Validation of a Risk Assessment Model for Postoperative Delirium Based on Artificial Intelligence

NCT05639348 | Completed

• 1 other identifier: 2022-00990; am21Dell- Kuster
• Study Type: observational
• Target: 993
• Locations: 1 country
• Sites: 3

Brief Summary

Postoperative delirium (POD) is a frequent postoperative complication in the elderly, characterised by fluctuating disturbances in attention, awareness, and cognition. Identifying the patients at highest risk of developing POD was the aim of the artificial intelligence (AI)-based algorithm PIPRA. This prospective cohort study is to externally validate the AI-based PIPRA algorithm. The primary endpoint is the performance (AUC) of the PIPRA algorithm in predicting POD. The secondary endpoint is the performance (AUC) of the clinicians in predicting POD (and how it compares with the performance of the PIPRA algorithm).

Conditions

Postoperative Delirium (POD)

Keywords

Perioperative neurocognitive disorders (PND); Postoperative cognitive dysfunction (POCD); Acute neuropsychiatric disorder; Cognitive testing; Artificial intelligence (AI)-based algorithm PIPRA; Intensive Care Delirium Screening Checklist (ICDSC); 4 "A" Tests (4AT)

Outcome Measures

Primary Outcomes (2)

• Change in 4 'A's Test (4AT) to evaluate presence of POD

  4 'A's Test (4AT) is a bedside medical scale with 4 parameters: 1. Alertness 2. Abbreviated mental test-4 (AMT4) 3. Attention (months backwards test) 4. Acute change or fluctuating course. The score range is 0-12, with scores of 4 or more suggesting possible delirium. Scores of 1-3 suggest possible cognitive impairment.

  Twice daily (morning and evening) from postoperative day 1 until postoperative day 5, hospital discharge or a positive diagnosis of POD, whichever occurs first.

• Change in Intensive Care Delirium Screening Checklist (ICDSC) to evaluate presence of POD

  The ICDSC is an 8-item delirium screening instrument (range: 0-8 points) that evaluates a patient's level of consciousness, inattention, disorientation, hallucinations or delusions, psychomotor activity, inappropriate speech or mood, sleep disturbance and fluctuation of symptoms (no delirium with a score of 0, less than clinical threshold symptoms of delirium with a score of 1-3 and clinical delirium with a score of 4-8).

  Twice daily (morning and evening) from postoperative day 1 until postoperative day 5, hospital discharge or a positive diagnosis of POD, whichever occurs first.

Interventions

Data collection on POD for calculation of the PIPRA score OTHER

Data collection for presence of POD as diagnosed by the 4 "A" Tests (4AT) or the Intensive Care Delirium Screening Checklist (ICDSC). The collected data will be used to validate the existing PIPRA algorithm and to improve the algorithm and evaluate it in a cross-validation setting. For the model validation the area under the receiver operating characteristics (ROC) curve (AUC) will be computed.

Eligibility Criteria

• Age: 60 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Consecutive surgical patients at multiple sites in Switzerland.

You may qualify if:

• Surgical patients ≥60 years old
• Planned postoperative hospital stay ≥ 2 days
• Consent from patient

You may not qualify if:

• Preoperative delirium
• Insufficient knowledge in German or French
• Intracranial surgery
• Cardiac surgery
• Surgery within the two previous weeks
• Patient unable to consent

Sponsors & Collaborators

• University Hospital, Basel, Switzerland: lead
• Innosuisse - Swiss Innovation Agency: collaborator

Study Sites (3)

University Hospital Basel, Anaesthesiology

Basel, 4031, Switzerland

Location

Hôpitaux Universitaires de Genève, Anesthesiology

Geneva, 1205, Switzerland

Location

Centre Hospitalier Universitaire Vaudois, Anesthesiology

Lausanne, 1011, Switzerland

Location

MeSH Terms

Conditions

Emergence Delirium; Postoperative Cognitive Complications

Condition Hierarchy (Ancestors)

Delirium; Confusion; Neurobehavioral Manifestations; Neurologic Manifestations; Nervous System Diseases; Postoperative Complications; Pathologic Processes; Pathological Conditions, Signs and Symptoms; Signs and Symptoms; Neurocognitive Disorders; Mental Disorders; Cognitive Dysfunction; Cognition Disorders

Study Officials

• Luzius Steiner, Prof. Dr. med.

  University Hospital Basel, Department of Anaesthesiology

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: November 23, 2022
• First Posted: December 6, 2022
• Study Start: November 21, 2022
• Primary Completion: June 15, 2024
• Study Completion: June 15, 2024
• Last Updated: December 18, 2024

Record last verified: 2024-12

Locations

CH (3)