1
|
Abusoglu S, Serdar M, Unlu A, Abusoglu G. Comparison of three chatbots as an assistant for problem-solving in clinical laboratory. Clin Chem Lab Med 2024; 62:1362-1366. [PMID: 38095605 DOI: 10.1515/cclm-2023-1058] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2023] [Accepted: 12/05/2023] [Indexed: 05/30/2024]
Abstract
OBJECTIVES Data generation in clinical settings is ongoing and perpetually increasing. Artificial intelligence (AI) software may help detect data-related errors or facilitate process management. The aim of the present study was to test the extent to which the frequently encountered pre-analytical, analytical, and postanalytical errors in clinical laboratories, and likely clinical diagnoses can be detected through the use of a chatbot. METHODS A total of 20 case scenarios, 20 multiple-choice, and 20 direct questions related to errors observed in pre-analytical, analytical, and postanalytical processes were developed in English. Difficulty assessment was performed for the 60 questions. Responses by 4 chatbots to the questions were scored in a blinded manner by 3 independent laboratory experts for accuracy, usefulness, and completeness. RESULTS According to Chi-squared test, accuracy score of ChatGPT-3.5 (54.4 %) was significantly lower than CopyAI (86.7 %) (p=0.0269) and ChatGPT v4.0. (88.9 %) (p=0.0168), respectively in cases. In direct questions, there was no significant difference between ChatGPT-3.5 (67.8 %) and WriteSonic (69.4 %), ChatGPT v4.0. (78.9 %) and CopyAI (73.9 %) (p=0.914, p=0.433 and p=0.675, respectively) accuracy scores. CopyAI (90.6 %) presented significantly better performance compared to ChatGPT-3.5 (62.2 %) (p=0.036) in multiple choice questions. CONCLUSIONS These applications presented considerable performance to find out the cases and reply to questions. In the future, the use of AI applications is likely to increase in clinical settings if trained and validated by technical and medical experts within a structural framework.
Collapse
Affiliation(s)
- Sedat Abusoglu
- Department of Biochemistry, Selcuk University Faculty of Medicine, Konya, Türkiye
| | - Muhittin Serdar
- Department of Biochemistry, Acıbadem Mehmet Ali Aydinlar University Faculty of Medicine, İstanbul, Türkiye
| | - Ali Unlu
- Department of Biochemistry, Selcuk University Faculty of Medicine, Konya, Türkiye
| | - Gulsum Abusoglu
- Department of Medical Laboratory Techniques, Selcuk University Vocational School of Medicine, Konya, Türkiye
| |
Collapse
|
2
|
Plebani M. Harmonizing the post-analytical phase: focus on the laboratory report. Clin Chem Lab Med 2024; 62:1053-1062. [PMID: 38176022 DOI: 10.1515/cclm-2023-1402] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2023] [Accepted: 12/27/2023] [Indexed: 01/06/2024]
Abstract
The final, post-analytical, phase of laboratory testing is increasingly recognized as a fundamental step in maximizing quality and effectiveness of laboratory information. There is a need to close the loop of the total testing cycle by improving upon the laboratory report, and its notification to users. The harmonization of the post-analytical phase is somewhat complicated, mainly because it calls for communication that involves parties speaking different languages, including laboratorians, physicians, information technology specialists, and patients. Recently, increasing interest has been expressed in integrated diagnostics, defined as convergence of imaging, pathology, and laboratory tests with advanced information technology (IT). In particular, a common laboratory, radiology and pathology diagnostic reporting system that integrates text, sentinel images and molecular diagnostic data to an integrated, coherent interpretation enhances management decisions and improves quality of care.
Collapse
Affiliation(s)
- Mario Plebani
- Clinical Biochemistry and Clinical Molecular Biology, University of Padova, Padova, Italy
- Department of Pathology, University of Texas, Medical Branch, Galveston, TX, USA
| |
Collapse
|
3
|
Lippi G, Mattiuzzi C, Favaloro EJ. Artificial intelligence in the pre-analytical phase: State-of-the art and future perspectives. J Med Biochem 2024; 43:1-10. [PMID: 38496022 PMCID: PMC10943465 DOI: 10.5937/jomb0-45936] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/08/2023] [Accepted: 08/24/2023] [Indexed: 03/19/2024] Open
Abstract
The use of artificial intelligence (AI) has become widespread in many areas of science and medicine, including laboratory medicine. Although it seems obvious that the analytical and post-analytical phases could be the most important fields of application in laboratory medicine, a kaleidoscope of new opportunities has emerged to extend the benefits of AI to many manual labor-intensive activities belonging to the pre-analytical phase, which are inherently characterized by enhanced vulnerability and higher risk of errors. These potential applications involve increasing the appropriateness of test prescription (with computerized physician order entry or demand management tools), improved specimen collection (using active patient recognition, automated specimen labeling, vein recognition and blood collection assistance, along with automated blood drawing), more efficient sample transportation (facilitated by the use of pneumatic transport systems or drones, and monitored with smart blood tubes or data loggers), systematic evaluation of sample quality (by measuring serum indices, fill volume or for detecting sample clotting), as well as error detection and analysis. Therefore, this opinion paper aims to discuss the state-of-the-art and some future possibilities of AI in the preanalytical phase.
Collapse
Affiliation(s)
- Giuseppe Lippi
- University of Verona, Section of Clinical Biochemistry and School of Medicine, Verona, Italy
| | - Camilla Mattiuzzi
- Hospital of Rovereto, Provincial Agency for Social and Sanitary Services (APSS), Medical Direction, Trento, Italy
| | - Emmanuel J. Favaloro
- Institute of Clinical Pathology and Medical Research (ICPMR), Sydney Centres for Thrombosis and Haemostasis, Department of Haematology, NSW Health Pathology, Westmead Hospital, Westmead, NSW Australia
| |
Collapse
|
4
|
Affiliation(s)
- Maria Salinas
- Clinical Laboratory, Hospital de San Juan de Alicante, San Juan, Alicante, Spain
| |
Collapse
|
5
|
Gruson D, Greaves R, Dabla P, Bernardini S, Gouget B, Öz TK. A new door to a different world: opportunities from the metaverse and the raise of meta-medical laboratories. Clin Chem Lab Med 2023; 61:1567-1571. [PMID: 36855921 DOI: 10.1515/cclm-2023-0108] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/30/2023] [Accepted: 02/20/2023] [Indexed: 03/02/2023]
Abstract
OBJECTIVES In the digital age, the metaverse has emerged with impressive potential for many segments of society. The metaverse could be presented as a parallel dimension able to enhance the physical world as well as our actions and decisions in it with the objective to use a coalition between the natural and virtual worlds for value creation. Our aim was to elaborate on the impact of the metaverse on laboratory medicine. METHODS Based on the available evidence, literature and reports, we analyzed the different perspectives of the metaverse on laboratory medicine and the needs for an efficient transition. RESULTS The convergence and integration of technologies in the metaverse will participate to the reimagination of laboratory medicine services with augmented services, users' experiences, efficiency, and personalized care. The revolution around the metaverse offers different opportunities for laboratory medicine but also open multiple related challenges that are presented in this article. CONCLUSIONS Scientific societies, multidisciplinary teams and specialists in laboratory medicine must prepare the integration metaverse and meta-medical laboratories, raise the awareness, educate, set guidance to obtain a maximum of value and mitigate potential adverse consequences.
Collapse
Affiliation(s)
- Damien Gruson
- Department of Clinical Biochemistry, Cliniques Universitaires St-Luc and Université Catholique de Louvain, Brussels, Belgium
- Pôle de recherche en Endocrinologie, Diabète et Nutrition, Institut de Recherche Expérimentale et Clinique, Cliniques Universitaires St-Luc and Université Catholique de Louvain, Brussels, Belgium
- National Committee for the Selection of Reference Laboratories, Ministry of Health, Paris, France
| | - Ronda Greaves
- Murdoch Children's Research Institute, Parkville, VIC, Australia
- Emerging Technologies Division and MHBLM Committee, International Federation Clinical Chemistry and Laboratory Medicine (IFCC), Milan, Italy
| | - Pradeep Dabla
- Department of Biochemistry, G.B. Pant Institute of Postgraduate Medical Education & Research, Associated Maulana Azad Medical College, New Delhi, India
- MHBLM Committee, International Federation Clinical Chemistry and Laboratory Medicine (IFCC), Milan, Italy
| | - Sergio Bernardini
- Department of Experimental Medicine, University of Tor Vergata, Rome, Italy
- Emerging Technologies Division and MHBLM Committee, International Federation Clinical Chemistry and Laboratory Medicine (IFCC), Milan, Italy
| | - Bernard Gouget
- National Committee for the Selection of Reference Laboratories, Ministry of Health, Paris, France
- MHBLM Committee, International Federation Clinical Chemistry and Laboratory Medicine (IFCC), Milan, Italy
| | - Tuğba Kemaloğlu Öz
- Liv Hospital Ulus, Beşiktaş/Istanbul, Türkiye
- Istinye University, Faculty of Medicine, Istanbul, Türkiye
| |
Collapse
|
6
|
Cadamuro J, Cabitza F, Debeljak Z, De Bruyne S, Frans G, Perez SM, Ozdemir H, Tolios A, Carobene A, Padoan A. 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). Clin Chem Lab Med 2023; 61:1158-1166. [PMID: 37083166 DOI: 10.1515/cclm-2023-0355] [Citation(s) in RCA: 26] [Impact Index Per Article: 26.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/07/2023] [Accepted: 04/12/2023] [Indexed: 04/22/2023]
Abstract
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.
Collapse
Affiliation(s)
- Janne Cadamuro
- Department of Laboratory Medicine, Paracelsus Medical University Salzburg, Salzburg, Austria
| | - Federico Cabitza
- DISCo, Università degli Studi di Milano-Bicocca, Milano, Italy
- IRCCS Istituto Ortopedico Galeazzi, Milan, Italy
| | - Zeljko Debeljak
- Faculty of Medicine, Josip Juraj Strossmayer University of Osijek, Osijek, Croatia
- Clinical Institute of Laboratory Diagnostics, University Hospital Center Osijek, Osijek, Croatia
| | - Sander De Bruyne
- Department of Laboratory Medicine, Ghent University Hospital, Ghent, Belgium
| | - Glynis Frans
- Department of Laboratory Medicine, University Hospitals Leuven, KU Leuven, Leuven, Belgium
| | - Salomon Martin Perez
- Unidad de Bioquímica Clínica, Hospital Universitario Virgen Macarena, Sevilla, Spain
| | - Habib Ozdemir
- Department of Medical Biochemistry, Faculty of Medicine, Manisa Celal Bayar University, Manisa, Türkiye
| | - Alexander Tolios
- Department of Transfusion Medicine and Cell Therapy, Medical University of Vienna, Vienna, Austria
| | - Anna Carobene
- IRCCS San Raffaele Scientific Institute, Milan, Italy
| | - Andrea Padoan
- Department of Medicine (DIMED), University of Padova, Padova, Italy
| |
Collapse
|
7
|
Rampi V, Bisazza O. The EU Green Deal: the challenge of greening medical technologies. Clin Chem Lab Med 2023; 61:651-653. [PMID: 36719081 DOI: 10.1515/cclm-2023-0088] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/25/2023] [Accepted: 01/25/2023] [Indexed: 02/01/2023]
Abstract
As sustainability has been a growing priority of the European Union (EU) in the last decade, especially since the establishment of the EU Green Deal, the medical technology sector - including the in vitro diagnostics (IVD) sector - must comply with European legislation in this field, like all other sectors. However, this sector faces particular challenges as the health and safety of human lives are at stake. Chemicals, in particular, can comprise a politically sensitive issue, as they can pose risks to the environment that need to be managed. At the same time, the same chemicals can be considered essential to safeguard continuity of diagnostic services to health systems, who rely on laboratory medicines for the treatment of patients. An important task for the EU Green Deal to succeed, from an IVD sector perspective, is therefore to find the right balance between serving patients on the one hand and protecting the planet on the other.
Collapse
|