Doctor's Orders-Why Radiologists Should Consider Adjusting Commercial Machine Learning Applications in Chest Radiography to Fit Their Specific Needs.

This retrospective study evaluated a commercial deep learning (DL) software for chest radiographs and explored its performance in different scenarios. A total of 477 patients (284 male, 193 female, mean age 61.4 (44.7-78.1) years) were included. For the reference standard, two radiologists performed independent readings on seven diseases, thus reporting 226 findings in 167 patients. An autonomous DL reading was performed separately and evaluated against the gold standard regarding accuracy, sensitivity and specificity using ROC analysis. The overall average AUC was 0.84 (95%-CI 0.76-0.92) with an optimized DL sensitivity of 85% and specificity of 75.4%. The best results were seen in pleural effusion with an AUC of 0.92 (0.885-0.955) and sensitivity and specificity of each 86.4%. The data also showed a significant influence of sex, age, and comorbidity on the level of agreement between gold standard and DL reading. About 40% of cases could be ruled out correctly when screening for only one specific disease with a sensitivity above 95% in the exploratory analysis. For the combined reading of all abnormalities at once, only marginal workload reduction could be achieved due to insufficient specificity. DL applications like this one bear the prospect of autonomous comprehensive reporting on chest radiographs but for now require human supervision. Radiologists need to consider possible bias in certain patient groups, e.g., elderly and women. By adjusting their threshold values, commercial DL applications could already be deployed for a variety of tasks, e.g., ruling out certain conditions in screening scenarios and offering high potential for workload reduction.

Smell and taste in idiopathic blepharospasm.

The pathophysiology of blepharospasm is incompletely understood. Current concepts suggest that blepharospasm is a network disorder, involving basal ganglia, thalamus, cortex, and, possibly, the cerebellum. Tracing, imaging, and clinical studies revealed that these structures are also concerned with olfaction and taste. Because of this anatomical overlap, dysfunction of the chemical senses in blepharospasm is expected. Injections of botulinum toxin into the eyelid muscles are the first-line treatment of blepharospasm. Yet, the effects of botulinum toxin on the chemical senses have not been systematically assessed. To contribute to a better understanding of blepharospasm, olfactory and gustatory abilities were assessed in 17 subjects with blepharospasm and 17 age-/sex-matched healthy controls. Sniffin Sticks were used to assess odor threshold, odor discrimination, and odor identification. Results of these three Sniffin Sticks subtests were added to the composite olfactory score. The Taste Strips were applied to assess taste. In an adjacent study, we assessed the sense of smell and taste in eight subjects with blepharospasm before and 4 weeks after botulinum toxin treatment. Subjects with blepharospasm had significantly lower (= worse) scores for odor threshold and for the composite olfactory score than healthy controls, while odor discrimination, odor identification, and the composite taste score were not different between groups. The adjacent study revealed that botulinum toxin did not impact the chemical senses. In this study, subjects with blepharospasm had a lower (= worse) odor threshold than healthy controls. As olfaction is important in daily life, findings justify further research of olfaction in blepharospasm.

Olfaction as a Marker for Dystonia: Background, Current State and Directions.

Dystonia is a heterogeneous group of hyperkinetic movement disorders. The unifying descriptor of dystonia is the motor manifestation, characterized by continuous or intermittent contractions of muscles that cause abnormal movements and postures. Additionally, there are psychiatric, cognitive, and sensory alterations that are possible or putative non-motor manifestations of dystonia. The pathophysiology of dystonia is incompletely understood. A better understanding of dystonia pathophysiology is highly relevant in the amelioration of significant disability associated with motor and non-motor manifestations of dystonia. Recently, diminished olfaction was found to be a potential non-motor manifestation that may worsen the situation of subjects with dystonia. Yet, this finding may also shed light into dystonia pathophysiology and yield novel treatment options. This article aims to provide background information on dystonia and the current understanding of its pathophysiology, including the key structures involved, namely, the basal ganglia, cerebellum, and sensorimotor cortex. Additionally, involvement of these structures in the chemical senses are reviewed to provide an overview on how olfactory (and gustatory) deficits may occur in dystonia. Finally, we describe the present findings on altered chemical senses in dystonia and discuss directions of research on olfactory dysfunction as a marker in dystonia.

Smell and taste in cervical dystonia.

The pathophysiology of cervical dystonia is not completely understood. Current concepts of the pathophysiology propose that it is a network disorder involving the basal ganglia, cerebellum and sensorimotor cortex. These structures are primarily concerned with sensorimotor control but are also involved in non-motor functioning such as the processing of information related to the chemical senses. This overlap lets us hypothesize a link between cervical dystonia and altered sense of smell and taste. To prove this hypothesis and to contribute to the better understanding of cervical dystonia, we assessed olfactory and gustatory functioning in 40 adults with idiopathic cervical dystonia and 40 healthy controls. The Sniffin Sticks were used to assess odor threshold, discrimination and identification. Furthermore, the Taste Strips were applied to assess the combined taste score. Motor and non-motor deficits of cervical dystonia including neuropsychological and psychiatric alterations were assessed as cofactors for regression analyses. We found that cervical dystonia subjects had lower scores than healthy controls for odor threshold (5.8 ± 2.4 versus 8.0 ± 3.2; p = 0.001), odor identification (11.7 ± 2.3 versus 13.1 ± 1.3; p = 0.001) and the combined taste score (9.5 ± 2.2 versus 11.7 ± 2.7; p < 0.001), while no difference was found in odor discrimination (12.0 ± 2.5 versus 12.9 ± 1.8; p = 0.097). Regression analysis suggests that age is the main predictor for olfactory decline in subjects with cervical dystonia. Moreover, performance in the Montreal Cognitive Assessment is a predictor for gustatory decline in cervical dystonia subjects. Findings propose that cervical dystonia is associated with diminished olfactory and gustatory functioning.