[Evaluation of the impact of teledermatology in decreasing the waiting list in the Bages region (2009-2012)]

Exploring the potential of artificial intelligence in improving skin lesion diagnosis in primary care

Dermatological conditions are a relevant health problem. Machine learning (ML) models are increasingly being applied to dermatology as a diagnostic decision support tool using image analysis, especially for skin cancer detection and disease classification. The objective of this study was to perform a prospective validation of an image analysis ML model, which is capable of screening 44 skin diseases, comparing its diagnostic accuracy with that of General Practitioners (GPs) and teledermatology (TD) dermatologists in a real-life setting. Prospective, diagnostic accuracy study including 100 consecutive patients with a skin problem who visited a participating GP in central Catalonia, Spain, between June 2021 and October 2021. The skin issue was first assessed by the GPs. Then an anonymised skin disease picture was taken and uploaded to the ML application, which returned a list with the Top-5 possible diagnosis in order of probability. The same image was then sent to a dermatologist via TD for diagnosis, as per clinical practice. The GPs Top-3, ML model's Top-5 and dermatologist's Top-3 assessments were compared to calculate the accuracy, sensitivity, specificity and diagnostic accuracy of the ML models. The overall Top-1 accuracy of the ML model (39%) was lower than that of GPs (64%) and dermatologists (72%). When the analysis was limited to the diagnoses on which the algorithm had been explicitly trained (n = 82), the balanced Top-1 accuracy of the ML model increased (48%) and in the Top-3 (75%) was comparable to the GPs Top-3 accuracy (76%). The Top-5 accuracy of the ML model (89%) was comparable to the dermatologist Top-3 accuracy (90%). For the different diseases, the sensitivity of the model (Top-3 87% and Top-5 96%) is higher than that of the clinicians (Top-3 GPs 76% and Top-3 dermatologists 84%) only in the benign tumour pathology group, being on the other hand the most prevalent category (n = 53). About the satisfaction of professionals, 92% of the GPs considered it as a useful diagnostic support tool (DST) for the differential diagnosis and in 60% of the cases as an aid in the final diagnosis of the skin lesion. The overall diagnostic accuracy of the model in this study, under real-life conditions, is lower than that of both GPs and dermatologists. This result aligns with the findings of few existing prospective studies conducted under real-life conditions. The outcomes emphasize the significance of involving clinicians in the training of the model and the capability of ML models to assist GPs, particularly in differential diagnosis. Nevertheless, external testing in real-life conditions is crucial for data validation and regulation of these AI diagnostic models before they can be used in primary care.

The acceptability of two remote monitoring modalities for patients waiting for services in a physiotherapy outpatient clinic

INTRODUCTION

Access to public rehabilitation services for patients with non-urgent conditions - which suffer mainly from musculoskeletal disorders - is problematic around the world. Remote rehabilitation services are recognized as effective means to increase accessibility. Patient acceptability is an important element in the successful implementation of such clinical innovations and has not yet been studied thoroughly in this context. Thus, the aim of this study was to evaluate and compare the acceptability of two remote consultation modalities - phone and teleconsultation - for patients waiting for public outpatient non-urgent rehabilitation services.

METHODS

We conducted a qualitative descriptive study nested within a randomized clinical trial in which participants received either phone or teleconsultation follow-ups with a physiotherapist after a first systematic face-to-face evaluation. Semi-structured interviews were conducted with participants of both groups selected with purposive sampling. Sekhon's acceptability metaframework was used and interviews were transcribed and coded with thematic analysis.

ETHIC APPROVAL

The research protocol was approved by the Research Ethics Board of the Centre intégré universitaire de santé et de services sociaux - Centre hospitalier universitaire de Sherbrooke (CIUSSS de l'Estrie - CHUS) (#2019-2919).

RESULTS

Twenty participants were recruited. Results show both follow-up modalities have a good level of acceptability for participants; however, teleconsultation stands out because its visual dimension offers higher quality human contact and satisfactorily meets greater needs for support.

CONCLUSION

Systematic in-person assessment and advice combined with telephone or teleconsultation follow-up can contribute to diversifying the services offered in physiotherapy outpatient clinics. Offering a range of service modalities with different resource requirements may shorten wait times. Such an approach seems to be well accepted by patients, especially with teleconsultation.

CLINICALTRIALS

gov ID: NCT03991858.

Using Artificial Intelligence as a Diagnostic Decision Support Tool in Skin Disease: Protocol for an Observational Prospective Cohort Study

BACKGROUND

Dermatological conditions are a relevant health problem. Each person has an average of 1.6 skin diseases per year, and consultations for skin pathology represent 20% of the total annual visits to primary care and around 35% are referred to a dermatology specialist. Machine learning (ML) models can be a good tool to help primary care professionals, as it can analyze and optimize complex sets of data. In addition, ML models are increasingly being applied to dermatology as a diagnostic decision support tool using image analysis, especially for skin cancer detection and classification.

OBJECTIVE

This study aims to perform a prospective validation of an image analysis ML model as a diagnostic decision support tool for the diagnosis of dermatological conditions.

METHODS

In this prospective study, 100 consecutive patients who visit a participant general practitioner (GP) with a skin problem in central Catalonia were recruited. Data collection was planned to last 7 months. Anonymized pictures of skin diseases were taken and introduced to the ML model interface (capable of screening for 44 different skin diseases), which returned the top 5 diagnoses by probability. The same image was also sent as a teledermatology consultation following the current stablished workflow. The GP, ML model, and dermatologist's assessments will be compared to calculate the precision, sensitivity, specificity, and accuracy of the ML model. The results will be represented globally and individually for each skin disease class using a confusion matrix and one-versus-all methodology. The time taken to make the diagnosis will also be taken into consideration.

RESULTS

Patient recruitment began in June 2021 and lasted for 5 months. Currently, all patients have been recruited and the images have been shown to the GPs and dermatologists. The analysis of the results has already started.

CONCLUSIONS

This study will provide information about ML models' effectiveness and limitations. External testing is essential for regulating these diagnostic systems to deploy ML models in a primary care practice setting.

Descriptive study of a telemedicine program in palpebral pathology for primary care (tele-eyelid)

BACKGROUND AND OBJECTIVE

In 2013 we implemented an asynchronous telemedicine circuit for the diagnosis of eyelid diseases (tele-eyelid), connecting the outpatient primary healthcare with the hospital's specialists. The purpose of this study is to assess the use of telemedicine in the diagnosis of eyelid diseases by primary care teams, to evaluate its usefulness and to analyse the epidemiology of the pathological conditions referred to the tertiary level hospital, as well as the need for surgery.

MATERIALS AND METHODS

This study was carried out in the Spanish public health system, in a mainly rural area assisted by the Institut Català de la Salut (ICS) and Althaia Xarxa Assistencial Universitària de Manresa. This is a retrospective, descriptive analysis of the telematic consultations undertaken between 2013 and 2019. The consultations between 2018 and 2019 underwent a further descriptive retrospective-prospective analysis to assess the conditions referred to the hospital.

RESULTS

Unnecessary referrals were avoided in 72% of telematic consultations. More than 50% of primary care practitioners used tele-eyelid. Up to 68% of the referrals were due to eyelid tumours, 50% needed surgery and 18%, a biopsy. Moreover, we found a high reliability between telematic and face-to-face diagnosis.

CONCLUSIONS

Teleophthalmology applied to eyelid pathology is a useful tool to improve access to specialized care and helps solving pathological conditions. It avoids unnecessary consultations and increases efficiency, both in primary and hospital care.

Using artificial intelligence as a diagnostic decision support tool in skin disease: observational prospective cohort study (Preprint)

Background

Dermatological conditions are a relevant health problem. Each person has an average of 1.6 skin diseases per year, and consultations for skin pathology represent 20% of the total annual visits to primary care and around 35% are referred to a dermatology specialist. Machine learning (ML) models can be a good tool to help primary care professionals, as it can analyze and optimize complex sets of data. In addition, ML models are increasingly being applied to dermatology as a diagnostic decision support tool using image analysis, especially for skin cancer detection and classification.

Objective

This study aims to perform a prospective validation of an image analysis ML model as a diagnostic decision support tool for the diagnosis of dermatological conditions.

Methods

In this prospective study, 100 consecutive patients who visit a participant general practitioner (GP) with a skin problem in central Catalonia were recruited. Data collection was planned to last 7 months. Anonymized pictures of skin diseases were taken and introduced to the ML model interface (capable of screening for 44 different skin diseases), which returned the top 5 diagnoses by probability. The same image was also sent as a teledermatology consultation following the current stablished workflow. The GP, ML model, and dermatologist’s assessments will be compared to calculate the precision, sensitivity, specificity, and accuracy of the ML model. The results will be represented globally and individually for each skin disease class using a confusion matrix and one-versus-all methodology. The time taken to make the diagnosis will also be taken into consideration.

Results

Patient recruitment began in June 2021 and lasted for 5 months. Currently, all patients have been recruited and the images have been shown to the GPs and dermatologists. The analysis of the results has already started.

Conclusions

This study will provide information about ML models’ effectiveness and limitations. External testing is essential for regulating these diagnostic systems to deploy ML models in a primary care practice setting.

Cost-minimization analysis of teledermatology versus conventional care in the Brazilian National Health System

Aims: Cost-minimization analysis (CMA) comparing the teledermatology service of the State of Santa Catarina, Brazil with the provision of conventional care, from the societal perspective. Patients & methods: All costs related to direct patient care were considered in calculation of outpatient costs. The evaluation was performed using the parameters avoided referrals and profile of hospitalizations. The economic analysis was developed through a decision tree. Results: Totally, 40% of 79,411 tests performed could be managed in primary care, avoiding commuting and expanding the patients' access. The CMA showed the teledermatology service had a cost per patient of US$196.04, and the conventional care of US$245.66. Conclusion: In this scenario, teledermatology proved to be a cost-saving alternative to conventional care, reducing commuting costs.

Economic impact and cost savings of teledermatology units compared to conventional monitoring at hospitals in southern Spain

INTRODUCTION

Asynchronous teledermatology (TD) has undergone exponential growth in the past decade, allowing better diagnosis. Moreover, it saves both cost and time and reduces the number of visits involving travel and opportunity cost of time spent on visits to the hospital. The present study performed a cost-saving analysis of TD units and assessed whether they offered a cheaper alternative to conventional monitoring (CM) in hospitals from the perspective of public health-care systems (PHS) and patients.

METHODS

This study was a retrospective assessment of 7030 patients. A cost-saving analysis comparing TD units to CM for patients at the Hospital de Poniente was performed over a period of one year. The TD network covered the Hospital de Poniente reference area (Spain) linked to 37 primary care (PC) centres that belonged to the Poniente Health District of Almeria.

RESULTS

We observed a significant cost saving for TD units compared to participants in the conventional follow-up group. From the perspective of a PHS, there was a cost saving of 31.68% in the TD group (€18.59 TD vs. €27.20 CM) during the follow-up period. The number of CM visits to the hospital reduced by 38.14%. From the patients' perspective, the costs were lower, and the cost saving was 73.53% (€5.45 TD vs. €20.58 CM).

DISCUSSION

The cost-saving analysis showed that the TD units appeared to be significantly cheaper compared to CM.

A Cost-Minimization Analysis of a Medical Record-based, Store and Forward and Provider-to-provider Telemedicine Compared to Usual Care in Catalonia: More Agile and Efficient, Especially for Users

Background: Telemedicine (interconsultation between primary and hospital care teams) has been operating in the counties of Central Catalonia Bages, Moianès and Berguedà since 2011, specializing in teledermatology, teleulcers, teleophthalmology and teleaudiometries. For the period until the end of 2019, a total of 52,198 visits were recorded. Objective: To analyze the differential costs between telemedicine and usual care in a semi-urban environment. Methodology: A cost-minimization evaluation, including direct and indirect costs from a societal perspective, distinguishing healthcare and user’s costs, was carried out over a three-month period. Results: Telemedicine saved € 780,397 over the period analyzed. A differential cost favorable to telemedicine of about € 15 per visit was observed, with the patient being the largest beneficiary of this saving (by 85%) in terms of shorter waiting times and travel costs. From the healthcare system perspective, moving the time spent in a hospital care consultation to primary care is efficient in terms of the total time devoted per patient. In social terms and in this context, telemedicine is more efficient than usual care. Conclusion: Allowing users to save time in terms of consultation and travel is the main driver of interconsultation between primary and hospital care savings in a semi-urban context. The telemedicine service is also economically favorable for the healthcare system, enabling it to provide a more agile service, which also benefits healthcare professionals.