This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in JMIR Formative Research, is properly cited. The complete bibliographic information, a link to the original publication on https://formative.jmir.org, as well as this copyright and license information must be included.
A potential benefit of electronic health records (EHRs) is that they could potentially save clinician time and improve documentation by auto-generating the history of present illness (HPI) in partnership with patients prior to the clinic visit. We developed an online patient portal called AEGIS (Automated Evaluation of Gastrointestinal [GI] Symptoms) that systematically collects patient GI symptom information and then transforms the data into a narrative HPI that is available for physicians to review in the EHR prior to seeing the patient.
This study aimed to compare whether use of an online GI symptom history taker called AEGIS improves physician-centric outcomes vs usual care.
We conducted a pragmatic controlled trial among adults aged ≥18 years scheduled for a new patient visit at 4 GI clinics at an academic medical center. Patients who completed AEGIS were matched with controls in the intervention period who did not complete AEGIS as well as controls who underwent usual care in the pre-intervention period. Of note, the pre-intervention control group was formed as it was not subject to contamination bias, unlike for post-intervention controls. We then compared the following outcomes among groups: (1) documentation of alarm symptoms, (2) documentation of family history of GI malignancy, (3) number of follow-up visits in a 6-month period, (4) number of tests ordered in a 6-month period, and (5) charting time (difference between appointment time and time the encounter was closed). Multivariable regression models were used to adjust for potential confounding.
Of the 774 patients who were invited to complete AEGIS, 116 (15.0%) finished it prior to their visit. The 116 AEGIS patients were then matched with 343 and 102 controls in the pre- and post-intervention periods, respectively. There were no statistically significant differences among the groups for documentation of alarm symptoms and GI cancer family history, number of follow-up visits and ordered tests, or charting time (all
Use of a validated online HPI-generation portal did not improve physician documentation or reduce workload. Given universal adoption of EHRs, further research examining how to optimally leverage patient portals for improving outcomes are needed.
To facilitate communication between patients and physicians in electronic health record (EHR)–integrated environments, we developed an online patient portal (MyGiHealth) that uses a computer algorithm called Automated Evaluation of Gastrointestinal (GI) Symptoms (AEGIS) to systematically collect patients’ symptom information before the clinic visit. Once collected, the data are transformed into a full narrative history of present illness (HPI) that clinicians can review prior to meeting the patient. While our prior studies noted that AEGIS creates higher quality HPIs and collects more alarm features vs physicians [
We performed a pragmatic controlled study among adults aged ≥18 years scheduled for a new patient visit at an academic GI teaching practice and 3 community-based GI clinics at Cedars-Sinai Medical Center. This study was approved by the Cedars-Sinai Institutional Review Board, Los Angeles, CA (Pro45243).
During the intervention period (April 17, 2017-February 7, 2018), patients were invited via email to complete AEGIS via the MyGiHealth app 1 week prior to their visit. We describe AEGIS elsewhere [
Sample Automated Evaluation of Gastrointestinal Symptoms (AEGIS) history of present illness (HPI) [
Once recruitment ceased, 5 resident physicians reviewed patient charts and collected outcomes data using a REDCap data abstraction sheet [
Statistical analyses were performed using Stata 13.1 (StataCorp LP, College Station, TX). A two-tailed
Of the 774 patients invited to complete AEGIS (
Predictors of completing the Automated Evaluation of Gastrointestinal Symptoms (AEGIS) prior to the clinic visit (N=774).
Variable | Completed AEGIS (n=116) | ORa (95% CI)b | |||
Age (years), mean (SD) | 49.9 (16.1) | 0.985 (0.972-0.998) | |||
|
|
|
|||
|
Male | 45 (14.9) | reference | ||
|
Female | 71 (15.1) | 0.99 (0.66-1.51) | ||
|
|
|
|||
|
Non-Hispanic white | 83 (17.9) | Reference | ||
|
Non-Hispanic black | 11 (11.0) | 0.57 (0.29-1.13) | ||
|
Latino | 10 (13.7) | 0.66 (0.32-1.36) | ||
|
Non-Hispanic Asian | 5 (7.3) | 0.33 (0.13-0.85) | ||
|
Other/unknown | 7 (10.5) | 0.48 (0.21-1.11) | ||
|
|
|
|||
|
Resident/fellow GIc clinic | 19 (17.4) | Reference | ||
|
Physician A | 37 (18.2) | 1.08 (0.58-2.02) | ||
|
Physician B | 29 (12.7) | 0.68 (0.36-1.30) | ||
|
Physician C | 31 (13.3) | 0.74 (0.38-1.42) |
aOR: odds ratio.
bThe logistic regression model adjusted for all covariates in the table.
cGI: gastrointestinal.
Patients who completed AEGIS (n=116) were matched with 343 patients from the pre-intervention period and 102 from the intervention period who did not complete AEGIS.
Demographics of those in the matched cohort analysis (N=561).
Variable | Control group: pre-AEGISa period (n=343) | Control group: did not complete AEGIS (n=102) | Intervention group: completed AEGIS (n=116) |
|
|||||
Age (years), mean (SD) | 51.4 (16.1) | 53.7 (16.2) | 49.9 (16.1) | .21 | |||||
|
|
|
|
.51 | |||||
|
Male | 136 (39.7) | 34 (33.3) | 45 (38.8) | |||||
|
Female | 207 (60.4) | 68 (66.7) | 71 (61.2) | |||||
|
|
|
|
.25 | |||||
|
Non-Hispanic white | 264 (77.0) | 86 (84.3) | 83 (71.6) | |||||
|
Non-Hispanic black | 35 (10.2) | 7 (6.9) | 11 (9.5) | |||||
|
Latino | 23 (6.7) | 2 (2.0) | 10 (8.6) | |||||
|
Non-Hispanic Asian | 10 (2.9) | 5 (4.9) | 5 (4.3) | |||||
|
Other/unknown | 11 (3.2) | 2 (2.0) | 7 (6.0) | |||||
|
|
|
|
.67 | |||||
|
Resident/fellow GIc clinic | 43 (12.5) | 9 (8.8) | 19 (16.4) | |||||
|
Physician A | 112 (32.7) | 30 (29.4) | 37 (31.9) | |||||
|
Physician B | 90 (26.2) | 28 (27.5) | 29 (25.0) | |||||
|
Physician C | 98 (28.6) | 35 (34.3) | 31 (26.7) | |||||
|
|
|
|
|
|||||
|
Abdominal pain | 77 (22.5) | 27 (26.5) | 28 (24.1) | .69 | ||||
|
Anemia evaluation | 2 (0.6) | 1 (1.0) | 0 (0) | .60 | ||||
|
Bloating | 30 (8.8) | 17 (16.7) | 21 (18.1) | .008 | ||||
|
Blood in stool | 18 (5.3) | 2 (2.0) | 5 (4.3) | .37 | ||||
|
Bowel incontinence | 2 (0.6) | 1 (1.0) | 1 (0.9) | .90 | ||||
|
Colorectal cancer screening | 101 (29.5) | 25 (24.5) | 34 (29.3) | .61 | ||||
|
Constipation | 48 (14.0) | 13 (12.8) | 19 (16.4) | .73 | ||||
|
Diarrhea | 42 (12.2) | 10 (9.8) | 17 (14.7) | .55 | ||||
|
Dysphagia | 15 (4.4) | 1 (1.0) | 4 (3.5) | .27 | ||||
|
Gastroesophageal reflux disease | 46 (13.4) | 15 (14.7) | 33 (28.5) | .001 | ||||
|
Inflammatory bowel disease | 19 (5.5) | 4 (3.9) | 6 (5.2) | .81 | ||||
|
Liver disease | 2 (0.6) | 1 (1.0) | 1 (0.9) | .90 | ||||
|
Nausea/vomiting | 25 (7.3) | 9 (8.8) | 8 (6.9) | .84 | ||||
|
Rectal pain | 2 (0.6) | 0 (0) | 2 (1.7) | .29 | ||||
|
Other | 47 (13.7) | 19 (18.6) | 16 (13.8) | .45 |
aAEGIS: Automated Evaluation of Gastrointestinal Symptoms.
b
cGI: gastrointestinal.
In
Physician-related outcomes according to study group (N=561).
Variable | Control group: pre-AEGISa period (n=343; reference) | Control group: did not complete AEGIS (n=102) | Adjusted |
Intervention group: completed AEGIS (n=116) | Adjusted |
Documentation of an alarm symptom in initial noteb, n (%) | 61 (17.8) | 22 (21.6) | .18 | 18 (15.5) | .39 |
Documentation of GIc cancer family history in initial noteb, n (%) | 64 (18.7) | 20 (19.6) | .86 | 27 (23.3) | .28 |
Charting time, which is the time until initial EHRd chart encounter was closede (hours), median (IQR) | 3.1 (1.4-9.2) | 3.3 (1.0-12.7) | .34 | 3.7 (1.1-10.0) | .58 |
Number of follow-up visits within the 6-month periodf, median (IQR) | 0 (0-1) | 0 (0-0) | .22 | 0 (0-1) | .11 |
Number of tests ordered within the 6-month periodg, median (IQR) | 1 (1-3) | 1 (0-2) | .21 | 1 (0-3) | .85 |
aAEGIS: Automated Evaluation of Gastrointestinal Symptoms.
bLogistic regression model adjusted for group assignment, patient age, sex, race/ethnicity, and clinic.
cGI: gastrointestinal.
dEHR: electronic health record.
eLinear regression model adjusted for group assignment, patient age, sex, race/ethnicity, and clinic. Patients seen in the resident or fellow GI clinic (n=71) were excluded from this analysis as trainees first needed to complete their note before attendings could review or edit the note and close the encounter. Patients of Physicians A-C who were seen earlier or later than their originally scheduled appointment time (n=92) were also excluded from this analysis.
fZero-inflated negative binomial regression model adjusted for group assignment, patient age, sex, race/ethnicity, and clinic.
gNegative binomial regression model adjusted for group assignment, patient age, sex, race/ethnicity, and clinic.
We discovered that uptake of AEGIS was low, as only 15% of patients accessed the online portal. Surprisingly, this rate was lower than that seen in our prior AEGIS trial (37%) focused on patient-centric outcomes [
While AEGIS was built to enhance patient-physician communication by systematically collecting salient components of the history, one-time use of the app did not increase documentation of alarm symptoms or family history of GI malignancy in the initial note. This suggests that physicians in our study may adequately screen for and document relevant red flags and family history
Of note, we previously found that AEGIS collected more alarm features when compared to physicians [
A limitation of our study was that we could not fully assess whether and how closely physicians reviewed the AEGIS reports in the EHR. While 40.5% of physicians’ notes for the intervention patients contained a portion of the AEGIS report, we do not know how rigorously they reviewed the report after copying it into their notes. On the other hand, for the remaining patients, it is possible that clinicians thoroughly read the AEGIS report in the EHR but chose to not copy and paste it into their official consultant notes. Development of novel, effective methods for alerting and assessing how clinicians use newly uploaded, app-generated data in the EHR and that maximize its use at the point of care are urgently needed. Another limitation was that AEGIS was administered as a one-time intervention; longitudinal use of the app for tracking symptom severity could have impacted outcomes such as numbers of follow-up visits and ordered tests. Notably, longitudinal symptom monitoring via a portal decreased emergency room visits and improved survival among patients with metastatic cancer [
In summary, we found that uptake of AEGIS was low, as less than 1 in 6 patients completed it before their visit. Moreover, one-time use of a carefully developed and validated patient-provider portal did not improve documentation of key elements of the note nor reduce clinician work burden. This is disappointing as it is well known that the EHR has greatly increased physician charting time [
Supplementary Figure 1. Sample email sent to physicians the day before their clinic notifying them of the patients that completed AEGIS.
Supplementary Table 1. Demographics of the cohort invited to complete AEGIS (N=774).
Automated Evaluation of Gastrointestinal Symptoms
electronic health record
gastrointestinal
history of present illness
odds ratio
This study was funded by a Junior Faculty Development Grant from the American College of Gastroenterology awarded to CVA. CVA and BMRS are supported by a CTSI grant from the NIH/NCATS UL1TR001881-01. CVA is also supported by a loan repayment award from the NIH/NIDDK L30 DK106734. Support for the MyGiHealth portal that administers AEGIS was obtained from Ironwood Pharmaceuticals. The Cedars-Sinai Center for Outcomes Research and Education (CS-CORE) is supported by The Marc and Sheri Rapaport Fund for Digital Health Sciences & Precision Health.
BMRS has served on advisory boards and received grant support from Ironwood Pharmaceuticals. CVA has a stock option grant in My Total Health. The remaining authors do not have any relevant disclosures.