Surgeon-Informed Clinical Decision Support Software for Surgical Risk Prediction and Outcomes Tracking

Area of Science:

• Surgical Informatics
• Health Informatics
• Clinical Decision Support Systems

Background:

• Effective clinical decision support software (CDSS) implementation hinges on integration into clinical context and workflow.
• This study aimed to define surgeon-centric design principles for a novel CDSS app.

Purpose of the Study:

• To prospectively define surgeon-centric design principles for a novel CDSS app.
• To combine incisional hernia risk prediction with patient outcomes tracking.

Main Methods:

• A three-round online modified-Delphi panel of 30 surgeons from eight specialties assessed a pilot CDSS app.
• Feasibility, importance, and acceptability of the risk model, user interface, and workflow integration were assessed using Likert scales and qualitative analysis.

Main Results:

• Surgeons defined acceptable performance metrics for risk models (e.g., FN rate <10%, FP rate <15%, AUC ≥0.8).
• Visual risk depictions, transparent weighting, team-based data entry, and customizable reminders were crucial for usability and mitigating user burden.
• Risk models are mainly used for high-risk patients to enhance communication; statistical literacy and workflow integration are key for adoption.

Conclusions:

• Findings provide surgeon-informed principles for developing surgical CDSS tools.
• Successful CDSS must be interpretable, efficient, and augment clinical judgment.
• Addressing end-user needs for transparency, statistical literacy, and workflow integration is essential for CDSS adoption.