Application of artificial intelligence techniques for non-alcoholic fatty liver disease diagnosis: A systematic review (2005-2023).

BACKGROUND AND OBJECTIVES: Non-alcoholic fatty liver disease (NAFLD) is a common liver disease with a rapidly growing incidence worldwide. For prognostication and therapeutic decisions, it is important to distinguish the pathological stages of NAFLD: steatosis, steatohepatitis, and liver fibrosis, which are definitively diagnosed on invasive biopsy. Non-invasive ultrasound (US) imaging, including US elastography technique, and clinical parameters can be used to diagnose and grade NAFLD and its complications. Artificial intelligence (AI) is increasingly being harnessed for developing NAFLD diagnostic models based on clinical, biomarker, or imaging data. In this work, we systemically reviewed the literature for AI-enabled NAFLD diagnostic models based on US (including elastography) and clinical (including serological) data. METHODS: We performed a comprehensive search on Google Scholar, Scopus, and PubMed search engines for articles published between January 2005 and June 2023 related to AI models for NAFLD diagnosis based on US and/or clinical parameters using the following search terms: "non-alcoholic fatty liver disease", "non-alcoholic steatohepatitis", "deep learning", "machine learning", "artificial intelligence", "ultrasound imaging", "sonography", "clinical information". RESULTS: We reviewed 64 published models that used either US (including elastography) or clinical data input to detect the presence of NAFLD, non-alcoholic steatohepatitis, and/or fibrosis, and in some cases, the severity of steatosis, inflammation, and/or fibrosis as well. The performances of the published models were summarized, and stratified by data input and algorithms used, which could be broadly divided into machine and deep learning approaches. CONCLUSION: AI models based on US imaging and clinical data can reliably detect NAFLD and its complications, thereby reducing diagnostic costs and the need for invasive liver biopsy. The models offer advantages of efficiency, accuracy, and accessibility, and serve as virtual assistants for specialists to accelerate disease diagnosis and reduce treatment costs for patients and healthcare systems.

The Therapeutic Potential of Resistant Starch in Modulation of Insulin Resistance, Endotoxemia, Oxidative Stress and Antioxidant Biomarkers in Women with Type 2 Diabetes: A Randomized Controlled Clinical Trial.

AIMS: This trial aims to determine the effects of resistant starch (RS) subtype 2 (RS2) on glycemic status, metabolic endotoxemia and markers of oxidative stress. METHODS: A randomized, controlled, parallel-group clinical trial group of 56 females with type 2 diabetes mellitus (T2DM) was divided to 2 groups. The intervention group (n = 28) and control group (n = 28) received 10 g/day RS2 or placebo for 8 weeks, respectively. Fasting blood samples were taken to determine glycemic status, endotoxin, high sensitivity C-reactive protein (hs-CRP), malondialdehyde (MDA), total antioxidant capacity (TAC), antioxidant enzymes concentrations as well as uric acid at baseline and after the intervention. RESULTS: After 8 weeks, RS2 caused a significant decrease in the levels of MDA (-34.10%), glycosylated hemoglobin (-9.40%), insulin (-29.36%), homeostasis model of insulin resistance (-32.85%) and endotoxin (-25.00%), a significant increase in TAC (18.10%) and glutathione peroxidase (11.60%) as compared with control. No significant changes were observed in fasting plasma glucose, quantitative insulin sensitivity check index, hs-CRP, superoxide dismutase, catalase and uric acid in the RS2 group as compared with the control group. CONCLUSION: Supplementation with RS2 may be improved glycemic status, endotoxemia and markers of oxidative stress in patients with T2DM.

Interdigital intertrigo due to Fusarium oxysporum.

BACKGROUND AND PURPOSE: Fusariosis is a fungal infection often involving the skin. Various species can cause local, focally invasive, or disseminated infections. The routes of entry for Fusarium species include the respiratory tract, gastrointestinal tract, toe nails, trauma to the skin, and indwelling central venous catheter. CASE REPORT: Herein, we present the case of a 35-year-old woman presenting with interdigital intertrigo. The patient had no predisposing factors and she did not take any antifungal agents. Fusiform macroconidia were observed on the slide culture of the fungus. The etiological agent of the infection was identified as Fusarium oxysporum through sequencing of the translation elongation factor-1 alpha (TEF-1α) gene using the primers EF1 and EF2. CONCLUSION: Fusariosis commonly presents as a severe fungal infection in immunocompromised patients. However, this infection may also occur in immunocompetent patients. Although treatment with amphotericin B is a routine antifungal therapy for fusariosis, many azoles such as cloterimazole can be used topically with fewer side-effects.

Identification of Candida species in the oral cavity of diabetic patients.

BACKGROUND AND PURPOSE: Diabetic patients are more susceptible to oral candidiasis infection than non-diabetics due to the factors promoting oral carriage of Candida. Several factors can increase colonization of Candida species in the oral cavity such as xerostomia, which reduces the salivary flow and is a salivary pH disorder. In the current study, we aimed to identify and compare the colonization level of Candida spp. in the oral cavity of diabetic and non-diabetic groups. MATERIALS AND METHODS: Swabs were taken from the mouth of 106 participants and were cultured on Sabouraud dextrose agar (SDA) medium. Likewise, the saliva samples were collected for salivary glucose and pH measurements. The study was performed during June 2014-September 2015 on two groups of diabetic patients (n=58) and non-diabetics (n=48) as the control group. The Candida spp. were identified with PCR-restriction fragment length polymorphism (RFLP) using the restriction enzymes HinfI and MspI and were differentiated by culture on CHROMagar Candida medium. RESULTS: The frequency of Candida spp. was higher in diabetic patients compared to non-diabetics. The most frequent Candida spp. in the diabetic patients were Candidaalbicans (%36.2),C. Krusei (%10.4), C. Glabrata (%5.1), and C.tropcalis .(%3.4)Likewise, C. albicans was the most frequent species (%27) in the non-diabetic individuals. In this study, the results of both methods for identification of the isolates were consistent with each other. CONCLUSION: Xerostomia and disturbance of physiological factors including pH and glucose can promote overgrowth of Candida flora in the oral cavity. These factors are considered important predisposing factors for oral candidiasis in diabetic patients. In the present study, it was observed that application of CHROMagar Candida and PCR-RFLP methods at the same time contributes to more accurate identification of isolates.

The incidence of opportunistic fungi in patients suspected of tuberculosis.

The incidence of opportunistic fungi in bronchoalveolar lavage specimens from patients suspected of tuberculosis in Isfahan, Iran, was determined. From 200 patients 36 yeasts (18%) and seven filamentous fungi (3.5%) were isolated. Out of 44 patients who had fungal infections, 12 cases were affected with definite tuberculosis.

Prevalence and aetiology of dermatophytoses in Isfahan, Iran.

In this study the prevalence and causative agents of dermatophytoses in Isfahan, a large province of Iran, were determined. Of 16,578 clinically suspected cases 13.3% were affected with dermatophytoses. Lesions of tinea capitis were the most prevalent clinical type of dermatophytoses (54.1%), followed by tinea corporis (23.8%) and tinea pedis (8.9%). Trichophyton verrucosum was the most frequent causative agent (32.8%), followed by Epidermophyton floccosum (17.6%), T. mentagrophytes (16.2%) and Microsporum canis (12.3%). We found a relationship between the spread of dermatophytoses and live-stock infected with dermatophytoses in Isfahan.