A direct comparison in diagnostic performance of CDUS, FDG-PET/CT and MRI in patients suspected of giant cell arteritis.

OBJECTIVES: This study directly compares diagnostic performance of Colour Duplex Ultrasound (CDUS), Fluor-18-deoxyglucose Positron Emission Tomography Computed Tomography (FDG-PET/CT) and Magnetic Resonance Imaging (MRI) in patients suspected of giant cell arteritis (GCA). METHODS: Patients with suspected GCA were included in a nested-case control pilot study. CDUS, whole body FDG-PET/CT and cranial MRI were performed within 5 working days after initial clinical evaluation. Clinical diagnosis after six months follow-up by experienced rheumatologists in the field of GCA, blinded for imaging, was used as reference standard. Diagnostic performance of the imaging modalities was determined. Stratification for GCA subtype was performed and imaging results were evaluated in different risk stratification groups. RESULTS: In total, 23 patients with GCA and 19 patients suspected of but not diagnosed with GCA were included. Sensitivity was 69.6% (95%CI 50.4%-88.8%) for CDUS, 52.2% (95%CI 31.4%-73.0%) for FDG-PET/CT and 56.5% (95%CI 35.8%-77.2%) for MRI. Specificity was 100% for CDUS, FDG-PET/CT and MRI. FDG-PET/CT was negative for GCA in all isolated cranial GCA patients (n = 8), while MRI was negative in all isolated extracranial GCA patients (n = 4). In 4 GCA patients with false-negative (n = 2; intermediate and high risk) or inconclusive (n = 2; low and intermediate risk) CDUS results, further imaging confirmed diagnosis. CONCLUSIONS: Sensitivity of CDUS was highest, while specificity was excellent in all imaging modalities. Nevertheless, confidence intervals of all imaging modalities were overlapping. Following EULAR recommendations, CDUS can be used as a first test to diagnose GCA. With insufficient evidence for GCA, further testing considering GCA subtype is warranted.

Comparison of Commercial AI Software Performance for Radiograph Lung Nodule Detection and Bone Age Prediction.

Background Multiple commercial artificial intelligence (AI) products exist for assessing radiographs; however, comparable performance data for these algorithms are limited. Purpose To perform an independent, stand-alone validation of commercially available AI products for bone age prediction based on hand radiographs and lung nodule detection on chest radiographs. Materials and Methods This retrospective study was carried out as part of Project AIR. Nine of 17 eligible AI products were validated on data from seven Dutch hospitals. For bone age prediction, the root mean square error (RMSE) and Pearson correlation coefficient were computed. The reference standard was set by three to five expert readers. For lung nodule detection, the area under the receiver operating characteristic curve (AUC) was computed. The reference standard was set by a chest radiologist based on CT. Randomized subsets of hand (n = 95) and chest (n = 140) radiographs were read by 14 and 17 human readers, respectively, with varying experience. Results Two bone age prediction algorithms were tested on hand radiographs (from January 2017 to January 2022) in 326 patients (mean age, 10 years ± 4 [SD]; 173 female patients) and correlated strongly with the reference standard (r = 0.99; P < .001 for both). No difference in RMSE was observed between algorithms (0.63 years [95% CI: 0.58, 0.69] and 0.57 years [95% CI: 0.52, 0.61]) and readers (0.68 years [95% CI: 0.64, 0.73]). Seven lung nodule detection algorithms were validated on chest radiographs (from January 2012 to May 2022) in 386 patients (mean age, 64 years ± 11; 223 male patients). Compared with readers (mean AUC, 0.81 [95% CI: 0.77, 0.85]), four algorithms performed better (AUC range, 0.86-0.93; P value range, <.001 to .04). Conclusions Compared with human readers, four AI algorithms for detecting lung nodules on chest radiographs showed improved performance, whereas the remaining algorithms tested showed no evidence of a difference in performance. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Omoumi and Richiardi in this issue.

Accurate and Reliable Classification of Unstructured Reports on Their Diagnostic Goal Using BERT Models.

Understanding the diagnostic goal of medical reports is valuable information for understanding patient flows. This work focuses on extracting the reason for taking an MRI scan of Multiple Sclerosis (MS) patients using the attached free-form reports: Diagnosis, Progression or Monitoring. We investigate the performance of domain-dependent and general state-of-the-art language models and their alignment with domain expertise. To this end, eXplainable Artificial Intelligence (XAI) techniques are used to acquire insight into the inner workings of the model, which are verified on their trustworthiness. The verified XAI explanations are then compared with explanations from a domain expert, to indirectly determine the reliability of the model. BERTje, a Dutch Bidirectional Encoder Representations from Transformers (BERT) model, outperforms RobBERT and MedRoBERTa.nl in both accuracy and reliability. The latter model (MedRoBERTa.nl) is a domain-specific model, while BERTje is a generic model, showing that domain-specific models are not always superior. Our validation of BERTje in a small prospective study shows promising results for the potential uptake of the model in a practical setting.

Radiology report generation for proximal femur fractures using deep classification and language generation models.

Proximal femur fractures represent a major health concern, and substantially contribute to the morbidity of elderly. Correct classification and diagnosis of hip fractures has a significant impact on mortality, costs and hospital stay. In this paper, we present a method and empirical validation for automatic subclassification of proximal femur fractures and Dutch radiological report generation that does not rely on manually curated data. The fracture classification model was trained on 11,000 X-ray images obtained from 5000 electronic health records in a general hospital. To generate the Dutch reports, we first trained an embedding model on 20,000 radiological reports of pelvic region fractures, and used its embeddings in the report generation model. We trained the report generation model on the 5000 radiological reports associated with the fracture cases. Our report generation model is on par with state-of-the-art in terms of BLEU and ROUGE scores. This is promising, because in contrast to those earlier works, our approach does not require manual preprocessing of either images or the reports. This boosts the applicability of automatic clinical report generation in practice. A quantitative and qualitative user study among medical students found no significant difference in provenance of real and generated reports. A qualitative, in-depth clinical relevance study with medical domain experts showed that from a human perspective the quality of the generated reports approximates the quality of the original reports and highlights challenges in creating sufficiently detailed and versatile training data for automatic radiology report generation.

A Tale of Diagnostic Delay with Detrimental Consequences: Illustrating the Challenging Nature of Diagnosing Giant Cell Arteritis.

Giant cell arteritis is a medical emergency as severe, irreversible complications may occur if it is not treated in a timely manner. However, in daily practice early diagnosis can be challenging. We report the case of a 70-year-old woman who presented with multiple ischaemic cerebral vascular accidents related to newly diagnosed giant cell arteritis. Review of her charts revealed a substantial delay from the onset of symptoms to diagnosis. This case demonstrates the need for additional efforts to reduce delay in referring patients with giant cell arteritis and the need to implement fast-track clinics to prevent serious complications. LEARNING POINTS: Giant cell arteritis is a medical emergency and unnecessary diagnostic delay can result in severe complications.Despite implementation of fast-track clinics, diagnostic delay still occurs due to the generic nature of signs and symptoms and inadequate case finding.As diagnostic delay can lead to preventable complications, increased knowledge and awareness of the characteristics and urgency of giant cell arteritis is needed among referring physicians.

Prolonged Unconsciousness Following Severe COVID-19.

OBJECTIVE: We report a case series of patients with prolonged but reversible unconsciousness after coronavirus disease 2019 (COVID-19)-related severe respiratory failure. METHODS: A case series of patients who were admitted to the intensive care unit due to COVID-19-related acute respiratory failure is described. RESULTS: After cessation of sedatives, the described cases all showed a prolonged comatose state. Diagnostic neurologic workup did not show signs of devastating brain injury. The clinical pattern of awakening started with early eye opening without obeying commands and persistent flaccid weakness in all cases. Time between cessation of sedatives to the first moment of being fully responsive with obeying commands ranged from 8 to 31 days. CONCLUSION: Prolonged unconsciousness in patients with severe respiratory failure due to COVID-19 can be fully reversible, warranting a cautious approach for prognostication based on a prolonged state of unconsciousness.

Automatic Process Comparison for Subpopulations: Application in Cancer Care.

Processes in organisations, such as hospitals, may deviate from the intended standard processes, due to unforeseeable events and the complexity of the organisation. For hospitals, the knowledge of actual patient streams for patient populations (e.g., severe or non-severe cases) is important for quality control and improvement. Process discovery from event data in electronic health records can shed light on the patient flows, but their comparison for different populations is cumbersome and time-consuming. In this paper, we present an approach for the automatic comparison of process models that were extracted from events in electronic health records. Concretely, we propose comparing processes for different patient populations by cross-log conformance checking, and standard graph similarity measures obtained from the directed graph underlying the process model. We perform a user study with 20 participants in order to obtain a ground truth for similarity of process models. We evaluate our approach on two data sets, the publicly available MIMIC database with the focus on different cancer patients in intensive care, and a database on breast cancer patients from a Dutch hospital. In our experiments, we found average fitness to be a good indicator for visual similarity in the ZGT use case, while the average precision and graph edit distance are strongly correlated with visual impression for cancer process models on MIMIC. These results are a call for further research and evaluation for determining which similarity or combination of similarities is needed in which type of process model comparison.

Post-Structuring Radiology Reports of Breast Cancer Patients for Clinical Quality Assurance.

Hospitals often set protocols based on well defined standards to maintain the quality of patient reports. To ensure that the clinicians conform to the protocols, quality assurance of these reports is needed. Patient reports are currently written in free-text format, which complicates the task of quality assurance. In this paper, we present a machine learning based natural language processing system for automatic quality assurance of radiology reports on breast cancer. This is achieved in three steps: we i) identify the top-level structure (headings) of the report, ii) classify the report content into the top-level headings, and iii) convert the free-text detailed findings in the report to a semi-structured format (post-structuring). Top level structure and content of report were predicted with an F1 score of 0.97 and 0.94, respectively, using Support Vector Machine (SVM) classifiers. For automatic structuring, our proposed hierarchical Conditional Random Field (CRF) outperformed the baseline CRF with an F1 score of 0.78 versus 0.71. The determined structure of the report is represented in semi-structured XML format of the free-text report, which helps to easily visualize the conformance of the findings to the protocols. This format also allows easy extraction of specific information for other purposes such as search, evaluation, and research.