Laboratory medicine has evolved from a mainly manual profession, providing few selected test results to a highly automated and standardized medical discipline, generating millions of test results per ...year. As the next inevitable evolutional step, artificial intelligence (AI) algorithms will need to assist us in structuring and making sense of the masses of diagnostic data collected today. Such systems will be able to connect clinical and diagnostic data and to provide valuable suggestions in diagnosis, prognosis or therapeutic options. They will merge the often so separated worlds of the laboratory and the clinics. When used correctly, it will be a tool, capable of freeing the physicians time so that he/she can refocus on the patient. In this narrative review I therefore aim to provide an overview of what AI is, what applications currently are available in healthcare and in laboratory medicine in particular. I will discuss the challenges and pitfalls of applying AI algorithms and I will elaborate on the question if healthcare workers will be replaced by such systems in the near future.
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.
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.
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.
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.
This document provides a joint recommendation for venous blood sampling of the European Federation of Clinical Chemistry and Laboratory Medicine (EFLM) Working Group for Preanalytical Phase (WG-PRE) ...and Latin American Working Group for Preanalytical Phase (WG-PRE-LATAM) of the Latin America Confederation of Clinical Biochemistry (COLABIOCLI). It offers guidance on the requirements for ensuring that blood collection is a safe and patient-centered procedure and provides practical guidance on how to successfully overcome potential barriers and obstacles to its widespread implementation. The target audience for this recommendation are healthcare staff members directly involved in blood collection. This recommendation applies to the use of a closed blood collection system and does not provide guidance for the blood collection with an open needle and syringe and catheter collections. Moreover, this document neither addresses patient consent, test ordering, sample handling and transport nor collection from children and unconscious patients. The recommended procedure is based on the best available evidence. Each step was graded using a system that scores the quality of the evidence and the strength of the recommendation. The process of grading was done at several face-to-face meetings involving the same mixture of stakeholders stated previously. The main parts of this recommendation are: 1) Pre-sampling procedures, 2) Sampling procedure, 3) Post-sampling procedures and 4) Implementation. A first draft of the recommendation was circulated to EFLM members for public consultation. WG-PRE-LATAM was also invited to comment the document. A revised version has been sent for voting on to all EFLM and COLABIOCLI members and has been officially endorsed by 33/40 EFLM and 21/21 COLABIOCLI members. We encourage professionals throughout Europe and Latin America to adopt and implement this recommendation to improve the quality of blood collection practices and increase patient and workers safety.
Since beginning of medical diagnostics, laboratory specialists have done an amazing job, continuously improving quality, spectrum and speed of laboratory tests, currently contributing to the majority ...of medical decision making. These improvements are mostly of an incremental evolutionary fashion, meaning improvements of current processes. Sometimes these evolutionary innovations are of a radical fashion, such as the invention of automated analyzers replacing manual testing or the implementation of mass spectrometry, leading to one big performance leap instead of several small ones. In few cases innovations may be of disruptive nature. In laboratory medicine this would be applicable to digitalization of medicine or the decoding of the human genetic material. Currently, laboratory medicine is again facing disruptive innovations or technologies, which need to be adapted to as soon as possible. One of the major disruptive technologies is the increasing availability and medical use of artificial intelligence. It is necessary to rethink the position of the laboratory specialist within healthcare settings and the added value he or she can provide to patient care. The future of the laboratory specialist profession is bright, as it the only medical profession comprising such vast experience in patient diagnostics. However, laboratory specialists need to develop strategies to provide this expertise, by adopting to the quickly evolving technologies and demands. This opinion paper summarizes some of the disruptive technologies as well as strategies to secure and/or improve the quality of diagnostic patient care and the laboratory specialist profession.
Several lines of evidence now confirm that the vast majority of errors in laboratory medicine occur in the extra-analytical phases of the total testing processing, especially in the preanalytical ...phase. Most importantly, the collection of unsuitable specimens for testing (either due to inappropriate volume or quality) is by far the most frequent source of all laboratory errors, thus calling for urgent strategies for improving blood sample quality and managing data potentially generated measuring unsuitable specimens. A comprehensive overview of scientific literature leads us to conclude that hemolyzed samples are the most frequent cause of specimen non-conformity in clinical laboratories (40–70%), followed by insufficient or inappropriate sample volume (10–20%), biological samples collected in the wrong container (5–15%) and undue clotting (5–10%). Less frequent causes of impaired sample quality include contamination by infusion fluids (i.e. most often saline or glucose solutions), cross-contamination of blood tubes additives, inappropriate sample storage conditions or repeated freezing-thawing cycles. Therefore, this article is aimed to summarize the current evidence about the most frequent types of unsuitable blood samples, along with tentative recommendations on how to prevent or manage these preanalytical non-conformities.
The preanalytical phase is crucial for assuring the quality of in vitro diagnostics. The leading aspects which contribute to enhance the vulnerability of this part of the total testing process ...include the lack of standardization of different practices for collecting, managing, transporting and processing biological specimens, the insufficient compliance with available guidelines and the still considerable number of preventable human errors. As in heavy industry, road traffic and aeronautics, technological advancement holds great promise for decreasing the risk of medical and diagnostic errors, thus including those occurring in the extra-analytical phases of the total testing process. The aim of this article is to discuss some potentially useful technological advances, which are not yet routine practice, but may be especially suited for improving the quality of the preanalytical phase in the future. These are mainly represented by introduction of needlewielding robotic phlebotomy devices, active blood tubes, drones for biological samples transportation, innovative approaches for detecting spurious hemolysis and preanalytical errors recording software products.
This study was designed to determine the mineral composition of calculi in nephrocalcinosis with nephrolithiasis, diagnose the underlying disease, and monitor the course of renal function in patients ...with nephrocalcinosis-nephrolithiasis.
Renal calculi extruded in a series of 8 patients with nephrocalcinosis were analysed using Fourier transmission infrared spectrometry. In 4 patients, next-generation sequencing using a nephrocalcinosis-nephrolithiasis panel was performed to determine the nature of the underlying disease. In addition, longitudinal analysis of renal function was performed in all patients.
Seven patients revealed carbonate apatite as the sole constituent of renal calculi. One patient showed a mixed composition of dicalcium phosphate dihydrate/carbonate apatite at first analysis yet in subsequent episodes also had calculi composed of pure carbonate apatite. Further molecular analysis displayed distal renal tubular acidosis in 2 of 4 patients who consented to sequencing. No known genetic defect could be found in the other two cases. In line with prior reports, decline of renal function was dependent on underlying disease. Distal renal tubular acidosis revealed a progressive course of renal failure, whereas other causes showed stable renal function in long term analysis.
Nephrocalcinosis with nephrolithiasis is a rare condition with heterogeneous aetiology. Yet mineral composition of renal calculi predominantly consisted of pure carbonate apatite. This uniform finding is similar to subcutaneous calcifications of various origins and might propose a general principle of tissue calcification. Progressive decline of renal function was found in distal renal tubular acidosis, whereas other conditions remained stable over time.
Automatic assessment of hemoglobin (H), lipaemia (L) and icterus (I) in serum or plasma (HIL indices) is the mainstay for evaluating sample quality. We planned this study to verify whether in-house ...prepared internal quality control (IQC) materials may be suitable for quality assurance of HIL indices. Pools containing different values of each of the three HIL indices were prepared from routine plasma samples, divided in aliquots and frozen at -20°C. Stability of frozen materials was assessed by thawing one aliquot of each pool after different days of freezing (1, 4, 8, 15, 22 and 29), and by measuring HIL indices on baseline fresh samples and frozen-thawed aliquots with Roche Cobas c702. Five fresh liquid IQCs materials were also measured at the same time points. Intra-assay and inter-assay imprecision of HIL indices calculated with commercial IQC materials ranged between 1.1-2.0% and 1.6-3.3%, respectively. When target values of HIL indices were calculated using frozen-thawed aliquots, the inter-assay imprecision of in-house prepared materials was optimal, even better than that of commercial liquid IQCs (H-index, 0.8% versus 1.6%; L-index, 2.2% versus 2.5%; I-index, 0.8% versus 3.3%). In conclusion, in-house prepared IQC materials are cost-effective alternatives to commercial liquid IQCs for HIL quality assurance.
Prophylactic platelet concentrates transfusion represents a therapeutic choice in patients with chemotherapy-induced thrombocytopenia. This prospective, non-interventional study evaluated the effects ...of platelet concentrates transfusion on thromboelastometric parameters of platelet function in 36 transfusion occasions for 11 thrombocytopenic children undergoing chemotherapy. Pre- and posttransfusion (1-2 hours) blood samples were analyzed using standard coagulation tests and thromboelastometry (ROTEM) measurements (EXTEM and FIBTEM tests). Platelet component of the clot was calculated based on the EXTEM and FIBTEM maximum clot elasticity (MCE) results. After transfusion, mean platelet count increased from 16.5 × 109/L to 43.0 × 109/L (P < .001) and platelet component increased from 34.1 to 73.0 (P < .001). Statistically significant increases for posttransfusion EXTEM parameters A10, A20, and maximum clot firmness (MCF) were observed compared to pretransfusion values (P < .001). The EXTEM α-angle values increased posttransfusion (P < .05). The FIBTEM measurements were comparable pre- and posttransfusion. The study showed that platelet concentrates transfusion in thrombocytopenic children undergoing chemotherapy improves platelet-related coagulation pattern.
Background Fasting levels of glucagon are known to be elevated in youth and adults with type 2 diabetes mellitus (T2D). Children and adolescents with obesity were previously reported to show ...increasing fasting and post-glucose-challenge hyperglucagonemia across the spectrum of glucose tolerance, while no data are available in those with impaired fasting glucose (IFG). Materials and methods Individuals from the Beta-JUDO study population (Uppsala and Salzburg 2010–2016) (n=101, age 13.3 ± 2.8, m/f =50/51) were included (90 with overweight or obesity, 11 with normal weight). Standardized OGTT were performed and plasma glucose, glucagon and insulin concentrations assessed at baseline, 5, 10, 15, 30, 60, 90 and 120 minutes. Patients were grouped according to their glycemic state in six groups with normal glucose metabolism (NGM) and normal weight (NG-NW), NGM with obesity or overweight (NG-O), impaired glucose tolerance (IGT), impaired fasting glucose (IFG), IGT+IFG and T2D, and in two groups with NGM and impaired glucose metabolism (IGM), for statistical analysis. Results and conclusion Glucagon concentrations were elevated in young normoglycemic individuals with overweight or obesity (NG-O) compared to normoglycemic individuals with normal weight. Glucagon levels, fasting and dynamic, increased with progressing glycemic deterioration, except in IFG, where levels were comparable to those in NG-O. All glycemic groups showed an overall suppression of glucagon during OGTT. An initial increase of glucagon could be observed in T2D. In T2D, glucagon showed a strong direct linear correlation with plasma glucose levels during OGTT. Glucagon in adolescents, as in adults, may play a role in the disease progression of T2D.