Search

Purpose of Review: Current methods for thyroid nodule risk stratification are subjective, and artificial intelligence algorithms have been used to overcome this shortcoming. In this review, we summarize recent developments in the application of artificial intelligence algorithms for estimating the risks of malignancy in a thyroid nodule., Recent Findings: Artificial intelligence have been used to predict malignancy in thyroid nodules using ultrasound images, cytopathology images, and molecular markers. Recent clinical trials have shown that artificial intelligence model's performance matched that of experienced radiologists and pathologists. Explainable artificial intelligence models are being developed to avoid the black box problem. Risk stratification algorithms using artificial intelligence for thyroid nodules are now commercially available in many countries., Summary: Artificial intelligence models could become a useful tool in a thyroidolgist's armamentarium as a decision support tool. Increased adoption of this emerging technology will depend upon increased awareness of the potential benefits and pitfalls in using artificial intelligence.

Purpose: Adherence rates to published guidelines for diabetic retinopathy (DR) screening is between 35 and 60%. We evaluate a teleretinal DR screening (TDRS) program in a private practice vertically integrated system to increase compliance with retinal screening., Methods: A retrospective pre-post intervention longitudinal study was conducted in a private endocrinology practice using TDRS as the primary intervention. Compliance rates for diabetic retinal screening were compared between December 31, 2016 and December 31, 2018., Results: A total population of 3479 patients were evaluated. Retinal screening compliance improved from 56.5% of patients (1964) pre-intervention to 59.3% of patients (2064) post intervention. The McNemar test was used for statistical analysis and found the change significant (p = 0.004)., Conclusions: TDRS as an adjunct tool in a private practice endocrinology office significantly improved screening rates and can increase access to recommended diabetic eye care. However, the improvement in screening rates was smaller than other types of practice settings. We explore some of the unique challenges to implementation of TDRS in private practice settings., (© 2020 The Authors.)

BACKGROUND Sarcoidosis is a systemic disease that can affect any organ, including the liver. It is manifested by the presence of non-caseating granulomas within involved organs, most commonly the pulmonary, lymphatic, and hepatic system. Unlike pulmonary or lymphatic involvement, hepatic involvement is usually asymptomatic and it is underdiagnosed. Here, we report a case of a patient with a history of pulmonary sarcoidosis who developed hepatic sarcoidosis. CASE REPORT 68-year-old female with pulmonary sarcoidosis with a 2-week history of severe abdominal pain and epigastric tenderness presented to our center. Abdominal magnetic resonance imaging (MRI) demonstrated mild hepatic fibrosis and cirrhosis. A thorough workup was performed including a liver biopsy which showed chronic non-necrotizing granulomas consistent with sarcoidosis. She was started on prednisone and subsequently improved. The patient was symptom-free on follow-up 1 month later. CONCLUSIONS The majority of patients with hepatic sarcoidosis are usually asymptomatic, with only 5-30% presenting with abdominal pain, jaundice, nausea, vomiting, and hepatosplenomegaly. In rare cases, hepatic sarcoidosis can lead to cholestasis, portal hypertension, cirrhosis, or Budd-Chiari syndrome. Treatment with steroids is the mainstay of therapy; however, in severe cases, patients may require liver transplantation. This case report demonstrates that hepatic sarcoidosis is a serious condition, and if not treated, can lead to portal hypertension and cirrhosis. In patients with sarcoidosis, early detection and longitudinal follow-up is important in preventing overt liver failure.

Introduction Basal/bolus insulin (BBI) is superior to sliding scale insulin (SSI) for diabetic patients admitted to hospital general medicine and surgery services, but little has been published on strategies to promote the utilization of BBI by resident physicians. New approaches that promote the effective management of hyperglycemia in hospitals need to be developed. Materials and methods  A prospective study with historical controls was conducted to evaluate the impact of a pocket insulin dosing guide on the diabetes management practices of internal medicine resident physicians at the Southern Illinois University (SIU) School of Medicine, rotating on general medicine. The primary endpoint was the proportion of patients with preexisting diabetes mellitus managed with BBI. Pocket insulin dosing guides with instructions for initiating BBI and daily insulin adjustments were provided to all internal medicine residents in November 2010. BBI utilization rates were monitored over the period November 2010-February 2011 and were compared to the corresponding four-month period over the previous academic year (November 2009-February 2010), which was before the pocket insulin dosing guides were introduced (pilot study). Internal medicine house staff insulin ordering practices were subsequently evaluated for a 12-month period between October 2010-November 2011, with November 2009-October 2010 used as a historical control (study extension). New interns that were starting their residency training from July 2011 were provided with the pocket insulin dosing guides and given the same instructions as the previous academic year's resident physicians. Results  Historical controls (N = 579) and study patients (N = 584) were well matched, with the exception of the male gender (49% vs. 41%, P = 0.01) and diet-managed diabetes (10.5% vs. 6.4%, P = 0.01). During the pilot study, BBI increased from 12.8% of all resident insulin orders in November 2010 to 58.1% of all orders in February 2011 (P < 0.01 for trend). Overall, BBI as a proportion of all resident insulin orders was 35.7% during the pilot phase, which is a six-fold increase over the previous academic year (6%), and was also statistically significant (P<0.01). For the 12-month period of evaluation between November 2010 and October 2011, internal medicine residents ordered BBI for 41.9% of diabetes patients, compared to 16.7% of patients in the 12 months before the pocket insulin dosing guide was introduced (P < 0.01). Patients managed with BBI had higher blood glucose values at admission than patients managed with SSI (195 ± 95 mg/dL vs. 178 ± 83 mg/dL, P < 0.01) and experienced a 41 mg/dL improvement in mean daily capillary blood glucose (CBG) as compared to no change for patients managed with SSI (P = 0.01 for trend). The rate of hypoglycemia, defined as CBG < 70 mg/dL, was 2.4% for both BBI and SSI managed patients (P = 0.93). Conclusion The SIU pocket insulin dosing guide significantly increased the utilization of BBI, decreased SSI orders, and improved hospital glycemic control for patients with diabetes mellitus. However, over half of the general medicine patients were still managed with SSI despite the pocket insulin dosing guides. Conversion of the insulin dosing guide to a smartphone app might improve utilization of the protocol and further increase the use of BBI for inpatient diabetes management by internal medicine house staff., Competing Interests: The authors have declared that no competing interests exist.

Background: Increased blood glucose is associated with adverse clinical outcomes among patients with major illnesses. This study examined the association between blood glucose and adverse outcomes among hospitalized patients with acute exacerbation of chronic obstructive pulmonary disease, for which limited prior data were available., Methods: We studied a cohort of 209 hospitalized patients with acute exacerbation of chronic obstructive pulmonary disease. Univariate analyses and multivariate logistic regression analyses with backward elimination method were performed to evaluate factors associated with in-hospital complications, length of hospitalization, 30-day hospital readmission, and 90-day all-cause mortality., Results: Multivariate logistic regression analysis with backward elimination method revealed that lower blood glucose and age at hospital admission were the most significant risk factors for in-hospital complication. Received respiratory support and in-hospital complications were the most significant risk factors for the length of hospitalization. There were no significant risk factors associated with 30-day hospital readmission and 90-day all-cause mortality., Conclusion: The analyses failed to reveal significant associations between higher blood glucose levels and adverse outcomes. We showed that lower glucose levels (hypoglycemia) results in higher risk for in-hospital complications. In-hospital complications results in longer length of hospitalization, which implies that lower glucose levels (hypoglycemia) indirectly may result in longer length of hospitalization. More studies are needed to better clarify the cause for these associations.