Automated conversational agents for post-intervention follow-up: a systematic review | JoVE Visualize

Automated conversational agents for post-intervention follow-up: a systematic review

L Geoghegan¹, A Scarborough², J C R Wormald³

¹Section of Vascular Surgery, Department of Surgery and Cancer, Imperial College London, London, UK.

BJS Open|July 29, 2021

View abstract on PubMed

Summary

Chatbots show potential for patient follow-up after physical healthcare interventions, demonstrating varied engagement and response rates. Further research is needed to confirm their acceptability and efficacy in routine clinical care.

Area of Science:

Medical Informatics
Artificial Intelligence in Healthcare
Digital Health

Background:

Machine learning and natural language processing have enabled conversational agents (chatbots).
Chatbots are increasingly used commercially and in healthcare for symptom checking and psychotherapy.
Their application in post-physical intervention patient follow-up requires systematic evaluation.

Purpose of the Study:

To systematically review the acceptability and implementation success of chatbots in patient follow-up after physical healthcare interventions.

Main Methods:

A PRISMA-compliant systematic review of multiple databases (MEDLINE, EMBASE, etc.) and grey literature up to September 2020.
Duplicate abstract screening and data extraction were performed.
Risk of bias and quality assessments were conducted for included studies.

Main Results:

Ten studies met inclusion criteria, including RCTs and cohort studies.
Chatbots were used for monitoring after interventions for cancer, hypertension, asthma, orthopaedic issues, ureteroscopy, and varicose veins.
Mobile-deployed chatbots showed engagement rates from 31% to 97% response rates; patient safety was not assessed.

Conclusions:

A variety of chatbot designs and applications were identified for patient monitoring.
Further investigation into acceptability, efficacy, and mechanistic evaluation is recommended for outpatient care.
Findings may support the integration of chatbots into routine clinical practice.