ABSTRACT
Background: Published studies have reported that acute kidney injury (AKI) and other kidney related manifestations are associated with COVID-19 and linked with poor outcome. This study aimed to determine the incidence, risk factors and outcomes of AKI in hospitalized COVID-19 patients.
ABSTRACT
We present a case of mineralocorticoid induced hypertension secondary to Cushing's syndrome in a hospitalized patient with uncontrolled hypertension and hypokalemia.A 78-year-old female with hypertension, hypothyroidism, and known pituitary (1.6 cm) and left-sided adrenal mass (2.9 cm) since 2012, presented to the hospital with altered mental status and rectal bleeding with hemoglobin of 5.8 g/dL. On arrival, she was afebrile, blood pressure 87/51 mm Hg, pulse 95 bpm, and saturating at 97% on room air. The patient was altered and had bloody stool positive for fecal occult blood test, with the rest of the examination being normal. Her hospital course was complicated by uncontrolled hypertension (on lisinopril and amlodipine) and severe hypokalemia. During her hospital stay, her potassium ranged 2-2.5 mEq/L (3.5-5.1) and she had persistent metabolic alkalosis. Aldosterone <1 ng/dL, plasma renin activity (PRA) 0.38 ng/mL/hr and aldosterone/PRA ratio 2.6 (0.9-28.9). Thyroid function: TSH 0.709 uIU/mL (0.30-5.00), free T4 1.4 ng/dL (0.7-1.7). Catecholamines were not significantly elevated: free metanephrines <25 pg/mL (<57), normetanephrines 158 pg/mL (<148). Further investigation revealed severe hypercortisolism: 24-hour urinary free cortisol 422 mcg/24 hours, cortisol AM 29.2 mcg/dL (3.7-19.4), and cortisol 31 mcg/dL with 1 mg dexamethasone suppression test. Late-night salivary cortisol was not obtained. ACTH was 138 pg/mL (9-46) and cortisol level after 8 mg dexamethasone suppression test was elevated at 17.2 ug/dL. MRI brain showed a pituitary macroadenoma sized 1.6×1.4×1.1 cm, stable since 2012. CT abdomen showed a left adrenal nodule measuring 2.3×3.3×2.8 cm. Further workup revealed free testosterone 10.6 pg/mL(0.2-3.7), total testosterone 22 ng/dL (2-45), DHEA-Sulfate 533 mcg/dL (45-430), IGF-1 81 ng/mL(34-245), Human growth hormone 0.2 ng/mL (<10), FSH 0.3 mIU/mL, LH 0.1 mIU/mL, prolactin 18.9 ng/mL(0-29), and deoxycorticosterone <16 ng/dL (<16). Given the patient's clinical presentation (rectal bleeding, altered mental status) with associated laboratory abnormalities, the plausible explanation for her hypertension and hypokalemia was ACTH-mediated hypercortisolism resulting in increased mineralocorticoid activity. Other possible etiologies considered were syndrome of apparent mineralocorticoid excess, Liddle's syndrome, deoxycorticosterone tumors, and exogenous intake of steroids. The patient was started on spironolactone and amiloride, both blood pressure and potassium levels improved. A decision was made to proceed with inferior petrosal sinus sampling, to determine the exact source of ACTH, however, prior to completion patient developed COVID pneumonia and expired.Our case highlights the importance of considering hypercortisolism in patients presenting with hypertension, hypokalemia, and metabolic alkalosis with suppressed aldosterone and renin levels. Furthermore, Cushing's syndrome should be a consideration even in the absence of classic cushingoid features as in this patient.Presentation: Monday, June 13, 2022 12:30 p.m. - 2:30 p.m.
ABSTRACT
Classification and regression are the major applications of machine learning algorithms which are widely used to solve problems in numerous domains of engineering and computer science. Different classifiers based on the optimization of the decision tree have been proposed, however, it is still evolving over time. This paper presents a novel and robust classifier based on a decision tree and tabu search algorithms, respectively. In the aim of improving performance, our proposed algorithm constructs multiple decision trees while employing a tabu search algorithm to consistently monitor the leaf and decision nodes in the corresponding decision trees. Additionally, the used tabu search algorithm is responsible to balance the entropy of the corresponding decision trees. For training the model, we used the clinical data of COVID-19 patients to predict whether a patient is suffering. The experimental results were obtained using our proposed classifier based on the built-in sci-kit learn library in Python. The extensive analysis for the performance comparison was presented using Big O and statistical analysis for conventional supervised machine learning algorithms. Moreover, the performance comparison to optimized state-of-the-art classifiers is also presented. The achieved accuracy of 98%, the required execution time of 55.6 ms and the area under receiver operating characteristic (AUROC) for proposed method of 0.95 reveals that the proposed classifier algorithm is convenient for large datasets. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.