Browsing by Author "Cadamuro, J"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    A comprehensive survey of artificial intelligence adoption in European laboratory medicine: current utilization and prospects
    Cadamuro, J; Carobene, A; Cabitza, F; Debeljak, Z; De Bruyne, S; van Doorn, W; Johannes, E; Frans, G; Özdemir, S; Perez, SM; Rajdl, D; Tolios, A; Padoan, A
    Background As the healthcare sector evolves, Artificial Intelligence's (AI's) potential to enhance laboratory medicine is increasingly recognized. However, the adoption rates and attitudes towards AI across European laboratories have not been comprehensively analyzed. This study aims to fill this gap by surveying European laboratory professionals to assess their current use of AI, the digital infrastructure available, and their attitudes towards future implementations.Methods We conducted a methodical survey during October 2023, distributed via EFLM mailing lists. The survey explored six key areas: general characteristics, digital equipment, access to health data, data management, AI advancements, and personal perspectives. We analyzed responses to quantify AI integration and identify barriers to its adoption.Results From 426 initial responses, 195 were considered after excluding incomplete and non-European entries. The findings revealed limited AI engagement, with significant gaps in necessary digital infrastructure and training. Only 25.6 % of laboratories reported ongoing AI projects. Major barriers included inadequate digital tools, restricted access to comprehensive data, and a lack of AI-related skills among personnel. Notably, a substantial interest in AI training was expressed, indicating a demand for educational initiatives.Conclusions Despite the recognized potential of AI to revolutionize laboratory medicine by enhancing diagnostic accuracy and efficiency, European laboratories face substantial challenges. This survey highlights a critical need for strategic investments in educational programs and infrastructure improvements to support AI integration in laboratory medicine across Europe. Future efforts should focus on enhancing data accessibility, upgrading technological tools, and expanding AI training and literacy among professionals. In response, our working group plans to develop and make available online training materials to meet this growing educational demand.
  • No Thumbnail Available
    Item
    Potentials and pitfalls of ChatGPT and natural-language artificial intelligence models for the understanding of laboratory medicine test results. An assessment by the European Federation of Clinical Chemistry and Laboratory Medicine (EFLM) Working Group on Artificial Intelligence (WG-AI)
    Cadamuro, J; Cabitza, F; Debeljak, Z; De Bruyne, S; Frans, G; Perez, SM; Ozdemir, H; Tolios, A; Carobene, A; Padoan, A
    Objectives: ChatGPT, a tool based on natural language processing (NLP), is on everyone's mind, and several potential applications in healthcare have been already proposed. However, since the ability of this tool to interpret laboratory test results has not yet been tested, the EFLM Working group on Artificial Intelligence (WG-AI) has set itself the task of closing this gap with a systematic approach.Methods: WG-AI members generated 10 simulated laboratory reports of common parameters, which were then passed to ChatGPT for interpretation, according to reference intervals (RI) and units, using an optimized prompt. The results were subsequently evaluated independently by all WG-AI members with respect to relevance, correctness, helpfulness and safety.Results: ChatGPT recognized all laboratory tests, it could detect if they deviated from the RI and gave a test-by-test as well as an overall interpretation. The interpretations were rather superficial, not always correct, and, only in some cases, judged coherently. The magnitude of the deviation from the RI seldom plays a role in the interpretation of laboratory tests, and artificial intelligence (AI) did not make any meaningful suggestion regarding follow-up diagnostics or further procedures in general.Conclusions: ChatGPT in its current form, being not specifically trained on medical data or laboratory data in particular, may only be considered a tool capable of interpreting a laboratory report on a test-by-test basis at best, but not on the interpretation of an overall diagnostic picture. Future generations of similar AIs with medical ground truth training data might surely revolutionize current processes in healthcare, despite this implementation is not ready yet.