Validation of PMcardio AI-assisted Clinical Assistant in Primary Care (PMCARDIO-PT1)

Powerful Medical

Status: Completed

Conditions: Syncope; Electrocardiogram; Dyspnea; Medical Device; Breath Shortness; Chest Pain; Cardiovascular Diseases; Primary Health Care; General Practitioner

Treatments: Device: AI-assisted Clinical Assistant PMcardio

Study type: Interventional

Funder types: Other

Identifiers

NCT05329246

202106001

CIV-21-09-037810 (Other Identifier)

Details and patient eligibility

About

This study aimed to analyze and investigate whether the use of the PMcardio clinical assistant leads to a more efficient patient management in primary care and more accessible specialised care compared to usual standards of care and to assess the reliability and safety of the PMcardio smartphone application in the primary care use environment. Additionally, to evaluate time savings and cost saving implications of increased availability of specialised care at the primary care level.

Full description

It is a multi-centric, physician-driven, patient-blinded randomized controlled trial of patients presenting to the general practitioner with typical cardiovascular symptoms (specifically, chest pain, syncope, palpitations, or shortness of breath) constituting an electrocardiogram examination. Eligible patients will be enrolled at the participating general practitioner clinics and managed either through the PMcardio platform with AI-assisted diagnostics, patient management recommendations or usual standard of care throughout their initial visit. Enrolled participants will be followed-up through health insurance billing codes and there will be no personal follow-up visits required. The aim of the study is to investigate whether the use of the PMcardio clinical assistant leads to a more efficient patient management in primary care and more accessible specialised care compared to usual standards of care and to assess the reliability and safety of the PMcardio smartphone application in the primary care use environment. Additionally, to assess time savings and cost saving implications of increased availability of specialised care at the primary care level.

Enrollment: 836 patients

Sex: All

Ages: 55+ years old

Volunteers: No Healthy Volunteers

Inclusion criteria

• Male or Female aged 55 years or above.
• Participant is willing and able to give informed consent for participation in the study.
• Presenting to the GP with ANY of the following cardiovascular symptoms: palpitations, chest pain, syncope, shortness of breath.
• Patients insured by Dôvera ZP or Union ZP health insurance providers.

Exclusion criteria

• Reason for doing the ECG at the GP clinic is a routine examination or pre-operative assessment.
• Participant does not present with cardiovascular symptoms: palpitations, chest pain, syncope, shortness of breath.
• Participant is already included in the study due to a prior GP visit throughout the trial period (e.g., participant comes for a second visit to GP clinic due to cardiovascular symptoms).
• Patients insured by VšZP health insurance provider
• Female participants who are pregnant, lactating or planning pregnancy during the study.
• Any other significant comorbidity, disease, or disorder which, in the opinion of the Investigator, may either put the participants at risk because of participation in the study, or may influence the result of the study, or the participant's ability to participate in the study.

Trial design

Primary purpose: Treatment

Allocation: Randomized

Interventional model: Parallel Assignment

Masking: None (Open label)

---

836 participants in 2 patient groups

Experimental Intervention Group

Experimental group

Description:

AI-assisted interpretation of the ECG including the predicted ECG diagnoses, disease-specific anamnestic questions, and patient management recommendations for referral to secondary care, including suggestions for procedures and further diagnostic tests

Treatment:

Device: AI-assisted Clinical Assistant PMcardio

Control Group

No Intervention group

Description:

The usual standard of care, with NO AI-based diagnosis or treatment recommendation available.