanations for improving clinician acceptance of AI-powered CDSSs.
- Trust, satisfaction, and usability are key factors mediating the acceptance of XAI-CDSS.
- Best practices for strategic XAI-CDSS implementation should prioritize clear, clinically relevant explanations to foster trust and adoption in healthcare.
These videos have been matched automatically. Contact us if they are not relevant.
These videos have been matched automatically. Contact us if they are not relevant.
Related Concept Videos
Information is everywhere and its presentation—such as how and when items are presented—can impact our perceptions and decisions surrounding the info. This broad concept umbrellas framing effects—influences that occur due to the way information is framed in its appearance, whether it’s purely the order or the specific wording of a message. Let’s take a look at numerous ways in which two versions of something can objectively say the same thing, yet we respond in...
Biopharmaceutical studies constitute a vital field aiming to enhance drug delivery methods and refine therapeutic approaches, drawing upon diverse interdisciplinary knowledge. In research methodologies, the choice between controlled and non-controlled studies significantly influences the study's reliability and accuracy.
Non-controlled studies, commonly employed for initial exploration, lack a control group, rendering them susceptible to biases and external influences. In contrast,...
Problem-intervention-evaluation (PIE) is a systematic approach to documentation used in healthcare settings for clinical decision-making and patient care planning. It is a structured approach to organizing patient data based on problems, interventions, and evaluations. Here's a breakdown of its key features and considerations:
Problem: Patient care is organized around issues identified or nursing diagnoses in the PIE system. Each problem is labeled with a "P" followed by a number....
Blinding is a commonly used method of not telling participants which treatment a subject is receiving. Blinding is a critical part of a randomized control trial or RCT. It reduces the bias that affects the results. In an RCT, blinding is used in the form of a placebo. A placebo effect occurs when untreated subjects falsely believe they have received the treatment and report improved symptoms. A placebo or a dummy treatment is administered to subjects to negate the bias caused by such an effect.
Patient-centered care involves delivering care beyond inpatient hospitalization. Reflective practice can enhance a patient-centered approach. Reflective practice is a process of reasoning that considers all aspects of the present situation, including practicalities, learning from personal practice, and consideration of patient needs. Patients appreciate care decisions made while considering their input. Involving the patient in their care provides the patient with a sense of contribution rather...
Charting by Exception, or CBE, is a method of documentation used in healthcare, particularly in nursing, that focuses on documenting only significant or abnormal findings rather than recording every detail. This approach aims to streamline the documentation process, improve efficiency, and ensure that healthcare providers can quickly identify deviations from normalcy in patient assessments.
In CBE, healthcare professionals establish predefined standards of practice that define what constitutes...