Automatic Diabetic Foot Ulcer Recognition Using Multi-Level Thermographic Image Data.

Lower extremity diabetic foot ulcers (DFUs) are a severe consequence of diabetes mellitus (DM). It has been estimated that people with diabetes have a 15% to 25% lifetime risk of acquiring DFUs which leads to the risk of lower limb amputations up to 85% due to poor diagnosis and treatment. Diabetic foot develops planter ulcers where thermography is used to detect the changes in the planter temperature. In this study, publicly available thermographic image data including both control group and diabetic group patients are used. Thermograms at image level as well as patch level are utilized for DFU detection. For DFU recognition, several machine-learning-based classification approaches are employed with hand-crafted features. Moreover, a couple of convolutional neural network models including ResNet50 and DenseNet121 are evaluated for DFU recognition. Finally, a CNN-based custom-developed model is proposed for the recognition task. The results are produced using image-level data, patch-level data, and image-patch combination data. The proposed CNN-based model outperformed the utilized models as well as the state-of-the-art models in terms of the AUC and accuracy. Moreover, the recognition accuracy for both the machine-learning and deep-learning approaches was higher for the image-level thermogram data in comparison to the patch-level or combination of image-patch thermograms.

Thromboprophylaxis in Intensive Care Unit Patients: A Literature Review.

Thromboembolism is a major complication in hospitalized patients. Intensive care unit (ICU) patients have a greater risk of thrombotic events due to additional risk factors such as immobilization, mechanical ventilation, and central catheters. The diagnosis and management of deep vein thrombosis (DVT) and pulmonary embolism (PE) in critically ill patients are challenging and these conditions are associated with high mortality. Medical thromboprophylaxis with low molecular weight heparin (LMWH) as well as unfractionated heparin (UFH) has been shown to reduce the incidence of thromboembolic events in such patients. For patients with high risk of bleeding, mechanical thromboprophylaxis can be used. Literature database was conducted on Medline for articles published up to 2018 using particular search terms such as thromboprophylaxis and venous thromboembolism in ICU patients. The following review summarizes the existing data regarding thromboprophylaxis in ICU patients with special consideration to the use of mechanical prophylaxis and pharmacologic prophylaxis using heparin products.

Frequency and correlates of symptoms of anxiety and depression among young caregivers of cancer patients: a pilot study.

OBJECTIVES: To determine the frequency of symptoms of anxiety and depression among the young caregivers of family members with cancer and their correlation with role of gender, age and socio-economic status. RESULTS: A total of 87.8% of caregivers were between 11 and 16 years of age, with 94.6% reported having support from another caregiver. At least 95% of caregivers reported symptoms of anxiety with a higher predisposition among females. Around 73% of caregivers had low monthly incomes followed by (22.9%) middle and (4.1%) high monthly incomes. Care givers belonging to low income groups were more likely to report anxiety and depressive symptoms (70%). Young adults 17-18 years of age reported fewer symptoms of anxiety (10.9%) than their younger counterparts. Reported symptoms of anxiety and depression decreased when the number of care givers increased-2 (67.5%), 3 (16.2%), 4 (5.4%). Increased hospital stay was associated with increased frequency of symptoms, but not beyond 5 weeks.

The efficiency, accuracy and acceptability of smartphone-delivered data collection in a low-resource setting - A prospective study.

Smartphones are increasingly used in healthcare, yet little is known about their utility in medical research as a means of data collection in low- and middle-income countries (LMIC). In this letter, we discuss results from our experiences with data collection on smartphones in an LMIC setting. Our experience found smartphones a secure and reliable data collection tool for medical research that can empower researchers in countries to participate in surgical studies.

Surface Microbiology of Smartphone Screen Protectors Among Healthcare Professionals.

BACKGROUND: The use of smartphones with touch screens has become a norm for healthcare professionals (HCP). The risk of smart screen contamination has been proven, and guidelines are available to deal with possible contamination. A large number of smartphone users apply plastic or glass screen protectors onto their mobile phone screens to prevent scratches. However, these materials are not scratch proof, and their antipathogenic properties have not been studied. METHODS: We have conducted a study to determine the frequency of smartphone screen protector contamination and compared the data with contamination on the bare area on the same mobile screens. The sample size included only HCPs working in acute care settings and having at least eight hours of exposure time every day. RESULTS: A total of 64 samples were collected, which reported 62.5% (n = 40/64) positive culture swabs from the protected areas of the screen and 45.3% (n = 29/64) from the unprotected area of the screen. Micrococcus and Gram-negative rods grew only on samples taken from the protected area whereas the bare area showed no such growth. There was no statistically significant difference in the frequency based on smart screen size, duration of use during duty hours, or the setting where it was used. CONCLUSIONS: Smartphone screen protectors from healthcare providers may harbor pathogenic bacteria, especially in acute care settings. Coagulase-negative Staphylococci followed by Bacillus species were the most commonly yielded bacteria among house officers and postgraduate trainees in the present study.