A Smartphone Application Using Artificial Intelligence Is Superior To Subject Self-Reporting When Assessing Stool Form.

INTRODUCTION: Stool form assessment relies on subjective patient reports using the Bristol Stool Scale (BSS). In a novel smartphone application (app), trained artificial intelligence (AI) characterizes digital images of users' stool. In this study, we evaluate this AI for accuracy in assessing stool characteristics. METHODS: Subjects with diarrhea-predominant irritable bowel syndrome image-captured every stool for 2 weeks using the app, which assessed images for 5 visual characteristics (BSS, consistency, fragmentation, edge fuzziness, and volume). In the validation phase, using 2 expert gastroenterologists as a gold standard, sensitivity, specificity, accuracy, and diagnostic odds ratios of subject-reported vs AI-graded BSS scores were compared. In the implementation phase, agreements between AI-graded and subject-reported daily average BSS scores were determined, and subject BSS and AI stool characteristics scores were correlated with diarrhea-predominant irritable bowel syndrome symptom severity scores. RESULTS: In the validation phase (n = 14), there was good agreement between the 2 experts and AI characterizations for BSS (intraclass correlation coefficients [ICC] = 0.782-0.852), stool consistency (ICC = 0.873-0.890), edge fuzziness (ICC = 0.836-0.839), fragmentation (ICC = 0.837-0.863), and volume (ICC = 0.725-0.851). AI outperformed subjects' self-reports in categorizing daily average BSS scores as constipation, normal, or diarrhea. In the implementation phase (n = 25), the agreement between AI and self-reported BSS scores was moderate (ICC = 0.61). AI stool characterization also correlated better than subject reports with diarrhea severity scores. DISCUSSION: A novel smartphone application can determine BSS and other visual stool characteristics with high accuracy compared with the 2 expert gastroenterologists. Moreover, trained AI was superior to subject self-reporting of BSS. AI assessments could provide more objective outcome measures for stool characterization in gastroenterology.

Protein-enriched meal replacements do not adversely affect liver, kidney or bone density: an outpatient randomized controlled trial.

BACKGROUND: There is concern that recommending protein-enriched meal replacements as part of a weight management program could lead to changes in biomarkers of liver or renal function and reductions in bone density. This study was designed as a placebo-controlled clinical trial utilizing two isocaloric meal plans utilizing either a high protein-enriched (HP) or a standard protein (SP) meal replacement in an outpatient weight loss program. SUBJECTS/METHODS: 100 obese men and women over 30 years of age with a body mass index (BMI) between 27 to 40 kg/m2 were randomized to one of two isocaloric weight loss meal plans 1). HP group: providing 2.2 g protein/kg of lean body mass (LBM)/day or 2). SP group: providing 1.1 g protein/kg LBM/day. Meal replacement (MR) was used twice daily (one meal, one snack) for 3 months and then once a day for 9 months. Body weight, lipid profiles, liver function, renal function and bone density were measured at baseline and 12 months. RESULTS: Seventy subjects completed the study. Both groups lost weight (HP -4.29 ± 5.90 kg vs. SP -4.66 ± 6.91 kg, p < 0.01) and there was no difference in weight loss observed between the groups at one year. There was no significant change noted in liver function [AST (HP -2.07 ± 10.32 U/L, p = 0.28; SP 0.27 ± 6.67 U/L, p = 0.820), ALT (HP -1.03 ± 10.08 U/L, p = 0.34; SP -2.6 ± 12.51 U/L, p = 0.24), bilirubin (HP 0.007 ± 0.33, U/L, p = 0.91; SP 0.07 ± 0.24 U/L, p = 0.120), alkaline phosphatase (HP 2.00 ± 9.07 U/L, p = 0.240; SP -2.12 ± 11.01 U/L, p = 0.280)], renal function [serum creatinine (HP 0.31 ± 1.89 mg/dL, p = 0.380; SP -0.05 ± 0.15 mg/dL, p = 0.060), urea nitrogen (HP 1.33 ± 4.68 mg/dL, p = 0.130; SP -0.24 ± 3.03 mg/dL, p = 0.650), 24 hour urine creatinine clearance (HP -0.02 ± 0.16 mL/min, p = 0.480; SP 1.18 ± 7.53 mL/min, p = 0.400), and calcium excretion (HP -0.41 ± 9.48 mg/24 hours, p = 0.830; SP -0.007 ± 6.76 mg/24 hours, p = 0.990)] or in bone mineral density by DEXA (HP 0.04 ± 0.19 g/cm2, p = 0.210; SP -0.03 ± 0.17 g/cm2, p = 0.320) in either group over one year. CONCLUSIONS: These studies demonstrate that protein-enriched meals replacements as compared to standard meal replacements recommended for weight management do not have adverse effects on routine measures of liver function, renal function or bone density at one year.

A controlled trial of protein enrichment of meal replacements for weight reduction with retention of lean body mass.

BACKGROUND: While high protein diets have been shown to improve satiety and retention of lean body mass (LBM), this study was designed to determine effects of a protein-enriched meal replacement (MR) on weight loss and LBM retention by comparison to an isocaloric carbohydrate-enriched MR within customized diet plans utilizing MR to achieve high protein or standard protein intakes. METHODS: Single blind, placebo-controlled, randomized outpatient weight loss trial in 100 obese men and women comparing two isocaloric meal plans utilizing a standard MR to which was added supplementary protein or carbohydrate powder. MR was used twice daily (one meal, one snack). One additional meal was included in the meal plan designed to achieve individualized protein intakes of either 1) 2.2 g protein/kg of LBM per day [high protein diet (HP)] or 2) 1.1 g protein/kg LBM/day standard protein diet (SP). LBM was determined using bioelectrical impedance analysis (BIA). Body weight, body composition, and lipid profiles were measured at baseline and 12 weeks. RESULTS: Eighty-five subjects completed the study. Both HP and SP MR were well tolerated, with no adverse effects. There were no differences in weight loss at 12 weeks (-4.19 +/- 0.5 kg for HP group and -3.72 +/- 0.7 kg for SP group, p > 0.1). Subjects in the HP group lost significantly more fat weight than the SP group (HP = -1.65 +/- 0.63 kg; SP = -0.64 +/- 0.79 kg, P = 0.05) as estimated by BIA. There were no significant differences in lipids nor fasting blood glucose between groups, but within the HP group a significant decrease in cholesterol and LDL cholesterol was noted at 12 weeks. This was not seen in the SP group. CONCLUSION: Higher protein MR within a higher protein diet resulted in similar overall weight loss as the standard protein MR plan over 12 weeks. However, there was significantly more fat loss in the HP group but no significant difference in lean body mass. In this trial, subject compliance with both the standard and protein-enriched MR strategy for weight loss may have obscured any effect of increased protein on weight loss demonstrated in prior weight loss studies using whole food diets.

Insulin, hs-CRP, leptin, and adiponectin. An analysis of their relationship to the metabolic syndrome in an obese population with an elevated waist circumference.

BACKGROUND: Various adipose tissue factors have been implicated as biomarkers of the metabolic syndrome (MS). The objective of this study was to assess which specific adipose tissue factors would discriminate the presence of MS in a strictly obese population meeting waist circumference (WC) criteria for the MS. METHODS: This was a cross-sectional study of 148 subjects recruited from a university-based weight loss program prior to starting the program. Patients were eligible if they had a BMI more than 25 kg/m(2) and had WC more than 40 and 35 inches in males and females, respectively. Biomarkers measured included high sensitivity C-reactive protein (hs-CRP), leptin, adiponectin, and total insulin. RESULTS: Of the total population, 33.8% satisfied criteria for the MS. Insulin was the only biomarker to consistently differentiate between presence and absence of MS in this obese population (P = 0.0001 in males, P = 0.006 in females). All biomarkers measured with the exception of leptin had a statistically significant relationship with increasing criteria for the MS. CONCLUSIONS: In a population where an excess amount of adipose tissue exists, insulin is the only reliable biomarker to differentiate MS status. We surmise that differences in hs-CRP, leptin, and adiponectin are a reflection of their measurements in individuals with statistically different amounts of adipose tissue.

Are high-protein, vegetable-based diets safe for kidney function? A review of the literature.

In individuals with chronic kidney disease, high-protein diets have been shown to accelerate renal deterioration, whereas low-protein diets increase the risk of protein malnutrition. Vegetarian diets have been promoted as a way to halt progression of kidney disease while maintaining adequate nutrition. We review the literature to date comparing the effects of animal and vegetable protein on kidney function in health and disease. Diets with conventional amounts of protein, as well as high-protein diets, are reviewed. The literature shows that in short-term clinical trials, animal protein causes dynamic effects on renal function, whereas egg white, dairy, and soy do not. These differences are seen both in diets with conventional amounts of protein and those with high amounts of protein. The long-term effects of animal protein on normal kidney function are not known. Although data on persons with chronic kidney disease are limited, it appears that high intake of animal and vegetable proteins accelerates the underlying disease process not only in physiologic studies but also in short-term interventional trials. The long-term effects of high protein intake on chronic kidney disease are still poorly understood. Several mechanisms have been suggested to explain the different effects of animal and vegetable proteins on normal kidney function, including differences in postprandial circulating hormones, sites of protein metabolism, and interaction with accompanying micronutrients.

Assessment of obesity management in medical examination.

Obesity is a growing international health problem that has already reached epidemic proportions, particularly within the United States where a majority of the population is overweight or obese. Effective methods of treatment are needed, and should be taught to physicians by efficient means. There exists a disconnect between the rising obesity prevalence with its high toll on medical resources, and the lack of obesity education provided to practitioners in the course of their training. One particular shortfall is the lack of representation of obesity on standardized medical examinations. Physician attitudes toward obesity are influenced by their lack of familiarity with the management of the disease. This may include dietary restriction, increasing physical activity, behavior modification, pharmacotherapy, and surgical interventions. Thus, curricular changes in the medical education of obesity could help reduce morbidity and mortality associated with this disease.

Initial experience with wireless capsule enteroscopy in the diagnosis and management of inflammatory bowel disease.

BACKGROUND AND AIMS: Wireless capsule enteroscopy (WCE) offers the potential to directly visualize the entire small bowel and identify superficial lesions not detected by traditional endoscopy and radiography. The aim of this study is to assess the clinical utility of WCE in the evaluation of patients with known or suspected inflammatory bowel disease (IBD). METHODS: Fifty patients with ongoing symptoms underwent Given M2A endoscopic capsule examinations. Indications included: (1) evaluation for small-bowel involvement in patients with IBD with isolated colitis (n = 22), (2) determination of the extent of small-bowel disease in patients with Crohn's disease (CD; n = 20), and (3) workup of suspected IBD (n = 8). Outcome measures were classified as diagnostic when multiple ulcerations were present, suspicious when