Improving Quality of ICD-10 Coding Using AI: Protocol for a Crossover Randomized Controlled Trial (ClinCode)

Improving Quality of ICD-10 (International Statistical Classification of Diseases, Tenth Revision) Coding Using AI: Protocol for a Crossover Randomized Controlled Trial

The goal of this randomised trial is to learn about the role of AI in clinical coding practice. The main question it aims to answer is:

Can the AI-based CAC system reduce the burden of clinical coding and also improve the quality of such coding? Participants will be asked to code clinical texts both while they use our CAC system and while they do not.

Study Overview

• Status: Recruiting
• Conditions: Gastrointestinal Diseases
• Intervention / Treatment: Other: Easy-ICD

Detailed Description

Once participants are recruited, they are randomly allocated to 2 groups without allocation concealment. Allocation concealment will not be relevant for clinical coders since it is known whether a participant is assisted or not, and we will not develop a placebo coding assistant. We will, however, conceal the allocation of subjects for the analyses.

In total, participants will code 20 clinical notes, where each note belongs to a single patient. The participants are asked to complete the experiment in 1 sitting without interruptions, and they cannot revisit or go back to previous notes. In the event that participants are interrupted, they are asked to exit the experiment, and any incomplete records are discarded as invalid.

The user study process can be summarized in the following steps:

1. Study participants are randomly allocated to group 1 and group 2.
2. To prepare participants for the experiment, a short video tutorial is played after the consent form is signed and right before the clinical coding task commences.
3. In period 1 with 10 clinical notes, group 1 uses the control interface, while group 2 uses the intervention interface.
4. Data are logged in the background using button presses (eg. time, assigned codes, and comments).
5. Then, there is an immediate crossover to period 2 for the last 10 clinical notes.
6. Data continue to be logged in the background using button presses.
7. At the end, participants in both groups will complete the system usability scale.

• Study Type: Interventional
• Enrollment (Estimated): 30
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Taridzo F Chomutare, PhD; Phone Number: +4747680032; Email: taridzo.chomutare@ehealthresearch.no

Study Locations

• Norway
  • Troms
    • Tromso, Troms, Norway, 9019
      • Recruiting
      • Norwegian Centre for E-health Research
      • Contact: Taridzo F Chomutare, PhD; Phone Number: +4747680032; Email: taridzo.chomutare@ehealthresearch.no
      • Contact: Hercules Dalianis, PhD; Phone Number: +46705681359; Email: hercules@dsv.su.se

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• participant has coded clinical texts before, preferably ICD-10 coding
• is a healthcare professional, eg. clinician, nurse, professional coders
• can understand Swedish

Exclusion Criteria:

• participants outside Norway and Sweden

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: Randomized
• Interventional Model: Crossover Assignment
• Masking: Single

Number of Arms

2

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Active Comparator: Easy-ICD interface; This arm uses our AI-based computer-assisted clinical coding (CAC) system, Easy-ICD	Other: Easy-ICD; Easy-ICD is an AI-based computer-assisted clinical coding (CAC) system that helps clinical coder assign ICD-10 codes to clinical notes such as discharge summaries.
No Intervention: Control interface; This control arm uses an interface similar to Easy-ICD, but without the AI functionality

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Time	Time in seconds taken to assign ICD-10 codes to each of the 20 clinical notes.	1 hour
Accuracy	Accuracy is calculated by dividing the number of correct ICD-10 codes by the total number of codes assigned.	1 hour

Collaborators and Investigators

• Sponsor: University Hospital of North Norway
• Collaborators: The Research Council of Norway
• Investigators: Principal Investigator: Hercules Dalianis, PhD, Norwegian Centre for E-health Research

Study record dates

Study Major Dates

• Study Start (Actual): October 20, 2023
• Primary Completion (Estimated): April 1, 2024
• Study Completion (Estimated): April 1, 2024

Study Registration Dates

• First Submitted: February 16, 2024
• First Submitted That Met QC Criteria: February 23, 2024
• First Posted (Estimated): February 29, 2024

Study Record Updates

• Last Update Posted (Estimated): February 29, 2024
• Last Update Submitted That Met QC Criteria: February 23, 2024
• Last Verified: February 1, 2024

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Gastrointestinal Diseases; Digestive System Diseases
• Other Study ID Numbers: 260972(REK)

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: The data we collect in the study are all anonymous and will be shared publicly after the user study is published.
• IPD Sharing Time Frame: At the publishing of the user study.
• IPD Sharing Access Criteria: The anonymous data will be publicly available.
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ICF

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No