Technology-Driven Intervention for Cognitive Impairment

(CI Wizard Trial)

Recruiting at 1 trial location

Overseen By Bethany Crouse, PhD

Age: 65+

Sex: Any

Trial Phase: Academic

Sponsor: HealthPartners Institute

Disqualifiers: Chemotherapy, Stage 4 cancer, Hospice, others

No Placebo Group All trial participants will receive the active study treatment (no placebo)

Approved in 1 Jurisdiction This treatment is already approved in other countries

Compensation: Varies

Number of Visits: Unknown

3001 Participants Needed

Trial Summary

What is the purpose of this trial?

Most experts advocate for early detection of cognitive impairment (CI) so that patients and caregivers can be prepared for making difficult decisions and to improve quality of life, but studies show that screening alone isn't sufficient to change clinician actions related to early detection. Using predictive modelling developed with machine learning methods and sophisticated clinical decision support (CDS) tools, it is possible to identify patients at elevated risk for CI and make it much easier for primary care to engage and support patients and caregivers in meaningful care planning. The goal of this study is to implement and evaluate a low-cost, highly scalable CI-CDS system integrated within the electronic health record that has high potential to improve early CI detection and care and translate massive public and private sector investments in health informatics into tangible health benefits for large numbers of people.

Will I have to stop taking my current medications?

The trial information does not specify whether you need to stop taking your current medications. It is best to discuss this with the trial coordinators or your doctor.

What data supports the effectiveness of the treatment CI-CDS System for cognitive impairment?

Research shows that clinical decision support systems (CDSS) can improve patient care by helping healthcare providers make better decisions. While specific data on CI-CDS for cognitive impairment is not available, similar systems have shown potential benefits in managing other conditions, like insulin use and patient-reported outcomes. ^{1 2 3 4 5}

Is the Technology-Driven Intervention for Cognitive Impairment generally safe for humans?

Clinical decision support systems (CDSS) are generally safe and can help prevent medical errors, but their design is crucial. Poor design can lead to new errors, so it's important that the system is well-designed and tested for usability to ensure safety. ^{6 7 8 9 10}

How is the CI-CDS System treatment different from other treatments for cognitive impairment?

The CI-CDS System is unique because it uses technology to provide personalized support and decision-making assistance for cognitive impairment, enhancing the connection between patients and clinicians, unlike traditional treatments that may lack this personalized interaction. ^{11 12 13 14 15}

Eligibility Criteria

This trial is for people aged 65 or older who visit a participating primary care clinic, have no prior diagnosis of cognitive impairment (CI), and show signs of CI based on specific tests. They must not have had chemotherapy for advanced cancer in the last year, be in hospice or palliative care.

Inclusion Criteria

Patient has no CI diagnosis documented in the EHR prior to the visit

First visit during the accrual period at which all prior inclusion criteria are met

Primary care office visit at a randomized clinic during the accrual period

Exclusion Criteria

My cancer is at stage 4.

I am enrolled in a hospice or palliative care program.

I have had chemotherapy through injection or IV in the past year.

Timeline

Screening

Participants are screened for eligibility to participate in the trial

Accrual period

All primary care visits during accrual period

Intervention

Implementation of CI-CDS system in primary care clinics to improve early detection and management of cognitive impairment

24 months

Primary care visits with CI-CDS tool usage

Follow-up

Participants are monitored for CI diagnosis and clinician confidence in CI detection and management

24 months

Regular primary care visits

Treatment Details

Interventions

• CI-CDS

Trial Overview The study is testing a new system called CI-CDS that uses machine learning to help doctors spot early signs of dementia. It's integrated into electronic health records and aims to improve detection and management of cognitive issues.

Participant Groups

Group I: CI-CDS Experimental Treatment 1 Intervention

In clinics randomized to the CI-CDS, the providers will be given the option to use the CI-CDS tool during eligible patient encounters.

Group II: Usual Care (UC) Active Control 1 Intervention

In clinics randomized to UC, patients will receive usual care at their primary care visits over the accrual period (no intervention will be given).

Who Is Running the Clinical Trial?

HealthPartners Institute

Lead Sponsor

Trials

196

Recruited

3,721,000+

National Institute on Aging (NIA)

Collaborator

Trials

1,841

Recruited

28,150,000+

OCHIN, Inc.

Collaborator

Trials

24

Recruited

9,964,000+

Findings from Research

The article highlights the need for improved patient-centered clinical decision support (PC CDS) tools to enhance healthcare decision-making, emphasizing the importance of making research findings more shareable and publicly available.

A comprehensive assessment involving a technical expert panel, literature review, and interviews with 18 stakeholders identified key areas for improvement, including the need for standardized processes to integrate clinical guidelines and patient-generated health data into PC CDS systems.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The technical landscape for patient-centered CDS: progress, gaps, and challenges. Dullabh, P., Heaney-Huls, K., Lobach, DF., et al.[2022]

A clinical decision support system (CDS) for managing tuberculosis (TB) patients was positively received by 12 healthcare professionals, indicating its potential to improve patient care despite some initial usability challenges.

The assessment highlighted the value of decision support features and automated reporting, suggesting that while there were workflow issues, the system could enhance coordination and efficiency in TB management.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

An information management system for patients with tuberculosis: usability assessment with end-users. Darby, J., Black, J., Morrison, D., et al.[2012]

A survey of 64 ICU physicians revealed that 92% believe a discharge AI-CDS tool could be valuable for predicting patient readmission and mortality risk, indicating strong support for AI integration in clinical practice.

Despite differing opinions on the complexity of discharge decisions, most physicians (86%) felt that AI could enhance their decision-making, highlighting a positive outlook on the potential benefits of AI in improving patient outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Intensive Care Unit Physicians' Perspectives on Artificial Intelligence-Based Clinical Decision Support Tools: Preimplementation Survey Study. van der Meijden, SL., de Hond, AAH., Thoral, PJ., et al.[2023]

A systematic review of 24 randomized controlled trials involving 7653 participants found that clinical decision support systems (CDSS) can improve insulin use and blood glucose control, with 70% of studies showing lower mean blood glucose levels after using computerized insulin dose adjustments.

While CDSSs showed promise in reducing hyperglycemia events and improving insulin therapy, the overall quality of evidence was moderate, indicating a need for better-designed and longer-term studies to confirm these findings.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

The effects of clinical decision support systems on insulin use: A systematic review. Jia, P., Jia, P., Chen, J., et al.[2021]

A systematic review of 15 studies involving 13,480 patients found that computer-based clinical decision support systems (CCDSS) can have marginal positive effects on patient-reported outcomes (PRO), particularly in symptom management.

No negative effects were reported from the use of CCDSS, suggesting they are safe to implement, but further development of user-friendly systems with clear evidence-based guidance is needed to enhance their effectiveness.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Computer-Based Clinical Decision Support Systems and Patient-Reported Outcomes: A Systematic Review. Blum, D., Raj, SX., Oberholzer, R., et al.[2018]

A study analyzing the usability of clinical decision support systems (CDSS) for community-acquired pneumonia and neutropenic fever found 422 recorded events, including 3 mistakes that could have been life-threatening, highlighting the critical need for careful design and evaluation of these systems.

Incorporating usability engineering principles early in the design of CDSS can help identify interface issues that may lead to adverse medical events, emphasizing the importance of user-friendly software in improving patient safety.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

How usability of a web-based clinical decision support system has the potential to contribute to adverse medical events. Graham, TA., Kushniruk, AW., Bullard, MJ., et al.[2022]

A usability study involving 8 medical residents identified 51 usability problems in a clinical decision support system (CDSS) for antibiotic treatment, highlighting areas for improvement in its design and functionality.

Most identified issues were minor or cosmetic, but some could lead to significant ordering errors, emphasizing the need to prioritize redesign efforts based on their potential impact on clinical outcomes.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

A usability study to improve a clinical decision support system for the prescription of antibiotic drugs. Akhloufi, H., Verhaegh, SJC., Jaspers, MWM., et al.[2020]

A new computerized clinical decision support system (G-MEDSS) was developed to assist accredited clinical pharmacists in managing high-risk medications for older adults, including those with dementia, based on feedback from healthcare professionals and caregivers.

The G-MEDSS demonstrated fair to good usability with a mean score of 69.0 on the System Usability Scale, indicating it effectively supports person-centered medication reviews tailored to individual patient goals.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Development, validation and evaluation of the Goal-directed Medication review Electronic Decision Support System (G-MEDSS)©. Kouladjian O'Donnell, L., Reeve, E., Hilmer, SN.[2022]

A clinical decision support system (CDSS) helps healthcare providers by detecting potential drug interactions and errors, which can lead to improved patient safety and reduced clinical errors.

The implementation of a CDSS can save time and money while also decreasing morbidity and mortality rates, highlighting its effectiveness in enhancing patient care and supporting nursing informatics.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Clinical decision support in critical care nursing. Lyons, A., Richardson, S.[2019]

Effective clinical decision support (CDS) systems for medication prescribing should focus on high-severity alerts that minimize workflow interruptions, while integrating relevant patient data to enhance decision-making accuracy and efficiency.

Design recommendations include using clear and consistent visual elements, minimizing information clutter, and allowing quick responses to alerts, which can significantly improve human-computer interaction and ultimately enhance patient safety.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Design of decision support interventions for medication prescribing. Horsky, J., Phansalkar, S., Desai, A., et al.[2015]

Age-related cognitive impairment (ARCI) is linked to underlying brain pathology, highlighting the need for early detection and personalized interventions to improve health span.

The Intelligent Technology Therapy Assistant (ITA) concept, exemplified by platforms like the Guttman Neuro Personal Trainer® and the Barcelona Brain Health Initiative app, aims to enhance access to clinical expertise while maintaining a personal connection between patients and clinicians, potentially improving the effectiveness of cognitive interventions.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Aging in the Digital Age: Using Technology to Increase the Reach of the Clinician Expert and Close the Gap Between Health Span and Life Span. Gomes-Osman, J., Solana-Sánchéz, J., Rogers, E., et al.[2023]

The RESILIEN-T system, designed for older adults with Mild Cognitive Impairment (MCI), showed high user acceptance and engagement, indicating its potential as a supportive tool for self-management despite no significant differences in most quantitative outcomes.

Participants using the RESILIEN-T system reported an improvement in their perceived memory capability, suggesting that while overall efficacy was not statistically significant, the system may still positively impact users' self-perception of cognitive function.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Results of the Italian RESILIEN-T Pilot Study: A Mobile Health Tool to Support Older People with Mild Cognitive Impairment. Bevilacqua, R., Felici, E., Cucchieri, G., et al.[2023]

Computer-based cognitive interventions (CCIs) have shown significant benefits in improving specific cognitive domains such as memory and attention in individuals with mild cognitive impairment (MCI), based on a systematic review of 24 randomized controlled trials.

While CCIs did not demonstrate significant improvements in global cognition for individuals with dementia, one study indicated that CCIs could lead to memory improvements in those with subjective cognitive decline (SCD), suggesting that early intervention may be key for cognitive preservation.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Effectiveness of computer-based interventions for community-dwelling people with cognitive decline: a systematic review with meta-analyses. Zuschnegg, J., Schoberer, D., Häussl, A., et al.[2023]

In a study of 429 patients with subjective cognitive decline (SCD) and mild cognitive impairment (MCI), the PredictND tool did not significantly improve overall prognostic accuracy for predicting progression to dementia, but it did show promise in a subgroup with more certain classifications, increasing accuracy by 6.4%.

The use of the PredictND tool significantly boosted clinicians' confidence in their predictions, indicating its potential value in clinical settings for assessing patients with cognitive complaints.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Impact of a clinical decision support tool on prediction of progression in early-stage dementia: a prospective validation study. Bruun, M., Frederiksen, KS., Rhodius-Meester, HFM., et al.[2020]

A systematic review of 10 studies on cognitive interventions for older adults with mild cognitive impairment (MCI) or dementia found that most technologies were computer-based programs, often in the form of serious games, which showed positive user experiences despite some interface difficulties.

Elderly users required more time and assistance to complete tasks, highlighting the need for technology that is tailored to their capabilities, and emphasizing the importance of usability and user experience measurements in developing effective cognitive interventions.

NCBI (Pubmed)

pubmed.ncbi.nlm.nih.gov

Usability and User Experience of Cognitive Intervention Technologies for Elderly People With MCI or Dementia: A Systematic Review. Contreras-Somoza, LM., Irazoki, E., Toribio-Guzmán, JM., et al.[2022]

References

1. England pubmed.ncbi.nlm.nih.gov

The technical landscape for patient-centered CDS: progress, gaps, and challenges. [2022]

2. Netherlands pubmed.ncbi.nlm.nih.gov

An information management system for patients with tuberculosis: usability assessment with end-users. [2012]

3. Canada pubmed.ncbi.nlm.nih.gov

Intensive Care Unit Physicians' Perspectives on Artificial Intelligence-Based Clinical Decision Support Tools: Preimplementation Survey Study. [2023]

4. England pubmed.ncbi.nlm.nih.gov

The effects of clinical decision support systems on insulin use: A systematic review. [2021]

5. New Zealand pubmed.ncbi.nlm.nih.gov

Computer-Based Clinical Decision Support Systems and Patient-Reported Outcomes: A Systematic Review. [2018]

6. United States pubmed.ncbi.nlm.nih.gov

How usability of a web-based clinical decision support system has the potential to contribute to adverse medical events. [2022]

7. United States pubmed.ncbi.nlm.nih.gov

A usability study to improve a clinical decision support system for the prescription of antibiotic drugs. [2020]

8. United States pubmed.ncbi.nlm.nih.gov

Development, validation and evaluation of the Goal-directed Medication review Electronic Decision Support System (G-MEDSS)©. [2022]

9. United States pubmed.ncbi.nlm.nih.gov

Clinical decision support in critical care nursing. [2019]

10. Ireland pubmed.ncbi.nlm.nih.gov

Design of decision support interventions for medication prescribing. [2015]

11. Switzerland pubmed.ncbi.nlm.nih.gov

Aging in the Digital Age: Using Technology to Increase the Reach of the Clinician Expert and Close the Gap Between Health Span and Life Span. [2023]

12. Switzerland pubmed.ncbi.nlm.nih.gov

Results of the Italian RESILIEN-T Pilot Study: A Mobile Health Tool to Support Older People with Mild Cognitive Impairment. [2023]

13. England pubmed.ncbi.nlm.nih.gov

Effectiveness of computer-based interventions for community-dwelling people with cognitive decline: a systematic review with meta-analyses. [2023]

14. England pubmed.ncbi.nlm.nih.gov

Impact of a clinical decision support tool on prediction of progression in early-stage dementia: a prospective validation study. [2020]

15. Switzerland pubmed.ncbi.nlm.nih.gov

Usability and User Experience of Cognitive Intervention Technologies for Elderly People With MCI or Dementia: A Systematic Review. [2022]