Development and interpretable machine learning models for classification of pancreatic pseudocyst risk in acute pancreatitis

IntroductionPancreatic pseudocysts (PPC) are a late local complication of acute pancreatitis (AP). Persistent PPC carry a high risk of severe outcomes. Existing models, which are

Implementing AI innovation in radiology departments in the English NHS: a qualitative study on the experiences of professionals, patient groups and innovators

IntroductionDigital solutions and Artificial Intelligence (AI) innovations are often presented as the answer to many challenges faced by healthcare systems around the world. The UK

Development and Evaluation of a Hallucination Awareness Scale for Healthcare Professionals and its impact on diagnostic confidence

Generative artificial intelligence (Gen AI) has gained immense significance in recent years, particularly in the field of healthcare. Despite its significant role in streamlining healthcare-related

Planning and delivering co-creation workshops: practical lessons from digital health device design

Co-creation methods are increasingly recognised as essential in digital health and care, yet engineers and physical scientists new to the field often find the literature

Promises and challenges of applying large language models in the healthcare domain

Large language models are rapidly moving from theoretical concepts to active clinical pilots. Current approaches diverge between general-purpose models, which adapt to healthcare via prompt

A pre-treatment comparison of referral pathways to guided ICBT for depression and anxiety disorders – A naturalistic study in routine clinical care

March 18, 2026

IntroductionSelf-referral to therapist-guided internet-delivered cognitive behavioral therapy (guided ICBT) is increasingly being implemented in specialized mental healthcare settings to reduce barriers to care. Little is known about the characteristics of patients who access treatment through this pathway compared to the traditional referral pathway from general practitioner (GP). This study aims to compare demographic characteristics, socioeconomic and social factors between GP- and self-referred patients receiving guided ICBT for depression and anxiety disorders.MethodNaturalistic cross-sectional study comparing pre-treatment characteristics between GP- and self-referred patients in a specialized routine care ICBT clinic.ResultsThe study included 460 patients, 305 GP-referred, 155 self-referred. We found statistically significant differences between referral pathways in the socioeconomic factors; educational level (P < .001), employment status (P = .002), source of income (P = .004), social support (P = .029), types of healthcare utilization 6 months prior to treatment (P < .001) and information source about the treatment (P < .001). We found no difference in pre-treatment symptom level or basic demographics. Multiple logistic regression reduced the number of findings.DiscussionDifferent referral pathways potentially attract distinct patient populations, with self-referred patients being more likely to report greater socioeconomic resources than GP-referred. GP-referral remains crucial for individuals who may need more structured guidance to navigate healthcare systems. To promote equitable access, referral strategies should be tailored to reach those less likely to self-refer. Offering two pathways may support broader access to specialized mental healthcare. Future studies should further explore these identified statistical differences to optimize referral systems and ensure equitable access to mental healthcare for all in need.

Subscribe for Updates

Copyright 2025 dijee Intelligence Ltd. dijee Intelligence Ltd. is a private limited company registered in England and Wales at Media House, Sopers Road, Cuffley, Hertfordshire, EN6 4RY, UK registration number 16808844