With rising demand for outpatient services across Australia, patients are experiencing excessive delays for specialist input, linked with subsequent deterioration in health. Advice-and-Guidance and eConsult are outpatient substitution models which have been implemented internationally. Based on the extensively evaluated Canadian Champlain eConsult BASE Service, eConsultant provides an asynchronous, digital, clinician-to-clinician advice service, giving general practitioners (GPs) remote access to specialist support for patient care within 3-business days. GPs send a Request-for-Advice (RFA) to the specialist and advise patients to schedule a timely follow-up appointment to discuss the eConsultant advice. We studied the implementation of the first Australian eConsultant service to determine if it would improve access and be more efficient to deliver than a traditional outpatient service. The main outcomes were time to specialist input and incremental cost saving per patient from a health system perspective. The cost analysis used a decision analytic model. Qualitative interviews were conducted with GPs and stakeholders to understand determinants of implementation. Interview transcripts were coded deductively. Methods were guided by the Consolidated Framework of Implementation Research.
RFAs have been generated for 191 patients (mean age 60 years) from 63 GPs in 22 general practices. The mean specialist response time was 1.7 (SD 2.3) days and patients mean time to specialist input (initial GP to GP follow-up appointment) was 13.0 (SD 2.7) days (well below average waiting times for hospital-based appointments). eConsultant is associated with an efficiency gain of $361.07 per patient. Qualitative interviews with 11 GPs/4 stakeholders identified implementation barriers related to digital infrastructure and reliance on existing referral options. Key facilitators identified were the positive response from patients to the program, and the relative advantage of eConsultant over other options.
This research supports broader implementation of the international eConsultant model, which will provide a fundamental change to health care delivery in Australia.

1. eConsultant is feasible in Australia with benefits to the health system of timely specialist support for patients without the cost of subsidised patient travel, face-to-face visits, and potentially preventable hospital admissions.
2. eConsultant provides GPs with a reliable, auditable record of advice given by specialists, an opportunity for GP practice capacity building and more direct partnership with specialist colleagues.
3. eConsultant offers a streamlined evidence-based option, implementable state-wide, to support patients and primary care providers.

The UK Department for International Trade (DIT) and the National Institution for Transforming India (NITI Aayog) funded a Health Artificial Intelligence Catalyst (HAIC) Pilot Study in 2021.

Objective was to assess the usability, usefulness, and adherence to Standard Treatment Guidelines (STGs) in Indian public healthcare settings with the use of Elsevier’s declarative AI technology through a pilot intervention.

In Phase 1, 10 Indian Standard Treatment Guidelines for maternal and child health have been transformed into Computer-Interpretable Guidelines (CIGs). The validity of the CIGs content was systematically examined through simulated cases. The content reliability was tested through an inter-rater agreement which compared outputs from CIGs with Subject Matter Expert (SME) assessment. Content validation was performed in clinical practice, in accordance with ethics committee approval.

In Phase 2 feasibility testing was carried out in Bahraich District, Uttar Pradesh, India. 49 Frontline Health Workers (FLHWs) in Bahraich enrolled in the pilot study and initiated Clinical Decision Support (CDS) for 4460 beneficiaries.

The pilot demonstrated that multiple STGs can be implemented as CIGs and can be delivered as a seamless CDS experience to FLHWs via a mobile app. STG adherence for maternal indicators was 77.28% (95% CI: 65.0 – 89.6). STG adherence for paediatric indicators was 74.96% (95% CI: 58.1 – 91.8).

Overall, the satisfaction of Frontline Health Workers (FLHWs) with this technology was high. In the usability testing 76.09% (Mean Likert Score 3.99; 95% CI: 3.41 – 4.57) respondents agreed or strongly agreed on the Usability of CDSS. 80.43% (Mean Likert Score 4.03; 95% CI: 2.38 – 4.77) respondents agreed or strongly agreed on the Usefulness of CDSS.

1. Clinical Decision Support Solutions can work as an effective job – aid for Frontline Health Workers in rural areas.
2. Clinical Decision Support Solutions can help to achieve task-shifting by enabling lower trained Frontline Health Workers to conduct guideline-led screenings, identify high risk cases and refer accurately - leading to a more proactive management of high risk cases in rural areas.
3. Clinical Decision Support can merge content and assess compliance to multiple published guidelines, personalised to each patient

Background:
There is an ongoing digital shift in family medicine regarding the way consultations are provided to patients, with introduction of video and text-based consultations. Knowledge of gains and losses associated with this transformation is deficient.

Objective:
To explore future potentials and pitfalls for GPs and patients using digital consultations within the context of a regular GP scheme.

Methods:
Qualitative study based on five focus groups with GPs from all over Norway.

Results:
In a context characterized by continuity of care, digital consultations can increase the overall quality and efficiency of the health service. GPs’ preferences vary as for how and when to implement digital consultations in the trajectory of care. Some prefer them for triage, others for follow-up. Video consultations can facilitate relationship building with certain vulnerable patients. Text consultations offer advantages as the patient and GP can attach text, images and videos that explain the disease. GPs report that variations between different types of consultations help them regulate emotional intensity and stress during the workday.

A downside of digital consultations is that they tend to follow a "one problem approach," limiting the chances of addressing more implicit and complex issues. Easy access to digital consultations might reduce patients' capacity for self-care, displacing more important requests. GPs expressed willingness to offer more digital consultations than they find professionally optimal, hoping to protect their patients from commercial one-time consultations and retaining a well-functioning GP scheme.

Ethical dilemmas arise about responsibility, if e.g., serious patient events occurring while their requests for medical care remain unread in the busy GP’s inbox.

Implications:
Digital consultations provide opportunities for increased variety for GP and patient, increased quality in patient treatment and increased responsibility for both parties. A lower threshold for contacting the GP might increase the total workload and lead to unfavorable resource allocation.

1. Video consultations can facilitate relationship building with certain vulnerable patients.
2. Text consultations offer advantages as the patient and GP can attach text, images and videos that explain the disease and management.
3. GPs report that variations between different types of consultations help them regulate emotional intensity and stress during the workday.

International classifications are a crucial tool for various aspects of healthcare, including general medical practice, population health analysis, and research. However, coding health records can prove to be a tedious and inaccurate task, given the complexity of the classifications, limited time available, need for previous training, and dependence on professional experience. Natural language processing encompasses a range of technologies that provide insight into text data and can be utilized for various purposes, including text data classification.

The aim of this research is twofold. Firstly, to develop a neural network that can analyze primary care medical records and classify the reasons for patient visits using the International Classification of Primary Care, second edition. Secondly, to compare the results of automated coding with those coded by family physicians with varying levels of experience in ICPC for benchmarking purposes. The main hypothesis is that a natural language processing-based neural network will perform comparably to a general practitioner with some experience in ICPC coding.

This technology has the potential to provide value by reducing distractions and saving healthcare providers time and cognitive effort for more patient-centered activities. Furthermore, it can generate consistent data that will contribute to future research and general practice. The primary objectives of this presentation are to discuss the problems that this technology can solve, present preliminary research results, and highlight expected limitations and challenges.

The key points to be taken away from my presentation are:
1. Natural language processing is a rapidly developing technology that has numerous benefits in fields such as primary care and general medical practice.
2. The task of medical coding is intricate and requires a significant amount of time and effort, which could be put to better use.
3. Artificial intelligence has the capability to perform complex tasks that are challenging for health professionals, freeing up time for more patient-focused activities.

From November 2022 to June 2023, NCN Health, comprising three health service sites in Northern Victoria, implemented a pilot Virtual Inpatient Care Program utilising an external service provider (Telecare Australia).

This pilot, aimed at alleviation of the rural medical workforce burden, operated exclusively in the after-hours periods from Friday evening to Monday morning, when local medical workforce capacity was constrained.

Extensive stakeholder engagement, development of project protocols and ICT resources (including digitally created National Inpatient Medication Charts) and staff training occurred prior to the commencement of the pilot.

Over 5 months of the trial, 131 patients were managed virtually, with 278 virtual ward reviews and 5 new admissions, being transfers from major regional hospitals to NCN sites for continued treatment of patients closer to home and release of beds in regional hospitals.

Due to the positive impact of this NCN pilot this model is currently being actively considered for broader implementation to other hospitals in the Hume Health Services Partnership

Detailed evaluation of this project is currently underway and will be presented in the final WONCA presentation. This evaluation will include service system processes involved with implementation, perspectives of health service staff, patients/carers, the service provider (Telecare) and the regional health service. Whilst initial assessment demonstrated capability to support regional workforce limitations, improve access to local provision of healthcare for patients, and reduce bed pressures at larger regional services, the comprehensive study will provide further information to better identify improvements, adaptations, and scalability of this virtual model of health care.