Patient-specific workup of adrenal incidentalomas

Thyroid and adrenal incidentalomas on chest CT: Prevalence, diagnostic work-up and outcomes in a cohort of COVID-19 suspected patients

OBJECTIVE

Due to increased use of computed tomography (CT), prevalence of thyroid and adrenal incidentalomas is rising. Yet, previous studies on the outcomes of diagnostic work-up of incidentalomas are subjected to inclusion bias. Therefore, we aimed to investigate prevalence and outcomes of diagnostic work-up of thyroid and adrenal incidentalomas detected on chest CT in a less selected population of COVID-19 suspected patients.

DESIGN

A retrospective, observational cohort study.

METHODS

We included all COVID-19 suspected patients who underwent chest CT between March 2020 and March 2021. Radiology reports and medical records were reviewed for the presence and subsequent diagnostic work-up of thyroid and adrenal incidentalomas.

RESULTS

A total of 1,992 consecutive COVID-19 patients were included (59.4% male, median age 71 years [IQR: 71-80]). Thyroid and adrenal incidentalomas were identified in 95 (4.8%) and 133 (6.7%) patients, respectively. Higher prevalence was observed with increasing age, among female patients and in patients with malignancy. Forty-four incidentalomas were further analyzed, but no malignancies were found. Only three lesions were hormonally active (1 thyrotoxicosis and 2 mild autonomous cortisol secretion). Diagnostic work-up did not lead to any change in clinical management in 97.7% of the analyzed patients.

CONCLUSION

Prevalence rates of thyroid and adrenal incidentalomas on chest CT in a less selected COVID-19 cohort were 4.8% and 6.7%, respectively. Yet, as all incidentalomas turned out to be benign and only three lesions were (mildly) hormonally active, this raises the question whether intensive diagnostic work-up of incidentalomas is necessary in all patients.

Computer-assisted Reporting and Decision Support Increases Compliance with Follow-up Imaging and Hormonal Screening of Adrenal Incidentalomas

OBJECTIVE

To assess the impact of using a computer-assisted reporting and decision support (CAR/DS) tool at the radiologist point-of-care on ordering provider compliance with recommendations for adrenal incidentaloma workup.

METHOD

Abdominal CT reports describing adrenal incidentalomas (2014 - 2016) were retrospectively extracted from the radiology database. Exclusion criteria were history of cancer, suspected functioning adrenal tumor, dominant nodule size < 1 cm or ≥ 4 cm, myelolipomas, cysts, and hematomas. Multivariable logistic regression models were employed to predict follow-up imaging (FUI) and hormonal screening orders as a function of patient age and sex, nodule size, and CAR/DS use. CAR/DS reports were compared to conventional reports regarding ordering provider compliance with, frequency, and completeness of, guideline-warranted recommendations for FUI and hormonal screening of adrenal incidentalomas using Chi-square test.

RESULT

Of 174 patients (mean age 62.4; 51.1% women) with adrenal incidentalomas, 62% (108/174) received CAR/DS-based recommendations versus 38% (66/174) unassisted recommendations. CAR/DS use was an independent predictor of provider compliance both with FUI (Odds Ratio [OR]=2.47, p = 0.02) and hormonal screening (OR=2.38, p = 0.04). CAR/DS reports recommended FUI (97.2%,105/108) and hormonal screening (87.0%,94/108) more often than conventional reports (respectively, 69.7% [46/66], 3.0% [2/66], both p <0.0001). CAR/DS recommendations more frequently included instructions for FUI time, protocol, and modality than conventional reports (all p <0.001).

CONCLUSION

Ordering providers were at least twice as likely to comply with report recommendations for FUI and hormonal evaluation of adrenal incidentalomas generated using CAR/DS versus unassisted reporting. CAR/DS-directed recommendations were more adherent to guidelines than those generated without.

Incidental Adrenal Masses: Adherence to Guidelines and Methods to Improve Initial Follow-Up, A Systematic Review

OBJECTIVE

Incidental adrenal masses (IAMs) are detected in approximately 1%-2% of abdominal computed tomography (CT) scans. Recent estimates suggest that more than 70-million relevant CT scans are performed annually in the United States; thus, IAMs represent a significant clinical entity. Most clinical guidelines recommend an initial follow-up evaluation that includes imaging and biochemical testing after index IAM detection.

METHODS

Systematic review of literature in the PubMed, EMBASE and Web of Science databases to determine whether guidelines regarding IAM evaluation are followed and to identify effective management strategies. Our initial search was in January 2018 and updated in November, 2019.

RESULTS

31 studies met inclusion criteria. In most institutions, only a minority of patients with IAMs undergo initial follow-up imaging (median 34%, IQR 20%-50%) or biochemical testing (median 18%, IQR 15%-28%). 2 interventions shown to improve IAM evaluation are IAM-specific recommendations in radiology reports and dedicated multi-disciplinary teams. Interventions focused solely on alerting the ordering clinician or primary care provider to the presence of an IAM have not demonstrated effectiveness. Patients who are referred to an endocrinologist are more likely to have a complete IAM evaluation, but few are referred.

DISCUSSION

Most patients with an IAM do not have an initial evaluation. The radiology report has been identified as a key component in determining whether IAMs are evaluated appropriately. Care teams dedicated to management of incidental radiographic findings also improve IAM follow-up. Although the evidence base is sparse, these interventions may be a starting point for further inquiry into optimizing care in this common clinical scenario.

Can abdominal CT features predict autonomous cortisol secretion in patients with adrenal nodules?

PURPOSE

To determine if CT features of adrenal nodules and of the remainder of the abdomen can predict autonomous cortisol secretion (ACH) in patients with adrenal nodules, and to identify a nodule size threshold below which ACH is unlikely.

METHODS

Retrospective review of adult patients with adrenal nodules who underwent CT of abdomen and 1-mg Dexamethasone suppression test within 1 year of each other. Patients were considered to have no ACH if serum cortisol was ≤ 1.8 µg/dL after the 1-mg dexamethasone suppression test and to have possible or definite autonomous cortisol secretion if serum cortisol was > 1.8 µg/dL. The following CT features were assessed: Adrenal nodule length, nodule width, unenhanced nodule attenuation, contralateral adrenal gland thickness, visceral and subcutaneous adipose tissue area, skeletal muscle area and density, and unenhanced liver attenuation.

RESULTS

29 patients had no autonomous cortisol secretion and 29 patients had possible or definite autonomous cortisol secretion. Nodule length and width were the only two variables that significantly differed between patients with nonfunctional nodules and those with possibly or definitely functional nodules. Using a threshold nodule length of 1.5 cm, the sensitivity and specificity for predicting possible or definite autonomous cortisol secretion was 93.1% and 37.9%, respectively.

CONCLUSION

Autonomous cortisol secretion in patients with adrenal nodules correlates with increasing nodule size. A nodule length threshold of 1.5 cm provides 93.1% sensitivity for predicting possible or definite ACH based on the 1-mg Dexamethasone suppression test.

Adrenocortical neoplasm of uncertain malignant potential with a myelolipomatous component

Macroscopic fat inside an adrenal lesion on CT is pathognomonic for myelolipoma, a benign neoplasm. Without macroscopic fat, it can be difficult to discern the nature of an indeterminate adrenal mass on imaging. One possible diagnosis for an indeterminate lesion without macroscopic fat is an adrenal oncocytic neoplasm (AON). Despite its typical benign presentation cases of malignant AON have been reported. Patients with malignant AON are often not surgical candidates and survival for unresected disease is 20%-35%. We present the third report of an AON of uncertain malignant potential (AONUMP) associated with a macroscopic fatty component with the largest reported size and longest duration of follow-up in the literature. This report details diagnostic and therapeutic challenges posed by AONUMP. This case highlights how pathognomonic radiographical findings associated with benign myelolipoma might mask rare, potentially malignant, lipomatous tumours.

Drug-drug interaction extraction via hybrid neural networks on biomedical literature

Adverse events caused by drug-drug interaction (DDI) not only pose a serious threat to health, but also increase additional medical care expenditure. However, despite the emergence of many excellent text mining-based DDI classification methods, achieving a balance between using simpler method and better model performance is still unsatisfactory. In this article, we present a deep learning method of stacked bidirectional Gated Recurrent Unit (GRU)- convolutional neural network (SGRU-CNN) model which apply stacked bidirectional GRU (BiGRU) network and convolutional neural network (CNN) on lexical information and entity position information respectively to conduct DDIs extraction task. Furthermore, SGRU-CNN model assigns the weights of each word feature to improve performance with one attentive pooling layer. On the condition that other values are not inferior to other algorithms, experimental results on the DDI Extraction 2013 corpus show that our model achieves a 1.54% improvement in recall value. And the proposed SGRU-CNN model reaches great performance (F1-score: 0.75) with the fewest features, indicating an excellent balance between avoiding redundant preprocessing task and higher accuracy in relation extraction on biomedical literature using our method.

Plasma Steroid Profiles in Subclinical Compared With Overt Adrenal Cushing Syndrome

CONTEXT

Diagnosis of subclinical adrenal hypercortisolism is based on several tests of the hypothalamic-pituitary-adrenal axis to establish mild alterations of cortisol secretion and dysregulated cortisol physiology.

OBJECTIVE

We assessed whether plasma steroid profiles might assist diagnosis of subclinical Cushing syndrome (SC).

DESIGN

Retrospective cross-sectional study.

SETTING

Two tertiary medical centers.

PATIENTS

Of 208 patients tested for hypercortisolism, disease was excluded in 152 and confirmed in 21 with overt adrenal Cushing syndrome (AC) compared to 35 with SC. Another 277 age- and sex-matched hypertensive and normotensive volunteers were included for reference.

MAIN OUTCOME MEASURES

A panel of 15 plasma steroids was measured by mass spectrometry, with classification by discriminant analysis.

RESULTS

Patients with SC had lower plasma concentrations of dehydroepiandrosterone and dehydroepiandrosterone-sulfate than subjects without SC (P < 0.05). The largest increases (P < 0.001) in plasma steroids among patients with SC were observed for 11-deoxycortisol and 11-deoxycorticosterone. Nevertheless, concentrations of 11-deoxycorticosterone, 11-deoxycortisol, and pregnenolone in patients with AC were higher (P < 0.05) than in those with SC. Patients with SC or AC could be distinguished from subjects without disease using this combination of steroids as precisely as with use of measurements of serum cortisol after administration of dexamethasone. The steroid combination provided superior diagnostic performance compared with each of the other routine biochemical tests.

CONCLUSION

Distinct plasma steroid profiles in patients with SC may provide a simple and reliable screening method for establishing the diagnosis.

Investigation of Fusion Features for Apple Classification in Smart Manufacturing

Smart manufacturing optimizes productivity with the integration of computer control and various high level adaptability technologies including the big data evolution. The evolution of big data offers optimization through data analytics as a predictive solution in future planning decision making. However, this requires accurate and reliable informative data as input for analytics. Therefore, in this paper, the fusion features for apple classification is investigated to classify between defective and non-defective apple for automatic inspection, sorting and further predictive analytics. The fusion features with Decision Tree classifier called Curvelet Wavelet-Gray Level Co-occurrence Matrix (CW-GLCM) is designed based on symmetrical pattern. The CW-GLCM is tested on two apple datasets namely NDDA and NDDAW with a total of 1110 apple images. Each dataset consists of a binary class of apple which are defective and non-defective. The NDDAW consists more low-quality region images. Experimental results show that CW-GLCM successfully classify 98.15% of NDDA dataset and 89.11% of NDDAW dataset. A lower classification accuracy is observed in other five existing image recognition methods especially on NDDAW dataset. Finally, the results show that CW-GLCM is more accurate among all the methods with the difference of more than 10.54% of classification accuracy.

A Novel MOGA-SVM Multinomial Classification for Organ Inflammation Detection

Wrist pulse signal (WPS) contains crucial information of humans’ health condition. It can serve as an alternative method for diagnosing of organ inflammation instead of traditional clinical measurement. In this paper, a novel multi-objective genetic algorithm based support vector machine (MOGA-SVM) has been proposed for the multinomial classification of the inflammations of appendix, pancreas, and duodenum. A customized similarity kernel (KCS) has been optimally designed. The performance of multinomial classification using KCS is compared with five types of kernels, linear, radial basis function (RBF), polynomial and sigmoid kernel, as well as mixtures of polynomial and RBF, to verify the effectiveness of KCS. The sensitivity, specificity and accuracy (Acc) of the proposed method are 92%, 91.2%, and 91.6% respectively. The results have demonstrated that KCS improves the accuracy of classification from 8.9% to 59.6%. When compared to related work, the proposed method increases the performance by more than 10%. It is believed that WPS can serve as alternative measures to diagnose organ inflammations.

Tumor characteristics and surgical outcome in incidentally discovered pheochromocytomas and paragangliomas

OBJECTIVE

The proportion of incidentally discovered pheochromocytomas and paragangliomas(PPGL) has increased over time. However, our knowledge of them is quite limited. The purpose of this retrospective study is to generalize the commonalities in incidentally discovered PPGL, offer evidences for clinical diagnosis and management.

METHODS

526 patients were included in our study after filtration from the database of West China Hospital of Sichuan University between May, 2007 and December, 2016.Among the patients, 148 of them were incidental findings and 378 of them were suspected findings. All patients' demography and tumor characteristics were recorded in detail, especially hemodynamic records and hormonal assays. The reasons for taking radiography were also collected. Most patients received preoperative medical preparation . Intraoperative and postoperative courses as well as surgical outcomes were also analyzed to identify differences between incidental findings and suspected findings.

RESULTS

Incidentally discovered PPGL took up 28.1% of the study population. Suspected PPGLs had a higher prevalence of hypertension, lower proportion of non-functioning PPGL, higher prevalence of MEN2 and better post-surgical blood pressure recovery than incidental finding group. However, patients in the incidental finding group showed no significant difference in preoperative blood pressure and hormonal assays with suspected findings in metaphrine and normetaphrine in plasma and urine (P>0.05).

CONCLUSIONS

Due to the development of technology, more PPGLs are discovered incidentally. Considering the tumor characteristics and surgical outcome, surgical decisions should be made more cautiously.