Diagnosis最新文献

Objectives: Analytical interferences, caused by antibodies, often go unnoticed and require a deep understanding of analyzer principles in the correct clinical context.

Methods: A case report details a 56-year-old man with symptoms of hyperviscosity syndrome (HVS) due to multiple myeloma.

Results: The DxH 900 analyzer revealed abnormalities in the nucleated red blood cell (nRBC) graph, attributed to a high concentration of IgA kappa. Immediate plasmapheresis successfully treated HVS, reducing the monoclonal component and eliminating the aberrant green signal.

Conclusions: In the appropriate clinical context, the recognition of analytical interferences is necessary for accurate clinical interpretation, and it is only possible with knowledge of the analytical principles of the instruments. In this case, the high concentration of IgA kappa generated an aberrant green signal in the VCSm.

Atrial fibrillation (AF) is the most frequent type of cardiac arrhythmia that affects over six million individuals in Europe. The incidence and prevalence of AF rises with age, and often occurs after cardiac surgery. Other risk factors correlated with AF comprise high blood pressure, diabetes mellitus, left atrial enlargement, ischemic heart disease, and congestive heart failure. Considering the high prevalence of AF in aging societies, strategies to prevent serious complications, such as stroke or heart failure, are important because they are correlated with high morbidity and mortality. The supplementation of sea-derived n-3 polyunsaturated fatty acids (PUFA) is widely discussed in this context, but the results of experimental and observational studies are in contrast to randomized placebo-controlled intervention trials (RCTs). Specifically, larger placebo-controlled n-3 PUFA supplementation studies with long follow-up showed a dose-dependent rise in incident AF. Daily n-3 PUFA doses of ≥1 g/d are correlated with a 50 % increase in AF risk, whereas a daily intake of <1 g/d causes AF in only 12 %. Individuals with a high cardiovascular risk (CVD) risk and high plasma-triglycerides seem particularly prone to develop AF upon n-3 PUFA supplementation. Therefore, we should exercise caution with n-3 PUFA supplementation especially in patients with higher age, CVD, hypertriglyceridemia or diabetes. In summary, existing data argue against the additive intake of n-3 PUFA for preventative purposes because of an incremental AF risk and lacking CVD benefits. However, more clinical studies are required to disentangle the discrepancy between n-3 PUFA RCTs and observational studies showing a lower CVD risk in individuals who regularly consume n-3 PUFA-rich fish.

Objectives: Validate the diagnostic accuracy of the Artificial Intelligence Large Language Model ChatGPT4 by comparing diagnosis lists produced by ChatGPT4 to Isabel Pro.

Methods: This study used 201 cases, comparing ChatGPT4 to Isabel Pro. Systems inputs were identical. Mean Reciprocal Rank (MRR) compares the correct diagnosis's rank between systems. Isabel Pro ranks by the frequency with which the symptoms appear in the reference dataset. The mechanism ChatGPT4 uses to rank the diagnoses is unknown. A Wilcoxon Signed Rank Sum test failed to reject the null hypothesis.

Results: Both systems produced comprehensive differential diagnosis lists. Isabel Pro's list appears immediately upon submission, while ChatGPT4 takes several minutes. Isabel Pro produced 175 (87.1 %) correct diagnoses and ChatGPT4 165 (82.1 %). The MRR for ChatGPT4 was 0.428 (rank 2.31), and Isabel Pro was 0.389 (rank 2.57), an average rank of three for each. ChatGPT4 outperformed on Recall at Rank 1, 5, and 10, with Isabel Pro outperforming at 20, 30, and 40. The Wilcoxon Signed Rank Sum Test confirmed that the sample size was inadequate to conclude that the systems are equivalent. ChatGPT4 fabricated citations and DOIs, producing 145 correct references (87.9 %) but only 52 correct DOIs (31.5 %).

Conclusions: This study validates the promise of Clinical Diagnostic Decision Support Systems, including the Large Language Model form of artificial intelligence (AI). Until the issue of hallucination of references and, perhaps diagnoses, is resolved in favor of absolute accuracy, clinicians will make cautious use of Large Language Model systems in diagnosis, if at all.

Objectives: Diagnostic errors are the leading cause of preventable harm in clinical practice. Implementable tools to quantify and target this problem are needed. To address this gap, we aimed to generalize the Symptom-Disease Pair Analysis of Diagnostic Error (SPADE) framework by developing its computable phenotype and then demonstrated how that schema could be applied in multiple clinical contexts.

Methods: We created an information model for the SPADE processes, then mapped data fields from electronic health records (EHR) and claims data in use to that model to create the SPADE information model (intention) and the SPADE computable phenotype (extension). Later we validated the computable phenotype and tested it in four case studies in three different health systems to demonstrate its utility.

Results: We mapped and tested the SPADE computable phenotype in three different sites using four different case studies. We showed that data fields to compute an SPADE base measure are fully available in the EHR Data Warehouse for extraction and can operationalize the SPADE framework from provider and/or insurer perspective, and they could be implemented on numerous health systems for future work in monitor misdiagnosis-related harms.

Conclusions: Data for the SPADE base measure is readily available in EHR and administrative claims. The method of data extraction is potentially universally applicable, and the data extracted is conveniently available within a network system. Further study is needed to validate the computable phenotype across different settings with different data infrastructures.

Objectives: It has been recognized that shortened activated partial thromboplastin time (aPTT) may be caused by various preanalytical conditions. As coagulation Factor VIII is included in the in vitro intrinsic coagulation cascade measured by aPTT, we hypothesized that the shortened aPTT could be a result of elevated FVIII activity. We aimed to inspect the connection of elevated FVIII with shortened aPTT, and the possible effect inflammation has on routine laboratory parameters.

Methods: 40 patients from various hospital departments with aPTT measurement below the lower limit of the reference interval (<23.0 s) were included in the study. To compare the obtained results with aPTT measurements in the non-inflammatory state, samples from 25 volunteers (laboratory personnel) were collected. White blood cell count, C-reactive protein, aPTT, and FVIII values were measured in the control group.

Results: Only two samples among 40 patients with shortened aPTT (5 %) were clotted. Out of the remaining 38, 26 had FVIII activity above 150 % (upper limit of a reference interval), median value of 194 % (IQR: 143-243 %). Seven samples in the control group had shortened aPTT results (36 %). However, all coagulation samples were clot and hemolysis-free. Multiple regression identified only FVIII activity as an independent variable in predicting aPTT values (p=0.001).

Conclusions: Our results support the thesis that shortened aPTT is rarely a consequence of preanalytical problems. Elevated FVIII activity causes shortened aPTT, not only in the inflammatory state but also in individuals with concentration of inflammatory markers within reference intervals.

Objectives: This study evaluates the comparative diagnostic accuracy of dental students and artificial intelligence (AI), specifically a modified ChatGPT 4, in endodontic assessments related to pulpal and apical conditions. The findings are intended to offer insights into the potential role of AI in augmenting dental education.

Methods: Involving 109 dental students divided into junior (54) and senior (55) groups, the study compared their diagnostic accuracy against ChatGPT's across seven clinical scenarios. Juniors had the American Association of Endodontists (AEE) terminology assistance, while seniors relied on prior knowledge. Accuracy was measured against a gold standard by experienced endodontists, using statistical analysis including Kruskal-Wallis and Dwass-Steel-Critchlow-Fligner tests.

Results: ChatGPT achieved significantly higher accuracy (99.0 %) compared to seniors (79.7 %) and juniors (77.0 %). Median accuracy was 100.0 % for ChatGPT, 85.7 % for seniors, and 82.1 % for juniors. Statistical tests indicated significant differences between ChatGPT and both student groups (p<0.001), with no notable difference between the student cohorts.

Conclusions: The study reveals AI's capability to outperform dental students in diagnostic accuracy regarding endodontic assessments. This underscores AIs potential as a reference tool that students could utilize to enhance their understanding and diagnostic skills. Nevertheless, the potential for overreliance on AI, which may affect the development of critical analytical and decision-making abilities, necessitates a balanced integration of AI with human expertise and clinical judgement in dental education. Future research is essential to navigate the ethical and legal frameworks for incorporating AI tools such as ChatGPT into dental education and clinical practices effectively.

Objectives: We sought within an ambulatory safety study to understand if the Revised Safer Dx instrument may be helpful in identification of diagnostic missed opportunities in care of children with type 1 diabetes (T1D) and autism spectrum disorder (ASD).

Methods: We reviewed two months of emergency department (ED) encounters for all patients at our tertiary care site with T1D and a sample of such encounters for patients with ASD over a 15-month period, and their pre-visit communication methods to better understand opportunities to improve diagnosis. We applied the Revised Safer Dx instrument to each diagnostic journey. We chose potentially preventable ED visits for hyperglycemia, diabetic ketoacidosis, and behavioral crises, and reviewed electronic health record data over the prior three months related to the illness that resulted in the ED visit.

Results: We identified 63 T1D and 27 ASD ED visits. Using the Revised Safer Dx instrument, we did not identify any potentially missed opportunities to improve diagnosis in T1D. We found two potential missed opportunities (Safer Dx overall score of 5) in ASD, related to potential for ambulatory medical management to be improved. Over this period, 40 % of T1D and 52 % of ASD patients used communication prior to the ED visit.

Conclusions: Using the Revised Safer Dx instrument, we uncommonly identified missed opportunities to improve diagnosis in patients who presented to the ED with potentially preventable complications of their chronic diseases. Future researchers should consider prospectively collected data as well as development or adaptation of tools like the Safer Dx.

Objectives: To analyze the Big Three diagnostic errors (malignant neoplasms, cardiovascular diseases, and infectious diseases) through internists' self-reflection on their most memorable diagnostic errors.

Methods: This secondary analysis study, based on a web-based cross-sectional survey, recruited participants from January 21 to 31, 2019. The participants were asked to recall the most memorable diagnostic error cases in which they were primarily involved. We gathered data on internists' demographics, time to error recognition, and error location. Factors causing diagnostic errors included environmental conditions, information processing, and cognitive bias. Participants scored the significance of each contributing factor on a Likert scale (0, unimportant; 10, extremely important).

Results: The Big Three comprised 54.1 % (n=372) of the 687 cases reviewed. The median physician age was 51.5 years (interquartile range, 42-58 years); 65.6 % of physicians worked in hospital settings. Delayed diagnoses were the most common among malignancies (n=64, 46 %). Diagnostic errors related to malignancy were frequent in general outpatient settings on weekdays and in the mornings and were not identified for several months following the event. Environmental factors often contributed to cardiovascular disease-related errors, which were typically identified within days in emergency departments, during night shifts, and on holidays. Information gathering and interpretation significantly impacted infectious disease diagnoses.

Conclusions: The Big Three accounted for the majority of cases recalled by Japanese internists. The most relevant contributing factors were different for each of the three categories. Addressing these errors may require a unique approach based on the disease associations.

Objectives: Early skin cancer diagnosis can save lives; however, traditional methods rely on expert knowledge and can be time-consuming. This calls for automated systems using machine learning and deep learning. However, existing datasets often focus on flat skin surfaces, neglecting more complex cases on organs or with nearby lesions.

Methods: This work addresses this gap by proposing a skin cancer diagnosis methodology using a dataset named ASAN that covers diverse skin cancer cases but suffers from noisy features. To overcome the noisy feature problem, a segmentation dataset named SASAN is introduced, focusing on Region of Interest (ROI) extraction-based classification. This allows models to concentrate on critical areas within the images while ignoring learning the noisy features.

Results: Various deep learning segmentation models such as UNet, LinkNet, PSPNet, and FPN were trained on the SASAN dataset to perform segmentation-based ROI extraction. Classification was then performed using the dataset with and without ROI extraction. The results demonstrate that ROI extraction significantly improves the performance of these models in classification. This implies that SASAN is effective in evaluating performance metrics for complex skin cancer cases.

Conclusions: This study highlights the importance of expanding datasets to include challenging scenarios and developing better segmentation methods to enhance automated skin cancer diagnosis. The SASAN dataset serves as a valuable tool for researchers aiming to improve such systems and ultimately contribute to better diagnostic outcomes.