Computer versus physician identification of gastrointestinal alarm features

Christopher V Almario; William D Chey; Sentia Iriana; Francis Dailey; Karen Robbins; Anish V Patel; Mark Reid; Cynthia Whitman; Garth Fuller; Roger Bolus; Buddy Dennis; Rey Encarnacion; Bibiana Martinez; Jennifer Soares; Rushaba Modi; Nikhil Agarwal; Aaron Lee; Scott Kubomoto; Gobind Sharma; Sally Bolus; Lin Chang; Brennan M R Spiegel

doi:10.1016/j.ijmedinf.2015.07.006

Computer versus physician identification of gastrointestinal alarm features

Int J Med Inform. 2015 Dec;84(12):1111-7. doi: 10.1016/j.ijmedinf.2015.07.006. Epub 2015 Jul 26.

Authors

Christopher V Almario¹, William D Chey², Sentia Iriana³, Francis Dailey³, Karen Robbins³, Anish V Patel³, Mark Reid⁴, Cynthia Whitman⁵, Garth Fuller⁵, Roger Bolus⁶, Buddy Dennis⁷, Rey Encarnacion⁷, Bibiana Martinez⁸, Jennifer Soares⁸, Rushaba Modi⁹, Nikhil Agarwal⁹, Aaron Lee³, Scott Kubomoto³, Gobind Sharma³, Sally Bolus⁶, Lin Chang¹⁰, Brennan M R Spiegel¹¹

Affiliations

¹ Division of Gastroenterology, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Division of Gastroenterology, VA Greater Los Angeles Healthcare System, Los Angeles, CA, USA; Division of Digestive Diseases, UCLA, Los Angeles, CA, USA; Cedars-Sinai Center for Outcomes Research and Education (CS-CORE), Los Angeles, CA, USA.
² Division of Gastroenterology, University of Michigan, Ann Arbor, MI, USA.
³ Division of Gastroenterology, Cedars-Sinai Medical Center, Los Angeles, CA, USA.
⁴ Division of Gastroenterology, VA Greater Los Angeles Healthcare System, Los Angeles, CA, USA; Cedars-Sinai Center for Outcomes Research and Education (CS-CORE), Los Angeles, CA, USA.
⁵ Division of Gastroenterology, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Cedars-Sinai Center for Outcomes Research and Education (CS-CORE), Los Angeles, CA, USA.
⁶ Cedars-Sinai Center for Outcomes Research and Education (CS-CORE), Los Angeles, CA, USA.
⁷ UCLA Computing Technology Research Laboratory (CTRL), Los Angeles, CA, USA.
⁸ Division of Gastroenterology, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Division of Gastroenterology, VA Greater Los Angeles Healthcare System, Los Angeles, CA, USA; Cedars-Sinai Center for Outcomes Research and Education (CS-CORE), Los Angeles, CA, USA.
⁹ Division of Gastroenterology, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Division of Gastroenterology, VA Greater Los Angeles Healthcare System, Los Angeles, CA, USA; Division of Digestive Diseases, UCLA, Los Angeles, CA, USA.
¹⁰ Division of Digestive Diseases, UCLA, Los Angeles, CA, USA.
¹¹ Division of Gastroenterology, Cedars-Sinai Medical Center, Los Angeles, CA, USA; Division of Gastroenterology, VA Greater Los Angeles Healthcare System, Los Angeles, CA, USA; Cedars-Sinai Center for Outcomes Research and Education (CS-CORE), Los Angeles, CA, USA. Electronic address: Brennan.Spiegel@cshs.org.

Abstract

Objective: It is important for clinicians to inquire about "alarm features" as it may identify those at risk for organic disease and who require additional diagnostic workup. We developed a computer algorithm called Automated Evaluation of Gastrointestinal Symptoms (AEGIS) that systematically collects patient gastrointestinal (GI) symptoms and alarm features, and then "translates" the information into a history of present illness (HPI). Our study's objective was to compare the number of alarms documented by physicians during usual care vs. that collected by AEGIS.

Methods: We performed a cross-sectional study with a paired sample design among patients visiting adult GI clinics. Participants first received usual care by their physicians and then completed AEGIS. Each individual thus contributed both a physician-documented and computer-generated HPI. Blinded physician reviewers enumerated the positive alarm features (hematochezia, melena, hematemesis, unintentional weight loss, decreased appetite, and fevers) mentioned in each HPI. We compared the number of documented alarms within patient using the Wilcoxon signed-rank test.

Results: Seventy-five patients had both physician and AEGIS HPIs. AEGIS identified more patients with positive alarm features compared to physicians (53% vs. 27%; p<.001). AEGIS also documented more positive alarms (median 1, interquartile range [IQR] 0-2) vs. physicians (median 0, IQR 0-1; p<.001). Moreover, clinicians documented only 30% of the positive alarms self-reported by patients through AEGIS.

Conclusions: Physicians documented less than one-third of red flags reported by patients through a computer algorithm. These data indicate that physicians may under report alarm features and that computerized "checklists" could complement standard HPIs to bolster clinical care.

Keywords: Alarm features; Checklists; Patient-provider portal.

Publication types

Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't

MeSH terms

Algorithms*
Cross-Sectional Studies
Decision Support Systems, Clinical / organization & administration*
Diagnosis, Computer-Assisted / methods*
Electronic Health Records / organization & administration*
Gastrointestinal Diseases / diagnosis*
Humans
Medical History Taking / methods
Michigan
Observer Variation
Reproducibility of Results
Sensitivity and Specificity
Symptom Assessment / methods
User-Computer Interface*

Abstract

Publication types

MeSH terms

Grants and funding