Onychomycosis is common. Diagnosis can be confirmed by various methods; a commonly used method is the histological examination of nail clippings. A deep learning system was developed and its diagnostic accuracy compared with that of human experts. A dataset with annotations for fungal elements was used to train an artificial intelligence (AI) model. In a second dataset ( n =199) the diagnostic accuracy of the AI was compared with that of dermatopathologists. The results show a non-inferiority of the deep learning system to that of analogue diagnosis (non-inferiority margin 5%) with respect to specificity and the area under the receiver operating characteristic curve (AUC). The AI achieved an AUC of 0.981. One limitation of this system is the need for a large number of training images. The AI had difficulty recognizing spores and confused serum or aggregated bacteria with fungal elements. Use of this deep learning system in dermatopathology routine might help to diagnose onychomycosis more efficiently.
Major advances have been made regarding the utilization of machine learning techniques for disease diagnosis and prognosis based on complex and high‐dimensional data. Despite all justified enthusiasm, overoptimistic assessments of predictive performance are still common in this area. However, predictive models and medical devices based on such models should undergo a throughout evaluation before being implemented into clinical practice. In this work, we propose a multiple testing framework for (comparative) phase III diagnostic accuracy studies with sensitivity and specificity as co‐primary endpoints. Our approach challenges the frequent recommendation to strictly separate model selection and evaluation, that is, to only assess a single diagnostic model in the evaluation study. We show that our parametric simultaneous test procedure asymptotically allows strong control of the family‐wise error rate. A multiplicity correction is also available for point and interval estimates. Moreover, we demonstrate in an extensive simulation study that our multiple testing strategy on average leads to a better final diagnostic model and increased statistical power. To plan such studies, we propose a Bayesian approach to determine the optimal number of models to evaluate simultaneously. For this purpose, our algorithm optimizes the expected final model performance given previous (hold‐out) data from the model development phase. We conclude that an assessment of multiple promising diagnostic models in the same evaluation study has several advantages when suitable adjustments for multiple comparisons are employed.
Background Proton-pump inhibitors (PPI) are liberally prescribed in patients with liver cirrhosis. Observational studies link PPI therapy in cirrhotic patients with an increased risk for infectious complications, hepatic encephalopathy and an increased risk for hospitalization and mortality. However, patients with liver cirrhosis are also considered to be at risk for peptic ulcer bleeding. The STOPPIT trial evaluates if discontinuation of a pre-existing PPI treatment delays a composite endpoint of re-hospitalization and/or death in patients (recently) hospitalized with liver cirrhosis compared to patients on continued PPI medication. Methods The STOPPIT-trial is a prospective, multicentre, randomized, double-blinded, placebo-controlled, parallel-group trial. In total, 476 patients with complicated liver cirrhosis who already receive long-term PPI therapy without evidence-based indication are 1:1 randomized to receive either esomeprazole 20 mg (control group) or placebo (intervention group) for 360 days. Patients with an indication for PPI therapy (such as a recent diagnosis of peptic ulcers, severe reflux esophagitis, severe hemorrhagic gastritis, recent endoscopic therapy for oesophageal varices) are excluded. The primary composite endpoint is the time-to re-hospitalization and/or death. Secondary endpoints include rates of re-hospitalization, mortality, occurrence of infections, hepatic decompensation and acute-on-chronic liver failure. The safety endpoint is defined as manifestation of an evidence-based indication for PPI re-therapy. The impact of PPI continuation or discontinuation on the intestinal microbiota will be studied. The recruitment will take place at 18 study sites throughout Germany. Recruitment has started in April 2021. Discussion The STOPPIT trial is the first clinical trial to study the effects of PPI withdrawal on relevant outcome variables in patients with complicated liver cirrhosis. If the hypothesis that PPI withdrawal improves clinical outcomes of cirrhosis patients is confirmed, this would argue for a strong restriction of the currently liberal prescription practice of PPIs in this population. If, on the other hand, the trial demonstrates an increased risk of gastrointestinal bleeding events in patients after PPI withdrawal, this could create a rationale for a more liberal, prophylactic PPI treatment in patients with liver cirrhosis. Trial registration EU clinical trials register EudraCT 2019-005008-16 (registered December 27, 2019). ClinicalTrials.gov NCT04448028 (registered June 25, 2020). German Clinical Trials Register DRKS00021290 (registered March 10, 2021).
No abstract
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.