Trial Outcomes & Findings for Encouraging Flu Vaccination Among High-Risk Patients Identified by ML (NCT NCT04323137)
NCT ID: NCT04323137
Last Updated: 2024-12-30
Results Overview
Patient received a flu vaccination
COMPLETED
NA
117649 participants
Through the the end of the flu season (May 31st 2021), approximately 9 months assessment duration
2024-12-30
Participant Flow
Participant milestones
| Measure |
Control
This group receives no additional pro-vaccination intervention beyond the health system's normal efforts. Although some patients are currently targeted for flu vaccination encouragement due to a non-ML assessment that they are at high risk for complications, these patients are not told that they are at high risk or that they have been targeted.
|
High Risk Only
This group receives messages telling them they have been identified to be at high risk for flu complications without specifying how or why the health system believes this to be the case.
Risk reduction: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Medical Records
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Algorithm
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records by an AI/ML system.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
Algorithm-based recommendation: Mailed letter, SMS, and/or patient portal message
|
Sub-threshold Patients
Patients in this group are in the top 11-20% of risk for flu and complications, slightly lower risk than those included in the intervention, who are in the top 10% of risk for flu and complications. This group of patients does not receive an intervention, but is monitored for flu shots as a comparison to target patients.
|
Household Members
This group of patients share an address with target high-risk patients (in arms 1-4). This group does not receive an intervention but is monitored for spillover effects of the intervention.
Note that some household members of target patients were also sub-threshold risk. Additionally, some of these patients were household members of more than one target patient.
The numbers reported here reflect unique household members who were not also sub-threshold risk patients.
|
|---|---|---|---|---|---|---|
|
Overall Study
STARTED
|
11667
|
11639
|
11652
|
11644
|
46898
|
24149
|
|
Overall Study
COMPLETED
|
11667
|
11639
|
11652
|
11644
|
46898
|
24149
|
|
Overall Study
NOT COMPLETED
|
0
|
0
|
0
|
0
|
0
|
0
|
Reasons for withdrawal
Withdrawal data not reported
Baseline Characteristics
Encouraging Flu Vaccination Among High-Risk Patients Identified by ML
Baseline characteristics by cohort
| Measure |
Control
n=11667 Participants
This group receives no additional pro-vaccination intervention beyond the health system's normal efforts. Although some patients are currently targeted for flu vaccination encouragement due to a non-ML assessment that they are at high risk for complications, these patients are not told that they are at high risk or that they have been targeted.
|
High Risk Only
n=11639 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications without specifying how or why the health system believes this to be the case.
Risk reduction: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Medical Records
n=11652 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Algorithm
n=11644 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records by an AI/ML system.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
Algorithm-based recommendation: Mailed letter, SMS, and/or patient portal message
|
Sub-threshold Patients
n=46898 Participants
Patients in this group are in the top 11-20% of risk for flu and complications, slightly lower risk than those included in the intervention, who are in the top 10% of risk for flu and complications. This group of patients does not receive an intervention, but is monitored for flu shots as a comparison to target patients.
|
Household Members
n=24149 Participants
This group of patients share an address with target high-risk patients (in arms 1-4). This group does not receive an intervention but is monitored for spillover effects of the intervention.
Note that some household members of target patients were also sub-threshold risk. Additionally, some of these patients were household members of more than one target patient.
The numbers reported here reflect unique household members who were not also sub-threshold risk patients.
|
Total
n=117649 Participants
Total of all reporting groups
|
|---|---|---|---|---|---|---|---|
|
Age, Continuous
|
58.0 years
STANDARD_DEVIATION 19.3 • n=5 Participants
|
57.9 years
STANDARD_DEVIATION 19.3 • n=7 Participants
|
57.9 years
STANDARD_DEVIATION 19.2 • n=5 Participants
|
57.6 years
STANDARD_DEVIATION 19.4 • n=4 Participants
|
55.7 years
STANDARD_DEVIATION 19.5 • n=21 Participants
|
47.1 years
STANDARD_DEVIATION 20 • n=8 Participants
|
54.8 years
STANDARD_DEVIATION 19.9 • n=8 Participants
|
|
Sex: Female, Male
Female
|
7535 Participants
n=5 Participants
|
7514 Participants
n=7 Participants
|
7533 Participants
n=5 Participants
|
7438 Participants
n=4 Participants
|
29226 Participants
n=21 Participants
|
10744 Participants
n=8 Participants
|
69990 Participants
n=8 Participants
|
|
Sex: Female, Male
Male
|
4132 Participants
n=5 Participants
|
4125 Participants
n=7 Participants
|
4119 Participants
n=5 Participants
|
4206 Participants
n=4 Participants
|
17672 Participants
n=21 Participants
|
13405 Participants
n=8 Participants
|
47659 Participants
n=8 Participants
|
|
Ethnicity (NIH/OMB)
Hispanic or Latino
|
402 Participants
n=5 Participants
|
457 Participants
n=7 Participants
|
395 Participants
n=5 Participants
|
413 Participants
n=4 Participants
|
1684 Participants
n=21 Participants
|
1113 Participants
n=8 Participants
|
4464 Participants
n=8 Participants
|
|
Ethnicity (NIH/OMB)
Not Hispanic or Latino
|
11253 Participants
n=5 Participants
|
11159 Participants
n=7 Participants
|
11240 Participants
n=5 Participants
|
11207 Participants
n=4 Participants
|
45120 Participants
n=21 Participants
|
22777 Participants
n=8 Participants
|
112756 Participants
n=8 Participants
|
|
Ethnicity (NIH/OMB)
Unknown or Not Reported
|
12 Participants
n=5 Participants
|
23 Participants
n=7 Participants
|
17 Participants
n=5 Participants
|
24 Participants
n=4 Participants
|
94 Participants
n=21 Participants
|
259 Participants
n=8 Participants
|
429 Participants
n=8 Participants
|
|
Race/Ethnicity, Customized
American Indian or Alaska Native
|
22 Participants
n=5 Participants
|
21 Participants
n=7 Participants
|
15 Participants
n=5 Participants
|
22 Participants
n=4 Participants
|
47 Participants
n=21 Participants
|
32 Participants
n=8 Participants
|
159 Participants
n=8 Participants
|
|
Race/Ethnicity, Customized
Asian
|
32 Participants
n=5 Participants
|
37 Participants
n=7 Participants
|
28 Participants
n=5 Participants
|
31 Participants
n=4 Participants
|
189 Participants
n=21 Participants
|
124 Participants
n=8 Participants
|
441 Participants
n=8 Participants
|
|
Race/Ethnicity, Customized
Native Hawaiian or Other Pacific Islander
|
18 Participants
n=5 Participants
|
26 Participants
n=7 Participants
|
20 Participants
n=5 Participants
|
26 Participants
n=4 Participants
|
126 Participants
n=21 Participants
|
129 Participants
n=8 Participants
|
345 Participants
n=8 Participants
|
|
Race/Ethnicity, Customized
Black or African American
|
362 Participants
n=5 Participants
|
382 Participants
n=7 Participants
|
389 Participants
n=5 Participants
|
416 Participants
n=4 Participants
|
1603 Participants
n=21 Participants
|
1116 Participants
n=8 Participants
|
4268 Participants
n=8 Participants
|
|
Race/Ethnicity, Customized
White
|
11223 Participants
n=5 Participants
|
11159 Participants
n=7 Participants
|
11194 Participants
n=5 Participants
|
11136 Participants
n=4 Participants
|
44859 Participants
n=21 Participants
|
22674 Participants
n=8 Participants
|
112245 Participants
n=8 Participants
|
|
Race/Ethnicity, Customized
Unknown or Not Reported
|
10 Participants
n=5 Participants
|
14 Participants
n=7 Participants
|
6 Participants
n=5 Participants
|
13 Participants
n=4 Participants
|
74 Participants
n=21 Participants
|
72 Participants
n=8 Participants
|
189 Participants
n=8 Participants
|
|
Region of Enrollment
United States
|
11667 participants
n=5 Participants
|
11639 participants
n=7 Participants
|
11652 participants
n=5 Participants
|
11644 participants
n=4 Participants
|
46898 participants
n=21 Participants
|
24149 participants
n=8 Participants
|
44602 participants
n=8 Participants
|
PRIMARY outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Participants were excluded from analysis if they were vaccinated prior to the study start date or if they were contraindicated for flu vaccine.
Patient received a flu vaccination
Outcome measures
| Measure |
Control
n=9640 Participants
This group receives no additional pro-vaccination intervention beyond the health system's normal efforts. Although some patients are currently targeted for flu vaccination encouragement due to a non-ML assessment that they are at high risk for complications, these patients are not told that they are at high risk or that they have been targeted.
|
High Risk Only
n=9622 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications without specifying how or why the health system believes this to be the case.
Risk reduction: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Medical Records
n=9641 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Algorithm
n=9695 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records by an AI/ML system.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
Algorithm-based recommendation: Mailed letter, SMS, and/or patient portal message
|
|---|---|---|---|---|
|
Flu Vaccination Rate
|
4901 Participants
|
5042 Participants
|
5087 Participants
|
5090 Participants
|
PRIMARY outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Participants were excluded from analysis if they were vaccinated prior to the study start date or if they were contraindicated for flu vaccine.
Patient received a flu vaccination Note: For patients who received risk communications, those in the top 3% were always told they were in the top 3% of risk. Those in the top 4-10% of risk were randomized to be told that they were in the top 10% of risk or high risk. Control patients in the top 3% and top 4-10% of risk were allocated to the top 3% and randomized to either top 10% or high risk groups, respectively, at the same time as those in the patient contact groups, even though these control patients were not contacted.
Outcome measures
| Measure |
Control
n=9640 Participants
This group receives no additional pro-vaccination intervention beyond the health system's normal efforts. Although some patients are currently targeted for flu vaccination encouragement due to a non-ML assessment that they are at high risk for complications, these patients are not told that they are at high risk or that they have been targeted.
|
High Risk Only
n=9622 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications without specifying how or why the health system believes this to be the case.
Risk reduction: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Medical Records
n=9641 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Algorithm
n=9695 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records by an AI/ML system.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
Algorithm-based recommendation: Mailed letter, SMS, and/or patient portal message
|
|---|---|---|---|---|
|
Flu Vaccination Rate by Risk Level
Top 3%
|
1485 Participants
|
1536 Participants
|
1513 Participants
|
1537 Participants
|
|
Flu Vaccination Rate by Risk Level
Top 10%
|
1658 Participants
|
1749 Participants
|
1795 Participants
|
1799 Participants
|
|
Flu Vaccination Rate by Risk Level
High risk
|
1758 Participants
|
1757 Participants
|
1779 Participants
|
1754 Participants
|
PRIMARY outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Flu cases and other related outcomes (flu complications, ER visits for flu, hospitalizations for flu) in the 2020-2021 flu season were too low to detect any meaningful differences across study arms. Therefore, the study team did not collect data for this outcome.
Patient received a flu diagnosis via a positive PCR/antigen/molecular test
Outcome measures
Outcome data not reported
SECONDARY outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Flu cases and other related outcomes (flu complications, ER visits for flu, hospitalizations for flu) in the 2020-2021 flu season were too low to detect any meaningful differences across study arms. Therefore, the study team did not collect data for this outcome.
Patient received a diagnosis that was likely flu, as assessed via ICD codes or Tamiflu administration or positive PCR/antigen/molecular test. Note that this outcome is a superset of the "high confidence flu diagnosis rate" outcome.
Outcome measures
Outcome data not reported
SECONDARY outcome
Timeframe: Through 3 months after the end of the flu season (August 31st 2021), approximately 12 months assessment durationPopulation: Flu cases and other related outcomes (flu complications, ER visits for flu, hospitalizations for flu) in the 2020-2021 flu season were too low to detect any meaningful differences across study arms. Therefore, the study team did not collect data for this outcome.
Patient was diagnosed with flu-related complications
Outcome measures
Outcome data not reported
SECONDARY outcome
Timeframe: Within 12 months pre-intervention (Time 1) and within 12 months post-intervention (Time 2)Population: Flu cases and other related outcomes (flu complications, ER visits for flu, hospitalizations for flu) in the 2020-2021 flu season were too low to detect any meaningful differences across study arms. Therefore, the study team did not collect data for this outcome.
Number of patient visits to the ER, examining relative rate of visits across Time 1 and 2
Outcome measures
Outcome data not reported
SECONDARY outcome
Timeframe: Within 12 months pre-intervention (Time 1) and within 12 months post-intervention (Time 2)Population: Flu cases and other related outcomes (flu complications, ER visits for flu, hospitalizations for flu) in the 2020-2021 flu season were too low to detect any meaningful differences across study arms. Therefore, the study team did not collect data for this outcome.
Number of patient hospital visits, examining relative rate of visits across Time 1 and 2
Outcome measures
Outcome data not reported
SECONDARY outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Household members were excluded from analysis if they were vaccinated prior to the study start date or if they were contraindicated for flu vaccine. Household members who shared an address with multiple patients in the intervention were counted in this outcome once for every eligible target participant who shared their address.
Non-targeted fellow household members of targeted patients received a flu vaccination
Outcome measures
| Measure |
Control
n=7584 Participants
This group receives no additional pro-vaccination intervention beyond the health system's normal efforts. Although some patients are currently targeted for flu vaccination encouragement due to a non-ML assessment that they are at high risk for complications, these patients are not told that they are at high risk or that they have been targeted.
|
High Risk Only
n=7981 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications without specifying how or why the health system believes this to be the case.
Risk reduction: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Medical Records
n=7773 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Algorithm
n=7516 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records by an AI/ML system.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
Algorithm-based recommendation: Mailed letter, SMS, and/or patient portal message
|
|---|---|---|---|---|
|
Flu Vaccination Among Fellow Household Members
|
2136 Participants
|
2207 Participants
|
2165 Participants
|
2175 Participants
|
SECONDARY outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Flu cases and other related outcomes (flu complications, ER visits for flu, hospitalizations for flu) in the 2020-2021 flu season were too low to detect any meaningful differences across study arms. Therefore, the study team did not collect data for this outcome.
Non-targeted fellow household members of targeted patients received a flu diagnosis (via a positive PCR/antigen/molecular test)
Outcome measures
Outcome data not reported
SECONDARY outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Flu cases and other related outcomes (flu complications, ER visits for flu, hospitalizations for flu) in the 2020-2021 flu season were too low to detect any meaningful differences across study arms. Therefore, the study team did not collect data for this outcome.
Non-targeted fellow household members of targeted patients received a diagnosis that was likely flu (as assessed via ICD codes or Tamiflu administration or positive PCR/antigen/molecular test)
Outcome measures
Outcome data not reported
SECONDARY outcome
Timeframe: Through 3 months after the end of the flu season (August 31st 2021), approximately 12 months assessment durationPopulation: Flu cases and other related outcomes (flu complications, ER visits for flu, hospitalizations for flu) in the 2020-2021 flu season were too low to detect any meaningful differences across study arms. Therefore, the study team did not collect data for this outcome.
Non-targeted fellow household members of targeted patients were diagnosed with flu-related complications
Outcome measures
Outcome data not reported
SECONDARY outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Participants were excluded from analysis if they were vaccinated prior to the study start date or if they were contraindicated for flu vaccine.
Non-targeted sub-threshold risk patients received a flu vaccination
Outcome measures
| Measure |
Control
n=40030 Participants
This group receives no additional pro-vaccination intervention beyond the health system's normal efforts. Although some patients are currently targeted for flu vaccination encouragement due to a non-ML assessment that they are at high risk for complications, these patients are not told that they are at high risk or that they have been targeted.
|
High Risk Only
This group receives messages telling them they have been identified to be at high risk for flu complications without specifying how or why the health system believes this to be the case.
Risk reduction: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Medical Records
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Algorithm
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records by an AI/ML system.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
Algorithm-based recommendation: Mailed letter, SMS, and/or patient portal message
|
|---|---|---|---|---|
|
Flu Vaccination Among Those at Sub-threshold Risk
|
18268 Participants
|
—
|
—
|
—
|
SECONDARY outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Flu cases and other related outcomes (flu complications, ER visits for flu, hospitalizations for flu) in the 2020-2021 flu season were too low to detect any meaningful differences across study arms. Therefore, the study team did not collect data for this outcome.
Non-targeted sub-threshold risk patients received a flu diagnosis (via a positive PCR/antigen/molecular test)
Outcome measures
Outcome data not reported
SECONDARY outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Flu cases and other related outcomes (flu complications, ER visits for flu, hospitalizations for flu) in the 2020-2021 flu season were too low to detect any meaningful differences across study arms. Therefore, the study team did not collect data for this outcome.
Non-targeted sub-threshold risk patients received a diagnosis that was likely flu (as assessed via ICD codes or Tamiflu administration or positive PCR/antigen/molecular test)
Outcome measures
Outcome data not reported
SECONDARY outcome
Timeframe: Through 3 months after the end of the flu season (August 31st 2021), approximately 12 months assessment durationPopulation: Flu cases and other related outcomes (flu complications, ER visits for flu, hospitalizations for flu) in the 2020-2021 flu season were too low to detect any meaningful differences across study arms. Therefore, the study team did not collect data for this outcome.
Non-targeted sub-threshold risk patients were diagnosed with flu-related complications
Outcome measures
Outcome data not reported
POST_HOC outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Participants were excluded from analysis if they were vaccinated prior to the study start date or if they were contraindicated for flu vaccine.
Patient received a flu vaccination
Outcome measures
| Measure |
Control
n=9640 Participants
This group receives no additional pro-vaccination intervention beyond the health system's normal efforts. Although some patients are currently targeted for flu vaccination encouragement due to a non-ML assessment that they are at high risk for complications, these patients are not told that they are at high risk or that they have been targeted.
|
High Risk Only
n=9622 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications without specifying how or why the health system believes this to be the case.
Risk reduction: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Medical Records
n=9641 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Algorithm
n=9695 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records by an AI/ML system.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
Algorithm-based recommendation: Mailed letter, SMS, and/or patient portal message
|
|---|---|---|---|---|
|
Flu Vaccination Rate by Race
American Indian or Alaska Native
|
6 Participants
|
9 Participants
|
6 Participants
|
7 Participants
|
|
Flu Vaccination Rate by Race
Asian
|
19 Participants
|
14 Participants
|
15 Participants
|
13 Participants
|
|
Flu Vaccination Rate by Race
Black or African American
|
115 Participants
|
134 Participants
|
143 Participants
|
142 Participants
|
|
Flu Vaccination Rate by Race
Native Hawaiian or Other Pacific Islander
|
5 Participants
|
9 Participants
|
7 Participants
|
7 Participants
|
|
Flu Vaccination Rate by Race
White
|
4751 Participants
|
4871 Participants
|
4916 Participants
|
4914 Participants
|
|
Flu Vaccination Rate by Race
Unknown
|
5 Participants
|
5 Participants
|
0 Participants
|
7 Participants
|
POST_HOC outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Participants were excluded from analysis if they were vaccinated prior to the study start date or if they were contraindicated for flu vaccine.
Patient received a flu vaccination
Outcome measures
| Measure |
Control
n=9640 Participants
This group receives no additional pro-vaccination intervention beyond the health system's normal efforts. Although some patients are currently targeted for flu vaccination encouragement due to a non-ML assessment that they are at high risk for complications, these patients are not told that they are at high risk or that they have been targeted.
|
High Risk Only
n=9622 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications without specifying how or why the health system believes this to be the case.
Risk reduction: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Medical Records
n=9641 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Algorithm
n=9695 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records by an AI/ML system.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
Algorithm-based recommendation: Mailed letter, SMS, and/or patient portal message
|
|---|---|---|---|---|
|
Flu Vaccination Rate by Gender
Female
|
3118 Participants
|
3245 Participants
|
3235 Participants
|
3197 Participants
|
|
Flu Vaccination Rate by Gender
Male
|
1783 Participants
|
1797 Participants
|
1852 Participants
|
1893 Participants
|
POST_HOC outcome
Timeframe: Through the the end of the flu season (May 31st 2021), approximately 9 months assessment durationPopulation: Participants were excluded from analysis if they were vaccinated prior to the study start date or if they were contraindicated for flu vaccine.
Patient received a flu vaccination
Outcome measures
| Measure |
Control
n=9640 Participants
This group receives no additional pro-vaccination intervention beyond the health system's normal efforts. Although some patients are currently targeted for flu vaccination encouragement due to a non-ML assessment that they are at high risk for complications, these patients are not told that they are at high risk or that they have been targeted.
|
High Risk Only
n=9622 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications without specifying how or why the health system believes this to be the case.
Risk reduction: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Medical Records
n=9641 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
|
High Risk Based on Algorithm
n=9695 Participants
This group receives messages telling them they have been identified to be at high risk for flu complications via analysis of their medical records by an AI/ML system.
Risk reduction: Mailed letter, SMS, and/or patient portal message
Medical records-based recommendation: Mailed letter, SMS, and/or patient portal message
Algorithm-based recommendation: Mailed letter, SMS, and/or patient portal message
|
|---|---|---|---|---|
|
Flu Vaccination Rate by Ethnicity
Hispanic or Latino
|
118 Participants
|
173 Participants
|
136 Participants
|
146 Participants
|
|
Flu Vaccination Rate by Ethnicity
Not Hispanic or Latino
|
4778 Participants
|
4860 Participants
|
4943 Participants
|
4938 Participants
|
|
Flu Vaccination Rate by Ethnicity
Unable to obtain
|
5 Participants
|
9 Participants
|
8 Participants
|
6 Participants
|
Adverse Events
Control
High Risk Only
High Risk Based on Medical Records
High Risk Based on Algorithm
Serious adverse events
Adverse event data not reported
Other adverse events
Adverse event data not reported
Additional Information
Results disclosure agreements
- Principal investigator is a sponsor employee
- Publication restrictions are in place