Improving emergency department patient-doctor conversation through an artificial intelligence symptom taking tool: an action-oriented design pilot study

Abstract

IMPORTANCECommunication between patients and healthcare professionals is frequently challenging in the crowded emergency department (ED), with few opportunities to develop rapport or empathy. Digital tools for patients and physicians have been proposed as helpful but their utility is not established.OBJECTIVETo evaluate a patient-facing digital symptom and history taking, as well as handover tool in the waiting room.DESIGNA two-phase, questionnaire-based quality improvement study. Phase I observations guided iterative improvement, which was then further evaluated in Phase II.SETTINGED of a German tertiary referral and major trauma hospital providing interdisciplinary treatment for an average of 120 patients daily.PARTICIPANTSAll patients who were willing/able to provide consent, excluding patients: (i) with severe injury/illness requiring immediate treatment; (ii) with traumatic injury; (iii) incapable of completing a health assessment; or, (iv) under 18 years old. Of 1699 patients presenting to the ED, 815 were eligible based on triage level. With available recruitment staff, 135 were approached, of whom 81 were included in the study.INTERVENTION/OBSERVATIONPatients entered information into the tool, which generated a handover report to be accessed via a clinician dashboard. All users completed evaluation questionnaires. Clinicians were trained to observationally assess the tool as a prototype, without relying upon it for clinical care.MAIN OUTCOMES AND MEASURESPatient and clinician Likert scale ratings of tool performance.RESULTSRespondents were strongly positive in endorsing the tool’s usefulness in facilitating conversation (75% of patients, 73% physicians, 100% nurses). Nurses judged the tool as potentially time saving, whilst physicians assessed it as time saving only in some ED medical specialisms (e.g. Surgery). Patients understood the tool questions and reported high usability. The proportion of patients, physicians and nurses who would recommend the tool was 78%, 53% and 76%.CONCLUSIONS AND RELEVANCEThe system has clear potential to improve patient-HCP interaction and make efficiency savings in the ED. Future research and development will extend the range of patients for which the history collection has clinical utility.Key PointsQuestionCan a patient-facing digital symptom and clinical history taking tool provide conversational support, aid in symptom taking, facilitate record keeping, and lead to improved rapport between patients, physicians and nurses in the emergency department (ED)?FindingsAcceptability was high, with improved rapport experienced 90% of the time for patients, 73% for physicians and 100% for nurses. Nurses assessed the tool as having workflow benefit through potential time saving. Physicians assessed the current tool design as providing time saving in certain ED medical specialisms including Surgery.MeaningThe patient-facing tool for symptom and history taking provided meaningful conversation support and showed potential for efficiency savings, however, further research and testing is required before time savings can be consistently delivered to ED clinicians across the range of relevant ED medical specialisms.

Optimization of Patient Flow in Urgent Care Centers Using a Digital Tool for Recording Patient Symptoms and History: Simulation Study

“…A 2019 pilot involving structured interviews with 5 ED clinicians who viewed the handover report produced by the app estimated a time saving between 4 and 6 minutes (personal communication by email of unpublished product development data, Joseph Wolanski, Ada Health GmbH). Finally, in an observational study, time savings in the ED were estimated in the range of 2.5-5 minutes by triage nurses and physicians [ 13 ]. Based on these data, a range of potential time savings were modeled in this study.…”

“…Utilization was defined as the ratio of the time the health care professionals are occupied to the total simulated time. Based on the previous study [ 13 ], we used a range of time savings by the app for triage (2.5, 3, 3.5, 4, 4.5, and 5 minutes) and for consultation (1.5, 2, 2.5, 3, and 3.5 minutes) to parameterize the model. We simulated 33 scenarios, including the baseline setting.…”

“…In the ED setting, a waiting room–based patient self-symptom and history-taking app (Ada Health, Germany) facilitated patient-to-health care professional communication, and triage nurses perceived this app as also having a workflow benefit by saving time [ 13 ]. The tool uses a probabilistic reasoning engine to collect demographic information, medical history, and symptoms.…”

The potential for digital patient symptom recording through symptom assessment applications to optimize patient flow and reduce waiting times in Urgent Care Centers: a simulation study

“…Were history taking to be performed by a digital symptom assessment application by patients in the waiting room, this might enable professionals to save time and treat more patients [9]. One such tool, Ada uses a probabilistic reasoning engine to collect demographic information, medical history, and symptoms.…”

“…A 2019 pilot conducted structured interviews with 5 ED clinicians, who viewed the handover report produced by the app and estimated a time saving of between 4-6 minutes (unpublished data). Finally, in an observational study time savings in the ED were estimated in the range of 2.5-5 minutes by triage nurses and physicians [9]. Setting Model Parameters -Overcrowding Firstly, we simulated the flow with different arrival rates to cause overcrowding, defined as more than 5 patients waiting for staff.…”