Computer-assisted, Decision Making, General Practitioners, Patient Engagement
Conditions
Keywords
differential diagnosis, hospital outpatient clinics, clinical applications software
Brief summary
Single-center, unblinded, 2:1 parallel pseudo-randomized efficacy trial. In the intervention group only, resident physicians will be assisted by the automated medical history-taking device Diaana during their consultations in outpatient ambulatory unit of the Geneva University Hospital. In both groups, the differential diagnosis of the resident physician will be compared to the gold-standard diagnosis of the senior physician.
Detailed description
Automated medical history-taking devices (AMHTD) are emerging tools with the potential to increase the quality of medical consultations by providing physicians with an exhaustive, high-quality, standardized anamnesis and differential diagnosis. In this study, the investigators aimed to establish whether an AMHTD of interest, Diaana, allowed the physician to establish a more precise differential diagnosis. A single-center, unblinded, 2:1 parallel pseudo-randomized efficacy trial will be performed. A consultation follow-up is organized at 4-6 weeks, were the gold-standard diagnosis is established by the senior physician. The study will take place in the emergency outpatient unit of La Colline Hospital (Geneva, Switzerland) and include patients suffering from symptoms covered by Diaana. Patients in the intervention group will fulfill Dianna. Then, the resident physician will read Diaana summary, perform his consultation, and fulfill case report form, including his differential diagnosis. Then, the senior physician will see the patient and establish the gold-standard diagnosis. In the control group, the residents will directly establish a differential diagnosis, without the help of Diaana.
Interventions
DEVICEDiaana
Diaana, the AMHTD used, functions as follows: on the basis of an interactive questionnaire completed by the patient before the consultation, it performs an exhaustive anamnesis focused on the problem and proposes a panel of DDs with a high sensitivity. The artificial reasoning system of Diaana mimics how a specialist physician would reason to establish a DD. The information transmitted is in an easy-to-use form for the physician that includes a summary of the anamnesis centered on relevant elements from the questionnaire and a list of possible diagnoses with their emergency level, potential contributing factors, and first-line management proposals.
Sponsors
Adrien Schwitzguebel
Study design
Allocation
NON_RANDOMIZED
Intervention model
PARALLEL
Primary purpose
DIAGNOSTIC
Masking
NONE
Intervention model description
For each of the six resident physicians of the outpatients clinic, the 6 first eligible patients will be attributed to the control group (with access to Diaana), then the 12 next eligible patients will be attributed to the interventional group (with access to Diaana). There will therefore be 36 patients in the control group and 72 in the interventional group.
Eligibility
Sex/Gender
ALL
Age
16 Years to 65 Years
Healthy volunteers
No
Inclusion criteria
* Patients presenting to the emergency outpatient unit of La Colline hospital (Geneva, Switzerland) * Patients suffering from symptoms localized to the superior or inferior member, the back, hand the chest wall.
Exclusion criteria
* Strictly dermatologic concerns * Toes trauma (because the diagnosis of those conditions is generally obvious) * Medical condition considered as urgent * Inability to complete de digilatized Diaana form (sight problems, language, inability to use a tablet computer)
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Accuracy of the diagnosis established by the resident physician | At day 0 | The resident physician will select up to 5 diagnose in an exhaustive list, from the most to the least relevant. The accuracy of the diagnosis established will be measured as following: * 100% if the gold-standard diagnosis is in position#1 into the resident diagnosis list * 80% if the gond-standard diagnosis is in position#2 * 60% in position #3 * 40% in position #4 * 20% in position #5 * 0% if the gold-standard diagnosis absent of the resident diagnosis list A higher percentage is considered as a better outcome. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Consultation time | At day 0 | The resident's consultation (with and without the patient) will be measured by the research coordinator. Consultation time will be compared between groups. A shorter consultation time will be considered as a better outcome. |
| Patient satisfaction: Likert 1-4 scale | At day 0 | Into the experimental group, the patient's satisfaction will be evalatued on a Likert 1-4 scale. 1= fully dissatisfied; 2 = partially dissatisfied; 3 = partially satisfied; 4 = fully satisfied A higher score is considered as a better outcome. |
| Differential diagnosis established by Diaana | At day 0 | The Diaana system will select diagnoses in an exhaustive list. The percentage of cases were the gold-standard diagnosis is present into the differential diagnosis list will be measured. A higher percentage is a better outcome. |
Countries
Switzerland
Outcome results
None listed