Not provided
| ID | Type | Description | Link |
|---|---|---|---|
| R01AG069765-01 | U.S. NIH Grant/Contract | View source |
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Class |
|---|---|
| National Institute on Aging (NIA) | NIH |
Not provided
Not provided
Not provided
Not provided
The specific aim of the pragmatic trial is to evaluate the practical utility and effect of the PDM, the QDRS, and the combined approach (PDM + QDRS) in improving the annual rate of new documented ADRD diagnosis in primary care practices.
Alzheimer's disease and related dementias (ADRD) negatively impact millions of Americans with an annual societal cost of more than $200 million.1 Currently, half of Americans living with ADRD never receive a diagnosis.2-7 For those who do, the diagnosis often occurs two to five years after the onset of symptoms.6-9 As stated by the National Institute on Aging (NIA) (RFA-AG-20-051) "The inability to diagnose and treat cognitive impairment results in prolonged and expensive medical care" and "early detection could help persons with dementia and their care partners plan for the future". Furthermore, if the development of disease modifying therapeutics for ADRD is successful, this may require the use of such therapeutics at a very early stage of ADRD.1 However, the current approaches of using cognitive tests or biomarkers for early detection of ADRD are not scalable due to their low acceptance, their invasive nature, their cost, or their lack of accessibility in rural or underserved areas. Thus, the NIA called out for the development of low cost, effective, and scalable approaches for early detection of ADRD (RFA-AG-20-051).
In response to the RFA-AG-20-051 call for the "validation, and translation of screening and assessment tools for measuring cognitive decline a pragmatic cluster-randomized controlled comparative effectiveness (NIH Stage IV) trial will be executed in Eskenazi Health in central Indiana and one additional replicated pragmatic trial among patients from diverse rural, suburban and urban primary care practices in south Florida. The pragmatic trial will incorporate the Passive Digital Marker (PDM) and the Quick Dementia Rating Scale (QDRS) within the Medicare paid Annual Wellness Visit (AWV) for a cohort of patients from practices across the two independent sites, with practices randomized in each pragmatic trial to one of the 3 arms (AWV alone, the AWV with PDM and the PDM and the QDRS).
Quick Dementia Rating Scale (QDRS)- is a validated patient reported outcome (PRO) tool.
Passive Digital Marker (PDM) - is a Machine Learning (ML) algorithm which can predict ADRD one year and three years prior to its onset by using routine care electronic health record (EHR) data. The algorithm was trained using structured and unstructured data from three EHR datasets: diagnosis (Dx), prescriptions (Rx), and medical notes (Nx). Individual algorithms derived from each of the three datasets were developed and compared to a combined one that included all three datasets.
Not provided
Not provided
Not provided
Not provided
Not provided
| Label | Type | Description | Intervention Names |
|---|---|---|---|
| Annual Well Visit or any other visit to Primary Care Doctor | No Intervention | Annual Well Visit or any other visit to Primary Care Doctor: This is the usual care arm. Electronic Health Record Data for patients from the clinics randomized to usual care will be collected for comparison with the other 2 arms. Patients from these primary care clinics must have had a visit to their doctor either as an annual well visit (AWV) or any other type of visit. These clinics will not have to do anything for the study but run their business as usual without altering anything. | |
| Passive Digital Marker (PDM) | Experimental | Passive Digital Marker (PDM): Electronic Health Record Data from those clinics randomized to PDM will be run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. |
|
| Passive Digital Marker (PDM) + Quick Dementia Rating Scale (QDRS) | Active Comparator | Patients in the primary care clinics randomized to PDM+QDRS will have Electronic Health Record Data of their patients run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. In addition, patients from these clinics will have their patients complete the QDRS, a validated patient reported outcome (PRO) tool. This combined approach will assess the value of early detection of ADRD and if the annual well visit can overcome the barriers related to early detection of ADRD. |
|
| Name | Type | Description | Arm Group Labels | Other Names |
|---|---|---|---|---|
| Passive Digital Marker for screening for ADRD | Other | Patients in the primary care clinics randomized to PDM+QDRS will have Electronic Health Record Data of their patients run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. In addition, patients from these clinics will have their patients complete the QDRS, a validated patient reported outcome (PRO) tool. This combined approach will assess the value of early detection of ADRD and if the annual well visit can overcome the barriers related to early detection of ADRD. |
| Measure | Description | Time Frame |
|---|---|---|
| 12-Month Cumulative Incidence of ADRD Diagnoses | Any new ADRD case identified (documented in the EHR) within 12 months of the Annual Wellness Visit (index visit). | 12 months after index visit |
| Measure | Description | Time Frame |
|---|---|---|
| 12-Month Cumulative Incidence of ADRD Services | The secondary outcome measures is receipt of any services related to cognitive diagnostic assessment in the post Annual Wellness Visit (index) period that providers may order to diagnose or exclude ADRD. Specifically, the metrics of diagnostic assessment are evaluated as proportions of patients with a record of 1 or more of:
|
Not provided
Inclusion Criteria:
Exclusion Criteria:
Not provided
Not provided
Not provided
Not provided
Not provided
Not provided
| Name | Affiliation | Role |
|---|---|---|
| Malaz Boustani, MD, MPH | Indiana University | Principal Investigator |
| Facility | Status | City | State | ZIP | Country | Contacts |
|---|---|---|---|---|---|---|
| Indiana University | Indianapolis | Indiana | 46202 | United States |
| PubMed Identifier | Type | Citation | Retractions |
|---|---|---|---|
| 41212562 | Derived | Boustani MA, Ben Miled Z, Owora AH, Fowler NR, Dexter P, Puster E, Grout RW, Summanwar D, Erazo SF, Disla S, Coppedge K, Galvin JE. Digital Detection of Dementia in Primary Care: A Randomized Clinical Trial. JAMA Netw Open. 2025 Nov 3;8(11):e2542222. doi: 10.1001/jamanetworkopen.2025.42222. | |
| 36221141 | Derived | Kleiman MJ, Plewes AD, Owora A, Grout RW, Dexter PR, Fowler NR, Galvin JE, Miled ZB, Boustani M. Digital detection of dementia (D3): a study protocol for a pragmatic cluster-randomized trial examining the application of patient-reported outcomes and passive clinical decision support systems. Trials. 2022 Oct 11;23(1):868. doi: 10.1186/s13063-022-06809-5. |
Not provided
Not provided
We are collecting clinic based aggregated data.
Not provided
Not provided
Not provided
Not provided
Within each clinic, enrolled patients include only those who:
D2 trial was launched at 9 clinics on July 5, 2022 (3 clinics in each study arm). D2 trial was completed in July 2024. The D2 trial deployed the Passive Digital Marker (PDM) on 5,325 older patients who were eligible and enrolled to receive primary care services within one of the 9 randomized clinics.
| ID | Title | Description |
|---|---|---|
| FG000 | Annual Well Visit or Any Other Visit to Primary Care Doctor | Annual Well Visit or any other visit to Primary Care Doctor: This is the usual care arm. Electronic Health Record Data for patients from the clinics randomized to usual care will be collected for comparison with the other 2 arms. Patients from these primary care clinics must have had a visit to their doctor either as an annual well visit (AWV) or any other type of visit. These clinics will not have to do anything for the study but run their business as usual without altering anything. |
| FG001 | Passive Digital Marker (PDM) | Passive Digital Marker (PDM): Electronic Health Record Data from those clinics randomized to PDM will be run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. |
| FG002 | Passive Digital Marker (PDM) + Quick Dementia Rating Scale (QDRS) | Patients in the primary care clinics randomized to PDM+QDRS will have Electronic Health Record Data of their patients run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. In addition, patients from these clinics will have their patients complete the QDRS, a validated patient reported outcome (PRO) tool. This combined approach will assess the value of early detection of ADRD and if the annual well visit can overcome the barriers related to early detection of ADRD. |
| Title | Milestones | Reasons Not Completed | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Overall Study |
|
Enrolled patients include only those who:
Not provided
| ID | Title | Description |
|---|---|---|
| BG000 | Annual Well Visit or Any Other Visit to Primary Care Doctor | Annual Well Visit or any other visit to Primary Care Doctor: This is the usual care arm. Electronic Health Record Data for patients from the clinics randomized to usual care will be collected for comparison with the other 2 arms. Patients from these primary care clinics must have had a visit to their doctor either as an annual well visit (AWV) or any other type of visit. These clinics will not have to do anything for the study but run their business as usual without altering anything. |
| Units | Counts |
|---|---|
| Participants |
|
| Title | Description | Population Description | Parameter Type | Dispersion Type | Unit of Measure | Calculate Percentage | Denominator Units Selected | Denominators | Classes |
|---|---|---|---|---|---|---|---|---|---|
| Age, Continuous | Mean |
| Type | Title | Description | Population Description | Reporting Status | Anticipated Posting Date | Parameter Type | Dispersion Type | Unit of Measure | Calculate Percentage | Time Frame | Units Analyzed | Denominator Units Selected | Arm/Group Information | Denominators | Classes | Analyses | |||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Primary | 12-Month Cumulative Incidence of ADRD Diagnoses | Any new ADRD case identified (documented in the EHR) within 12 months of the Annual Wellness Visit (index visit). | 9 clinics were randomized, and patients were treated as per the randomization arm (3 clinics per arm) | Posted | Number | Number of new ADRD cases | 12 months after index visit |
|
12-Months of follow-up after index visit (enrollment date)
Not provided
Not provided
| ID | Title | Description | Deaths (Affected) | Deaths (At Risk) | Serious Events (Affected) | Serious Events (At Risk) | Other Events (Affected) | Other Events (At Risk) |
|---|---|---|---|---|---|---|---|---|
| EG000 | Annual Well Visit or Any Other Visit to Primary Care Doctor | Annual Well Visit or any other visit to Primary Care Doctor: This is the usual care arm. Electronic Health Record Data for patients from the clinics randomized to usual care will be collected for comparison with the other 2 arms. Patients from these primary care clinics must have had a visit to their doctor either as an annual well visit (AWV) or any other type of visit. These clinics will not have to do anything for the study but run their business as usual without altering anything. |
| Term | Organ System | Source Vocabulary | Assessment Type | Notes | Statistical Information |
|---|---|---|---|---|---|
| Positive for PDM and had Hospitalization | General disorders | Systematic Assessment |
Not provided
We had a delay in releasing the second cohort of the PDM by about 3 months due to enabling an HL7 process. This made it possible for Epic to run a program to flag PDM and PDM+QDRS automatically. For the first cohort, we manually entered the data.
| Title | Organization | Phone | Extension | |
|---|---|---|---|---|
| Katrina Coppedge | Indiana University | 317-278-1602 | kcoppedg@iu.edu |
Not provided
| Type | Includes Protocol | Includes SAP | Includes ICF | Document Label | Document Date | Document Uploaded Date | Document File Name |
|---|---|---|---|---|---|---|---|
| Prot_SAP | Yes | Yes | No | Study Protocol and Statistical Analysis Plan | Apr 5, 2023 | Jul 2, 2025 | Prot_SAP_000.pdf |
| ICF | No | No | Yes | Informed Consent Form | Nov 28, 2022 | Jul 2, 2025 | ICF_001.pdf |
Not provided
| ID | Term |
|---|---|
| D000544 | Alzheimer Disease |
| ID | Term |
|---|---|
| D003704 | Dementia |
| D001927 | Brain Diseases |
| D002493 | Central Nervous System Diseases |
| D009422 | Nervous System Diseases |
Not provided
Not provided
| ID | Term |
|---|---|
| D008403 | Mass Screening |
| D000071066 | Patient Reported Outcome Measures |
| ID | Term |
|---|---|
| D019937 | Diagnostic Techniques and Procedures |
| D003933 | Diagnosis |
| D006306 | Health Surveys |
| D011795 | Surveys and Questionnaires |
Not provided
Not provided
This is a pragmatic cluster randomized control trial with randomizing clinic and with wavier of consent for human subjects. The data collection is from the EHR. There is no research data collection outside the EHR.
Not provided
Not provided
Not provided
|
|
| 12 months after index visit |
| BG001 | Passive Digital Marker (PDM) | Passive Digital Marker (PDM): Electronic Health Record Data from those clinics randomized to PDM will be run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. |
| BG002 | Passive Digital Marker (PDM) + Quick Dementia Rating Scale (QDRS) | Patients in the primary care clinics randomized to PDM+QDRS will have Electronic Health Record Data of their patients run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. In addition, patients from these clinics will have their patients complete the QDRS, a validated patient reported outcome (PRO) tool. This combined approach will assess the value of early detection of ADRD and if the annual well visit can overcome the barriers related to early detection of ADRD. |
| BG003 | Total | Total of all reporting groups |
| years |
|
| Sex/Gender, Customized | Sex at birth. | Count of Participants | Participants | No |
|
| Race (NIH/OMB) | Count of Participants | Participants |
|
| OG001 | Passive Digital Marker (PDM) | Passive Digital Marker (PDM): Electronic Health Record Data from those clinics randomized to PDM will be run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. |
| OG002 | Passive Digital Marker (PDM) + Quick Dementia Rating Scale (QDRS) | Patients in the primary care clinics randomized to PDM+QDRS will have Electronic Health Record Data of their patients run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. In addition, patients from these clinics will have their patients complete the QDRS, a validated patient reported outcome (PRO) tool. This combined approach will assess the value of early detection of ADRD and if the annual well visit can overcome the barriers related to early detection of ADRD. |
|
|
|
| Secondary | 12-Month Cumulative Incidence of ADRD Services | The secondary outcome measures is receipt of any services related to cognitive diagnostic assessment in the post Annual Wellness Visit (index) period that providers may order to diagnose or exclude ADRD. Specifically, the metrics of diagnostic assessment are evaluated as proportions of patients with a record of 1 or more of:
| 9 clinics were randomized, and patients were treated as per the randomization arm (3 clinics per arm) | Posted | Number | Participants with ADRD related servicess | 12 months after index visit |
|
|
|
|
| 26 |
| 1,724 |
| 561 |
| 1,724 |
| 0 |
| 1,724 |
| EG001 | Passive Digital Marker (PDM) | Passive Digital Marker (PDM): Electronic Health Record Data from those clinics randomized to PDM will be run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. Passive Digital Marker for screening for ADRD: Patients in the primary care clinics randomized to PDM+QDRS will have Electronic Health Record Data of their patients run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. In addition, patients from these clinics will have their patients complete the QDRS, a validated patient reported outcome (PRO) tool. This combined approach will assess the value of early detection of ADRD and if the annual well visit can overcome the barriers related to early detection of ADRD. | 7 | 1,300 | 398 | 1,300 | 0 | 1,300 |
| EG002 | Passive Digital Marker (PDM) + Quick Dementia Rating Scale (QDRS) | Patients in the primary care clinics randomized to PDM+QDRS will have Electronic Health Record Data of their patients run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. In addition, patients from these clinics will have their patients complete the QDRS, a validated patient reported outcome (PRO) tool. This combined approach will assess the value of early detection of ADRD and if the annual well visit can overcome the barriers related to early detection of ADRD. Passive Digital Marker for screening for ADRD: Patients in the primary care clinics randomized to PDM+QDRS will have Electronic Health Record Data of their patients run through the PDM, a machine learning algorithm which can predict ADRD one year and three years prior to its onset. In addition, patients from these clinics will have their patients complete the QDRS, a validated patient reported outcome (PRO) tool. This combined approach will assess the value of early detection of ADRD and if the annual well visit can overcome the barriers related to early detection of ADRD. | 25 | 2,301 | 816 | 2,301 | 0 | 2,301 |
| Positive for PDM and had ER visit | General disorders | Systematic Assessment |
|
| Positive for PDM and had PCC visit | General disorders | Systematic Assessment |
|
| Positive for PDM and had Memory clinic visit | General disorders | Systematic Assessment |
|
| Positive for PDM and had NEW Dementia Diagnosis | General disorders | Systematic Assessment |
|
| Positive for PDM and had NEW Depression Diagnosis | General disorders | Systematic Assessment |
|
| Positive for PDM and had NEW Suicidal Ideation Diagnosis | General disorders | Systematic Assessment |
|
| Positive for PDM and had NEW significant incapacity Diagnosis | General disorders | Systematic Assessment |
|
Not provided
Not provided
| D024801 |
| Tauopathies |
| D019636 | Neurodegenerative Diseases |
| D019965 | Neurocognitive Disorders |
| D001523 | Mental Disorders |
| D003625 | Data Collection |
| D004812 | Epidemiologic Methods |
| D008919 | Investigative Techniques |
| D003954 | Diagnostic Services |
| D011314 | Preventive Health Services |
| D006296 | Health Services |
| D005159 | Health Care Facilities Workforce and Services |
| D017531 | Health Care Evaluation Mechanisms |
| D011787 | Quality of Health Care |
| D017530 | Health Care Quality, Access, and Evaluation |
| D011634 | Public Health |
| D004778 | Environment and Public Health |
| D015980 | Public Health Practice |
| D019538 | Health Care Surveys |
| D006302 | Health Services Research |
| D006285 | Health Planning |
| D004472 | Health Care Economics and Organizations |
| D063868 | Patient Outcome Assessment |
| D017063 | Outcome Assessment, Health Care |
| D010043 | Outcome and Process Assessment, Health Care |
| D006298 | Health Services Administration |
| 0.919 |
The p-value is adjusted for multiple comparisons and the a priori threshold for statistical significance is 0.05 |
| Odds Ratio (OR) |
| 1.02 |
| 2-Sided |
| 95 |
| 0.69 |
| 1.50 |
| Superiority |