Taking a History: Man versus Computer

As noted in a previous blog (The future of gastrointestinal disease and symptom … – gutsandgrowth), a well-designed computer program (Link: Computer-generated history) allows GI patients to provide a history that is better than a history taken by a physician.

Here’s a link: LA Times Business review of this report

Here’s the abstract of the study:

Computer-Generated Vs. Physician-Documented History of Present Illness (HPI): Results of a Blinded Comparison

Christopher V Almario, William Chey, Aung Kaung, Cynthia Whitman, Garth Fuller, Mark Reid, Ken Nguyen, Roger Bolus, Buddy Dennis, Rey Encarnacion, Bibiana Martinez, Jennifer Talley, Rushaba Modi, Nikhil Agarwal, Aaron Lee, Scott Kubomoto, Gobind Sharma, Sally Bolus, Lin Chang and Brennan M R Spiegel


Healthcare delivery now mandates shorter visits with higher documentation requirements, undermining the patient–provider interaction. To improve clinic visit efficiency, we developed a patient–provider portal that systematically collects patient symptoms using a computer algorithm called Automated Evaluation of Gastrointestinal Symptoms (AEGIS). AEGIS also automatically “translates” the patient report into a full narrative history of present illness (HPI). We aimed to compare the quality of computer-generated vs. physician-documented HPIs.


We performed a cross-sectional study with a paired sample design among individuals visiting outpatient adult gastrointestinal (GI) clinics for evaluation of active GI symptoms. Participants first underwent usual care and then subsequently completed AEGIS. Each individual thereby had both a physician-documented and a computer-generated HPI. Forty-eight blinded physicians assessed HPI quality across six domains using 5-point scales: (i) overall impression, (ii) thoroughness, (iii) usefulness, (iv) organization, (v) succinctness, and (vi) comprehensibility. We compared HPI scores within patient using a repeated measures model.


Seventy-five patients had both computer-generated and physician-documented HPIs. The mean overall impression score for computer-generated HPIs was higher than physician HPIs (3.68 vs. 2.80; P<0.001), even after adjusting for physician and visit type, location, mode of transcription, and demographics. Computer-generated HPIs were also judged more complete (3.70 vs. 2.73; P<0.001), more useful (3.82 vs. 3.04; P<0.001), better organized (3.66 vs. 2.80; P<0.001), more succinct (3.55 vs. 3.17; P<0.001), and more comprehensible (3.66 vs. 2.97; P<0.001).


Computer-generated HPIs were of higher overall quality, better organized, and more succinct, comprehensible, complete, and useful compared with HPIs written by physicians during usual care in GI clinics.