Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Human Factors

Date Submitted: Feb 23, 2024
Open Peer Review Period: Mar 22, 2024 - May 17, 2024
Date Accepted: Jun 22, 2024
(closed for review but you can still tweet)

The final, peer-reviewed published version of this preprint can be found here:

Novel Approach to Personalized Physician Recommendations Using Semantic Features and Response Metrics: Model Evaluation Study

Zheng Y, Cai Y, Yan Y, Chen S, Gong K

Novel Approach to Personalized Physician Recommendations Using Semantic Features and Response Metrics: Model Evaluation Study

JMIR Hum Factors 2024;11:e57670

DOI: 10.2196/57670

PMID: 39146009

PMCID: 11362707

Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.

Enhancing Online Medical Consultations: A Novel Approach to Personalized Doctor Recommendation Using Semantic Features and Response Metrics

  • Yingbin Zheng; 
  • Yunping Cai; 
  • Yiwei Yan; 
  • Sai Chen; 
  • Kai Gong

ABSTRACT

Background:

The rapid growth of online medical services has highlighted the significance of smart triage systems in helping patients find the most appropriate doctors. However, traditional triage methods often rely on department recommendations, and are insufficient to accurately match patients’ textual questions with doctors' specialties. There is an urgent need to develop algorithms for recommending doctors.

Objective:

To develop and validate a patient-doctor hybrid recommendation model with response metrics (PDHR model) for better triage performance.

Methods:

A total of 646,383 online medical consultation records from the Internet Hospital of the First Affiliated Hospital of Xiamen University were collected. Semantic features representing patients and doctors were developed to identify the set of most similar questions and to semantically expand the pool of recommended doctor candidates, respectively. The doctors’ response rate was designed to improve candidate rankings. These three characteristics combine to create the PDHR model. Five doctors participated to evaluate the efficiency of the PDHR model through multiple metrics and questionnaires, as well as the performance of SBERT and Doc2Vec in text embedding.

Results:

The PDHR model reaches the best recommendation performance when the number of recommended doctors is 14. At this point, the model has an F1-score of 76.25%, a proportion of high-quality services of 41.05%, and a rating of 3.90. After removing doctors’ characteristics and response rates from PDHR model, the F1-score decreased by 12.05%, the proportion of high-quality services fell by 10.87%, the average hit ratio dropped by 1.06%, and the rating declined by 11.43%. According to whether those five doctors were hit by PDHR model, SBERT achieved an average hit ratio of 88.60%, while Doc2Vec achieved an average hit ratio of 53.40%.

Conclusions:

The PDHR model uses semantic features and response metrics to enable patients to accurately find the doctor that best suits their needs.


 Citation

Please cite as:

Zheng Y, Cai Y, Yan Y, Chen S, Gong K

Novel Approach to Personalized Physician Recommendations Using Semantic Features and Response Metrics: Model Evaluation Study

JMIR Hum Factors 2024;11:e57670

DOI: 10.2196/57670

PMID: 39146009

PMCID: 11362707

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.