Clinic Waiting Room-based Study of Swahili Language Artificial Intelligence-driven Symptom Assessments in Tanzanian Primary Health Care Facilities

NCT04958577 | Unknown

• 1 other identifier: AFYA
• Study Type: observational
• Target: 109
• Locations: 1 country
• Sites: 1

Brief Summary

This study will evaluate the accuracy of the condition suggestions and urgency advice of the Swahili language Ada symptom assessment application (SAA), when symptoms are input by a lay-person user and a medical professional; these SAA results will then be compared to the condition suggestions and urgency advice of different tiers of doctors and a "gold standard" created by a panel.

Conditions

Abdominal Pain/Gastrointestinal Issues; Lower Respiratory System Conditions; Upper Respiratory System Conditions; Mental Health Conditions; Ophthalmology Conditions; Orthopedic Conditions; Cardiovascular System Conditions; Genitourinary System Conditions; ENT Conditions; Dermatology Conditions; Gynecology/Obstetrics Conditions; Neurological Conditions

Outcome Measures

Primary Outcomes (1)

• Accuracy and Comprehensiveness measures of Ada WRA and HDA

  The condition-suggestion accuracy and comprehensiveness of the SAA, evaluated against the gold-standard differential diagnosis determined by the review panel, reported in the context of the accuracy of the usual care health practitioner.

  through study completion, an average of 4 months

Secondary Outcomes (3)

• Comparison of usual care doctor condition suggestions

  through study completion, an average of 4 months

• Urgency advice accuracy

  through study completion, an average of 4 months

• Questionnaire data insights

  through study completion, an average of 4 months

Study Arms (2)

Wing A (Ada WRA)

Patients in this group will be filling out the Ada assessment themselves and then heading to a normal consultation by first the usual care doctor and then the study-provided physician.

Device: Ada Waiting Room App (WRA) and Ada Diagnostic Support Application (HDA)

Wing B (Ada HDA)

Patients in this group will be asked questions from the Ada assessment by a health care practitioner and then heading to a normal consultation by first the usual care doctor and then the study-provided physician.

Device: Ada Waiting Room App (WRA) and Ada Diagnostic Support Application (HDA)

Interventions

Ada Waiting Room App (WRA) and Ada Diagnostic Support Application (HDA) DEVICE

This device is a medical device but will be used only observationally--this device takes a patient's symptoms into account by asking questions and gives a ranked list of likely conditions that the patient might have based on the answers to these questions. The assessment report also includes urgency advice levels, that is, which care the patient should proceed to based on the condition suggestions. The WRA is used by the patient directly and the HDA is used by the doctor to ask the questions to the patient.

Wing A (Ada WRA); Wing B (Ada HDA)

Eligibility Criteria

• Age: 2 Months+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

Patients will only be included if they are waiting in the clinic waiting room of the hospital where this study will take place. Inclusion of patients will be monitored throughout the study in order to ensure recruitment of a study sample of patients with a comprehensive spectrum of symptoms constellations and conditions: this is to ensure that this pilot study tests the performance of SAA on a broad range of scenarios. Study recruitment will be carried out to a target of enrolling between 2-5 patients for 10 different body system categories (including at least one adult and one child in each category).

You may qualify if:

• All patients who enter the clinic and that are willing/able to provide consent will be included, except those who fall under certain conditions listed below

You may not qualify if:

• Patients with severe injury/illness requiring immediate treatment
• Patients with traumatic injury (many of these patients require minimal anamnesis, and it is not rational to include them in a pilot study)
• Patients incapable of completing a health assessment (e.g. due to illiteracy, mental impairment or inebriation or other incapacity).

Sponsors & Collaborators

• Ada Health GmbH: lead
• Muhimbili University of Health and Allied Sciences: collaborator

Study Sites (1)

Mbagala Rangi Tatu Hospital

Dar es Salaam, Tanzania

Location

Related Publications (2)

• Schmude M, Salim N, Azadzoy H, Bane M, Millen E, O'Donnell L, Bode P, Turk E, Vaidya R, Gilbert S. Investigating the Potential for Clinical Decision Support in Sub-Saharan Africa With AFYA (Artificial Intelligence-Based Assessment of Health Symptoms in Tanzania): Protocol for a Prospective, Observational Pilot Study. JMIR Res Protoc. 2022 Jun 7;11(6):e34298. doi: 10.2196/34298.

  PMID: 35671073 DERIVED

• Millen E, Salim N, Azadzoy H, Bane MM, O'Donnell L, Schmude M, Bode P, Tuerk E, Vaidya R, Gilbert SH. Study protocol for a pilot prospective, observational study investigating the condition suggestion and urgency advice accuracy of a symptom assessment app in sub-Saharan Africa: the AFYA-'Health' Study. BMJ Open. 2022 Apr 11;12(4):e055915. doi: 10.1136/bmjopen-2021-055915.

  PMID: 35410928 DERIVED

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: PROSPECTIVE
• Sponsor Type: INDUSTRY
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: June 30, 2021
• First Posted: July 12, 2021
• Study Start: August 3, 2021
• Primary Completion: December 17, 2021
• Study Completion: June 1, 2022
• Last Updated: May 17, 2022

Record last verified: 2022-05

Data Sharing

• IPD Sharing: Will not share

Locations

TA (1)