Olga Kostopoulou

Understanding where C-reactive protein ‘fits’ in the diagnostic assessment of patients with acute infections

Peder Halvorsen, Alastair D Hay, Martine Nurek, Olga Kostopoulou

Is C-reactive protein the answer to antibiotics over-prescribing in primary care? A behavioural experiment in two European countries

Martine Nurek, Alastair D Hay, Peder Halvorsen, Olga Kostopoulou

Abstract Background Antibiotic overprescribing fuels antimicrobial resistance. C-reactive protein (CRP) is widely promoted as a point-of-care test for targeted prescribing. While routinely used in some European countries such as Norway, it is not part of standard practice in UK primary care. Understanding …

gb, no (code pays fourni par la source)

Advice taking in medical decision making

Olga Kostopoulou

Clinicians often prefer to use their clinical judgement instead of relying on statistical algorithms - a phenomenon also observed in other domains of decision making. This review explores this phenomenon using insights from the advice taking literature. One of the most consistent …

gb (code pays fourni par la source)

The ‘Hippocratic Oath’ for AI-based clinical decision support systems

Solomon Bracey, Ben Ainsworth, Joseph Edward Alderman, Christopher R S Banjeri et autres

BACKGROUND: The implementation of Artificial Intelligence assisted Clinical Decision Support Systems (AI-CDSS) shows significant potential to improve healthcare. However, implementing AI-CDSS has many associated challenges. This article introduces the 'Hippocratic Oath' for AI which promotes safe and effective AI-CDSS development and implementation. …

gb (code pays fourni par la source)

Learning Health Systems provide a glide path to safe landing for AI in health

Vasa Ćurčin, Brendan C. Delaney, Ahmad Alkhatib, Neil Cockburn et autres

Artificial Intelligence (AI) holds significant promise for healthcare but often struggles to transition from development to clinical integration. This paper argues that Learning Health Systems (LHS)-socio-technical ecosystems designed for continuous data-driven improvement-provide a potential "glide path" for safe, sustainable AI deployment. Just …

gb, us (code pays fourni par la source)

Exploring the Effect of Explanation Content and Format on User Comprehension and Trust in Healthcare

Antonio Rago, Bence Pálfi, Purin Sukpanichnant, Kavyesh Vivek et autres

AI-driven tools for healthcare are widely acknowledged as potentially beneficial to health practitioners and patients, e.g. the QCancer regression tool for cancer risk prediction. However, for these tools to be trusted, they need to be supplemented with explanations. We examine how explanations’ …

gb (code pays fourni par la source)

Determinants of Physicians’ Referrals for Suspected Cancer Given a Risk-Prediction Algorithm: Linking Signal Detection and Fuzzy Trace Theory

Olga Kostopoulou, Bence Pálfi, Kavleen Arora, Valerie F. Reyna

Background Previous research suggests that physicians’ inclination to refer patients for suspected cancer is a relatively stable characteristic of their decision making. We aimed to identify its psychological determinants in the presence of a risk-prediction algorithm. Methods We presented 200 UK general …

gb, us (code pays fourni par la source)

Explainable AI: definition and attributes of a good explanation for health AI

Evangelia Kyrimi, Scott McLachlan, Jared M. Wohlgemut, Zane Perkins et autres

Abstract Proposals of artificial intelligence (AI) solutions based on more complex and accurate predictive models are becoming ubiquitous across many disciplines. As the complexity of these models increases, there is a tendency for transparency and users’ understanding to decrease. This means accurate …

gb (code pays fourni par la source)

AI for medical diagnosis: does a single negative trial mean it is ineffective?

Olga Kostopoulou, Brendan C. Delaney

It is disheartening to read the results of a negative trial in an area we have extensively researched for 20 years. However, improving medical diagnosis using clinical diagnostic decision support systems (CDDSSs) that use artificial intelligence (AI) is a complex endeavour and …

gb (code pays fourni par la source)

Factors influencing UK arthroplasty surgeons' decision‐making between total and medial unicompartmental knee surgery: A vignette‐based behavioural experiment

Martine Nurek, Omar Musbahi, Martinique Vella‐Baldacchino, Robert M. Hamm et autres

Abstract Purpose Surgical options for end‐stage knee osteoarthritis (OA) include total and medial unicompartmental knee replacement (TKR and UKR). Deciding which surgery to perform is complex and ill‐defined, yet it has important implications for patients and the health service. The study aimed …

gb, us (code pays fourni par la source)

Determinants of Physicians' Referrals for Suspected Cancer Given a Riskprediction Algorithm: Linking Signal Detection and Fuzzy-Trace Theory

Olga Kostopoulou, Bence Pálfi, Kavleen Arora, Valerie F. Reyna

gb, us (code pays fourni par la source)

Improving Cancer Risk Assessment with Vignettes and Algorithmic Feedback: An Interview Study

Olga Kostopoulou, Bence Pálfi, Martine Nurek, Kavleen Arora

gb (code pays fourni par la source)