IMAGINATIVE: Impact of Machine Learning-based Clinician Decision Support Algorithms in Perioperative Care

• Sponsor: Singapore General Hospital (Other)
• Overall Status: Not yet recruiting
• CT.gov ID: NCT05809232
• Collaborator: (none)
• Enrollment: 9,200
• Location: 1
• Arms: 2
• Anticipated Duration (Months): 55
• Patients Per Site Per Month: 167.2

Study Details

Study Description

Brief Summary

Predicting surgical risks are important to patients and clinicians for shared decision making process and management plan. The study team aim to conduct a hybrid type 1 effectiveness implementation study design. A Randomized Controlled Trial where participants undergoing surgery In Singapore General Hospital (SGH) will be allocated in 1:1 ratio to CARES-guided (unblinded to risk level) or to unguided (blinded to risk level) groups. All participants undergoing elective surgeries in SGH will be considered eligible for enrolment into the study. For elective surgeries, the participants will mainly be recruited from Pre-admission Centre. The outcome of this study will help patients and clinicians make better decisions together. Firstly, the deployment of the CARES model in a live clinical environment could potentially reduce postoperative complications and improve the quality of surgical care provision. The findings from this study would allow fine-tuning of CARES as well as further deployment of additional risk models for specific complications other than Mortality and ICU stay. This in turn would translate to better health for the surgical population and improved cost-effectiveness. This is significant as the surgical population is expected to continuously grow due to improved access to care, better technologies and the aging population. Secondly, IMAGINATIVE will be instrumental in improving our understanding of the deployment strategies for AI/ML predictive models in healthcare. Models such as CARES could be the standard of care in the future if proven to improve the health outcomes of patients. As model deployments are costly and can be disruptive to the EMR processes, this study would be the initial spark for future deployment and health services research focusing on improving the value of these model deployments.

Condition or Disease	Intervention/Treatment	Phase
Machine Learning	Other: CARES-guided Group	N/A

Study Design

• Study Type: Interventional
• Anticipated Enrollment: 9200 participants
• Allocation: Randomized
• Intervention Model: Parallel Assignment
• Masking: None (Open Label)
• Primary Purpose: Other
• Official Title: Impact of Machine Learning-based Clinician Decision Support Algorithms in Perioperative Care - A Randomized Control Trial (IMAGINATIVE Trial)
• Anticipated Study Start Date: May 1, 2023
• Anticipated Primary Completion Date: Jul 1, 2027
• Anticipated Study Completion Date: Dec 1, 2027

Arms and Interventions

Arm	Intervention/Treatment
Active Comparator: CARES-guided Group The Intervention	Other: CARES-guided Group; Participants randomised to the CARES-guided arm will have their CARES-score calculated and entered into the Pre-Anesthesia Assessment electronic form within the Electronic Medical Records (EMR). This score and its relevant advisories will be prominently displayed on this electronic form. (Participants on this arm will receive this intervention in addition to the routine practice).
No Intervention: Non CARES-Guided Group The control - Participants randomized to the control arm will continue to have their routine Pre-Anesthesia Assessment on the electronic form, without the CARES calculator calculations, as per current practice

Outcome Measures

Primary Outcome Measures

1. Change in perioperative mortality rates [Five years]

   To assess the effectiveness of the Machine Learning Clinical Decision Support (ML-CDS). Hypothesis: The CARES-guided group will have a 30% relative reduction in one-year mortality rate due to the increased clinician awareness of the risks.

Secondary Outcome Measures

1. Change in potentially avoidable planned ICU admission after surgery [Five years]

   To assess the effectiveness of the ML-CDS algorithm in optimizing ICU bed utilization, which is an important and costly hospital resource Hypothesis: There will be a 25% relative reduction in the potentially avoidable planned ICU admission after surgery in the CARES-guided group

Other Outcome Measures

1. Shift in adoption rate of CARES's CDS recommendations among anesthesiologists, intensivists, surgeons and nurses [Five years]

   To assess adoption and acceptability, and to understand user experience and concerns regarding an ML based prediction application designed to improve patient safety in a clinical setting. Hypothesis: There is high adoption of CARES's CDS recommendations among anesthesiologists, intensivists, surgeons and nurses respectively.

Eligibility Criteria

Criteria

• Ages Eligible for Study: 21 Years to 100 Years
• Sexes Eligible for Study: All
• Accepts Healthy Volunteers: No

Inclusion Criteria:

1. Patients >=21 Years old

2. Patients going for elective surgery

For semi-structured interview:

1. Any clinician or nurse that used CARES during the research trial

Exclusion Criteria:

1. Patients with reduced mental capacity

2. Patients who are unable to give consent

Contacts and Locations

Locations

	Site	City	State	Country	Postal Code
1	Singapore General Hospital	Singapore		Singapore

Sponsors and Collaborators

• Singapore General Hospital

Investigators

None specified.

Study Documents (Full-Text)

None provided.

More Information

Publications

None provided.

• Responsible Party: Singapore General Hospital
• ClinicalTrials.gov Identifier: NCT05809232
• Other Study ID Numbers: IMAGINATIVE Trial
• First Posted: Apr 12, 2023
• Last Update Posted: Apr 12, 2023
• Last Verified: Mar 1, 2023

• Individual Participant Data (IPD) Sharing Statement: No
• Plan to Share IPD: No
• Studies a U.S. FDA-regulated Drug Product: No
• Studies a U.S. FDA-regulated Device Product: No

Study Results

No Results Posted as of Apr 12, 2023