Analysis of the implementation of an innovative IT solution to improve waiting times, communication with primary care and efficiency in Rheumatology

E-consults between primary care and internal medicine: implementation, accessibility, benefits, and implications

AIM

This work aims to evaluate whether electronic consultations (e-consults) are a clinically useful, safe tool for assessing patients between primary care and internal medicine.

METHODS

This is a retrospective cohort study of all e-consults ordered by the Primary Care Department to the Internal Medicine Department between September 2019 and December 2023. The results of initial consultations, emergency department visits and subsequent admissions, and survival were assessed and complaints and claims filed were reviewed.

RESULTS

A total of 11,434 e-consults were recorded (55.4% women) with a mean age of 62.1 (SD19.4) years and a wide range (15-102 years). The mean response time was 2.55 (SD 1.6) days. As a result of the e-consults, 5645 patients (49.4%) were given an in-person appointment. For the remaining 5789 (50.6%), a written response was provided. Among those given appointments, the time between the response and in-person appointment was less than five days (95% of cases). Compared to those not given appointments, in-person appointments were older (p < 0.0001), visited the emergency department more times (one month: p = 0.04; three months: p = 0.001), were admitted to the hospital more times (one month: p = 0.0001; three months: p = 0.0001), and had higher mortality at one year (12.7% vs. 9.8% p = 0.0001). In the Cox analysis, only in-person appointments (RR = 1.11; p = 0.04)) and age (RR = 1.09; p < 0.01) were independent factors of mortality. No complaints or claims of any kind were registered.

CONCLUSIONS

These data suggest that e-consults are a clinically useful, safe tool for assessing patients referred from primary care to internal medicine departments.

Delphi consensus on the use of telemedicine in rheumatology: RESULTAR study

BACKGROUND AND OBJECTIVES

There is growing interest in the potential of telemedicine (TM) as an alternative to physical consultation. Although numerous studies prove the benefits of TM in rheumatology, there are no recommendations on its implementation in Spain. The aim of this study was to analyze the application of TM in rheumatology consultations in Spain.

MATERIALS AND METHODS

Qualitative, cross-sectional, multicenter study with Delphi methodology in two rounds of queries. A structured ad hoc questionnaire was designed that included statements on teleconsultation, nursing teleconsultation, telecare, telerehabilitation, teleradiology, telehealth tele-education, main barriers, advantages and disadvantages of telehealth tele-education and TM in rheumatoid arthritis. The participants were rheumatology specialists practicing in Spain.

RESULTS

The participating rheumatologists (N = 80) had a mean age of 42.4 (±9.0) years, with 12.6 (±8.4) years of experience. Some of the aspects of TM that obtained the greatest consensus were: TM is useful for follow-up of some patients, to help determine if a face-to-face consultation is necessary, or to assist patients with rheumatoid arthritis if they present low activity or in remission; certain patients, such as those in their first consultation or those who present digital barriers or cognitive deterioration, should be seen face-to-face; TM presents some technical and patient access barriers; TM can be useful in nursing and in continued medical education.

CONCLUSIONS

TM can be beneficial for the treatment and follow-up of patients with rheumatic diseases, as well as for alleviating the face-to-face care burden in rheumatology.

Usefulness of an electronic consultation system between primary care health centres and the rheumatology department of a tertiary hospital

BACKGROUND AND OBJECTIVE

Rheumatic diseases account for almost 30% of consultations attended in Spanish primary care centres. The main objective was to analyse the demand for rheumatology consultations from Primary Care and their resolution using the electronic consultation system.

PATIENTS AND METHODS

Retrospective descriptive study of electronic consultations from primary care centres in the health area to the Rheumatology service of a tertiary hospital, between July 2020 and May 2021.

RESULTS

The last 500 consecutive consultations were collected. Mean age of patients was 59.5 years; 74.2% were women. Main reasons for consultation were osteoporosis and treatment of patients with rheumatoid arthritis and spondyloarthritis under follow-up by the department. Mean response time was 2 days. Fifty-seven per cent of patients required outpatient appointments.

DISCUSSION

Over 40% of queries were resolved thanks to the electronic consultation system in an average of 2 days, otherwise patients would have been referred to specialized care.

Machine learning-based improvement of an online rheumatology referral and triage system

Introduction

Rheport is an online rheumatology referral system allowing automatic appointment triaging of new rheumatology patient referrals according to the respective probability of an inflammatory rheumatic disease (IRD). Previous research reported that Rheport was well accepted among IRD patients. Its accuracy was, however, limited, currently being based on an expert-based weighted sum score. This study aimed to evaluate whether machine learning (ML) models could improve this limited accuracy.

Materials and methods

Data from a national rheumatology registry (RHADAR) was used to train and test nine different ML models to correctly classify IRD patients. Diagnostic performance was compared of ML models and the current algorithm was compared using the area under the receiver operating curve (AUROC). Feature importance was investigated using shapley additive explanation (SHAP).

Results

A complete data set of 2265 patients was used to train and test ML models. 30.5% of patients were diagnosed with an IRD, 69.3% were female. The diagnostic accuracy of the current Rheport algorithm (AUROC of 0.534) could be improved with all ML models, (AUROC ranging between 0.630 and 0.737). Targeting a sensitivity of 90%, the logistic regression model could double current specificity (17% vs. 33%). Finger joint pain, inflammatory marker levels, psoriasis, symptom duration and female sex were the five most important features of the best performing logistic regression model for IRD classification.

Conclusion

In summary, ML could improve the accuracy of a currently used rheumatology online referral system. Including further laboratory parameters and enabling individual feature importance adaption could increase accuracy and lead to broader usage.

A glance into the future of diagnosis and treatment of spondyloarthritis

The last two decades have seen major developments in the field of spondyloarthritis (SpA), but there are still important unmet needs to address. In the future, we envisage important advances in the diagnosis and treatment of SpA. In the diagnosis of SpA, the use of online and social media tools will increase awareness of the disease and facilitate the referral of patients to rheumatology clinics. In addition, more specific diagnostic tests will be available, especially advanced imaging methods and new biomarkers. This will allow most patients to be diagnosed at an early stage of the disease. In the treatment of SpA, an increasing number of novel treatment targets can be expected, most of which will be directed against intracellular enzymes. We hope to see more strategy trials shaping treatment pathways in SpA and accommodating principals of precision medicine. Approved treatment options will be available for both axial and peripheral SpA. We also hope to intervene not only at the inflammation level but also at the level of underlying immunological processes that might be associated with a higher probability of long-standing remission if not a cure. Finally, artificial intelligence techniques will allow for the analysis of large-scale data to answer relevant research questions for the diagnosis and management of patients with SpA.