Development and validation of a neural network for NAFLD diagnosis.

Non-Alcoholic Fatty Liver Disease (NAFLD) affects about 20-30% of the adult population in developed countries and is an increasingly important cause of hepatocellular carcinoma. Liver ultrasound (US) is widely used as a noninvasive method to diagnose NAFLD. However, the intensive use of US is not cost-effective and increases the burden on the healthcare system. Electronic medical records facilitate large-scale epidemiological studies and, existing NAFLD scores often require clinical and anthropometric parameters that may not be captured in those databases. Our goal was to develop and validate a simple Neural Network (NN)-based web app that could be used to predict NAFLD particularly its absence. The study included 2970 subjects; training and testing of the neural network using a train-test-split approach was done on 2869 of them. From another population consisting of 2301 subjects, a further 100 subjects were randomly extracted to test the web app. A search was made to find the best parameters for the NN and then this NN was exported for incorporation into a local web app. The percentage of accuracy, area under the ROC curve, confusion matrix, Positive (PPV) and Negative Predicted Value (NPV) values, precision, recall and f1-score were verified. After that, Explainability (XAI) was analyzed to understand the diagnostic reasoning of the NN. Finally, in the local web app, the specificity and sensitivity values were checked. The NN achieved a percentage of accuracy during testing of 77.0%, with an area under the ROC curve value of 0.82. Thus, in the web app the NN evidenced to achieve good results, with a specificity of 1.00 and sensitivity of 0.73. The described approach can be used to support NAFLD diagnosis, reducing healthcare costs. The NN-based web app is easy to apply and the required parameters are easily found in healthcare databases.

Selecting the best machine learning algorithm to support the diagnosis of Non-Alcoholic Fatty Liver Disease: A meta learner study.

BACKGROUND & AIMS: Liver ultrasound scan (US) use in diagnosing Non-Alcoholic Fatty Liver Disease (NAFLD) causes costs and waiting lists overloads. We aimed to compare various Machine learning algorithms with a Meta learner approach to find the best of these as a predictor of NAFLD. METHODS: The study included 2970 subjects, 2920 constituting the training set and 50, randomly selected, used in the test phase, performing cross-validation. The best predictors were combined to create three models: 1) FLI plus GLUCOSE plus SEX plus AGE, 2) AVI plus GLUCOSE plus GGT plus SEX plus AGE, 3) BRI plus GLUCOSE plus GGT plus SEX plus AGE. Eight machine learning algorithms were trained with the predictors of each of the three models created. For these algorithms, the percent accuracy, variance and percent weight were compared. RESULTS: The SVM algorithm performed better with all models. Model 1 had 68% accuracy, with 1% variance and an algorithm weight of 27.35; Model 2 had 68% accuracy, with 1% variance and an algorithm weight of 33.62 and Model 3 had 77% accuracy, with 1% variance and an algorithm weight of 34.70. Model 2 was the most performing, composed of AVI plus GLUCOSE plus GGT plus SEX plus AGE, despite a lower percentage of accuracy. CONCLUSION: A Machine Learning approach can support NAFLD diagnosis and reduce health costs. The SVM algorithm is easy to apply and the necessary parameters are easily retrieved in databases.

Fatty liver and mortality: a cohort population study in South Italy.

OBJECTIVE: Alcoholic fatty liver (AFLD) and non-alcoholic fatty liver (NAFLD) are two common conditions. However, if they can increase the risk of death is poorly explored. We therefore aimed to investigate the potential association between the presence and severity of liver steatosis and mortality in a large sample of older people. DESIGN: Prospective. SETTING: Community. PARTICIPANTS: Women and men randomly sampled from the electoral rolls of the population of Castellana Grotte, a town in Southern Italy (Apulia region) between 2005 and 2006. Among 1942 initially contacted, 1708 (=87.9%) participated to the baseline survey (Multicentrica Colelitiasi III (MICOL III)). This specific study included 1445 older participants (mean age=65.2 years, females=44.2%). EXPOSURE: NAFLD or AFLD. PRIMARY AND SECONDARY OUTCOMES: Mortality (all-cause and specific-cause). RESULTS: After a median of 12 years, 312 participants (=21.6%) died. After adjusting for nine potential confounders, the presence of steatosis was not associated with any increased risk of death in both NAFLD and AFLD. The severity of liver steatosis was not associated with any increased risk of mortality in NAFLD, while in AFLD, the presence of moderate steatosis significantly increased the risk of overall (HR=2.16; 95% CI 1.19 to 3.91) and cancer-specific (HR=3.54; 95% CI 1.16 to 10.87) death. CONCLUSIONS: Liver steatosis is not associated with any increased risk of death in NAFLD, while moderate steatosis could be a risk factor for mortality (particularly due to cancer) in people affected by AFLD.

Effectiveness of two physical activity programs on non-alcoholic fatty liver disease. a randomized controlled clinical trial.

Introduction: To estimate the effectiveness of two physical activity programs on NAFLD. Methods: Participants come from a survey conducted in southern Italy. Subjects with moderate or severe NAFLD were invited to participate. After giving informed consent, they completed a questionnaire, underwent ultrasonography and anthropometric measurements. Then they were randomized an Aerobic or a Combined Exercise program and followed up for six months. The first group followed a program of moderate aerobic activity lasting 30 minutes, 5 days per week. The second group did aerobic training with the addition of muscle training involving the large muscle groups, stimulating them to make more intense efforts, for a duration of 60 minutes, at least, 3 days a week. Compliance with the programs was measured. A mixed linear model was applied to the data. Results: Compliance with Aerobic Exercise was homogeneous and increased over time. Combined Program compliance was equal to 100%. There was no significant difference in the NAFLD mean score by treatment at baseline and after six months. However, there was a significant reduction in the NAFLD mean score for treatments after six months. The NAFLD measured score was reduced by 22% in the Aerobic treatment group when confronted with the other program. In the Combined program, after 6 months, results showed to be less effective than the Aerobic Exercise in reducing the NAFLD score. Conclusion: An aerobic exercise program is a realistic intervention which could be included as a part of primary prevention of several chronic diseases.

Introducción: Estimar la eficiencia de dos programas de actividad física sobre la NAFLD Métodos: Sujetos con NAFLD moderada o severa que habían participado a un estudio de pobación en el sur de Italia fueron invitados a participar. Fue completado un cuestionario, se tomaron medidas antropométricas y se realizó una ecografia hepática. Cada participante proveyó el consenso informato. Los participantes fueron aleatorizados a un programa aerobico (actividad aerobica moderada per 30 minutos, 5 veces a la semana) o un programa mixto (aerobico más entrenamiento de la fuerza de los grandes grupos musculares, 60 minutos, tres veces a la semana). Fue medida la adherencia a los programas y se aplicó un modelo linear mixto a los datos. Resultados: El programa aerobico tuvo muy buena adherencia y esta aumentó con el tiempo mientras el programa mixto tuvo 100% de adherencia. No hubo diferencias estadísticamente significativas en el score de NAFLD al enrolamiento, mientras hubo diferencias estadísticamente significativas en el score medio de NAFLD después de 6 meses pero el score en el grupo del programa aerobico tuvo una reducción del 22% más intensa que el programa mixto. Este último programa por lo tanto se ha mostrado menos efectivo que el programa aerobico. Conclusión: Un programa de actividad física aerobica es un tratamiento realístico que podría ser efectuado no solo para la NAFLD sino también como prevención primaria de otras enfermedades crónicas.

Reducing NAFLD-screening time: A comparative study of eight diagnostic methods offering an alternative to ultrasound scans.

BACKGROUND & AIMS: The use of ultrasound scan (US) in non-alcoholic fatty liver disease (NAFLD) screening overloads US waiting lists. We hypothesized and tested a hybrid two-step method, consisting of applying a formula, to exclude subjects at low risk, before US. METHODS: The sample included 2970 males and females (937 with NAFLD) diagnosed by US. We selected eight formulas: Fatty Liver Index (FLI), Hepatic Steatosis Index (HIS), body mass index (BMI), waist circumference (WC), Abdominal Volume Index (AVI), waist-to-height ratio (WHtR), waist/height0.5 (WHT.5R) and Body Roundness Index (BRI), and calculated their performance in the two-step method evaluating percentage reduction of the number of liver US (US reduction percentage), percentage of false negative and percentage of NAFLD identified. RESULTS: The US reductions percentage were 52.2% (WHtR), 52.1% (HIS), 51.8% (FLI), 50.8% (BRI), 50.7% (BMI and WHt_5R), 46.5% (WC) and 45.2% (AVI). The false negative percentage were 8.5% (WHtR), 7.9% (BRI), 7.3% (WHt_5R), 7.2% (BMI), 6.7% (HIS), 6.6% (FLI), 5.6% (WC) and 5.2% (AVI). The best percentage of NALFD identified was obtained using AVI (83.6%) before US, then WC (82.2%), FLI (79%), HIS (78.9%), BMI (77.3%), WHt_5R (76.9%), BRI (74.8%) and WHtR (73%). CONCLUSION: The best formula to use in two-step diagnostic NAFLD screening was AVI, which showed a low false negative rate and a higher percentage of identified NAFLD. Other studies evaluating the economic advantages of this screening method are warranted.

Menopause Does Not Affect Fatty Liver Severity In Women: A Population Study in a Mediterranean Area.

BACKGROUND AND OBJECTIVE: Estrogens could protect the liver from fatty degeneration, but there is little information about whether menopause is associated with the severity of alcoholic (AFL) and non-alcoholic fatty liver (NAFL). Our aim was to evaluate the distribution of fatty liver detected by ultrasound in pre- and post-menopausal women and the factors associated with these conditions. METHODS: In this cross-sectional study, the years from menopause were investigated through selfreported information. The degree of fatty liver was assessed through a standardized ultrasound examination (scores 0 to 6, higher values reflecting a greater severity). Liver steatosis was classified as NAFL or AFL based on a daily alcohol intake > 20g/d. RESULTS: The study included 752 women in menopause and 535 in pre-menopause. The years from menopause were not associated with the severity of liver steatosis in NAFL (p for trend=0.74; Spearman correlation=0.04; 95%CI: -0.09 to 0.17), whereas all the indexes of adiposity and the number of metabolic syndrome factors were associated with a higher liver steatosis score. Taking AFL liver steatosis as the outcome, the years since menopause were not significantly associated with liver steatosis in AFL (p for trend=0.50; Spearman correlation=0.09; 95%CI: -0.17 to 0.34), whilst the association between anthropometric parameters and liver steatosis severity resulted stronger in postmenopausal compared to pre- menopausal women. CONCLUSION: the higher prevalence of fatty liver observed in post-menopausal women is probably not due to menopause per se, but to the adiposity (particularly abdominal) typical of this age and its consequences (such as metabolic syndrome).

Ultrasound evaluation and correlates of fatty liver disease: a population study in a Mediterranean area.

BACKGROUND: The aim of this study was to evaluate the distribution of fatty liver-nonalcoholic (NAFL) and alcoholic (AFL)-and its association with metabolic syndrome and its components in a population sample from a Mediterranean area. METHODS: A sample of 2974 subjects (1679 males, 1295 females, age range 30-89 years) was randomly drawn from the population of a town in southern Italy. The survey visit included a validated semiquantitative food frequency questionnaire, anthropometric measurements, a blood sample taken in the morning after overnight fasting, as well as abdominal ultrasound examination to evaluate liver fat with a standardized scoring system. The 2001 National Cholesterol Education Program Adult Treatment Panel III (NCEP ATP III) definition of the metabolic syndrome was adopted. RESULTS: In this Mediterranean population, where alcohol intake is mostly as wine with meals, NAFL is present in 36.8% of men and 25.7% of women and AFL in 13.8% of men and 5.5% of women. NAFL and AFL are associated with metabolic syndrome and its characteristics, body mass index (BMI), and visceral and subcutaneous fat (in AFL subjects, only in women) measured by ultrasound. Stratifying by BMI and controlling for confounders (age, height, smoking habit, and alcohol consumption), in overweight and obese subjects, liver and visceral fat are associated with the metabolic syndrome both in men and women and subcutaneous fat only in women. In normal weight subjects, only liver fat in men is associated with the metabolic syndrome. CONCLUSIONS: Fatty liver is highly prevalent in this Mediterranean population and is associated with metabolic syndrome in overweight and obese men and women as well as in men with normal BMI.

Inulin-enriched pasta improves intestinal permeability and modifies the circulating levels of zonulin and glucagon-like peptide 2 in healthy young volunteers.

Apart from the intestinal environment, inulin induces physiological effects, which includes a reduction in glucose and lipid concentrations and modulation of gastrointestinal motility through the release of different peptides. We hypothesized that inulin-enriched pasta may also improve small intestine permeability in relation to zonulin and glucagon-like peptide 2 (GLP-2) levels in healthy young subjects. Twenty healthy, young male volunteers completed a randomized, double-blind crossover study consisting of a 2-week run-in period and two 5-week study periods (11% inulin-enriched or control pasta), with an 8-week washout period in between. The intestinal barrier function was assessed by lactulose-mannitol excretion in urine. Zonulin values and GLP-2 release were evaluated by enzyme-linked immunosorbent assay. In the inulin group, the urinary lactulose recovery was significantly lower than the other 2 groups. There were no significant differences in urinary mannitol levels between groups. Accordingly, the lactulose-mannitol excretion ratio was significantly decreased in the inulin-enriched pasta group compared with the other 2 groups. The inulin-enriched pasta group had significantly lower zonulin serum values and significantly higher GLP-2 basal values when compared with the baseline and control pasta groups. The dietary use of inulin-enriched pasta preserves intestinal mucosal barrier functioning and modulates circulating levels of zonulin and GLP-2, suggesting that prebiotics could be used in the prevention of gastrointestinal diseases and metabolic disorders.

Increased serum levels of lipogenic enzymes in patients with severe liver steatosis.

BACKGROUND: Lipid metabolism is altered in subjects with liver steatosis. FAS is a key enzyme in de novo lipogenesis and both FAS gene expression and enzymatic activity are primarily regulated by metabolic signals in the liver. Lipoprotein lipase (LPL), the rate-limiting enzyme for the hydrolysis of core triglycerides, plays a pivotal role in lipid metabolism. This study aims to investigate if circulating levels of FAS and LPL could be clinically associated with liver steatosis. METHODS: In this work, we present data obtained from a subsample of 94 subjects with liver steatosis enrolled by NUTRIEPA study, a nutritional trial in subjects with liver steatosis. Serum levels of FAS protein and LPL activity were evaluated by ELISA test and by a fluorescent method, respectively. The diagnosis and the degree of liver steatosis were based on laboratory and ecographic measurements. Statistical methods included Kruskal-Wallis analysis of variance and Wilcoxon signed-rank test, where appropriate. The χ2 test has been performed to analyse categorical variables. RESULTS: The subjects with severe steatosis had significantly higher serum levels of FAS protein and LPL activity compared to subjects with mild and moderate liver steatosis. Moreover, a positive trend in serum levels of FAS expression from lower to higher degree of steatosis was also detected. CONCLUSIONS: We describe a relationship between human liver steatosis and elevated levels of circulating lipogenic enzymes. Increased serum levels of FAS expression and LPL activity could be considered a marker of severe liver steatosis.

Effects of a diet with inulin-enriched pasta on gut peptides and gastric emptying rates in healthy young volunteers.

AIM: Our group has previously shown that the administration of pasta enriched along with the prebiotic inulin induces a significant reduction in triglyceride and glucose levels with a significant delay in gastric emptying (GE) rates. This protective effect may occur by affecting the release of a number of gut peptides involved in the control of gastrointestinal motility. The aim of the present study was to evaluate the effects of inulin-enriched pasta on the circulating levels of neurotensin (NT), somatostatin (SS), and corticotropin-releasing factor (CRF) in relation to the GE time in young healthy subjects. METHODS: Twenty healthy young male volunteers completed a randomized double-blind crossover study consisting of a 2-week run-in period and two 5-week study periods (11% inulin-enriched/control pasta), with an 8-week wash-out period in between. Gut peptide concentrations were evaluated by radioimmunoassay. GE time was evaluated by ultrasonography. RESULTS: The prebiotic treatment significantly increased the area under the curve (AUC) values of both NT and SS (p < 0.05 Dunn's post-test). With regard to gastric motility, along with a significant delay in both the final time and T (1/2) gastric emptying time, a positive correlation was found between T (1/2) and SS AUC values (r = 0.57, p = 0.009) in the inulin-enriched pasta group. CONCLUSION: These results support the hypothesis that inulin plays an active role in mechanisms affecting the release of these gut peptides, which may modulate the gastric emptying of digesta.

Inulin-enriched pasta affects lipid profile and Lp(a) concentrations in Italian young healthy male volunteers.

BACKGROUND: Inulin has been suggested to have beneficial effects on lipids, especially on triglyceridemia. Few data are available about the effects of inulin on Lipoprotein(a), a low-density lipoprotein-like particle considered as an independent risk factor for atherosclerosis. Adding inulin to pasta could be a preventive strategy for delaying the onset of atherosclerosis. AIM OF THE STUDY: was to evaluate the effects of inulin-enriched pasta on lipid profile and on Lipoprotein(a) in young healthy subjects. METHODS: Twenty-two young healthy male volunteers entered a randomized double blind cross-over study consisting of a 2-weeks run-in period, a baseline assessment, two 5-weeks study periods (11% inulin-enriched or control pasta), and an 8-weeks wash-out period in between. Serum lipid concentrations were evaluated by routine biochemical analyses and plasma Lipoprotein(a) concentrations by ELISA. The size of apolipoprotein(a) isoforms was determined by Western blot and immunodetection. RESULTS: Significant differences at baseline and in the treatment groups were found for HDL-cholesterol (P = 0.004), total cholesterol/HDL-cholesterol ratio (P = 0.006), triglycerides (P = 0.04), and Lipoprotein(a) (P = 0.02) concentrations (data analyzed by Friedman test). Dunn's multiple comparison test was used to assess the significance of differences between inulin-enriched pasta diet vs. baseline. HDL-cholesterol concentrations increased by 35.9%; total cholesterol/HDL-cholesterol ratio, triglycerides, and Lipoprotein(a) concentrations decreased by 22.2, 23.4, and 16.5% respectively. CONCLUSIONS: Inulin-enriched pasta administration induced significant effects on lipid pattern parameters in young healthy volunteers, including a significant reduction in Lipoprotein(a) concentrations.

Early pathogenesis of atherosclerosis: the childhood obesity.

Obesity represents a chronic inflammatory status and adipocytes release either cytokines or an array of adipokines such as leptin, endowed with immunomodulating and systemic activities. The involvement of cytokines in obesity as well as of the adipokine leptin is supported by the notion that weight reduction normalizes mediators of inflammation. In this framework, we will demonstrate that in obese children, subjected for a period of six months to a hypocaloric diet, reduction of major biochemical and anthropometric parameters correlates with a normalization of immune status. In fact, absolute numbers of CD4+ cells and CD4/CD8 ratio increase, while leptin values fluctuate within normal ranges, being this adipokine involved in the modulation of either innate or adaptive immune responses. In the discussion, the immune abnormalities detected in obesity will be pointed out and emphasis will be placed on the increased frequency of infectious episodes occurring in obese adolescent and adults. Finally, the infectious etiology of obesity will be illustrated in the sense that adipocytes interacting with infectious agents may cause obesity. Taken together, the bulk of available data indicate that childhood obesity should be prevented or reduced to avoid more serious complications in adulthood.

Functional foods: salient features and clinical applications.

The term "functional food" refers to foods or ingredients of foods providing an additional physiological benefit beyond their basic nutritional needs. Health benefits are best obtained through a varied diet containing fruits, vegetables, grains, legumes and seeds. However, fortified foods and dietary supplements have been marketed and food industry have made functional food one of their current leading trends. Recently, the number of functional foods that have a potential benefit on health has hugely grown and scientific evidence is supporting the role of functional foods in prevention and treatment of several diseases. Cancer, diabetes, heart disease and hypertension are the most important diseases that can be treated or prevented by functional foods; other diseases are osteoporosis, abnormal bowel motility, and arthritis. It has been estimated that 80% of cancer in USA have a nutrition/diet component suggesting a great impact of functional food and foods components on incidence and treatment of cancer. Numerous factors complicate the evaluation of scientific evidence such as the complexity of food substance, effect on food, metabolic changes associated to dietary changes, the lack of biological markers of disease development. This paper reviews the scientific evidence supporting this area regarding only those foods and ingredients in which a clear experimental and clinical evidence exists for their chemopreventive and therapeutic effects.

Gastric electrical activity in normal neonates during the first year of life: effect of feeding with breast milk and formula.

BACKGROUND: To evaluate the effect of feeding with milk on the gastrointestinal tract, we studied gastric electrical activity in 27 healthy fullterm newborns (15 formula-fed newborns and 12 breast-fed newborns) during the first 6 months of life. METHODS: Three-hour electrogastrography (EGG) recordings were performed, using portable equipment, from the third to fifth day after birth until 6 months, at 3-month intervals. The EGG parameters were calculated as raw and integrated data, the latter as AUC of the whole postprandial period. RESULTS: There was a significant difference in the fasting 3-cpm activity between the two groups (repeated measures analysis of variance [ANOVA] P=0.02; multiple comparisons: formula milk at birth vs breast milk at birth P<0.001). In addition, a significant change in the percentage of postprandial bradygastria was found at 6 months, 1 month after weaning (repeated measures ANOVA, P=0.01; multiple comparisons: formula milk at 6 months vs formula milk at 3 months, P=0.03, formula milk at 6 months vs formula milk at birth, P=0.02; breast milk at 6 months vs breast milk at 3 months, P=0.03, breast milk at 6 months vs breast milk at birth P=0.02). CONCLUSIONS: An adult-like gastric 3-cpm activity can be observed in breast-fed newborns in contrast to formula-fed ones, probably as an effect of colostrum. The high bradygastria percentage recorded at 6 months of life might be the result of an increased low-frequency component of the EGG signal because of the transition to a mixed diet.